CINXE.COM
Applications of Support Vector Machine (SVM) Learning in Cancer Genomics | Cancer Genomics & Proteomics
<!DOCTYPE html> <html lang="en" dir="ltr" xmlns="http://www.w3.org/1999/xhtml" xmlns:mml="http://www.w3.org/1998/Math/MathML"> <head prefix="og: http://ogp.me/ns# article: http://ogp.me/ns/article# book: http://ogp.me/ns/book#" > <!--[if IE]><![endif]--> <link rel="dns-prefetch" href="//cdn.jsdelivr.net" /> <link rel="dns-prefetch" href="//cdn.foxycart.com" /> <link rel="dns-prefetch" href="//scholar.google.com" /> <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> <meta name="Generator" content="Drupal 7 (http://drupal.org)" /> <link rel="canonical" href="https://cgp.iiarjournals.org/content/15/1/41" /> <link rel="alternate" type="application/pdf" title="Full Text (PDF)" href="/content/15/1/41.full.pdf" /> <link rel="alternate" type="text/plain" title="Full Text (Plain)" href="/content/15/1/41.full.txt" /> <link rel="alternate" type="application/vnd.ms-powerpoint" title="Powerpoint" href="/content/15/1/41.ppt" /> <meta name="article_thumbnail" content="https://cgp.iiarjournals.org/content/cgp/15/1/41/embed/graphic-1.gif" /> <meta name="type" content="article" /> <meta name="category" content="review-article" /> <meta name="HW.identifier" content="/cgp/15/1/41.atom" /> <meta name="HW.pisa" content="cgp;15/1/41" /> <meta name="DC.Format" content="text/html" /> <meta name="DC.Language" content="en" /> <meta name="DC.Title" content="Applications of Support Vector Machine (SVM) Learning in Cancer Genomics" /> <meta name="DC.Date" content="2018-01-01" /> <meta name="DC.Publisher" content="International Institute of Anticancer Research" /> <meta name="DC.Rights" content="Copyright© 2018, International Institute of Anticancer Research (Dr. George J. Delinasios), All rights reserved." /> <meta name="DC.AccessRights" content="open-access" /> <meta name="DC.Description" content="Machine learning with maximization (support) of separating margin (vector), called support vector machine (SVM) learning, is a powerful classification tool that has been used for cancer genomic classification or subtyping. Today, as advancements in high-throughput technologies lead to production of large amounts of genomic and epigenomic data, the classification feature of SVMs is expanding its use in cancer genomics, leading to the discovery of new biomarkers, new drug targets, and a better understanding of cancer driver genes. Herein we reviewed the recent progress of SVMs in cancer genomic studies. We intend to comprehend the strength of the SVM learning and its future perspective in cancer genomic applications." /> <meta name="DC.Contributor" content="SHUJUN HUANG" /> <meta name="DC.Contributor" content="NIANGUANG CAI" /> <meta name="DC.Contributor" content="PEDRO PENZUTI PACHECO" /> <meta name="DC.Contributor" content="SHAVIRA NARRANDES" /> <meta name="DC.Contributor" content="YANG WANG" /> <meta name="DC.Contributor" content="WAYNE XU" /> <meta name="article:published_time" content="2018-01-01" /> <meta name="citation_title" content="Applications of Support Vector Machine (SVM) Learning in Cancer Genomics" /> <meta name="citation_abstract" lang="en" content="<p>Machine learning with maximization (support) of separating margin (vector), called support vector machine (SVM) learning, is a powerful classification tool that has been used for cancer genomic classification or subtyping. Today, as advancements in high-throughput technologies lead to production of large amounts of genomic and epigenomic data, the classification feature of SVMs is expanding its use in cancer genomics, leading to the discovery of new biomarkers, new drug targets, and a better understanding of cancer driver genes. Herein we reviewed the recent progress of SVMs in cancer genomic studies. We intend to comprehend the strength of the SVM learning and its future perspective in cancer genomic applications.</p>" /> <meta name="citation_journal_title" content="Cancer Genomics & Proteomics" /> <meta name="citation_publisher" content="International Institute of Anticancer Research" /> <meta name="citation_publication_date" content="2018/01/01" /> <meta name="citation_mjid" content="cgp;15/1/41" /> <meta name="citation_id" content="15/1/41" /> <meta name="citation_public_url" content="https://cgp.iiarjournals.org/content/15/1/41" /> <meta name="citation_abstract_html_url" content="https://cgp.iiarjournals.org/content/15/1/41.abstract" /> <meta name="citation_full_html_url" content="https://cgp.iiarjournals.org/content/15/1/41.full" /> <meta name="citation_pdf_url" content="https://cgp.iiarjournals.org/content/cgp/15/1/41.full.pdf" /> <meta name="citation_issn" content="1109-6535" /> <meta name="citation_issn" content="1790-6245" /> <meta name="citation_pmid" content="29275361" /> <meta name="citation_volume" content="15" /> <meta name="citation_issue" content="1" /> <meta name="citation_article_type" content="Review Article" /> <meta name="citation_firstpage" content="41" /> <meta name="citation_lastpage" content="51" /> <meta name="citation_access" content="all" /> <meta name="citation_author" content="SHUJUN HUANG" /> <meta name="citation_author_institution" content="College of Pharmacy, Rady Faculty of Health Sciences, University of Manitoba, Winnipeg, Canada" /> <meta name="citation_author_institution" content="Research Institute of Oncology and Hematology, CancerCare Manitoba, Winnipeg, Canada" /> <meta name="citation_author" content="NIANGUANG CAI" /> <meta name="citation_author_institution" content="Research Institute of Oncology and Hematology, CancerCare Manitoba, Winnipeg, Canada" /> <meta name="citation_author" content="PEDRO PENZUTI PACHECO" /> <meta name="citation_author_institution" content="Research Institute of Oncology and Hematology, CancerCare Manitoba, Winnipeg, Canada" /> <meta name="citation_author" content="SHAVIRA NARRANDES" /> <meta name="citation_author_institution" content="Research Institute of Oncology and Hematology, CancerCare Manitoba, Winnipeg, Canada" /> <meta name="citation_author_institution" content="Departments of Biochemistry and Medical Genetics, Rady Faculty of Health Sciences, University of Manitoba, Winnipeg, Canada" /> <meta name="citation_author" content="YANG WANG" /> <meta name="citation_author_institution" content="Department of Computer Science, Faculty of Sciences, University of Manitoba, Winnipeg, Canada" /> <meta name="citation_author" content="WAYNE XU" /> <meta name="citation_author_institution" content="College of Pharmacy, Rady Faculty of Health Sciences, University of Manitoba, Winnipeg, Canada" /> <meta name="citation_author_institution" content="Research Institute of Oncology and Hematology, CancerCare Manitoba, Winnipeg, Canada" /> <meta name="citation_author_institution" content="Departments of Biochemistry and Medical Genetics, Rady Faculty of Health Sciences, University of Manitoba, Winnipeg, Canada" /> <meta name="citation_author_email" content="wayne.xu@umanitoba.ca" /> <meta name="citation_reference" content="citation_journal_abbrev=Cancer Inform;citation_author=JA. Cruz;citation_author=DS. Wishart;citation_title=Applications of machine learning in cancer prediction and prognosis.;citation_pages=59-77;citation_volume=2;citation_year=2006;citation_pmid=19458758" /> <meta name="citation_reference" content="citation_journal_title=Clinical Chemistry;citation_journal_abbrev=Clinical Chemistry;citation_author=D. Cicchetti;citation_title=Neural networks and diagnosis in the clinical laboratory: state of the art;citation_pages=9-10;citation_volume=38;citation_year=1992;citation_issue=1;citation_pmid=1733613" /> <meta name="citation_reference" content="citation_journal_title=Journal of chronic diseases;citation_journal_abbrev=J Chronic Dis;citation_author=RJ. Simes;citation_title=Treatment selection for cancer patients: application of statistical decision theory to the treatment of advanced ovarian cancer.;citation_pages=171-186;citation_volume=38;citation_year=1985;citation_issue=2;citation_pmid=3882734;citation_doi=10.1016/0021-9681(85)90090-6" /> <meta name="citation_reference" content="citation_journal_title=Int J Comput Appl;citation_author=S. Aruna;citation_author=SP. Rajagopalan;citation_title=A novel SVM based CSSFFS feature selection algorithm for detecting breast cancer;citation_pages=14-20;citation_volume=31;citation_year=2011;citation_issue=8" /> <meta name="citation_reference" content="citation_title=Kernel methods in computational biology;citation_title=Support vector machine applications in computational biology;citation_author=W. Noble;citation_pages=71-92;citation_year=2004" /> <meta name="citation_reference" content="citation_journal_title=Nature biotechnology;citation_journal_abbrev=Nat Biotechnol;citation_author=WS. Noble;citation_title=What is a support vector machine?;citation_pages=1565-1567;citation_volume=24;citation_year=2006;citation_issue=12;citation_pmid=17160063;citation_doi=10.1038/nbt1206-1565" /> <meta name="citation_reference" content="citation_journal_title=Autom Remote Control;citation_author=V. Vapnik;citation_title=Pattern recognition using generalized portrait method;citation_pages=774-780;citation_volume=24;citation_year=1963" /> <meta name="citation_reference" content="citation_journal_title=Autom Remote Control;citation_author=MA. Aizerman;citation_author=EM. Braverman;citation_author=LI. Rozoner;citation_title=Theoretical foundations of the potential function method in pattern recognition learning;citation_pages=821-837;citation_volume=25;citation_year=1964" /> <meta name="citation_reference" content="citation_journal_title=Science;citation_journal_abbrev=Science;citation_author=TR. Golub;citation_author=DK. Slonim;citation_author=P. Tamayo;citation_author=C. Huard;citation_author=M. Gaasenbeek;citation_author=JP. Mesirov;citation_author=H. Coller;citation_author=ML. Loh;citation_author=JR. Downing;citation_author=MA. Caligiuri;citation_title=Molecular Classification of Cancer: Class Discovery and Class Prediction by Gene Expression Monitoring;citation_pages=531-537;citation_volume=286;citation_year=1999;citation_issue=5439;citation_pmid=10521349;citation_doi=10.1126/science.286.5439.531" /> <meta name="citation_reference" content="citation_title=Advances in Neural Information Processing Systems;citation_title=Support VectorMachine for Multivariate Density Estimation;citation_author=V. Vapnik;citation_author=S. Mukherjee;citation_pages=659-665;citation_year=2000" /> <meta name="citation_reference" content="citation_journal_title=Physiological Genomics;citation_journal_abbrev=Physiol. Genomics;citation_author=E. Moler;citation_author=M. Chow;citation_author=I. Mian;citation_title=Analysis of molecular profile data using generative and discriminative methods;citation_pages=109-126;citation_volume=4;citation_year=2000;citation_issue=2;citation_pmid=11120872;citation_doi=10.1006/geno.2000.6242" /> <meta name="citation_reference" content="citation_journal_title=Bioinformatics;citation_journal_abbrev=Bioinformatics;citation_author=TS. Furey;citation_author=N. Cristianini;citation_author=N. Duffy;citation_author=DW. Bednarski;citation_author=M. Schummer;citation_author=D. Haussler;citation_title=Support vector machine classification and validation of cancer tissue samples using microarray expression data;citation_pages=906-914;citation_volume=16;citation_year=2000;citation_issue=10;citation_pmid=11120680;citation_doi=10.1093/bioinformatics/16.10.906" /> <meta name="citation_reference" content="citation_journal_title=J Clin Oncol;citation_author=NH. Segal;citation_author=P. Pavlidis;citation_author=WS. Noble;citation_author=CR. Antonescu;citation_author=A. Viale;citation_author=UV. Wesley;citation_author=K. Busam;citation_author=H. Gallardo;citation_author=D. DeSantis;citation_author=MF. Brennan;citation_title=Classification of clear cell sarcoma as melanoma of soft parts by genomic profiling;citation_volume=21;citation_year=2003;citation_pmid=12721254;citation_doi=10.1200/JCO.2003.10.108" /> <meta name="citation_reference" content="citation_journal_title=American Journal Of Pathology;citation_journal_abbrev=Am. J. Pathol.;citation_author=NH. Segal;citation_author=P. Pavlidis;citation_author=CR. Antonescu;citation_author=RG. Maki;citation_author=WS. Noble;citation_author=D. DeSantis;citation_author=JM. Woodruff;citation_author=JJ. Lewis;citation_author=MF. Brennan;citation_author=AN. Houghton;citation_title=Classification and Subtype Prediction of Adult Soft Tissue Sarcoma by Functional Genomics;citation_pages=691-700;citation_volume=163;citation_year=2003;citation_issue=2;citation_pmid=12875988" /> <meta name="citation_reference" content="citation_title=arXiv preprint 1306.0239;citation_title=Deep learning using linear support vector machines;citation_author=Y. Tang;citation_year=2013" /> <meta name="citation_reference" content="citation_journal_title=Bioinformatics;citation_author=T. Li;citation_author=C. Zhang;citation_author=M. Ogihara;citation_title=A comparative study of feature selection and multiclass classification methods for tissue classification based on gene expression;citation_volume=20;citation_year=2004;citation_issue=15;citation_pmid=15087314;citation_doi=10.1093/bioinformatics/bth267" /> <meta name="citation_reference" content="citation_journal_title=Bioinformatics;citation_journal_abbrev=Bioinformatics;citation_author=F. Model;citation_author=P. Adorjan;citation_author=A. Olek;citation_author=C. Piepenbrock;citation_title=Feature selection for DNA methylation based cancer classification;citation_pages=S157-164;citation_volume=17;citation_year=2001;citation_issue=suppl 1;citation_pmid=11473005;citation_doi=10.1093/bioinformatics/17.suppl_1.S157" /> <meta name="citation_reference" content="citation_journal_title=Springerplus;citation_author=S. Kim;citation_title=Weighted K-means support vector machine for cancer prediction;citation_pages=1162;citation_volume=5;citation_year=2016;citation_issue=1" /> <meta name="citation_reference" content="citation_journal_title=Procedia Comput Sci;citation_author=Z. Yang;citation_author=M. Jin;citation_author=Z. Zhang;citation_author=J. Lu;citation_author=K. Hao;citation_title=Classification based on feature extraction for hepatocellular carcinoma diagnosis using high-throughput dna methylation sequencing data;citation_pages=412-417;citation_volume=107;citation_year=2017" /> <meta name="citation_reference" content="citation_journal_title=Soft Comput;citation_author=A. Alkuhlani;citation_author=M. Nassef;citation_author=I. Farag;citation_title=Multistage feature selection approach for high-dimensional cancer data;citation_pages=6895-6906;citation_volume=21;citation_year=2017" /> <meta name="citation_reference" content="citation_journal_title=Clin Epigenetics;citation_author=S. Guo;citation_author=F. Yan;citation_author=J. Xu;citation_author=Y. Bao;citation_author=J. Zhu;citation_author=X. Wang;citation_author=J. Wu;citation_author=Y. Li;citation_author=W. Pu;citation_author=Y. Liu;citation_author=Z. Jiang;citation_author=Y. Ma;citation_author=X. Chen;citation_author=M. Xiong;citation_author=L. Jin;citation_author=J. Wang;citation_title=Identification and validation of the methylation biomarkers of non-small cell lung cancer (NSCLC);citation_pages=3;citation_volume=7;citation_year=2015" /> <meta name="citation_reference" content="citation_journal_title=Anticancer Research;citation_journal_abbrev=Anticancer Res;citation_author=Z. Sun;citation_author=X. Fu;citation_author=L. Zhang;citation_author=X. Yang;citation_author=F. Liu;citation_author=G. Hu;citation_title=A Protein Chip System for Parallel Analysis of Multi-tumor Markers and its Application in Cancer Detection;citation_pages=1159-1166;citation_volume=24;citation_year=2004;citation_issue=2C;citation_pmid=15154641" /> <meta name="citation_reference" content="citation_journal_title=Nat Commun;citation_author=S. Tyanova;citation_author=R. Albrechtsen;citation_author=P. Kronqvist;citation_author=J. Cox;citation_author=M. Mann;citation_author=T. Geiger;citation_title=Proteomic maps of breast cancer subtypes;citation_pages=10259;citation_volume=7;citation_year=2016;citation_pmid=26725330;citation_doi=10.1038/ncomms10259" /> <meta name="citation_reference" content="citation_journal_title=Bioinformatics;citation_author=F. Rapaport;citation_author=E. Barillot;citation_author=JP. Vert;citation_title=Classification of arrayCGH data using fused SVM;citation_volume=24;citation_year=2008;citation_issue=13;citation_pmid=18586737;citation_doi=10.1093/bioinformatics/btn188" /> <meta name="citation_reference" content="citation_journal_title=BMC Syst Biol;citation_author=S. Vura;citation_author=X. Wang;citation_author=C. Guda;citation_title=Classification of breast cancer patients using somatic mutation profiles and machine learning approaches;citation_pages=62;citation_volume=10;citation_year=2016;citation_issue=suppl 3" /> <meta name="citation_reference" content="citation_journal_title=Oncotarget;citation_author=T. Wu;citation_author=Y. Wang;citation_author=R. Jiang;citation_author=X. Lu;citation_author=J. Tian;citation_title=A pathways-based prediction model for classifying breast cancer subtypes;citation_pages=58809-58822;citation_volume=8;citation_year=2017;citation_issue=35" /> <meta name="citation_reference" content="citation_journal_title=Biomark Res;citation_author=E. Lin;citation_author=HY. Lane;citation_title=Machine learning and systems genomics approaches for multi-omics data;citation_pages=2;citation_volume=5;citation_year=2017;citation_issue=1" /> <meta name="citation_reference" content="citation_journal_title=BioData Min;citation_author=S. Kim;citation_author=JH. Jhong;citation_author=J. Lee;citation_author=JY. Koo;citation_title=Meta-analytic support vector machine for integrating multiple omics data;citation_pages=2;citation_volume=10;citation_year=2017;citation_issue=1" /> <meta name="citation_reference" content="citation_journal_title=Anticancer Research;citation_journal_abbrev=Anticancer Res;citation_author=AJ. Yiu;citation_author=CY. Yiu;citation_title=Biomarkers in Colorectal Cancer;citation_pages=1093-1102;citation_volume=36;citation_year=2016;citation_issue=3;citation_pmid=26977004" /> <meta name="citation_reference" content="citation_journal_title=Bioinformatics;citation_author=W. He;citation_title=A spline function approach for detecting differentially expressed genes in microarray data analysis;citation_volume=20;citation_year=2004;citation_issue=17;citation_pmid=15180936;citation_doi=10.1093/bioinformatics/bth339" /> <meta name="citation_reference" content="citation_journal_title=Genome Research;citation_journal_abbrev=Genome Res;citation_author=JG. Thomas;citation_author=JM. Olson;citation_author=SJ. Tapscott;citation_author=LP. Zhao;citation_title=An Efficient and Robust Statistical Modeling Approach to Discover Differentially Expressed Genes Using Genomic Expression Profiles;citation_pages=1227-1236;citation_volume=11;citation_year=2001;citation_issue=7;citation_pmid=11435405;citation_doi=10.1101/gr.165101" /> <meta name="citation_reference" content="citation_journal_title=Bioinformatics;citation_journal_abbrev=Bioinformatics;citation_author=W. Pan;citation_title=A comparative review of statistical methods for discovering differentially expressed genes in replicated microarray experiments;citation_pages=546-554;citation_volume=18;citation_year=2002;citation_issue=4;citation_pmid=12016052;citation_doi=10.1093/bioinformatics/18.4.546" /> <meta name="citation_reference" content="citation_journal_title=Bioinformatics;citation_journal_abbrev=Bioinformatics;citation_author=OG. Troyanskaya;citation_author=ME. Garber;citation_author=PO. Brown;citation_author=D. Botstein;citation_author=RB. Altman;citation_title=Nonparametric methods for identifying differentially expressed genes in microarray data;citation_pages=1454-1461;citation_volume=18;citation_year=2002;citation_issue=11;citation_pmid=12424116;citation_doi=10.1093/bioinformatics/18.11.1454" /> <meta name="citation_reference" content="citation_journal_title=Gene;citation_author=G. Xu;citation_author=M. Zhang;citation_author=H. Zhu;citation_author=J. Xu;citation_title=A 15-gene signature for prediction of colon cancer recurrence and prognosis based on SVM;citation_pages=33-40;citation_volume=604;citation_year=2017" /> <meta name="citation_reference" content="citation_journal_title=BMC Genomics;citation_author=Y. Hu;citation_author=T. Hase;citation_author=HP. Li;citation_author=S. Prabhakar;citation_author=H. Kitano;citation_author=SK. Ng;citation_author=S. Ghosh;citation_author=LJ. Wee;citation_title=A machine learning approach for the identification of key markers involved in brain development from single-cell transcriptomic data;citation_pages=1025;citation_volume=17;citation_year=2016;citation_issue=suppl 13" /> <meta name="citation_reference" content="citation_journal_title=BMC cancer [electronic resource];citation_journal_abbrev=BMC Cancer;citation_author=C. Henneges;citation_author=D. Bullinger;citation_author=R. Fux;citation_author=N. Friese;citation_author=H. Seeger;citation_author=H. Neubauer;citation_author=S. Laufer;citation_author=CH. Gleiter;citation_author=M. Schwab;citation_author=A. Zell;citation_author=B. Kammerer;citation_title=Prediction of breast cancer by profiling of urinary RNA metabolites using Support Vector Machine-based feature selection.;citation_pages=104-104;citation_volume=9;citation_year=2009;citation_pmid=19344524;citation_doi=10.1186/1471-2407-9-104" /> <meta name="citation_reference" content="citation_journal_title=Oncology reports;citation_journal_abbrev=Oncol Rep;citation_author=M. Han;citation_author=J. Dai;citation_author=Y. Zhang;citation_author=Q. Lin;citation_author=M. Jiang;citation_author=X. Xu;citation_author=Q. Liu;citation_author=J. Jia;citation_title=Support vector machines coupled with proteomics approaches for detecting biomarkers predicting chemotherapy resistance in small cell lung cancer.;citation_pages=2233-2238;citation_volume=28;citation_year=2012;citation_issue=6;citation_pmid=22992788" /> <meta name="citation_reference" content="citation_journal_title=Bioinformatics;citation_author=T. Abeel;citation_author=T. Helleputte;citation_author=Y. Van de Peer;citation_author=P. Dupont;citation_author=Y. Saeys;citation_title=Robust biomarker identification for cancer diagnosis with ensemble feature selection methods;citation_pages=392-398;citation_volume=26;citation_year=2009;citation_issue=3;citation_pmid=19942583" /> <meta name="citation_reference" content="citation_journal_title=J Mach Learn Res;citation_author=I. Guyon;citation_author=A. Elisseeff;citation_title=An introduction to variable and feature selection;citation_pages=1157-1182;citation_volume=3;citation_year=2003;citation_doi=10.1162/153244303322753616" /> <meta name="citation_reference" content="citation_journal_title=Mach Learn;citation_author=I. Guyon;citation_author=J. Weston;citation_author=S. Barnhill;citation_author=V. Vapnik;citation_title=Gene selection for cancer classification using support vector machines;citation_pages=389-422;citation_volume=46;citation_year=2002;citation_issue=1;citation_doi=10.1023/A:1012487302797" /> <meta name="citation_reference" content="citation_journal_abbrev=BMC Syst Biol;citation_author=L. Chen;citation_author=J. Xuan;citation_author=RB. Riggins;citation_author=R. Clarke;citation_author=Y. Wang;citation_title=Identifying cancer biomarkers by network-constrained support vector machines.;citation_pages=161-161;citation_volume=5;citation_year=2011;citation_issue=1;citation_pmid=21992556;citation_doi=10.1186/1752-0509-5-161" /> <meta name="citation_reference" content="citation_journal_title=In Vivo;citation_journal_abbrev=In Vivo;citation_author=D. Stagos;citation_author=E. Karaberis;citation_author=D. Kouretas;citation_title=Assessment of Antioxidant / Anticarcinogenic Activity of Plant Extracts by a Combination of Molecular Methods;citation_pages=741-747;citation_volume=19;citation_year=2005;citation_issue=4;citation_pmid=15999544" /> <meta name="citation_reference" content="citation_journal_title=Journal of Chemical Information and Computer Sciences;citation_journal_abbrev=Journal of Chemical Information and Computer Sciences;citation_author=MK. Warmuth;citation_author=J. Liao;citation_author=G. Rätsch;citation_author=M. Mathieson;citation_author=S. Putta;citation_author=C. Lemmen;citation_title=Active learning with support vector machines in the drug discovery process.;citation_pages=667-673;citation_volume=43;citation_year=2003;citation_issue=2;citation_pmid=12653536" /> <meta name="citation_reference" content="citation_journal_title=Sci Rep;citation_author=S. Gupta;citation_author=K. Chaudhary;citation_author=R. Kumar;citation_author=G. Gautam;citation_author=JS. Nanda;citation_author=SK. Dhanda;citation_author=SK. Brahmachari;citation_author=GPS. Raghava;citation_title=Prioritization of anticancer drugs against a cancer using genomic features of cancer cells: A step towards personalized medicine;citation_pages=23857;citation_volume=6;citation_year=2016" /> <meta name="citation_reference" content="citation_journal_title=PLoS One;citation_author=S. Bundela;citation_author=A. Sharma;citation_author=PS. Bisen;citation_title=Potential compounds for oral cancer treatment: resveratrol, nimbolide, lovastatin, bortezomib, vorinostat, berberine, pterostilbene, deguelin, andrographolide, and colchicine;citation_pages=e0141719;citation_volume=10;citation_year=2015;citation_issue=11;citation_pmid=26536350" /> <meta name="citation_reference" content="citation_journal_title=Int J Mach Learn Comput;citation_author=A. Matsumoto;citation_author=S. Aoki;citation_author=H. Ohwada;citation_title=Comparison of random forest and SVM for raw data in drug discovery: prediction of radiation protection and toxicity case study;citation_pages=145-148;citation_volume=6;citation_year=2016;citation_issue=2" /> <meta name="citation_reference" content="citation_journal_title=Biochem Biophys Res Commun;citation_author=A. Morita;citation_author=S. Ariyasu;citation_author=B. Wang;citation_author=T. Asanuma;citation_author=T. Onoda;citation_author=A. Sawa;citation_author=K. Tanaka;citation_author=I. Takahashi;citation_author=S. Togami;citation_author=M. Nenoi;citation_title=AS-2, a novel inhibitor of p53-dependent apoptosis, prevents apoptotic mitochondrial dysfunction in a transcription-independent manner and protects mice from a lethal dose of ionizing radiation;citation_pages=1498-1504;citation_volume=450;citation_year=2014;citation_issue=4" /> <meta name="citation_reference" content="citation_journal_title=Journal of chemical information and modeling;citation_journal_abbrev=J Chem Inf Model;citation_author=A. Volkamer;citation_author=D. Kuhn;citation_author=T. Grombacher;citation_author=F. Rippmann;citation_author=M. Rarey;citation_title=Combining global and local measures for structure-based druggability predictions.;citation_pages=360-372;citation_volume=52;citation_year=2012;citation_issue=2;citation_pmid=22148551;citation_doi=10.1021/ci200454v" /> <meta name="citation_reference" content="citation_journal_title=Journal of chemical information and modeling;citation_journal_abbrev=J Chem Inf Model;citation_author=L. Li;citation_author=B. Wang;citation_author=SO. Meroueh;citation_title=Support vector regression scoring of receptor-ligand complexes for rank-ordering and virtual screening of chemical libraries.;citation_pages=2132-2138;citation_volume=51;citation_year=2011;citation_issue=9;citation_pmid=21728360;citation_doi=10.1021/ci200078f" /> <meta name="citation_reference" content="citation_journal_title=J Chem Inf Model;citation_author=GB. Li;citation_author=LL. Yang;citation_author=WJ. Wang;citation_author=LL. Li;citation_author=SY. Yang;citation_title=ID-Score: a new empirical scoring function based on a comprehensive set of descriptors related to protein-ligand interactions;citation_pages=592-600;citation_volume=53;citation_year=2013;citation_issue=3;citation_pmid=23394072;citation_doi=10.1021/ci300493w" /> <meta name="citation_reference" content="citation_journal_title=PloS One;citation_author=Q. Wang;citation_author=Y. Feng;citation_author=J. Huang;citation_author=T. Wang;citation_author=G. Cheng;citation_title=A novel framework for the identification of drug target proteins: Combining stacked auto-encoders with a biased support vector machine;citation_pages=e0176486;citation_volume=12;citation_year=2017;citation_issue=4" /> <meta name="citation_reference" content="citation_journal_title=Genome Med;citation_author=J. Jeon;citation_author=S. Nim;citation_author=J. Teyra;citation_author=A. Datti;citation_author=JL. Wrana;citation_author=SS. Sidhu;citation_author=J. Moffat;citation_author=PM. Kim;citation_title=A systematic approach to identify novel cancer drug targets using machine learning, inhibitor design and high-throughput screening;citation_pages=57;citation_volume=6;citation_year=2014;citation_issue=7" /> <meta name="citation_reference" content="citation_journal_title=BMC Cancer;citation_author=H. Singh;citation_author=R. Kumar;citation_author=S. Singh;citation_author=K. Chaudhary;citation_author=A. Gautam;citation_author=GP. Raghava;citation_title=Prediction of anticancer molecules using hybrid model developed on molecules screened against NCI-60 cancer cell lines;citation_pages=77;citation_volume=16;citation_year=2016;citation_issue=1" /> <meta name="citation_reference" content="citation_journal_title=BMC Genomics;citation_author=LC. Stetson;citation_author=T. Pearl;citation_author=Y. Chen;citation_author=JS. Barnholtz-Sloan;citation_title=Computational identification of multi-omic correlates of anticancer therapeutic response;citation_pages=S2;citation_volume=15;citation_year=2014;citation_issue=7" /> <meta name="citation_reference" content="citation_journal_title=CPT Pharmacometrics Syst Pharmacol;citation_author=HA. Hejase;citation_author=C. Chan;citation_title=Improving Drug Sensitivity Prediction Using Different Types of Data;citation_pages=98-105;citation_volume=4;citation_year=2015" /> <meta name="citation_reference" content="citation_journal_title=BMC Bioinformatics;citation_author=E. Hazai;citation_author=I. Hazai;citation_author=I. Ragueneau-Majlessi;citation_author=SP. Chung;citation_author=Z. Bikadi;citation_author=Q. Mao;citation_title=Predicting substrates of the human breast cancer resistance protein using a support vector machine method;citation_pages=130;citation_volume=14;citation_year=2013;citation_pmid=23586520;citation_doi=10.1186/1471-2105-14-130" /> <meta name="citation_reference" content="citation_journal_title=J Cell Biochem;citation_author=N. Normanno;citation_author=AM. Rachiglio;citation_author=C. Roma;citation_author=F. Fenizia;citation_author=C. Esposito;citation_author=R. Pasquale;citation_author=ML. La Porta;citation_author=A. Iannaccone;citation_author=F. Micheli;citation_author=M. Santangelo;citation_title=Molecular diagnostics and personalized medicine in oncology: challenges and opportunities;citation_pages=514-524;citation_volume=114;citation_year=2013;citation_issue=3;citation_pmid=22991232;citation_doi=10.1002/jcb.24401" /> <meta name="citation_reference" content="citation_journal_title=Science;citation_journal_abbrev=Science;citation_author=B. Vogelstein;citation_author=N. Papadopoulos;citation_author=VE. Velculescu;citation_author=S. Zhou;citation_author=LA. Diaz;citation_author=KW. Kinzler;citation_title=Cancer Genome Landscapes;citation_pages=1546-1558;citation_volume=339;citation_year=2013;citation_issue=6127;citation_pmid=23539594;citation_doi=10.1126/science.1235122" /> <meta name="citation_reference" content="citation_title=Machine learning predictions of cancer driver mutations;citation_author=EJ. Jordan;citation_author=R. Radhakrishnan" /> <meta name="citation_reference" content="citation_journal_title=Genomics;citation_journal_abbrev=Genomics;citation_author=E. Capriotti;citation_author=RB. Altman;citation_title=A new disease-specific machine learning approach for the prediction of cancer-causing missense variants.;citation_pages=310-317;citation_volume=98;citation_year=2011;citation_issue=4;citation_pmid=21763417;citation_doi=10.1016/j.ygeno.2011.06.010" /> <meta name="citation_reference" content="citation_journal_title=BMC Genomics;citation_author=JM. Izarzugaza;citation_author=A. del Pozo;citation_author=M. Vazquez;citation_author=A. Valencia;citation_title=Prioritization of pathogenic mutations in the protein kinase superfamily;citation_pages=S3;citation_volume=13;citation_year=2012;citation_issue=4" /> <meta name="citation_reference" content="citation_journal_title=Bioinformatics;citation_author=H. Tan;citation_author=J. Bao;citation_author=X. Zhou;citation_title=A novel missense-mutation-related feature extraction scheme for ‘driver’mutation identification;citation_volume=28;citation_year=2012;citation_issue=22;citation_pmid=23044540;citation_doi=10.1093/bioinformatics/bts558" /> <meta name="citation_reference" content="citation_journal_title=Genomics;citation_journal_abbrev=Genomics;citation_author=E. Capriotti;citation_author=RB. Altman;citation_title=A new disease-specific machine learning approach for the prediction of cancer-causing missense variants.;citation_pages=310-317;citation_volume=98;citation_year=2011;citation_issue=4;citation_pmid=21763417;citation_doi=10.1016/j.ygeno.2011.06.010" /> <meta name="citation_reference" content="citation_journal_title=Sci Rep;citation_author=MG. Bari;citation_author=CY. Ung;citation_author=C. Zhang;citation_author=S. Zhu;citation_author=H. Li;citation_title=Machine Learning-assisted network inference approach to identify a new class of genes that coordinate the functionality of cancer networks;citation_pages=6993;citation_volume=7;citation_year=2017" /> <meta name="citation_reference" content="citation_journal_title=Clinical Cancer Research;citation_journal_abbrev=Clin. Cancer Res.;citation_author=J. Listgarten;citation_author=S. Damaraju;citation_author=B. Poulin;citation_author=L. Cook;citation_author=J. Dufour;citation_author=A. Driga;citation_author=J. Mackey;citation_author=D. Wishart;citation_author=R. Greiner;citation_author=B. Zanke;citation_title=Predictive Models for Breast Cancer Susceptibility from Multiple Single Nucleotide Polymorphisms;citation_pages=2725-2737;citation_volume=10;citation_year=2004;citation_issue=8;citation_pmid=15102677;citation_doi=10.1158/1078-0432.CCR-1115-03" /> <meta name="citation_reference" content="citation_journal_title=Toxicology letters;citation_journal_abbrev=Toxicol Lett;citation_author=H. Schwender;citation_author=M. Zucknick;citation_author=K. Ickstadt;citation_author=HM. Bolt;citation_title=A pilot study on the application of statistical classification procedures to molecular epidemiological data.;citation_pages=291-299;citation_volume=151;citation_year=2004;citation_issue=1;citation_pmid=15177665;citation_doi=10.1016/j.toxlet.2004.02.021" /> <meta name="citation_reference" content="citation_journal_title=Genetic epidemiology;citation_journal_abbrev=Genet Epidemiol;citation_author=SH. Chen;citation_author=J. Sun;citation_author=L. Dimitrov;citation_author=AR. Turner;citation_author=TS. Adams;citation_author=DA. Meyers;citation_author=BL. Chang;citation_author=SL. Zheng;citation_author=H. Grönberg;citation_author=J. Xu;citation_title=A support vector machine approach for detecting gene-gene interaction.;citation_pages=152-167;citation_volume=32;citation_year=2008;citation_issue=2;citation_pmid=17968988;citation_doi=10.1002/gepi.20272" /> <meta name="citation_reference" content="citation_journal_title=Nucleic Acids Res;citation_author=Y. Guo;citation_author=L. Yu;citation_author=Z. Wen;citation_author=M. Li;citation_title=Using support vector machine combined with auto covariance to predict protein–protein interactions from protein sequences;citation_volume=36;citation_year=2008;citation_issue=9;citation_pmid=18390576;citation_doi=10.1093/nar/gkn159" /> <meta name="citation_reference" content="citation_journal_title=Genet Mol Res;citation_title=Protein-protein interaction network construction for cancer using a new L1/2-penalized Net-SVM model;citation_author=H. Chai;citation_author=HH. Huang;citation_author=HK. Jiang;citation_author=Y. Liang;citation_author=LY. Xia;citation_volume=15;citation_year=2016;citation_issue=3" /> <meta name="citation_reference" content="citation_journal_abbrev=PLoS Comput Biol;citation_author=AL. Tarca;citation_author=VJ. Carey;citation_author=XW. Chen;citation_author=R. Romero;citation_author=S. Drăghici;citation_title=Machine learning and its applications to biology.;citation_pages=e116-e116;citation_volume=3;citation_year=2007;citation_issue=6;citation_pmid=17604446;citation_doi=10.1371/journal.pcbi.0030116" /> <meta name="citation_fulltext_world_readable" content="" /> <meta name="twitter:title" content="Applications of Support Vector Machine (SVM) Learning in Cancer Genomics" /> <meta name="twitter:card" content="summary" /> <meta name="twitter:description" content="Machine learning with maximization (support) of separating margin (vector), called support vector machine (SVM) learning, is a powerful classification tool that has been used for cancer genomic classification or subtyping. Today, as advancements in high-throughput technologies lead to production of large amounts of genomic and epigenomic data, the classification feature of SVMs is expanding its use in cancer genomics, leading to the discovery of new biomarkers, new drug targets, and a better understanding of cancer driver genes. Herein we reviewed the recent progress of SVMs in cancer genomic studies. We intend to comprehend the strength of the SVM learning and its future perspective in cancer genomic applications." /> <meta name="og-title" property="og:title" content="Applications of Support Vector Machine (SVM) Learning in Cancer Genomics" /> <meta name="og-url" property="og:url" content="https://cgp.iiarjournals.org/content/15/1/41" /> <meta name="og-site-name" property="og:site_name" content="Cancer Genomics & Proteomics" /> <meta name="og-description" property="og:description" content="Machine learning with maximization (support) of separating margin (vector), called support vector machine (SVM) learning, is a powerful classification tool that has been used for cancer genomic classification or subtyping. Today, as advancements in high-throughput technologies lead to production of large amounts of genomic and epigenomic data, the classification feature of SVMs is expanding its use in cancer genomics, leading to the discovery of new biomarkers, new drug targets, and a better understanding of cancer driver genes. Herein we reviewed the recent progress of SVMs in cancer genomic studies. We intend to comprehend the strength of the SVM learning and its future perspective in cancer genomic applications." /> <meta name="og-type" property="og:type" content="article" /> <meta name="og-image" property="og:image" content="" /> <link rel="shortlink" href="/node/1056" /> <link rel="shortcut icon" href="https://cgp.iiarjournals.org/sites/default/files/images/favicon.ico" type="image/vnd.microsoft.icon" /> <meta name="viewport" content="width=device-width, initial-scale=1" /> <title>Applications of Support Vector Machine (SVM) Learning in Cancer Genomics | Cancer Genomics & Proteomics</title> <link type="text/css" rel="stylesheet" href="/sites/default/files/advagg_css/css__QEy_BpbtMcsqv3xURK855GSs2fFjOibU10yA758Mn4c__NucWi_bEk5E3BNVDtTt2nhiPtE1A5I24YwRDQ2fojJ0__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.css" media="all" /> <link type="text/css" rel="stylesheet" href="//cdn.jsdelivr.net/qtip2/2.2.1/jquery.qtip.min.css" media="all" /> <link type="text/css" rel="stylesheet" href="/sites/default/files/advagg_css/css__Bi_W5XyWR37hERhqY6fxVfxOJ8bc2ccuCkZKKYQaPQA__gtM5qunHvjDk9WKf5PN_Jvx9OzZNSINDUSxztvCxw_E__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.css" media="all" /> <style type="text/css" media="all"> /* <![CDATA[ */ #sliding-popup.sliding-popup-bottom,#sliding-popup.sliding-popup-bottom .eu-cookie-withdraw-banner,.eu-cookie-withdraw-tab{background:#0779bf}#sliding-popup.sliding-popup-bottom.eu-cookie-withdraw-wrapper{background:transparent}#sliding-popup .popup-content #popup-text h1,#sliding-popup .popup-content #popup-text h2,#sliding-popup .popup-content #popup-text h3,#sliding-popup .popup-content #popup-text p,.eu-cookie-compliance-secondary-button,.eu-cookie-withdraw-tab{color:#fff !important}.eu-cookie-withdraw-tab{border-color:#fff}.eu-cookie-compliance-more-button{color:#fff !important} /* ]]> */ </style> <!--[if lte IE 7]> <link type="text/css" rel="stylesheet" href="/sites/default/files/advagg_css/css__ElJr3PIJEvw3qLXc1cnYiLj2G4KgDPSXFOfm6Phf8hw__JdWGm15cDWjsK6KrFlQVXQix9YgNeYysf22XZHj-Y-c__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.css" media="all" /> <![endif]--> <link type="text/css" rel="stylesheet" href="/sites/default/files/advagg_css/css__BuoDuzoWcz2CL9-rYVqiOwZYB0s9mtqPm1bLrGHX4Z4__WNptNuPkTJ2rxI9jvljwIQXeYY9GgnsTxhjOkFT4fEY__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.css" media="all" /> <link type="text/css" rel="stylesheet" href="/sites/default/files/advagg_css/css__rG8r2V0cF_prwZJnN_tvDrDlTTg8BjA0vhYjNBaIOAk___du_bBf5kHj1iB8EQkEYeawhf4b7MIF4JLA4d_Cf1ns__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.css" media="all" /> <!--[if (lt IE 9)&(!IEMobile)]> <link type="text/css" rel="stylesheet" href="/sites/default/files/advagg_css/css__XH6bpcI0f2dImc-p674DLCZtWBGb-QwxJK1YexVGtno__vUceGprdo5nIhV6DH93X7fI3r8RcTJbChbas9TQXeW4__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.css" media="all" /> <![endif]--> <!--[if gte IE 9]><!--> <link type="text/css" rel="stylesheet" href="/sites/default/files/advagg_css/css__oWyrHF_mmv3c4PPGrsNSmh5Ub_1TfiuNA2i1_MOafWg__1kTjT7uqr7v6BlTbuE-4U2S8EzyEcBTxZhvp1VjA-qo__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.css" media="all" /> <!--<![endif]--> <!--[if gte IE 9]><!--> <link type="text/css" rel="stylesheet" href="/sites/default/files/advagg_css/css__-Kek3KTto4Kje1mJ9bp_-a_lv0D9QS29NgfFBV-inOY__90wksBfd5YlmG0UjedmGQFn8Ano49PMQRwGgVOM50YE__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.css" media="all" /> <!--<![endif]--> <link type="text/css" rel="stylesheet" href="/sites/default/files/advagg_css/css__3YKvtweamPhMwLDmcd4AZbWW-SNlgOntOT_-9J1hwa0__iBfm7f9Zjr1nQCVzxlloL1f_WY5-IVR9o7sZ7ib2wp0__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.css" media="all" /> <script type="text/javascript" src="/sites/default/files/advagg_js/js__BShWI0Bj1yPNunY96mdu5LhhXKGhe6T0j5bLG4Re33A__toIaeQSexL2pU3v-qq0II5m42ENHiNNbOt1OxsM-3gs__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.js"></script> <script type="text/javascript" src="//cdn.jsdelivr.net/qtip2/2.2.1/jquery.qtip.min.js"></script> <script type="text/javascript" src="/sites/default/files/advagg_js/js__tYyyy-ZDT34crTMTDjttk58W5PQ5bu0pCZhDKfkrMnI__I1c0MqTE3Bk41WOjzd700omtoDACPuU5yGsU1QJK6wo__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.js"></script> <script type="text/javascript"> <!--//--><![CDATA[//><!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i<a.length;i++)j=a[i],e(j)?g(j,0,l,0):w(j)?B(j):Object(j)===j&&h(j,l);else Object(a)===a&&h(a,l)},B.addPrefix=function(a,b){z[a]=b},B.addFilter=function(a){x.push(a)},B.errorTimeout=1e4,null==b.readyState&&b.addEventListener&&(b.readyState="loading",b.addEventListener("DOMContentLoaded",A=function(){b.removeEventListener("DOMContentLoaded",A,0),b.readyState="complete"},0)),a.yepnope=k(),a.yepnope.executeStack=h,a.yepnope.injectJs=function(a,c,d,e,i,j){var k=b.createElement("script"),l,o,e=e||B.errorTimeout;k.src=a;for(o in d)k.setAttribute(o,d[o]);c=j?h:c||f,k.onreadystatechange=k.onload=function(){!l&&g(k.readyState)&&(l=1,c(),k.onload=k.onreadystatechange=null)},m(function(){l||(l=1,c(1))},e),i?k.onload():n.parentNode.insertBefore(k,n)},a.yepnope.injectCss=function(a,c,d,e,g,i){var e=b.createElement("link"),j,c=i?h:c||f;e.href=a,e.rel="stylesheet",e.type="text/css";for(j in d)e.setAttribute(j,d[j]);g||(n.parentNode.insertBefore(e,n),m(c,0))}})(this,document); //--><!]]> </script> <script type="text/javascript"> <!--//--><![CDATA[//><!-- yepnope({ test: Modernizr.matchmedia, nope: '/sites/all/libraries/media-match/media.match.min.js' }); //--><!]]> </script> <script type="text/javascript"> <!--//--><![CDATA[//><!-- document.createElement( "picture" ); //--><!]]> </script> <script type="text/javascript"> <!--//--><![CDATA[//><!-- if(typeof window.MathJax === "undefined") window.MathJax = { menuSettings: { zoom: "Click" } }; //--><!]]> </script> <script type="text/javascript" src="/sites/default/files/advagg_js/js__GM3GJPR36rRIz0TRkjC5OQwrioSyN9aoYRivDhCO_AM__qAl84FcCv2jyN22yFGS5Oc85cjd9zKX6p_cFNLGhe-M__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.js" async="async"></script> <script type="text/javascript" defer="defer" async="async" src="//cdn.foxycart.com/iiar.ecommerce.highwire.org/loader.js"></script> <script type="text/javascript" async="async" src="https://scholar.google.com/scholar_js/casa.js"></script> <script type="text/javascript"> <!--//--><![CDATA[//><!-- jQuery.extend(Drupal.settings,{"basePath":"\/","pathPrefix":"","ajaxPageState":{"theme":"jcore_1","theme_token":"ru_hsVShx6v1nsQivD6iTeu0jVi8qOFCMuQoIDA4MyY","jquery_version":"1.8","css":{"modules\/system\/system.base.css":1,"modules\/system\/system.menus.css":1,"modules\/system\/system.messages.css":1,"modules\/system\/system.theme.css":1,"misc\/ui\/jquery.ui.core.css":1,"misc\/ui\/jquery.ui.theme.css":1,"misc\/ui\/jquery.ui.button.css":1,"misc\/ui\/jquery.ui.resizable.css":1,"misc\/ui\/jquery.ui.dialog.css":1,"misc\/ui\/jquery.ui.tooltip.css":1,"sites\/all\/modules\/contrib\/jquery_update\/replace\/ui\/themes\/base\/minified\/jquery.ui.accordion.min.css":1,"sites\/all\/modules\/contrib\/date\/date_api\/date.css":1,"sites\/all\/modules\/contrib\/date\/date_popup\/themes\/datepicker.1.7.css":1,"modules\/field\/theme\/field.css":1,"sites\/all\/modules\/highwire\/highwire\/highwire_draw\/css\/highwire-draw.css":1,"sites\/all\/modules\/highwire\/highwire\/highwire_folders\/highwire_folders.css":1,"sites\/all\/modules\/highwire\/highwire\/highwire_foxycart\/highwire_foxycart.css":1,"sites\/all\/modules\/highwire\/highwire\/highwire_responsive\/css\/highwire-responsive.css":1,"sites\/all\/modules\/highwire\/highwire\/highwire_saved_searches\/highwire_saved_searches.css":1,"sites\/all\/modules\/highwire\/highwire\/highwire_user\/highwire_user.css":1,"modules\/node\/node.css":1,"sites\/all\/modules\/contrib\/picture\/picture_wysiwyg.css":1,"modules\/search\/search.css":1,"modules\/user\/user.css":1,"sites\/all\/modules\/contrib\/views\/css\/views.css":1,"sites\/all\/modules\/contrib\/ckeditor\/css\/ckeditor.css":1,"sites\/all\/modules\/contrib\/colorbox\/styles\/default\/colorbox_style.css":1,"sites\/all\/modules\/contrib\/ctools\/css\/ctools.css":1,"sites\/all\/modules\/contrib\/foxycart\/foxycart.css":1,"sites\/all\/modules\/highwire\/highwire\/highwire.style.highwire.css":1,"sites\/all\/modules\/highwire\/highwire\/css\/nlm-elements.css":1,"sites\/all\/modules\/contrib\/panels\/css\/panels.css":1,"public:\/\/ctools\/css\/263bfdb18936424f0ade19d6bd885f37.css":1,"sites\/all\/modules\/contrib\/panels_ajax_tab\/css\/panels_ajax_tab.css":1,"sites\/all\/modules\/highwire\/highwire\/highwire.style.markup.css":1,"\/\/cdn.jsdelivr.net\/qtip2\/2.2.1\/jquery.qtip.min.css":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/layouts\/highwire_2col_stacked\/highwire-2col-stacked.css":1,"sites\/all\/modules\/contrib\/forward\/forward.css":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/content_types\/css\/highwire_share_link.css":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/content_types\/css\/highwire_copy_permalink.css":1,"sites\/all\/modules\/highwire\/highwire\/highwire_responsive\/plugins\/styles\/highwire_responsive_toggle\/highwire_responsive_toggle.css.less":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/content_types\/css\/highwire_corrections.css":1,"sites\/all\/modules\/contrib\/nice_menus\/css\/nice_menus.css":1,"sites\/all\/modules\/contrib\/nice_menus\/css\/nice_menus_default.css":1,"sites\/all\/modules\/contrib\/panels\/plugins\/layouts\/onecol\/onecol.css":1,"sites\/all\/modules\/contrib\/eu_cookie_compliance\/css\/eu_cookie_compliance.css":1,"sites\/all\/modules\/highwire\/highwire\/css\/highwire.gtranslate.css":1,"sites\/all\/themes\/highwire\/jcore_1\/css\/userbar-dropdown-menu.css":1,"sites\/all\/modules\/highwire\/highwire\/highwire_theme_tools\/css\/font-hwicons.css":1,"sites\/all\/modules\/highwire\/highwire\/highwire_theme_tools\/css\/font-hwicons-glyphs.css":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/content_types\/css\/highwire_reports_feed.css":1,"sites\/all\/modules\/highwire\/highwire\/css\/highwire-article-citation-list.css":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/content_types\/css\/highwire_citing_links.css":1,"sites\/all\/themes\/highwire\/jcore_1\/eu_cookie_compliance.css":1,"sites\/all\/themes\/highwire\/jcore_1\/css\/font-awesome-ie7.css":1,"sites\/all\/themes\/contrib\/omega\/alpha\/css\/alpha-reset.css":1,"sites\/all\/themes\/contrib\/omega\/alpha\/css\/alpha-mobile.css":1,"sites\/all\/themes\/contrib\/omega\/alpha\/css\/alpha-alpha.css":1,"sites\/all\/themes\/contrib\/omega\/omega\/css\/formalize.css":1,"sites\/all\/themes\/contrib\/omega\/omega\/css\/omega-text.css":1,"sites\/all\/themes\/contrib\/omega\/omega\/css\/omega-branding.css":1,"sites\/all\/themes\/contrib\/omega\/omega\/css\/omega-menu.css":1,"sites\/all\/themes\/contrib\/omega\/omega\/css\/omega-forms.css":1,"sites\/all\/modules\/highwire\/highwire\/css\/highwire-forms.css":1,"sites\/all\/themes\/highwire\/jcore_1\/css\/mobile-reset.css":1,"sites\/all\/themes\/highwire\/jcore_1\/css\/font-awesome.css":1,"sites\/all\/themes\/highwire\/jcore_1\/css\/forms.css":1,"sites\/all\/themes\/highwire\/jcore_1\/css\/global.css":1,"sites\/all\/themes\/highwire\/jcore_1\/css\/jquery-ui-elements.css":1,"sites\/all\/themes\/highwire\/jcore_1\/css\/text.css":1,"sites\/all\/themes\/highwire\/jcore_1\/css\/eletters.css":1,"sites\/all\/themes\/highwire\/jcore_1\/css\/colors.css.less":1,"ie::normal::sites\/all\/themes\/highwire\/jcore_1\/css\/jcore-1-jcore-default.css":1,"ie::normal::sites\/all\/themes\/highwire\/jcore_1\/css\/jcore-1-jcore-default-normal.css":1,"ie::normal::sites\/all\/themes\/highwire\/jcore_1\/css\/grid\/jcore_default\/normal\/jcore-default-normal-30.css":1,"narrow::sites\/all\/themes\/highwire\/jcore_1\/css\/jcore-1-jcore-default.css":1,"narrow::sites\/all\/themes\/highwire\/jcore_1\/css\/jcore-1-jcore-default-narrow.css":1,"sites\/all\/themes\/highwire\/jcore_1\/css\/grid\/jcore_default\/narrow\/jcore-default-narrow-30.css":1,"normal::sites\/all\/themes\/highwire\/jcore_1\/css\/jcore-1-jcore-default.css":1,"normal::sites\/all\/themes\/highwire\/jcore_1\/css\/jcore-1-jcore-default-normal.css":1,"sites\/all\/themes\/highwire\/jcore_1\/css\/grid\/jcore_default\/normal\/jcore-default-normal-30.css":1,"wide::sites\/all\/themes\/highwire\/jcore_1\/css\/jcore-1-jcore-default.css":1,"wide::sites\/all\/themes\/highwire\/jcore_1\/css\/jcore-1-jcore-default-wide.css":1,"sites\/all\/themes\/highwire\/jcore_1\/css\/grid\/jcore_default\/wide\/jcore-default-wide-30.css":1,"sites\/all\/modules\/shared\/jnl_iiar_styles\/css\/jnl_iiar_styles.css.less":1},"js":{"sites\/all\/libraries\/enquire.js\/enquire.min.js":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/content_types\/js\/highwire_panels_ajax_tab.js":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/highwire_markup_process\/js\/highwire_google_scholar_sprinkle.js":1,"sites\/all\/libraries\/lazysizes\/lazysizes.min.js":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/highwire_markup_process\/js\/highwire_openurl.js":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/highwire_markup_process\/js\/highwire_tables.js":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/highwire_markup_process\/js\/highwire_figures.js":1,"sites\/all\/modules\/highwire\/highwire\/highwire_user\/plugins\/content_types\/js\/highwire_user_salutation.js":1,"sites\/all\/modules\/highwire\/highwire\/highwire_foxycart\/highwire_foxycart.js":1,"sites\/all\/modules\/contrib\/eu_cookie_compliance\/js\/eu_cookie_compliance.js":1,"sites\/all\/libraries\/modernizr\/modernizr.min.js":1,"sites\/all\/modules\/contrib\/jquery_update\/replace\/jquery\/1.8\/jquery.min.js":1,"misc\/jquery-extend-3.4.0.js":1,"misc\/jquery.once.js":1,"misc\/drupal.js":1,"sites\/all\/modules\/contrib\/jquery_update\/replace\/ui\/ui\/minified\/jquery.ui.core.min.js":1,"sites\/all\/modules\/contrib\/jquery_update\/replace\/ui\/ui\/minified\/jquery.ui.widget.min.js":1,"sites\/all\/modules\/contrib\/jquery_update\/replace\/ui\/external\/jquery.cookie.js":1,"sites\/all\/modules\/contrib\/jquery_update\/replace\/misc\/jquery.form.min.js":1,"sites\/all\/modules\/contrib\/jquery_update\/replace\/ui\/ui\/minified\/jquery.ui.button.min.js":1,"sites\/all\/modules\/contrib\/jquery_update\/replace\/ui\/ui\/minified\/jquery.ui.mouse.min.js":1,"sites\/all\/modules\/contrib\/jquery_update\/replace\/ui\/ui\/minified\/jquery.ui.draggable.min.js":1,"sites\/all\/modules\/contrib\/jquery_update\/replace\/ui\/ui\/minified\/jquery.ui.position.min.js":1,"sites\/all\/modules\/contrib\/jquery_update\/replace\/ui\/ui\/minified\/jquery.ui.resizable.min.js":1,"sites\/all\/modules\/contrib\/jquery_update\/replace\/ui\/ui\/minified\/jquery.ui.dialog.min.js":1,"sites\/all\/modules\/contrib\/jquery_update\/replace\/ui\/ui\/minified\/jquery.ui.tooltip.min.js":1,"sites\/all\/libraries\/jquery.bgiframe\/jquery.bgiframe.js":1,"sites\/all\/libraries\/jquery.hoverIntent\/jquery.hoverIntent.js":1,"sites\/all\/libraries\/superfish\/superfish.js":1,"sites\/all\/modules\/contrib\/nice_menus\/js\/nice_menus.js":1,"sites\/all\/modules\/contrib\/jquery_update\/replace\/ui\/ui\/minified\/jquery.ui.accordion.min.js":1,"misc\/ajax.js":1,"sites\/all\/modules\/contrib\/jquery_update\/js\/jquery_update.js":1,"sites\/all\/modules\/highwire\/highwire\/js\/highwire.equal-heights.js":1,"sites\/all\/modules\/highwire\/highwire\/js\/highwire.panels-ajax-tab.js":1,"sites\/all\/libraries\/colorbox\/jquery.colorbox-min.js":1,"sites\/all\/modules\/contrib\/colorbox\/js\/colorbox.js":1,"sites\/all\/modules\/contrib\/colorbox\/styles\/default\/colorbox_style.js":1,"sites\/all\/modules\/contrib\/foxycart\/foxycart.js":1,"sites\/all\/modules\/highwire\/highwire\/highwire_log\/highwire_log.js":1,"sites\/all\/modules\/highwire\/highwire\/highwire_user\/js\/highwire_user_meta.js":1,"sites\/all\/modules\/contrib\/panels_ajax_tab\/js\/panels_ajax_tab.js":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/highwire_markup_process\/js\/highwire_at_symbol.js":1,"\/\/cdn.jsdelivr.net\/qtip2\/2.2.1\/jquery.qtip.min.js":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/highwire_markup_process\/js\/highwire_article_reference_popup.js":1,"misc\/progress.js":1,"sites\/all\/modules\/contrib\/captcha\/captcha.js":1,"misc\/textarea.js":1,"sites\/all\/modules\/highwire\/highwire\/highwire_citation\/plugins\/content_types\/js\/highwire_citation_export.js":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/content_types\/js\/minipanel_dialog_link.js":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/content_types\/js\/highwire_share_dialog.js":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/content_types\/js\/clipboard.min.js":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/content_types\/js\/highwire_clipboard.js":1,"sites\/all\/modules\/contrib\/service_links\/js\/twitter_button.js":1,"sites\/all\/modules\/contrib\/service_links\/js\/facebook_like.js":1,"sites\/all\/modules\/contrib\/service_links\/js\/google_plus_one.js":1,"sites\/all\/modules\/highwire\/highwire\/highwire_responsive\/plugins\/styles\/highwire_responsive_toggle\/highwire_responsive_toggle.js":1,"sites\/all\/modules\/highwire\/highwire\/js\/highwire.gtranslate.js":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/content_types\/js\/highwire_article_nav.js":1,"sites\/all\/modules\/highwire\/highwire\/plugins\/content_types\/js\/highwire_nav_float.js":1,"sites\/all\/modules\/highwire\/highwire\/highwire_search\/plugins\/content_types\/js\/highwire_search_similar_articles.js":1,"sites\/all\/modules\/contrib\/panels_accordion\/js\/panels_accordion.js":1,"sites\/all\/modules\/highwire\/highwire\/js\/highwire.article-citation-access.js":1,"sites\/all\/modules\/highwire\/highwire\/js\/highwire.article-citation-author-tooltip.js":1,"sites\/all\/themes\/highwire\/jcore_1\/js\/theme-scripts.js":1,"sites\/all\/themes\/contrib\/omega\/omega\/js\/jquery.formalize.js":1,"sites\/all\/themes\/contrib\/omega\/omega\/js\/omega-mediaqueries.js":1,"sites\/all\/themes\/contrib\/omega\/omega\/js\/omega-equalheights.js":1,"sites\/all\/modules\/highwire\/highwire\/highwire_responsive\/js\/highwire-mediaqueries.js":1,"sites\/all\/modules\/contrib\/picture\/picturefill2\/picturefill.min.js":1,"sites\/all\/modules\/contrib\/picture\/picture.min.js":1,"\/\/cdn.foxycart.com\/iiar.ecommerce.highwire.org\/loader.js":1,"https:\/\/scholar.google.com\/scholar_js\/casa.js":1}},"colorbox":{"opacity":"0.85","current":"{current} of {total}","previous":"\u00ab Prev","next":"Next \u00bb","close":"Close","maxWidth":"98%","maxHeight":"98%","fixed":true,"mobiledetect":true,"mobiledevicewidth":"480px"},"highwire":{"nid":"1056","apath":"\/cgp\/15\/1\/41.atom","pisa":"cgp;15\/1\/41","ac":{"\/cgp\/15\/1\/41.atom":{"access":{"full":true},"pisa_id":"","apath":"\/cgp\/15\/1\/41.atom","jcode":"cgp"}},"processed":["highwire_math"],"markup":[{"requested":"long","variant":"full-text","view":"full","pisa":"cgp;15\/1\/41"},{"requested":"full-text","variant":"full-text","view":"full","pisa":"cgp;15\/1\/41"},{"requested":"full-text","variant":"full-text","view":"full","pisa":"cgp;15\/1\/41"}],"modal_window_width":"560","share_modal_width":"560","share_modal_title":"Share this Article"},"user_uid":0,"customer_email":"","cartstack_siteid":"","foxycart_subdomain":"iiar.ecommerce.highwire.org","foxycart_always_show_cart_link":true,"hw_fc_cookie_domain":".iiarjournals.org","highwire_panel_tabs":[{"panel_name":"jnl_iiar_tab_pdf","panel_ajax_tab":"jnl_iiar_tab_pdf"}],"panel_ajax_tab":{"path":"sites\/all\/modules\/contrib\/panels_ajax_tab"},"instances":"{\u0022highwire_abstract_tooltip\u0022:{\u0022content\u0022:{\u0022text\u0022:\u0022\u0022},\u0022style\u0022:{\u0022tip\u0022:{\u0022width\u0022:20,\u0022height\u0022:20,\u0022border\u0022:1,\u0022offset\u0022:0,\u0022corner\u0022:true},\u0022classes\u0022:\u0022qtip-custom hw-tooltip hw-abstract-tooltip qtip-shadow qtip-rounded\u0022,\u0022classes_custom\u0022:\u0022hw-tooltip hw-abstract-tooltip\u0022},\u0022position\u0022:{\u0022at\u0022:\u0022right center\u0022,\u0022my\u0022:\u0022left center\u0022,\u0022viewport\u0022:true,\u0022adjust\u0022:{\u0022method\u0022:\u0022shift\u0022}},\u0022show\u0022:{\u0022event\u0022:\u0022mouseenter click \u0022,\u0022solo\u0022:true},\u0022hide\u0022:{\u0022event\u0022:\u0022mouseleave \u0022,\u0022fixed\u0022:1,\u0022delay\u0022:\u0022100\u0022}},\u0022highwire_author_tooltip\u0022:{\u0022content\u0022:{\u0022text\u0022:\u0022\u0022},\u0022style\u0022:{\u0022tip\u0022:{\u0022width\u0022:15,\u0022height\u0022:15,\u0022border\u0022:1,\u0022offset\u0022:0,\u0022corner\u0022:true},\u0022classes\u0022:\u0022qtip-custom hw-tooltip hw-author-tooltip qtip-shadow qtip-rounded\u0022,\u0022classes_custom\u0022:\u0022hw-tooltip hw-author-tooltip\u0022},\u0022position\u0022:{\u0022at\u0022:\u0022top center\u0022,\u0022my\u0022:\u0022bottom center\u0022,\u0022viewport\u0022:true,\u0022adjust\u0022:{\u0022method\u0022:\u0022\u0022}},\u0022show\u0022:{\u0022event\u0022:\u0022mouseenter \u0022,\u0022solo\u0022:true},\u0022hide\u0022:{\u0022event\u0022:\u0022mouseleave \u0022,\u0022fixed\u0022:1,\u0022delay\u0022:\u0022100\u0022}},\u0022highwire_reflinks_tooltip\u0022:{\u0022content\u0022:{\u0022text\u0022:\u0022\u0022},\u0022style\u0022:{\u0022tip\u0022:{\u0022width\u0022:15,\u0022height\u0022:15,\u0022border\u0022:1,\u0022mimic\u0022:\u0022top center\u0022,\u0022offset\u0022:0,\u0022corner\u0022:true},\u0022classes\u0022:\u0022qtip-custom hw-tooltip hw-ref-link-tooltip qtip-shadow qtip-rounded\u0022,\u0022classes_custom\u0022:\u0022hw-tooltip hw-ref-link-tooltip\u0022},\u0022position\u0022:{\u0022at\u0022:\u0022bottom left\u0022,\u0022my\u0022:\u0022top left\u0022,\u0022viewport\u0022:true,\u0022adjust\u0022:{\u0022method\u0022:\u0022flip\u0022}},\u0022show\u0022:{\u0022event\u0022:\u0022mouseenter \u0022,\u0022solo\u0022:true},\u0022hide\u0022:{\u0022event\u0022:\u0022mouseleave \u0022,\u0022fixed\u0022:1,\u0022delay\u0022:\u0022100\u0022}}}","qtipDebug":"{\u0022leaveElement\u0022:0}","ajax":{"edit-submit--3":{"callback":"highwire_alerts_login_form_submit","wrapper":"alerts-form-wrapper","event":"click","url":"\/system\/ajax","submit":{"_triggering_element_name":"op","_triggering_element_value":"Submit"}}},"urlIsAjaxTrusted":{"\/system\/ajax":true,"\/content\/15\/1\/41":true},"ws_fl":{"width":100,"height":21},"ws_gpo":{"size":"","annotation":"","lang":"","callback":"","width":300},"highwire_search_similar_articles":{"highwire-search-similar-articles-list-1":{"conf":{"context":"requiredcontext_entity:node_1","override_title":1,"override_title_text":"\u003Ci class=\u0022icon-caret-right\u0022\u003E\u003C\/i\u003E Similar Articles","number_per_page":"5","show_pager":0,"more_link_path":"similar\/articles","more_link":1,"empty_message":"No similar articles are available.","citation_style":"jcore_standard","title_type":"prefer_short","title_as_link":0,"display_subtitle":0,"choose_pubdate":"ppubdate","display_markup_snippet":"","display_original_link":0,"display_access_indicator":0,"display_cme_link":0,"display_access_indicator_text":0,"display_highlight_image":"0","display_variants":0,"display_supplements":0,"display_abstract_tooltip":0,"display_author_tooltip":0,"override_title_heading":"h2","citation_settings_source":"citation_manager","citation_manager_wrapper":{"citation_manager_citation":"jcore_list_title_only"},"corpus_config_wrapper":{"corpus_config_citation_context":[]},"cache_enabled":1,"cache_time":"600","short_title_options":{"char_count":"50","add_ellipsis":0},"access_indicator_settings":{"open_access":{"icon":"icon-unlock","title":"Open Access"},"user_access":{"icon":"icon-ok-sign","title":"You have access"},"no_access":{"icon":"icon-lock","title":"Restricted access"}},"pdf_download":{"display_pdf_download":0,"pdf_download_icon":"icon-cloud-download","pdf_download_text":"PDF"},"include_on_behalf":1,"show_mark_citation":0,"display_infotrieve_link":0,"infotrieve_link_settings":{"icon":"icon-usd","link_caption":"Order full text via Infotrieve"},"highlight_image_style":"","featured_image_variant":"large","featured_image_click_image":"colorbox","display_google_scholar_tooltip":1,"display_pubmed_tooltip":1,"display_advanced_search_tooltip":1,"display_author_landing_page_tooltip":1,"display_orcid_tooltip":0,"display_ads_search_tooltip":0,"display_agricola_tooltip":0,"author_site_search_path":"","display_translations":0,"display_translations_text":"","display_translations_text_icon":"","bundle_overrides_checkboxes":{"highwire_book_fragment":{"selector":0},"highwire_news_story":{"selector":0},"highwire_book_edition":{"selector":0},"highwire_article":{"selector":0},"highwire_issue":{"selector":0},"highwire_comment":{"selector":0},"highwire_fragment":{"selector":0},"highwire_book_section":{"selector":0},"highwire_journal":{"selector":0}},"bundle_overrides":{"highwire_book_fragment":{"selector":0,"citation_style":"jcore_title_and_author","cache_enabled":1,"cache_time":"600","title_type":"full","short_title_options":{"char_count":"50","add_ellipsis":0},"title_as_link":0,"display_subtitle":0,"choose_pubdate":"ppubdate","display_markup_snippet":"","highlight_image_toggle":0,"display_original_link":0,"display_access_indicator":"0","access_indicator_settings":{"open_access":{"icon":"icon-unlock","title":"Open Access"},"user_access":{"icon":"icon-ok-sign","title":"You have access"},"no_access":{"icon":"icon-lock","title":"Restricted access"}},"display_variants":0,"display_supplements":0,"pdf_download":{"display_pdf_download":0,"pdf_download_icon":"icon-cloud-download","pdf_download_text":"PDF"},"include_on_behalf":1,"cpath_prefix":"\/content","show_mark_citation":0,"display_infotrieve_link":0,"infotrieve_link_settings":{"icon":"icon-usd","link_caption":"Order full text via Infotrieve"},"display_highlight_image":0,"highlight_image_style":"thumbnail","display_fragment_caption":1,"display_parent_citation":1,"parent_citation_type":"highwire_book_section","parent_citation_settings":{"citation_style":"folio_book_sections_standard","cache_enabled":1,"cache_time":"600","title_type":"full","short_title_options":{"char_count":"50","add_ellipsis":0},"title_as_link":0,"display_subtitle":0,"choose_pubdate":"ppubdate","display_markup_snippet":"","highlight_image_toggle":0,"display_original_link":0,"display_access_indicator":0,"access_indicator_settings":{"open_access":{"icon":"icon-unlock","title":"Open Access"},"user_access":{"icon":"icon-ok-sign","title":"You have access"},"no_access":{"icon":"icon-lock","title":"Restricted access"}},"display_variants":0,"display_supplements":0,"pdf_download":{"display_pdf_download":0,"pdf_download_icon":"icon-cloud-download","pdf_download_text":"PDF"},"include_on_behalf":1,"cpath_prefix":"\/content","show_mark_citation":0,"display_infotrieve_link":0,"infotrieve_link_settings":{"icon":"icon-usd","link_caption":"Order full text via Infotrieve"},"display_highlight_image":0,"highlight_image_style":"","display_abstract_tooltip":0,"display_author_tooltip":0,"display_google_scholar_tooltip":1,"display_pubmed_tooltip":1,"display_advanced_search_tooltip":1,"display_author_landing_page_tooltip":0,"author_site_search_path":"search\/"}},"highwire_news_story":{"selector":0,"citation_style":"mla","cache_enabled":1,"cache_time":"600","title_type":"full","short_title_options":{"char_count":"50","add_ellipsis":0},"title_as_link":0,"display_subtitle":0,"choose_pubdate":"ppubdate","display_markup_snippet":"","highlight_image_toggle":0,"display_original_link":0,"display_access_indicator":0,"access_indicator_settings":{"open_access":{"icon":"icon-unlock","title":"Open Access"},"user_access":{"icon":"icon-ok-sign","title":"You have access"},"no_access":{"icon":"icon-lock","title":"Restricted access"}},"display_variants":0,"display_supplements":0,"pdf_download":{"display_pdf_download":0,"pdf_download_icon":"icon-cloud-download","pdf_download_text":"PDF"},"include_on_behalf":1,"cpath_prefix":"\/content","show_mark_citation":0,"display_infotrieve_link":0,"infotrieve_link_settings":{"icon":"icon-usd","link_caption":"Order full text via Infotrieve"},"display_highlight_image":"0","highlight_image_style":"","featured_image_click_image":"nothing","display_author_tooltip":0,"display_google_scholar_tooltip":0,"display_pubmed_tooltip":0,"display_advanced_search_tooltip":0},"highwire_book_edition":{"selector":0,"citation_style":"folio_books_standard","cache_enabled":1,"cache_time":"600","title_type":"full","short_title_options":{"char_count":"50","add_ellipsis":0},"title_as_link":0,"display_subtitle":0,"choose_pubdate":"ppubdate","display_markup_snippet":"","highlight_image_toggle":0,"display_original_link":0,"display_access_indicator":0,"access_indicator_settings":{"open_access":{"icon":"icon-unlock","title":"Open Access"},"user_access":{"icon":"icon-ok-sign","title":"You have access"},"no_access":{"icon":"icon-lock","title":"Restricted access"}},"display_variants":0,"display_supplements":0,"pdf_download":{"display_pdf_download":0,"pdf_download_icon":"icon-cloud-download","pdf_download_text":"PDF"},"include_on_behalf":1,"cpath_prefix":"\/content","show_mark_citation":0,"display_infotrieve_link":0,"infotrieve_link_settings":{"icon":"icon-usd","link_caption":"Order full text via Infotrieve"},"display_highlight_image":0,"highlight_image_style":"","display_author_tooltip":0,"display_google_scholar_tooltip":1,"display_pubmed_tooltip":1,"display_advanced_search_tooltip":1,"display_author_landing_page_tooltip":1,"display_orcid_tooltip":1,"author_site_search_path":"search\/"},"highwire_article":{"selector":0,"citation_style":"mla","cache_enabled":1,"cache_time":"600","title_type":"full","short_title_options":{"char_count":"50","add_ellipsis":0},"title_as_link":0,"display_subtitle":0,"choose_pubdate":"ppubdate","display_markup_snippet":"","highlight_image_toggle":0,"display_original_link":0,"display_access_indicator":0,"access_indicator_settings":{"open_access":{"icon":"icon-unlock","title":"Open Access"},"user_access":{"icon":"icon-ok-sign","title":"You have access"},"no_access":{"icon":"icon-lock","title":"Restricted access"}},"display_variants":0,"display_supplements":0,"pdf_download":{"display_pdf_download":0,"pdf_download_icon":"icon-cloud-download","pdf_download_text":"PDF"},"include_on_behalf":0,"cpath_prefix":"\/content","show_mark_citation":0,"display_infotrieve_link":0,"infotrieve_link_settings":{"icon":"icon-usd","link_caption":"Order full text via Infotrieve"},"display_highlight_image":"0","highlight_image_style":"","featured_image_variant":"large","featured_image_click_image":"nothing","display_cme_link":0,"display_abstract_tooltip":0,"display_author_tooltip":0,"display_google_scholar_tooltip":1,"display_pubmed_tooltip":1,"display_advanced_search_tooltip":1,"display_author_landing_page_tooltip":1,"display_orcid_tooltip":1,"display_ads_search_tooltip":0,"display_agricola_tooltip":0,"author_site_search_path":"search\/","display_translations":0,"display_translations_text":"Translations Available","display_translations_text_icon":"icon-globe"},"highwire_issue":{"selector":0,"citation_style":"mla","cache_enabled":1,"cache_time":"600","title_type":"full","short_title_options":{"char_count":"50","add_ellipsis":0},"title_as_link":0,"display_subtitle":0,"choose_pubdate":"ppubdate","display_markup_snippet":"","highlight_image_toggle":0,"display_original_link":0,"display_access_indicator":0,"access_indicator_settings":{"open_access":{"icon":"icon-unlock","title":"Open Access"},"user_access":{"icon":"icon-ok-sign","title":"You have access"},"no_access":{"icon":"icon-lock","title":"Restricted access"}},"display_variants":0,"display_supplements":0,"pdf_download":{"display_pdf_download":0,"pdf_download_icon":"icon-cloud-download","pdf_download_text":"PDF"},"include_on_behalf":1,"cpath_prefix":"\/content","show_mark_citation":0,"display_infotrieve_link":0,"infotrieve_link_settings":{"icon":"icon-usd","link_caption":"Order full text via Infotrieve"},"display_highlight_image":0,"highlight_image_style":"","featured_image_click_image":"nothing","display_author_tooltip":0,"display_google_scholar_tooltip":1,"display_pubmed_tooltip":1,"display_advanced_search_tooltip":1,"display_author_landing_page_tooltip":0,"display_orcid_tooltip":1,"author_site_search_path":"search\/"},"highwire_comment":{"selector":0,"citation_style":"highwire_comment","show_title":0,"title_as_link":0,"title_as_link_type":"tab_view","author_format_type":"fullname","author_format_custom":"","author_list_separator":", ","date_format":"(j F Y)","display_comment_body":1,"display_attachment":1,"display_conflict_of_interest":1},"highwire_fragment":{"selector":0,"citation_style":"jcore_title_and_author","cache_enabled":1,"cache_time":"600","title_type":"full","short_title_options":{"char_count":"50","add_ellipsis":0},"title_as_link":0,"display_subtitle":0,"choose_pubdate":"ppubdate","display_markup_snippet":"","highlight_image_toggle":0,"display_original_link":0,"display_access_indicator":"0","access_indicator_settings":{"open_access":{"icon":"icon-unlock","title":"Open Access"},"user_access":{"icon":"icon-ok-sign","title":"You have access"},"no_access":{"icon":"icon-lock","title":"Restricted access"}},"display_variants":0,"display_supplements":0,"pdf_download":{"display_pdf_download":0,"pdf_download_icon":"icon-cloud-download","pdf_download_text":"PDF"},"include_on_behalf":1,"cpath_prefix":"\/content","show_mark_citation":0,"display_infotrieve_link":0,"infotrieve_link_settings":{"icon":"icon-usd","link_caption":"Order full text via Infotrieve"},"display_highlight_image":0,"highlight_image_style":"","display_fragment_caption":1,"fragment_image_settings":{"fragment_image_variant":"medium","fragment_click_image":"colorbox","show_download_links":1},"display_parent_citation":1,"parent_citation_type":"highwire_article","parent_citation_settings":{"citation_style":"mla","cache_enabled":1,"cache_time":"600","title_type":"full","short_title_options":{"char_count":"50","add_ellipsis":0},"title_as_link":0,"display_subtitle":0,"choose_pubdate":"ppubdate","display_markup_snippet":"","highlight_image_toggle":0,"display_original_link":0,"display_access_indicator":0,"access_indicator_settings":{"open_access":{"icon":"icon-unlock","title":"Open Access"},"user_access":{"icon":"icon-ok-sign","title":"You have access"},"no_access":{"icon":"icon-lock","title":"Restricted access"}},"display_variants":0,"display_supplements":0,"pdf_download":{"display_pdf_download":0,"pdf_download_icon":"icon-cloud-download","pdf_download_text":"PDF"},"include_on_behalf":0,"cpath_prefix":"\/content","show_mark_citation":0,"display_infotrieve_link":0,"infotrieve_link_settings":{"icon":"icon-usd","link_caption":"Order full text via Infotrieve"},"display_highlight_image":"0","highlight_image_style":"","featured_image_variant":"large","featured_image_click_image":"nothing","display_cme_link":0,"display_abstract_tooltip":0,"display_author_tooltip":0,"display_google_scholar_tooltip":1,"display_pubmed_tooltip":1,"display_advanced_search_tooltip":1,"display_author_landing_page_tooltip":1,"display_orcid_tooltip":1,"display_ads_search_tooltip":0,"display_agricola_tooltip":0,"author_site_search_path":"search\/","display_translations":0,"display_translations_text":"Translations Available","display_translations_text_icon":"icon-globe"}},"highwire_book_section":{"selector":0,"citation_style":"folio_book_sections_standard","cache_enabled":1,"cache_time":"600","title_type":"full","short_title_options":{"char_count":"50","add_ellipsis":0},"title_as_link":0,"display_subtitle":0,"choose_pubdate":"ppubdate","display_markup_snippet":"","highlight_image_toggle":0,"display_original_link":0,"display_access_indicator":0,"access_indicator_settings":{"open_access":{"icon":"icon-unlock","title":"Open Access"},"user_access":{"icon":"icon-ok-sign","title":"You have access"},"no_access":{"icon":"icon-lock","title":"Restricted access"}},"display_variants":0,"display_supplements":0,"pdf_download":{"display_pdf_download":0,"pdf_download_icon":"icon-cloud-download","pdf_download_text":"PDF"},"include_on_behalf":1,"cpath_prefix":"\/content","show_mark_citation":0,"display_infotrieve_link":0,"infotrieve_link_settings":{"icon":"icon-usd","link_caption":"Order full text via Infotrieve"},"display_highlight_image":0,"highlight_image_style":"","display_abstract_tooltip":0,"display_author_tooltip":0,"display_google_scholar_tooltip":1,"display_pubmed_tooltip":1,"display_advanced_search_tooltip":1,"display_author_landing_page_tooltip":0,"author_site_search_path":"search\/"},"highwire_journal":{"selector":0,"citation_style":"mla","cache_enabled":1,"cache_time":"600","title_type":"full","short_title_options":{"char_count":"50","add_ellipsis":0},"title_as_link":0,"display_subtitle":0,"choose_pubdate":"ppubdate","display_markup_snippet":"","highlight_image_toggle":0,"display_original_link":0,"display_access_indicator":0,"access_indicator_settings":{"open_access":{"icon":"icon-unlock","title":"Open Access"},"user_access":{"icon":"icon-ok-sign","title":"You have access"},"no_access":{"icon":"icon-lock","title":"Restricted access"}},"display_variants":0,"display_supplements":0,"pdf_download":{"display_pdf_download":0,"pdf_download_icon":"icon-cloud-download","pdf_download_text":"PDF"},"include_on_behalf":1,"cpath_prefix":"\/content","show_mark_citation":0,"display_infotrieve_link":0,"infotrieve_link_settings":{"icon":"icon-usd","link_caption":"Order full text via Infotrieve"},"display_highlight_image":0,"highlight_image_style":"","display_author_tooltip":0,"display_google_scholar_tooltip":1,"display_pubmed_tooltip":1,"display_advanced_search_tooltip":1,"display_author_landing_page_tooltip":0,"display_orcid_tooltip":1,"author_site_search_path":"search\/"}},"cpath_prefix":"\/content","ajax_loading_icon_classes":"icon-spinner icon-spin icon-2x","ajax_loading_text":"","highlight_image_toggle":0,"more_link_label":"See more","url_parameters":{"q":"node\/1056","variant":"short"}},"nid":"1056"}},"panels_accordion":{"highwire_article_accordion_container":{"heightStyle":"content","autoHeight":false,"collapsible":0,"region_accordion_id":"highwire_article_accordion_container","active":0,"animated":"slide"}},"color":{"logo":"https:\/\/cgp.iiarjournals.org\/sites\/default\/files\/cgp-350_wide_0.png"},"HighWireFoxycart":{"link_text":"Add to Cart (%short-price)","link_icon":""},"nice_menus_options":{"delay":800,"speed":"fast"},"eu_cookie_compliance":{"popup_enabled":true,"popup_agreed_enabled":false,"popup_hide_agreed":false,"popup_clicking_confirmation":true,"popup_scrolling_confirmation":false,"popup_html_info":"\u003Cdiv\u003E\n \u003Cdiv class=\u0022popup-content info\u0022\u003E\n \u003Cdiv id=\u0022popup-text\u0022\u003E\n \u003Ch2\u003EWe use cookies on this site to enhance your user experience\u003C\/h2\u003E\u003Cp\u003EBy clicking any link on this page you are giving your consent for us to set cookies.\u003C\/p\u003E \u003C\/div\u003E\n \u003Cdiv id=\u0022popup-buttons\u0022\u003E\n \u003Cbutton type=\u0022button\u0022 role=\u0022dialog\u0022 aria-labelledby=\u0022OK, I agree\u0022\n class=\u0022agree-button eu-cookie-compliance-default-button\u0022\u003EOK, I agree\u003C\/button\u003E\n \u003Cbutton type=\u0022button\u0022 role=\u0022dialog\u0022 aria-labelledby=\u0022More info\u0022\n class=\u0022find-more-button eu-cookie-compliance-more-button\u0022\u003EMore info\u003C\/button\u003E\n \u003C\/div\u003E\n \u003C\/div\u003E\n\u003C\/div\u003E","use_mobile_message":false,"mobile_popup_html_info":"\u003Cdiv\u003E\n \u003Cdiv class=\u0022popup-content info\u0022\u003E\n \u003Cdiv id=\u0022popup-text\u0022\u003E\n \u003C\/div\u003E\n \u003Cdiv id=\u0022popup-buttons\u0022\u003E\n \u003Cbutton type=\u0022button\u0022 role=\u0022dialog\u0022 aria-labelledby=\u0022OK, I agree\u0022\n class=\u0022agree-button eu-cookie-compliance-default-button\u0022\u003EOK, I agree\u003C\/button\u003E\n \u003Cbutton type=\u0022button\u0022 role=\u0022dialog\u0022 aria-labelledby=\u0022More info\u0022\n class=\u0022find-more-button eu-cookie-compliance-more-button\u0022\u003EMore info\u003C\/button\u003E\n \u003C\/div\u003E\n \u003C\/div\u003E\n\u003C\/div\u003E","mobile_breakpoint":"768","popup_html_agreed":"\u003Cdiv\u003E\n \u003Cdiv class=\u0022popup-content agreed\u0022\u003E\n \u003Cdiv id=\u0022popup-text\u0022\u003E\n \u003Ch2\u003EThank you for accepting cookies\u003C\/h2\u003E\u003Cp\u003EYou can now hide this message or find out more about cookies.\u003C\/p\u003E \u003C\/div\u003E\n \u003Cdiv id=\u0022popup-buttons\u0022\u003E\n \u003Cbutton type=\u0022button\u0022 class=\u0022hide-popup-button eu-cookie-compliance-hide-button\u0022\u003EHide\u003C\/button\u003E\n \u003Cbutton type=\u0022button\u0022 class=\u0022find-more-button eu-cookie-compliance-more-button-thank-you\u0022 \u003EMore info\u003C\/button\u003E\n \u003C\/div\u003E\n \u003C\/div\u003E\n\u003C\/div\u003E","popup_use_bare_css":false,"popup_height":"auto","popup_width":"100%","popup_delay":1000,"popup_link":"\/help\/cookie-policy","popup_link_new_window":1,"popup_position":null,"popup_language":"en","store_consent":false,"better_support_for_screen_readers":0,"reload_page":0,"domain":"","popup_eu_only_js":0,"cookie_lifetime":365,"cookie_session":false,"disagree_do_not_show_popup":0,"method":"default","whitelisted_cookies":"","withdraw_markup":"\u003Cbutton type=\u0022button\u0022 class=\u0022eu-cookie-withdraw-tab\u0022\u003EPrivacy settings\u003C\/button\u003E\n\u003Cdiv class=\u0022eu-cookie-withdraw-banner\u0022\u003E\n \u003Cdiv class=\u0022popup-content info\u0022\u003E\n \u003Cdiv id=\u0022popup-text\u0022\u003E\n \u003Ch2\u003EWe use cookies on this site to enhance your user experience\u003C\/h2\u003E\u003Cp\u003EYou have given your consent for us to set cookies.\u003C\/p\u003E \u003C\/div\u003E\n \u003Cdiv id=\u0022popup-buttons\u0022\u003E\n \u003Cbutton type=\u0022button\u0022 class=\u0022eu-cookie-withdraw-button\u0022\u003EWithdraw consent\u003C\/button\u003E\n \u003C\/div\u003E\n \u003C\/div\u003E\n\u003C\/div\u003E\n","withdraw_enabled":false},"highwireResponsive":{"enquire_enabled":1,"breakpoints_configured":1,"breakpoints":{"zero":"all and (min-width: 0px)","xsmall":"all and (min-width: 380px)","narrow":"all and (min-width: 768px) and (min-device-width: 768px), (max-device-width: 800px) and (min-width: 768px) and (orientation:landscape)","normal":"all and (min-width: 980px) and (min-device-width: 980px), all and (max-device-width: 1024px) and (min-width: 1024px) and (orientation:landscape)","wide":"all and (min-width: 1220px)"}},"omega":{"layouts":{"primary":"normal","order":["narrow","normal","wide"],"queries":{"narrow":"all and (min-width: 768px) and (min-device-width: 768px), (max-device-width: 800px) and (min-width: 768px) and (orientation:landscape)","normal":"all and (min-width: 980px) and (min-device-width: 980px), all and (max-device-width: 1024px) and (min-width: 1024px) and (orientation:landscape)","wide":"all and (min-width: 1220px)"}}}}); //--><!]]> </script> <!--[if lt IE 9]><script src="http://html5shiv.googlecode.com/svn/trunk/html5.js"></script><![endif]--> </head> <body class="html not-front not-logged-in page-node page-node- page-node-1056 node-type-highwire-article context-content hw-default-jcode-cgp hw-article-type-review-article"> <div id="skip-link"> <a href="#main-content" class="element-invisible element-focusable">Skip to main content</a> </div> <div class="page clearfix page-box-shadows footer-borders panels-page panels-layout-jcore_2col" id="page"> <header id="section-header" class="section section-header"> <div id="zone-superheader-wrapper" class="zone-wrapper zone-superheader-wrapper clearfix mobile-only print-hidden"> <div id="zone-superheader" class="zone zone-superheader clearfix mobile-only print-hidden container-30"> <div class="grid-30 region region-superheader" id="region-superheader"> <div class="region-inner region-superheader-inner"> <div class="block block-panels-mini block-responsive-menu block-panels-mini-responsive-menu odd block-without-title" id="block-panels-mini-responsive-menu"> <div class="block-inner clearfix"> <div class="content clearfix"> <div class="panel-display panel-1col clearfix" id="mini-panel-responsive_menu"> <div class="panel-panel panel-col"> <div><div id="unique-id3" class="highwire-responsive-toggle-group"><div class="panel-pane pane-panels-mini pane-responsive-menu-main-menu" > <h2 class="pane-title"><span class="icon-reorder"></span><span class="element-invisible">Main menu</span></h2> <div class="pane-content"> <div class="panel-display panel-1col clearfix" id="mini-panel-responsive_menu_main_menu"> <div class="panel-panel panel-col"> <div><div class="panel-pane pane-menu-tree pane-main-menu" > <div class="pane-content"> <div class="menu-block-wrapper menu-block-ctools-main-menu-1 menu-name-main-menu parent-mlid-main-menu:0 menu-level-1"> <nav class="menubar-nav"><ul class="menu" role="menu"><li class="first leaf menu-mlid-734" role="menuitem"><a href="/" class="" data-icon-position="" data-hide-link-title="0">Home</a></li> <li class="expanded menu-mlid-736" role="menuitem"><a href="/content/current" data-hide-link-title="0" class="" data-icon-position="">Current Issue</a></li> <li class="leaf menu-mlid-738" role="menuitem"><a href="/content/by/year" class="" data-icon-position="" data-hide-link-title="0">Archive</a></li> <li class="expanded menu-mlid-739" role="menuitem"><a href="/content/instructions-authors-2024" data-hide-link-title="0" class="" data-icon-position="">Info for</a><nav class="menubar-nav"><ul class="menu" role="menu"><li class="first leaf menu-mlid-740" role="menuitem"><a href="/content/instructions-authors-2024" class="" data-icon-position="" data-hide-link-title="0">Authors</a></li> <li class="leaf menu-mlid-1229" role="menuitem"><a href="/content/editorial-policies" data-hide-link-title="0" class="" data-icon-position="">Editorial Policies</a></li> <li class="leaf menu-mlid-744" role="menuitem"><a href="/content/information-advertisers" data-hide-link-title="0" class="" data-icon-position="">Advertisers</a></li> <li class="leaf menu-mlid-749" role="menuitem"><a href="/content/editorial-board-cancer-genomics-proteomics-2024" data-hide-link-title="0" class="" data-icon-position="">Editorial Board</a></li> <li class="last leaf menu-mlid-1375" role="menuitem"><a href="/content/special-issues-2025" data-hide-link-title="0" class="" data-icon-position="">Special Issues 2025</a></li> </ul></nav></li> <li class="leaf menu-mlid-1368" role="menuitem"><a href="/content/journal-metrics" data-hide-link-title="0" class="" data-icon-position="">Journal Metrics</a></li> <li class="expanded menu-mlid-899" role="menuitem"><a href="/feedback" data-hide-link-title="0" class="" data-icon-position="">Other Publications</a><nav class="menubar-nav"><ul class="menu" role="menu"><li class="first leaf menu-mlid-900" role="menuitem"><a href="//ar.iiarjournals.org/" data-hide-link-title="0" class="" data-icon-position="">Anticancer Research</a></li> <li class="leaf menu-mlid-901" role="menuitem"><a href="//iv.iiarjournals.org/" data-hide-link-title="0" class="" data-icon-position="">In Vivo</a></li> <li class="last leaf menu-mlid-1033" role="menuitem"><a href="http://www.cancerdiagnosisprognosis.org/" data-hide-link-title="0" target="_blank" class="" data-icon-position="">Cancer Diagnosis & Prognosis</a></li> </ul></nav></li> <li class="expanded menu-mlid-750" role="menuitem"><a href="/content/advertising" class="" data-icon-position="" data-hide-link-title="0">More</a><nav class="menubar-nav"><ul class="menu" role="menu"><li class="first leaf menu-mlid-897" role="menuitem"><a href="https://iiar-anticancer.org/" data-hide-link-title="0" target="_blank" class="" data-icon-position="">IIAR</a></li> <li class="last leaf menu-mlid-898" role="menuitem"><a href="http://www.iiar-anticancer.org/conference/" data-hide-link-title="0" class="" data-icon-position="">Conferences</a></li> </ul></nav></li> <li class="last expanded menu-mlid-746" role="menuitem"><a href="/content/general-policy" data-hide-link-title="0" class="" data-icon-position="">About Us</a><nav class="menubar-nav"><ul class="menu" role="menu"><li class="first leaf menu-mlid-747" role="menuitem"><a href="/content/general-policy" data-hide-link-title="0" class="" data-icon-position="">General Policy</a></li> <li class="last leaf menu-mlid-753" role="menuitem"><a href="/feedback" data-hide-link-title="0" class="" data-icon-position="">Contact</a></li> </ul></nav></li> </ul></nav></div> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-menu-tree pane-umbrella-menu" > <div class="pane-content"> <div class="menu-block-wrapper menu-block-ctools-umbrella-menu-1 menu-name-umbrella-menu parent-mlid-umbrella-menu:0 menu-level-1"> <nav class="menubar-nav"><ul class="menu" role="menu"><li class="first last expanded menu-mlid-728" role="menuitem"><a href="/" class="" data-icon-position="" data-hide-link-title="0">Other Publications</a><nav class="menubar-nav"><ul class="menu" role="menu"><li class="first leaf menu-mlid-729" role="menuitem"><a href="/" data-hide-link-title="0" class="" data-icon-position="">Cancer Genomics & Proteomics</a></li> <li class="leaf menu-mlid-971" role="menuitem"><a href="//ar.iiarjournals.org/" data-hide-link-title="0" class="" data-icon-position="">Anticancer Research</a></li> <li class="last leaf menu-mlid-972" role="menuitem"><a href="//iv.iiarjournals.org/" data-hide-link-title="0" class="" data-icon-position="">In Vivo</a></li> </ul></nav></li> </ul></nav></div> </div> </div> </div> </div> </div> </div> </div> <div class="panel-pane pane-panels-mini pane-responsive-menu-user-menu" > <h2 class="pane-title"><span class="icon-gear"></span><span class="element-invisible">User menu</span></h2> <div class="pane-content"> <div class="panel-display panel-1col clearfix" id="mini-panel-responsive_menu_user_menu"> <div class="panel-panel panel-col"> <div><div class="panel-pane pane-menu-tree pane-user-menu" > <div class="pane-content"> <div class="menu-block-wrapper menu-block-ctools-user-menu-1 menu-name-user-menu parent-mlid-user-menu:0 menu-level-1"> <nav class="menubar-nav"><ul class="menu" role="menu"><li class="first leaf menu-mlid-762" role="menuitem"><a href="/user/register" class="" data-icon-position="" data-hide-link-title="0">Register</a></li> <li class="leaf menu-mlid-763" role="menuitem"><a href="/" class="" data-icon-position="" data-hide-link-title="0">Subscribe</a></li> <li class="leaf menu-mlid-764" role="menuitem"><a href="/alerts" class="" data-icon-position="" data-hide-link-title="0">My alerts</a></li> <li class="leaf menu-mlid-765" role="menuitem"><a href="/user/login?destination=/content/15/1/41" class="" data-icon-position="" data-hide-link-title="0">Log in</a></li> <li class="last leaf menu-mlid-919" role="menuitem"><a href="/cart" class="link-icon-only link-icon"><span class="icon-shopping-cart"></span> <span class="title element-invisible">My Cart</span></a></li> </ul></nav></div> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-highwire-user-identities" > <div class="pane-content"> <div class="highwire-user-message" data-separator="|"><span class="highwire-user-institution" data-id-type="institution" data-identity="a%3A2%3A%7Bs%3A4%3A%22show%22%3Bi%3A1%3Bs%3A7%3A%22message%22%3Bs%3A50%3A%22Institution%3A%20%5Bidentity%3Ainstitutional_display_name%5D%22%3B%7D"></span></div> </div> </div> </div> </div> </div> </div> </div> <div class="panel-pane pane-panels-mini pane-responsive-menu-search" > <h2 class="pane-title"><span class="icon-search"></span><span class="element-invisible">Search</span></h2> <div class="pane-content"> <div class="panel-display panel-1col clearfix" id="mini-panel-responsive_menu_search"> <div class="panel-panel panel-col"> <div><div class="panel-pane pane-highwire-seach-qsearch-nocontext" > <div class="pane-content"> <form class="highwire-quicksearch button-style-mini button-style-mini" action="/content/15/1/41" method="post" id="highwire-search-qsearch-nocontext-form" accept-charset="UTF-8"><div><div class="form-item form-item-label-invisible form-type-textfield form-item-keywords"> <label class="element-invisible" for="quick_search_header_keywords_569003862">Search for this keyword </label> <input placeholder="Search..." type="text" id="quick_search_header_keywords_569003862" name="keywords" value="" size="60" maxlength="128" class="form-text" /> </div> <div class="button-wrapper button-mini"><span class="icon-search"></span><input data-icon-only="1" data-font-icon="icon-search" data-icon-position="after" type="submit" id="quick_search_header_submit_1725471417" name="op" value="Search" class="form-submit" /></div><input type="hidden" name="form_build_id" value="form-E0YbFNAc5_oFim5feKuRoVPIUoXh9yidYPARnelcgPQ" /> <input type="hidden" name="form_id" value="highwire_search_qsearch_nocontext_form" /> </div></form> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-custom pane-1 highwire-responsive-advanced-search-link pane-menu-tree" > <div class="pane-content"> <ul class="menu"> <li><a href="/search" title="Advanced search">Advanced search</a></li> </ul> </div> </div> </div> </div> </div> </div> </div> </div></div> </div> </div> </div> </div> </div><div class="block block-panels-mini block-hw-small-logo block-panels-mini-hw-small-logo even block-without-title" id="block-panels-mini-hw-small-logo"> <div class="block-inner clearfix"> <div class="content clearfix"> <div class="panel-display panel-1col clearfix" id="mini-panel-hw_small_logo"> <div class="panel-panel panel-col"> <div><div class="panel-pane pane-small-logo" > <div class="pane-content"> <a href="/" class="" data-icon-position="" data-hide-link-title="0"><img src="https://cgp.iiarjournals.org/sites/default/files/cgp-350_wide.png" alt="Cancer Genomics & Proteomics" title="Cancer Genomics & Proteomics" /></a> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div><div id="zone-user-wrapper" class="zone-wrapper zone-user-wrapper clearfix zone-wrapper-twotone-bg mobile-hidden print-hidden"> <div id="zone-user" class="zone zone-user clearfix equal-height-container zone-twotone-bg mobile-hidden print-hidden container-30"> <div class="twotone-bg-region twotone-bg-region-first"></div> <div class="twotone-bg-region twotone-bg-region-second"></div> <div class="grid-10 region region-user-first equal-height-element" id="region-user-first"> <div class="region-inner region-user-first-inner"> <div class="block block-nice-menus block-2 block-nice-menus-2 odd block-without-title" id="block-nice-menus-2"> <div class="block-inner clearfix"> <div class="content clearfix user-menu-dropdown"> <nav class="menubar-nav"><ul class="nice-menu nice-menu-down nice-menu-umbrella-menu" id="nice-menu-2" role="menu"><li class="menu-728 menuparent menu-path-front first odd last" role="menuitem"><a href="/" class="" data-icon-position="" data-hide-link-title="0">Other Publications</a><ul role="menu"><li class="menu-729 menu-path-front first odd " role="menuitem"><a href="/" data-hide-link-title="0" class="" data-icon-position="">Cancer Genomics & Proteomics</a></li> <li class="menu-971 menu-path---ariiarjournalsorg- even " role="menuitem"><a href="//ar.iiarjournals.org/" data-hide-link-title="0" class="" data-icon-position="">Anticancer Research</a></li> <li class="menu-972 menu-path---iviiarjournalsorg- odd last" role="menuitem"><a href="//iv.iiarjournals.org/" data-hide-link-title="0" class="" data-icon-position="">In Vivo</a></li> </ul></li> </ul></nav> </div> </div> </div> </div> </div><div class="grid-20 region region-user-second equal-height-element" id="region-user-second"> <div class="region-inner region-user-second-inner"> <div class="block block-panels-mini highwire-uid-string block-jnl-iiar-uid-strng block-panels-mini-jnl-iiar-uid-strng odd block-without-title" id="block-panels-mini-jnl-iiar-uid-strng"> <div class="block-inner clearfix"> <div class="content clearfix"> <div class="panel-display panel-1col clearfix" id="mini-panel-jnl_iiar_uid_strng"> <div class="panel-panel panel-col"> <div><div class="panel-pane pane-highwire-user-identities" > <div class="pane-content"> <div class="highwire-user-message" data-separator=" | "><span class="highwire-user-institution" data-id-type="institution" data-identity="a%3A2%3A%7Bs%3A4%3A%22show%22%3Bi%3A1%3Bs%3A7%3A%22message%22%3Bs%3A85%3A%22%3Cspan%20class%3D%22narrow-hidden%22%3EInstitution%3A%20%3C%2Fspan%3E%5Bidentity%3Ainstitutional_display_name%5D%22%3B%7D"></span></div> </div> </div> <div class="panel-pane pane-block pane-system-user-menu links inline pane-system" > <div class="pane-content"> <nav class="menubar-nav"><ul class="menu" role="menu"><li class="first leaf" role="menuitem"><a href="/user/register" class="" data-icon-position="" data-hide-link-title="0">Register</a></li> <li class="leaf" role="menuitem"><a href="/" class="" data-icon-position="" data-hide-link-title="0">Subscribe</a></li> <li class="leaf" role="menuitem"><a href="/alerts" class="" data-icon-position="" data-hide-link-title="0">My alerts</a></li> <li class="leaf" role="menuitem"><a href="/user/login?destination=/content/15/1/41" class="" data-icon-position="" data-hide-link-title="0">Log in</a></li> <li class="last leaf" role="menuitem"><a href="/cart" class="link-icon-only link-icon"><span class="icon-shopping-cart"></span> <span class="title element-invisible">My Cart</span></a></li> </ul></nav> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> <div id="zone-branding" class="zone zone-branding clearfix mobile-hidden print-display-block container-30"> <div class="grid-19 prefix-1 region region-branding print-display-block" id="region-branding"> <div class="region-inner region-branding-inner"> <div class="branding-data clearfix"> <div class="logo-img"> <a href="/" rel="home" class="" data-icon-position="" data-hide-link-title="0"><img alt="Cancer Genomics & Proteomics" src="https://cgp.iiarjournals.org/sites/default/files/cgp-350_wide_0.png" /></a> </div> </div> </div> </div><div class="grid-9 suffix-1 region region-branding-second print-hidden" id="region-branding-second"> <div class="region-inner region-branding-second-inner"> <div class="block block-panels-mini block-jnl-iiar-search-box block-panels-mini-jnl-iiar-search-box odd block-without-title" id="block-panels-mini-jnl-iiar-search-box"> <div class="block-inner clearfix"> <div class="content clearfix"> <div class="panel-display panel-1col clearfix" id="mini-panel-jnl_iiar_search_box"> <div class="panel-panel panel-col"> <div><div class="panel-pane pane-highwire-seach-quicksearch no-margin-bottom" > <div class="pane-content"> <form class="highwire-quicksearch button-style-mini button-style-mini" action="/content/15/1/41" method="post" id="highwire-search-quicksearch-form-0" accept-charset="UTF-8"><div><div class="form-item form-item-label-invisible form-type-textfield form-item-keywords"> <label class="element-invisible" for="search_rightsidebar_keywords_1210073605">Search for this keyword </label> <input placeholder="search" type="text" id="search_rightsidebar_keywords_1210073605" name="keywords" value="" size="60" maxlength="128" class="form-text" /> </div> <div class="button-wrapper button-mini"><span class="icon-search"></span><input data-icon-only="1" data-font-icon="icon-search" data-icon-position="after" type="submit" id="search_rightsidebar_submit_1506130462" name="op" value="Search" class="form-submit" /></div><input type="hidden" name="form_build_id" value="form-qW8-qjkZq0ky2Q1a8eGCr-mECWTIAysI14EVjGpekM4" /> <input type="hidden" name="form_id" value="highwire_search_quicksearch_form_0" /> </div></form> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-custom pane-2" > <div class="pane-content"> <p><a href="/search">Advanced Search</a></p> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> <div id="zone-menu" class="zone zone-menu clearfix mobile-hidden container-30"> <div class="grid-28 suffix-1 prefix-1 region region-menu main-menu-active-caret" id="region-menu"> <div class="region-inner region-menu-inner region-menu-bg-opaque"> <div class="block block-nice-menus block-1 block-nice-menus-1 odd block-without-title" id="block-nice-menus-1"> <div class="block-inner clearfix"> <div class="content clearfix"> <nav class="menubar-nav"><ul class="nice-menu nice-menu-down nice-menu-main-menu" id="nice-menu-1" role="menu"><li class="menu-734 menu-path-front first odd " role="menuitem"><a href="/" class="" data-icon-position="" data-hide-link-title="0">Home</a></li> <li class="menu-736 menu-path-content-current even " role="menuitem"><a href="/content/current" data-hide-link-title="0" class="" data-icon-position="">Current Issue</a></li> <li class="menu-738 menu-path-content-by-year odd " role="menuitem"><a href="/content/by/year" class="" data-icon-position="" data-hide-link-title="0">Archive</a></li> <li class="menu-739 menuparent menu-path-node-1 even " role="menuitem"><a href="/content/instructions-authors-2024" data-hide-link-title="0" class="" data-icon-position="">Info for</a><ul role="menu"><li class="menu-740 menu-path-node-1 first odd " role="menuitem"><a href="/content/instructions-authors-2024" class="" data-icon-position="" data-hide-link-title="0">Authors</a></li> <li class="menu-1229 menu-path-node-5552 even " role="menuitem"><a href="/content/editorial-policies" data-hide-link-title="0" class="" data-icon-position="">Editorial Policies</a></li> <li class="menu-744 menu-path-node-5 odd " role="menuitem"><a href="/content/information-advertisers" data-hide-link-title="0" class="" data-icon-position="">Advertisers</a></li> <li class="menu-749 menu-path-node-3940 even " role="menuitem"><a href="/content/editorial-board-cancer-genomics-proteomics-2024" data-hide-link-title="0" class="" data-icon-position="">Editorial Board</a></li> <li class="menu-1375 menu-path-node-30813 odd last" role="menuitem"><a href="/content/special-issues-2025" data-hide-link-title="0" class="" data-icon-position="">Special Issues 2025</a></li> </ul></li> <li class="menu-1368 menu-path-node-30629 odd " role="menuitem"><a href="/content/journal-metrics" data-hide-link-title="0" class="" data-icon-position="">Journal Metrics</a></li> <li class="menu-899 menuparent menu-path-node-10 even " role="menuitem"><a href="/feedback" data-hide-link-title="0" class="" data-icon-position="">Other Publications</a><ul role="menu"><li class="menu-900 menu-path---ariiarjournalsorg- first odd " role="menuitem"><a href="//ar.iiarjournals.org/" data-hide-link-title="0" class="" data-icon-position="">Anticancer Research</a></li> <li class="menu-901 menu-path---iviiarjournalsorg- even " role="menuitem"><a href="//iv.iiarjournals.org/" data-hide-link-title="0" class="" data-icon-position="">In Vivo</a></li> <li class="menu-1033 menu-path-cancerdiagnosisprognosisorg- odd last" role="menuitem"><a href="http://www.cancerdiagnosisprognosis.org/" data-hide-link-title="0" target="_blank" class="" data-icon-position="">Cancer Diagnosis & Prognosis</a></li> </ul></li> <li class="menu-750 menuparent menu-path-node-9 odd " role="menuitem"><a href="/content/advertising" class="" data-icon-position="" data-hide-link-title="0">More</a><ul role="menu"><li class="menu-897 menu-path-siiar-anticancerorg- first odd " role="menuitem"><a href="https://iiar-anticancer.org/" data-hide-link-title="0" target="_blank" class="" data-icon-position="">IIAR</a></li> <li class="menu-898 menu-path-iiar-anticancerorg-conference- even last" role="menuitem"><a href="http://www.iiar-anticancer.org/conference/" data-hide-link-title="0" class="" data-icon-position="">Conferences</a></li> </ul></li> <li class="menu-746 menuparent menu-path-node-7 even last" role="menuitem"><a href="/content/general-policy" data-hide-link-title="0" class="" data-icon-position="">About Us</a><ul role="menu"><li class="menu-747 menu-path-node-7 first odd " role="menuitem"><a href="/content/general-policy" data-hide-link-title="0" class="" data-icon-position="">General Policy</a></li> <li class="menu-753 menu-path-node-10 even last" role="menuitem"><a href="/feedback" data-hide-link-title="0" class="" data-icon-position="">Contact</a></li> </ul></li> </ul></nav> </div> </div> </div><div class="block block-menu text-right block-menu-social-media block-menu-menu-social-media even block-without-title" id="block-menu-menu-social-media"> <div class="block-inner clearfix"> <div class="content clearfix"> <nav class="menubar-nav"><ul class="menu" role="menu"><li class="first leaf" role="menuitem"><a href="https://www.facebook.com/Cancer-Genomics-Proteomics-103266704417232" target="_blank" class="link-icon-only link-icon"><span class="icon-facebook-sign icon-2x"></span> <span class="title element-invisible">Visit iiar on Facebook</span></a></li> <li class="last leaf" role="menuitem"><a href="https://www.linkedin.com/company/28898783/admin/" target="_blank" class="link-icon-only link-icon"><span class="icon-linkedin-sign icon-2x"></span> <span class="title element-invisible">Follow us on Linkedin</span></a></li> </ul></nav> </div> </div> </div> </div> </div> </div> <div id="zone-header" class="zone zone-header clearfix container-30"> </div> </header> <section id="section-content" class="section section-content"> <div id="zone-content" class="zone zone-content clearfix container-30"> <div class="grid-28 suffix-1 prefix-1 region region-content" id="region-content"> <div class="region-inner region-content-inner"> <a id="main-content"></a> <div class="block block-system block-main block-system-main odd block-without-title" id="block-system-main"> <div class="block-inner clearfix"> <div class="content clearfix"> <div class="panel-display panels-960-layout jcore-2col-layout" > <div class="panel-row-wrapper panel-row-first clearfix"> <div class="top-wrapper"> <div class="panel-panel panel-region-top"> <div class="inside"><div class="panel-pane pane-highwire-article-citation" > <div class="pane-content"> <div class="highwire-article-citation highwire-citation-type-highwire-article node1056--5" data-node-nid="1056" id="top-node-1056--61604592117" data-pisa="cgp;15/1/41" data-pisa-master="cgp;15/1/41" data-apath="/cgp/15/1/41.atom" data-hw-author-tooltip-instance="highwire_author_tooltip"><div class="highwire-cite highwire-cite-highwire-article highwire-citation-jcore-article-title-complete clearfix has-author-tooltip highwire-citation-highwire-article-top-a"> <div class="highwire-cite-overline"><span class="highwire-cite-metadata-article-type highwire-cite-metadata">Review Article</span><span class="separator-pipe"></span><span class="highwire-cite-metadata-art-series highwire-cite-metadata">R</span></div> <div class="highwire-cite-access"><span class="highwire-citation-access"><i class="highwire-access-icon highwire-access-icon-open-access open-access hw-icon-open-access" title="Open Access" aria-hidden="true"></i><span class="element-invisible highwire-access-icon highwire-access-icon-open-access" style="">Open Access</span></span></div> <h1 class="highwire-cite-title" id="page-title">Applications of Support Vector Machine (SVM) Learning in Cancer Genomics</h1> <div class="highwire-cite-authors"><span class="highwire-citation-authors"><span class="highwire-citation-author first" data-delta="0">SHUJUN HUANG</span>, <span class="highwire-citation-author" data-delta="1">NIANGUANG CAI</span>, <span class="highwire-citation-author" data-delta="2">PEDRO PENZUTI PACHECO</span>, <span class="highwire-citation-author" data-delta="3">SHAVIRA NARRANDES</span>, <span class="highwire-citation-author" data-delta="4">YANG WANG</span> and <span class="highwire-citation-author" data-delta="5">WAYNE XU</span></span></div> <div class="highwire-cite-metadata"><span class="highwire-cite-metadata-journal highwire-cite-metadata">Cancer Genomics & Proteomics </span><span class="highwire-cite-metadata-date highwire-cite-metadata">January 2018, </span><span class="highwire-cite-metadata-volume highwire-cite-metadata">15 </span><span class="highwire-cite-metadata-issue highwire-cite-metadata">(1) </span><span class="highwire-cite-metadata-pages highwire-cite-metadata">41-51; </span></div> <div class="highwire-cite-extras"><span class="highwire-foxycart-add-to-cart-ahah highwire-foxycart-add-to-cart-ahah" data-text="Add to Cart (%short-price)" data-apath="/cgp/15/1/41.atom" data-type="link" data-font-icon="" data-parent-id="544"></span></div> </div> <div id="hw-article-author-popups-top-node-1056--61604592117" style="display: none;"><div class="author-tooltip-0"><div class="author-tooltip-name">SHUJUN HUANG </div><div class="author-tooltip-affiliation"><span class="author-tooltip-text"><div class='author-affiliation'><span class='nlm-sup'>1</span>College of Pharmacy, Rady Faculty of Health Sciences, University of Manitoba, Winnipeg, Canada</div><div class='author-affiliation'><span class='nlm-sup'>2</span>Research Institute of Oncology and Hematology, CancerCare Manitoba, Winnipeg, Canada</div></span></div><ul class="author-tooltip-find-more"><li class="author-tooltip-gs-link first"><a href="/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=SHUJUN%2BHUANG%2B" target="_blank" class="" data-icon-position="" data-hide-link-title="0">Find this author on Google Scholar</a></li><li class="author-tooltip-pubmed-link"><a href="/lookup/external-ref?access_num=HUANG%20S&link_type=AUTHORSEARCH" target="_blank" class="" data-icon-position="" data-hide-link-title="0">Find this author on PubMed</a></li><li class="author-site-search-link last"><a href="/search/author1%3ASHUJUN%2BHUANG%2B" rel="nofollow" class="" data-icon-position="" data-hide-link-title="0">Search for this author on this site</a></li></ul></div><div class="author-tooltip-1"><div class="author-tooltip-name">NIANGUANG CAI </div><div class="author-tooltip-affiliation"><span class="author-tooltip-text"><div class='author-affiliation'><span class='nlm-sup'>2</span>Research Institute of Oncology and Hematology, CancerCare Manitoba, Winnipeg, Canada</div></span></div><ul class="author-tooltip-find-more"><li class="author-tooltip-gs-link first"><a href="/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=NIANGUANG%2BCAI%2B" target="_blank" class="" data-icon-position="" data-hide-link-title="0">Find this author on Google Scholar</a></li><li class="author-tooltip-pubmed-link"><a href="/lookup/external-ref?access_num=CAI%20N&link_type=AUTHORSEARCH" target="_blank" class="" data-icon-position="" data-hide-link-title="0">Find this author on PubMed</a></li><li class="author-site-search-link last"><a href="/search/author1%3ANIANGUANG%2BCAI%2B" rel="nofollow" class="" data-icon-position="" data-hide-link-title="0">Search for this author on this site</a></li></ul></div><div class="author-tooltip-2"><div class="author-tooltip-name">PEDRO PENZUTI PACHECO </div><div class="author-tooltip-affiliation"><span class="author-tooltip-text"><div class='author-affiliation'><span class='nlm-sup'>2</span>Research Institute of Oncology and Hematology, CancerCare Manitoba, Winnipeg, Canada</div></span></div><ul class="author-tooltip-find-more"><li class="author-tooltip-gs-link first"><a href="/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=PEDRO%2BPENZUTI%2BPACHECO%2B" target="_blank" class="" data-icon-position="" data-hide-link-title="0">Find this author on Google Scholar</a></li><li class="author-tooltip-pubmed-link"><a href="/lookup/external-ref?access_num=PACHECO%20PP&link_type=AUTHORSEARCH" target="_blank" class="" data-icon-position="" data-hide-link-title="0">Find this author on PubMed</a></li><li class="author-site-search-link last"><a href="/search/author1%3APEDRO%2BPENZUTI%2BPACHECO%2B" rel="nofollow" class="" data-icon-position="" data-hide-link-title="0">Search for this author on this site</a></li></ul></div><div class="author-tooltip-3"><div class="author-tooltip-name">SHAVIRA NARRANDES </div><div class="author-tooltip-affiliation"><span class="author-tooltip-text"><div class='author-affiliation'><span class='nlm-sup'>2</span>Research Institute of Oncology and Hematology, CancerCare Manitoba, Winnipeg, Canada</div><div class='author-affiliation'><span class='nlm-sup'>3</span>Departments of Biochemistry and Medical Genetics, Rady Faculty of Health Sciences, University of Manitoba, Winnipeg, Canada</div></span></div><ul class="author-tooltip-find-more"><li class="author-tooltip-gs-link first"><a href="/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=SHAVIRA%2BNARRANDES%2B" target="_blank" class="" data-icon-position="" data-hide-link-title="0">Find this author on Google Scholar</a></li><li class="author-tooltip-pubmed-link"><a href="/lookup/external-ref?access_num=NARRANDES%20S&link_type=AUTHORSEARCH" target="_blank" class="" data-icon-position="" data-hide-link-title="0">Find this author on PubMed</a></li><li class="author-site-search-link last"><a href="/search/author1%3ASHAVIRA%2BNARRANDES%2B" rel="nofollow" class="" data-icon-position="" data-hide-link-title="0">Search for this author on this site</a></li></ul></div><div class="author-tooltip-4"><div class="author-tooltip-name">YANG WANG </div><div class="author-tooltip-affiliation"><span class="author-tooltip-text"><div class='author-affiliation'><span class='nlm-sup'>4</span>Department of Computer Science, Faculty of Sciences, University of Manitoba, Winnipeg, Canada</div></span></div><ul class="author-tooltip-find-more"><li class="author-tooltip-gs-link first"><a href="/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=YANG%2BWANG%2B" target="_blank" class="" data-icon-position="" data-hide-link-title="0">Find this author on Google Scholar</a></li><li class="author-tooltip-pubmed-link"><a href="/lookup/external-ref?access_num=WANG%20Y&link_type=AUTHORSEARCH" target="_blank" class="" data-icon-position="" data-hide-link-title="0">Find this author on PubMed</a></li><li class="author-site-search-link last"><a href="/search/author1%3AYANG%2BWANG%2B" rel="nofollow" class="" data-icon-position="" data-hide-link-title="0">Search for this author on this site</a></li></ul></div><div class="author-tooltip-5"><div class="author-tooltip-name">WAYNE XU </div><div class="author-tooltip-affiliation"><span class="author-tooltip-text"><div class='author-affiliation'><span class='nlm-sup'>1</span>College of Pharmacy, Rady Faculty of Health Sciences, University of Manitoba, Winnipeg, Canada</div><div class='author-affiliation'><span class='nlm-sup'>2</span>Research Institute of Oncology and Hematology, CancerCare Manitoba, Winnipeg, Canada</div><div class='author-affiliation'><span class='nlm-sup'>3</span>Departments of Biochemistry and Medical Genetics, Rady Faculty of Health Sciences, University of Manitoba, Winnipeg, Canada</div></span></div><ul class="author-tooltip-find-more"><li class="author-tooltip-gs-link first"><a href="/lookup/google-scholar?link_type=googlescholar&gs_type=author&author%5B0%5D=WAYNE%2BXU%2B" target="_blank" class="" data-icon-position="" data-hide-link-title="0">Find this author on Google Scholar</a></li><li class="author-tooltip-pubmed-link"><a href="/lookup/external-ref?access_num=XU%20W&link_type=AUTHORSEARCH" target="_blank" class="" data-icon-position="" data-hide-link-title="0">Find this author on PubMed</a></li><li class="author-site-search-link"><a href="/search/author1%3AWAYNE%2BXU%2B" rel="nofollow" class="" data-icon-position="" data-hide-link-title="0">Search for this author on this site</a></li><li class="author-corresp-email-link last"><span>For correspondence: <a href="mailto:wayne.xu@umanitoba.ca" class="" data-icon-position="" data-hide-link-title="0">wayne.xu@umanitoba.ca</a></span></li></ul></div></div></div> </div> </div> </div> </div> </div> </div> <!-- /.panel-row-wrapper --> <div class="panel-row-wrapper clearfix"> <div class="main-content-wrapper grid-17 suffix-1 alpha"> <div class="panel-panel panel-region-content"> <div class="inside"><div class="panel-pane pane-highwire-panel-tabs pane-panels-ajax-tab-tabs" > <div class="pane-content"> <div class="item-list"><ul class="tabs inline panels-ajax-tab"><li class="first"><a href="/content/15/1/41" class="panels-ajax-tab-tab" data-panel-name="jnl_iiar_tab_art" data-target-id="highwire_article_tabs" data-entity-context="node:1056" data-trigger="" data-url-enabled="1">Article</a><a href="/panels_ajax_tab/jnl_iiar_tab_art/node:1056/1" rel="nofollow" style="display:none" class="js-crawler-link"></a></li><li><a href="/content/15/1/41/tab-figures-data" class="panels-ajax-tab-tab" data-panel-name="jnl_iiar_tab_data" data-target-id="highwire_article_tabs" data-entity-context="node:1056" data-trigger="tab-figures-data" data-url-enabled="1">Figures & Data</a><a href="/panels_ajax_tab/jnl_iiar_tab_data/node:1056/1" rel="nofollow" style="display:none" class="js-crawler-link"></a></li><li><a href="/content/15/1/41/tab-article-info" class="panels-ajax-tab-tab" data-panel-name="jnl_iiar_tab_info" data-target-id="highwire_article_tabs" data-entity-context="node:1056" data-trigger="tab-article-info" data-url-enabled="1">Info & Metrics</a><a href="/panels_ajax_tab/jnl_iiar_tab_info/node:1056/1" rel="nofollow" style="display:none" class="js-crawler-link"></a></li><li class="last"><a href="/content/cgp/15/1/41.full.pdf" class="panels-ajax-tab-tab" data-panel-name="jnl_iiar_tab_pdf" data-target-id="highwire_article_tabs" data-entity-context="node:1056" data-trigger="tab-pdf" data-url-enabled="1"><i class="icon-file-alt"></i> PDF</a><a href="/panels_ajax_tab/jnl_iiar_tab_pdf/node:1056/1" rel="nofollow" style="display:none" class="js-crawler-link"></a></li></ul></div> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-highwire-panel-tabs-container" > <div class="pane-content"> <div data-panels-ajax-tab-preloaded="jnl_iiar_tab_art" id="panels-ajax-tab-container-highwire_article_tabs" class="panels-ajax-tab-container"><div class="panels-ajax-tab-loading" style ="display:none"><img class="loading" src="https://cgp.iiarjournals.org/sites/all/modules/contrib/panels_ajax_tab/images/loading.gif" alt="Loading" title="Loading" /></div><div class="panels-ajax-tab-wrap-jnl_iiar_tab_art"><div class="panel-display panel-1col clearfix" > <div class="panel-panel panel-col"> <div><div class="panel-pane pane-highwire-markup" > <div class="pane-content"> <div class="highwire-markup"><div xmlns="http://www.w3.org/1999/xhtml" data-highwire-cite-ref-tooltip-instance="highwire_reflinks_tooltip" class="content-block-markup" xmlns:xhtml="http://www.w3.org/1999/xhtml"><div class="article fulltext-view "><span class="highwire-journal-article-marker-start"></span><div class="section abstract" id="abstract-1"><h2>Abstract</h2><p id="p-2">Machine learning with maximization (support) of separating margin (vector), called support vector machine (SVM) learning, is a powerful classification tool that has been used for cancer genomic classification or subtyping. Today, as advancements in high-throughput technologies lead to production of large amounts of genomic and epigenomic data, the classification feature of SVMs is expanding its use in cancer genomics, leading to the discovery of new biomarkers, new drug targets, and a better understanding of cancer driver genes. Herein we reviewed the recent progress of SVMs in cancer genomic studies. We intend to comprehend the strength of the SVM learning and its future perspective in cancer genomic applications.</p></div><ul class="kwd-group"><li class="kwd"><a href="/keyword/machine-learning-ml" class="hw-term hw-article-keyword hw-article-keyword-machine-learning-ml" rel="nofollow">Machine learning (ML)</a></li><li class="kwd"><a href="/keyword/support-vector-machine-svm" class="hw-term hw-article-keyword hw-article-keyword-support-vector-machine-svm" rel="nofollow">support vector machine (SVM)</a></li><li class="kwd"><a href="/keyword/classifier" class="hw-term hw-article-keyword hw-article-keyword-classifier" rel="nofollow">classifier</a></li><li class="kwd"><a href="/keyword/genomics" class="hw-term hw-article-keyword hw-article-keyword-genomics" rel="nofollow">genomics</a></li><li class="kwd"><a href="/keyword/kernel-function" class="hw-term hw-article-keyword hw-article-keyword-kernel-function" rel="nofollow">kernel function</a></li><li class="kwd"><a href="/keyword/gene-expression" class="hw-term hw-article-keyword hw-article-keyword-gene-expression" rel="nofollow">gene expression</a></li><li class="kwd"><a href="/keyword/cancer-classification" class="hw-term hw-article-keyword hw-article-keyword-cancer-classification" rel="nofollow">cancer classification</a></li><li class="kwd"><a href="/keyword/gene-selection" class="hw-term hw-article-keyword hw-article-keyword-gene-selection" rel="nofollow">gene selection</a></li><li class="kwd"><a href="/keyword/biomarker-discovery" class="hw-term hw-article-keyword hw-article-keyword-biomarker-discovery" rel="nofollow">biomarker discovery</a></li><li class="kwd"><a href="/keyword/drug-discovery" class="hw-term hw-article-keyword hw-article-keyword-drug-discovery" rel="nofollow">drug discovery</a></li><li class="kwd"><a href="/keyword/driver-gene" class="hw-term hw-article-keyword hw-article-keyword-driver-gene" rel="nofollow">driver gene</a></li><li class="kwd"><a href="/keyword/gene-gene-interaction" class="hw-term hw-article-keyword hw-article-keyword-gene-gene-interaction" rel="nofollow">gene-gene interaction</a></li><li class="kwd"><a href="/keyword/review" class="hw-term hw-article-keyword hw-article-keyword-review" rel="nofollow">review</a></li></ul><p id="p-3">Machine learning (ML) “learns” a model from past data in order to predict future data (<a id="xref-ref-1-1" class="xref-bibr" href="#ref-1">1</a>). The key process is the learning which is one of the artificial intelligences. Many different statistical, probabilistic, and optimization techniques can be implemented as the learning methods such as the logistic regression, artificial neural networks (ANN), K-nearest neighbor (KNN), decision trees (DT) and Naive Bayes. There are two main types of ML learning - supervised learning and unsupervised learning. The supervised learning builds a model by learning from known classes (labeled training data). In contrast, unsupervised learning methods learn the common features from unknown class data (unlabeled training data).</p><p id="p-4">ML algorithms have been used for key feature training and recognition and for group classification. The strength of ML methods is it could detect hard-to-discern patterns from large, noisy or complex data sets. This capability is particularly well-suited to complex genomic data, especially in cancer studies. For example, ANN and DT have been used in cancer detection and diagnosis for nearly 20 years (<a id="xref-ref-2-1" class="xref-bibr" href="#ref-2">2</a>-<a id="xref-ref-3-1" class="xref-bibr" href="#ref-3">3</a>). The clinical implication of cancer heterogeneity and various cancer genomic data available motivate the applications of ML for cancer classification using genomic data.</p><p id="p-5">SVM learning is one of many ML methods. Compared to the other ML methods SVM is very powerful at recognizing subtle patterns in complex datasets (<a id="xref-ref-4-1" class="xref-bibr" href="#ref-4">4</a>). SVM can be used to recognize handwriting, recognize fraudulent credit cards, identify a speaker, as well as detect face (<a id="xref-ref-5-1" class="xref-bibr" href="#ref-5">5</a>). Cancer is a genetic disease where the genomic feature patterns or feature function patterns may represent the cancer subtypes, the outcome prognosis, drug benefit prediction, tumorigenesis drivers, or a tumor-specific biological process. Therefore, the Artificial Intelligence of SVM can help us in recognizing these patterns in a variety of applications.</p><div class="section" id="sec-1"><h2 class="">SVM Model</h2><p id="p-6">SVM is a powerful method for building a classifier. It aims to create a decision boundary between two classes that enables the prediction of labels from one or more feature vectors (<a id="xref-ref-6-1" class="xref-bibr" href="#ref-6">6</a>). This decision boundary, known as the hyperplane, is orientated in such a way that it is as far as possible from the closest data points from each of the classes. These closest points are called support vectors. Given a labeled training dataset: <span class="disp-formula" id="disp-formula-1"><span class="highwire-responsive-lazyload"><img src="data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7" class="highwire-embed lazyload" alt="Embedded Image" data-src="https://cgp.iiarjournals.org/sites/default/files/highwire/cgp/15/1/41/embed/graphic-1.gif"/><noscript><img class="highwire-embed" alt="Embedded Image" src="https://cgp.iiarjournals.org/sites/default/files/highwire/cgp/15/1/41/embed/graphic-1.gif"/></noscript></span> </span> where <em>x<sub>i</sub></em> is a feature vector representation and <em>y<sub>i</sub></em> the class label (negative or positive) of a training compound <em>i</em>.</p><p id="p-7">The optimal hyperplane can then be defined as: <span class="disp-formula" id="disp-formula-2"><span class="highwire-responsive-lazyload"><img src="data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7" class="highwire-embed lazyload" alt="Embedded Image" data-src="https://cgp.iiarjournals.org/sites/default/files/highwire/cgp/15/1/41/embed/graphic-2.gif"/><noscript><img class="highwire-embed" alt="Embedded Image" src="https://cgp.iiarjournals.org/sites/default/files/highwire/cgp/15/1/41/embed/graphic-2.gif"/></noscript></span> </span> where <em>w</em> is the weight vector, <em>x</em> is the input feature vector, and <em>b</em> is the bias.</p><p id="p-8">The w and b would satisfy the following inequalities for all elements of the training set: <span class="disp-formula" id="disp-formula-3"><span class="highwire-responsive-lazyload"><img src="data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7" class="highwire-embed lazyload" alt="Embedded Image" data-src="https://cgp.iiarjournals.org/sites/default/files/highwire/cgp/15/1/41/embed/graphic-3.gif"/><noscript><img class="highwire-embed" alt="Embedded Image" src="https://cgp.iiarjournals.org/sites/default/files/highwire/cgp/15/1/41/embed/graphic-3.gif"/></noscript></span> </span> </p><p id="p-9">The objective of training an SVM model is to find the <em>w</em> and <em>b</em> so that the hyperplane separates the data and maximizes the margin 1 / || w ||<sup>2</sup>.</p><p id="p-10">Vectors <em>x<sub>i</sub></em> for which |<em>y<sub>i</sub></em>| (<em>wx<sub>i</sub><sup>T</sup></em> + <em>b</em>)= 1 will be termed support vector (<a id="xref-fig-1-1" class="xref-fig" href="#F1">Figure 1</a>).</p><p id="p-11">The SVM algorithm was originally proposed to construct a linear classifier in 1963 by Vapnik (<a id="xref-ref-7-1" class="xref-bibr" href="#ref-7">7</a>). An alternative use for SVM is the kernel method, which enables us to model higher dimensional, non-linear models (<a id="xref-ref-8-1" class="xref-bibr" href="#ref-8">8</a>). In a non-linear problem, a kernel function could be used to add additional dimensions to the raw data and thus make it a linear problem in the resulting higher dimensional space (<a id="xref-fig-2-1" class="xref-fig" href="#F2">Figure 2</a>). Briefly, a kernel function could help do certain calculations faster which would otherwise would need computations in high dimensional space.</p><p id="p-12">It is defined as: <span class="disp-formula" id="disp-formula-4"><span class="highwire-responsive-lazyload"><img src="data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7" class="highwire-embed lazyload" alt="Embedded Image" data-src="https://cgp.iiarjournals.org/sites/default/files/highwire/cgp/15/1/41/embed/graphic-4.gif"/><noscript><img class="highwire-embed" alt="Embedded Image" src="https://cgp.iiarjournals.org/sites/default/files/highwire/cgp/15/1/41/embed/graphic-4.gif"/></noscript></span> </span> Here <em>K</em> is the kernel function, <em>x, y</em> are <em>n</em> dimensional inputs. <em>f</em> is used to map the input from n dimensional to m dimensional space. <<em>x, y</em>> denotes the dot product. With kernel functions, we could calculate the scalar product between two data points in a higher dimensional space without explicitly calculating the mapping from the input space to the higher dimensional space. In many cases, computing the kernel is easy while going to the high dimensional space to compute the inner product of two feature vectors is hard. The feature vector for even simple kernels can blow up in size, and for kernels like the Radial Basis Function (RBF) kernel (<em>K</em><sub>RBF</sub>(<em>x, y</em>) = exp (-γ||<em>x</em> - <em>y</em>||<sup>2</sup>), the corresponding feature vector is infinite dimensional. Yet, computing the kernel is almost trivial.</p><p id="p-13">The choice of kernel function among other factors could greatly affect the performance of an SVM model. However, there is no way to figure out which kernel would do the best for a specific pattern recognition problem. The only way to choose the best kernel is through trials. We can start with a simple SVM and then experiment with a variety of ‘standard’ kernel functions. Depending on the nature of the problem, it is possible that one kernel is better than the other kernels. An optimal kernel function can be selected from a fixed set of kernels in a statistically rigorous fashion by using cross-validation.</p><div id="F1" class="fig pos-float odd"><div class="highwire-figure"><div class="fig-inline-img-wrapper"><div class="fig-inline-img"><a href="https://cgp.iiarjournals.org/content/cgp/15/1/41/F1.large.jpg?width=800&height=600&carousel=1" title="Linear SVM model. Two classes (red versus blue) were classified." class="highwire-fragment fragment-images colorbox-load" rel="gallery-fragment-images-599357884" data-figure-caption="<div class="highwire-markup">Linear SVM model. Two classes (red versus blue) were classified.</div>" data-icon-position="" data-hide-link-title="0"><span class="hw-responsive-img"><img class="highwire-fragment fragment-image lazyload" alt="Figure 1." src="data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7" data-src="https://cgp.iiarjournals.org/content/cgp/15/1/41/F1.medium.gif" width="440" height="373"/><noscript><img class="highwire-fragment fragment-image" alt="Figure 1." src="https://cgp.iiarjournals.org/content/cgp/15/1/41/F1.medium.gif" width="440" height="373"/></noscript></span></a></div></div><ul class="highwire-figure-links inline"><li class="download-fig first"><a href="https://cgp.iiarjournals.org/content/cgp/15/1/41/F1.large.jpg?download=true" class="highwire-figure-link highwire-figure-link-download" title="Download Figure 1." data-icon-position="" data-hide-link-title="0">Download figure</a></li><li class="new-tab"><a href="https://cgp.iiarjournals.org/content/cgp/15/1/41/F1.large.jpg" class="highwire-figure-link highwire-figure-link-newtab" target="_blank" data-icon-position="" data-hide-link-title="0">Open in new tab</a></li><li class="download-ppt last"><a href="/highwire/powerpoint/2974" class="highwire-figure-link highwire-figure-link-ppt" data-icon-position="" data-hide-link-title="0">Download powerpoint</a></li></ul></div><div class="fig-caption" xmlns:xhtml="http://www.w3.org/1999/xhtml"><span class="fig-label">Figure 1.</span> <p id="p-14" class="first-child">Linear SVM model. Two classes (red versus blue) were classified.</p><div class="sb-div caption-clear"></div></div></div></div><div class="section" id="sec-2"><h2 class="">Cancer Classification and Subtyping</h2><p id="p-15">SVM as a classifier has been used in cancer classification since the high throughtput microarray gene expression data was avaliable in the early 2000's. Golub <em>et al.</em> (<a id="xref-ref-9-1" class="xref-bibr" href="#ref-9">9</a>) first tried a linear SVM to classify two different types of leukemia using gene expression microarray data. In this study, 38 patients were used as training set. A simple learning algorithm called “weighted voting” was trained to recognize the distinction between two known (labeled) forms of leukemia. The Affymetrix Hgu6800 chips covered 7,129 gene features (gene expression probes) and each of the whole gene features was weighted in contributing to the two classes. The learned SVM model was used to test another independent data of 34 patients. This study has demonstrated the superior performance of SVM in classifying high-dimensional (gene features) and low sample size data. Subsequently, Vapnik <em>et al.</em> (<a id="xref-ref-10-1" class="xref-bibr" href="#ref-10">10</a>) improved upon the accuracy of the weighted voting method of the SVM, reducing the error rate from 6% (2 errors out of 34) to 0%. But in this study no feature selection was performed before the model development.</p><p id="p-16">Moler <em>et al.</em> (<a id="xref-ref-11-1" class="xref-bibr" href="#ref-11">11</a>) applied SVM in a colon cancer tissue classification using selected features. They used a collection of 40 colon cancer tumors and 22 normal colon tissues. First, a feature selection metric, the naive Bayes relevance (NBR) score, was proposed, which was based on the probability of a class given the observed value of the feature, under a Gaussian model. SVMs were then trained using only the 50-200 top-ranked genes, which had the same or better generalization performance than the full repertoire of 1, 988 genes in discriminating non-tumor from tumor specimens. In addition, the performance of the SVM using various numbers of selected genes was compared to the performance of a naive Bayes classifier using the same genes. In each case, the SVM outperformed naive Bayes. Furey <em>et al.</em> (<a id="xref-ref-12-1" class="xref-bibr" href="#ref-12">12</a>) applied linear SVMs with feature selection to three cancer data sets. The first data set consisted of 31 tissues samples, including cancerous ovarian, normal ovarian and normal non-ovarian tissue. The other two sets were the leukemia (<a id="xref-ref-9-2" class="xref-bibr" href="#ref-9">9</a>) and colon cancer sets (<a id="xref-ref-11-2" class="xref-bibr" href="#ref-11">11</a>). In this study, A feature selection metric called the signal-to-noise ratio (<a id="xref-ref-9-3" class="xref-bibr" href="#ref-9">9</a>), which was closely related to the Fisher criterion score used in Fisher's linear discriminant, was used to select genes for training the classifier. Overall, the SVM provided reasonably good performance across multiple data sets, although the experiments also demonstrated that several perceptron-based algorithms performed similarly. Segal <em>et al.</em> (<a id="xref-ref-13-1" class="xref-bibr" href="#ref-13">13</a>) proposed a genome-based SVM classification scheme for clear cell sarcoma, which displays characteristics of both soft tissue sarcoma and melanoma. Firstly, 256 genes were selected by student t-test. Subsequently, a linear SVM was trained to recognize the distinction between melanoma and soft tissue sarcoma using the selected genes. In a leave-one-out setting, the classifier correctly classified 75 out of 76 examples. In another study (<a id="xref-ref-14-1" class="xref-bibr" href="#ref-14">14</a>), SVM was applied to investigate the complex histopathology of adult soft tissue sarcomas. A data set including 51 samples that had been classified by pathologists into nine histologic subtypes was used. The SVM could successfully recognize the four subtypes for which molecular phenotypes are already known. Among the remaining samples, a combination of SVMs and hierarchical clustering could uncover a well-separated subset of the malignant fibrous histiocytoma subtype, which is a particularly controversial subtype.</p><div id="F2" class="fig pos-float odd"><div class="highwire-figure"><div class="fig-inline-img-wrapper"><div class="fig-inline-img"><a href="https://cgp.iiarjournals.org/content/cgp/15/1/41/F2.large.jpg?width=800&height=600&carousel=1" title="Kernel function. Data that cannot be separated by linear SVM can be transformed and separated by a kernel function." class="highwire-fragment fragment-images colorbox-load" rel="gallery-fragment-images-599357884" data-figure-caption="<div class="highwire-markup">Kernel function. Data that cannot be separated by linear SVM can be transformed and separated by a kernel function.</div>" data-icon-position="" data-hide-link-title="0"><span class="hw-responsive-img"><img class="highwire-fragment fragment-image lazyload" alt="Figure 2." src="data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7" data-src="https://cgp.iiarjournals.org/content/cgp/15/1/41/F2.medium.gif" width="440" height="127"/><noscript><img class="highwire-fragment fragment-image" alt="Figure 2." src="https://cgp.iiarjournals.org/content/cgp/15/1/41/F2.medium.gif" width="440" height="127"/></noscript></span></a></div></div><ul class="highwire-figure-links inline"><li class="download-fig first"><a href="https://cgp.iiarjournals.org/content/cgp/15/1/41/F2.large.jpg?download=true" class="highwire-figure-link highwire-figure-link-download" title="Download Figure 2." data-icon-position="" data-hide-link-title="0">Download figure</a></li><li class="new-tab"><a href="https://cgp.iiarjournals.org/content/cgp/15/1/41/F2.large.jpg" class="highwire-figure-link highwire-figure-link-newtab" target="_blank" data-icon-position="" data-hide-link-title="0">Open in new tab</a></li><li class="download-ppt last"><a href="/highwire/powerpoint/3004" class="highwire-figure-link highwire-figure-link-ppt" data-icon-position="" data-hide-link-title="0">Download powerpoint</a></li></ul></div><div class="fig-caption"><span class="fig-label">Figure 2.</span> <p id="p-17" class="first-child">Kernel function. Data that cannot be separated by linear SVM can be transformed and separated by a kernel function.</p><div class="sb-div caption-clear"></div></div></div><div id="F3" class="fig pos-float odd"><div class="highwire-figure"><div class="fig-inline-img-wrapper"><div class="fig-inline-img"><a href="https://cgp.iiarjournals.org/content/cgp/15/1/41/F3.large.jpg?width=800&height=600&carousel=1" title="Feature selection methods. Two frameworks (Feature filter and wrapper) were presented." class="highwire-fragment fragment-images colorbox-load" rel="gallery-fragment-images-599357884" data-figure-caption="<div class="highwire-markup">Feature selection methods. Two frameworks (Feature filter and wrapper) were presented.</div>" data-icon-position="" data-hide-link-title="0"><span class="hw-responsive-img"><img class="highwire-fragment fragment-image lazyload" alt="Figure 3." src="data:image/gif;base64,R0lGODlhAQABAIAAAAAAAP///yH5BAEAAAAALAAAAAABAAEAAAIBRAA7" data-src="https://cgp.iiarjournals.org/content/cgp/15/1/41/F3.medium.gif" width="440" height="222"/><noscript><img class="highwire-fragment fragment-image" alt="Figure 3." src="https://cgp.iiarjournals.org/content/cgp/15/1/41/F3.medium.gif" width="440" height="222"/></noscript></span></a></div></div><ul class="highwire-figure-links inline"><li class="download-fig first"><a href="https://cgp.iiarjournals.org/content/cgp/15/1/41/F3.large.jpg?download=true" class="highwire-figure-link highwire-figure-link-download" title="Download Figure 3." data-icon-position="" data-hide-link-title="0">Download figure</a></li><li class="new-tab"><a href="https://cgp.iiarjournals.org/content/cgp/15/1/41/F3.large.jpg" class="highwire-figure-link highwire-figure-link-newtab" target="_blank" data-icon-position="" data-hide-link-title="0">Open in new tab</a></li><li class="download-ppt last"><a href="/highwire/powerpoint/2947" class="highwire-figure-link highwire-figure-link-ppt" data-icon-position="" data-hide-link-title="0">Download powerpoint</a></li></ul></div><div class="fig-caption"><span class="fig-label">Figure 3.</span> <p id="p-18" class="first-child">Feature selection methods. Two frameworks (Feature filter and wrapper) were presented.</p><div class="sb-div caption-clear"></div></div></div><p id="p-19">Above SVMs are binary sample classifiers. Cancer is heterogeneous and multiclass classification is needed. For example, breast cancer consists of mainly four molecular subtypes (Lumina A, Lumina B, HER2-enriched and Basal). SVM can be extended for multiclass problems using the so-called one-vs-rest approach (<a id="xref-ref-15-1" class="xref-bibr" href="#ref-15">15</a>). For N class problems, SVMs will be trained independently between one specific class which is seen as the positive class and the other classes will form the negative cases. Li <em>et al.</em> (<a id="xref-ref-16-1" class="xref-bibr" href="#ref-16">16</a>) compared various state-of-the-art classification methods on numerous multiclass gene expression datasets and found that the multiclass classification problem was much more difficult than the binary one for the gene expression datasets due to the fact that the data are of high dimensionality and small sample size.</p><p id="p-20">Besides mRNA expression features, DNA methylation was also applied in SVM modeling for cancer classification. Methylation is a molecular modification of DNA, where a methyl group is added to the nucleotide cytosine. Methylation patterns in the upstream regions of genes are considered a major factor in gene regulation. Twenty-five patients with two forms of leukemia were classified by methylation pattern that contained measurements from 81 positions along the DNA strand (<a id="xref-ref-17-1" class="xref-bibr" href="#ref-17">17</a>). In this study, various feature selection methods were employed prior to model training, including principle components analysis, the signal-to-noise ratio, the Fisher criterion score, the student <em>t</em>-test, and a method called backward elimination. Kim (<a id="xref-ref-18-1" class="xref-bibr" href="#ref-18">18</a>) proposed a weighted K-means support vector machine (wKM-SVM) method for two methylation profiles of breast and kidney cancer. Level 3 DNA methylation of beta values targeting on methylated and the un-methylated probes were downloaded from The Cancer Genome Atlas (TCGA) database (<a href="https://tcga-data.nci.nih.gov/tcga/">https://tcga-data.nci.nih.gov/tcga/</a>). The breast cancer set consisted of methylation data of 10,121 genes for 316 tumor samples and 27 control cases. The kidney set included methylation data of 10,121 genes for 219 tumor samples and 199 control cases. They compared wKM-SVM with other different algorithms, including classification and regression tree (CART), KNN and random forest in recognizing tumor from normal. The wKM-SVM had the best performance. Yang <em>et al.</em> (<a id="xref-ref-19-1" class="xref-bibr" href="#ref-19">19</a>) used an extension of the random forest, Boruta, to select important DNA methylation features and establish an SVM classifier for liver cancer diagnosis. Alkuhlani <em>et al.</em> (<a id="xref-ref-20-1" class="xref-bibr" href="#ref-20">20</a>) developed a multistage approach to select the optimal CpG sites from three different DNA methylation cancer datasets (breast, colon and lung). Three different filter feature selection methods (Fisher Criterion, t-test and Area Under ROC Curve) were first combined to reduce the CpG sites. The final SVM Recursive Feature Elimination (SVMRFE) resulted in classification accuracies of 96.02, 98.81 and 94.51% for the three cohorts, respectively. SVM was also applied in the identification and validation of the methylation biomarkers of non-small cell lung cancer (NSCLC) (<a id="xref-ref-21-1" class="xref-bibr" href="#ref-21">21</a>).</p><p id="p-21">Other data types were also used in SVM modeling. An SVM algorithm has been used to classify or diagnose multiple cancers based on a protein chip that was fabricated with twelve monoclonal antibodies to quantify the tumor markers (<a id="xref-ref-22-1" class="xref-bibr" href="#ref-22">22</a>). Tyanova <em>et al.</em> (<a id="xref-ref-23-1" class="xref-bibr" href="#ref-23">23</a>) used proteomics data to train an SVM model to classify breast cancer subtypes. Copy number variations (<a id="xref-ref-24-1" class="xref-bibr" href="#ref-24">24</a>) and single nucleotide polymorphisms (SNPs) (<a id="xref-ref-25-1" class="xref-bibr" href="#ref-25">25</a>) were used to train SVM classifiers for bladder, uveal cancer and breast cancer respectively. Wu <em>et al.</em> (<a id="xref-ref-26-1" class="xref-bibr" href="#ref-26">26</a>) built three SVM classification models based on the identified pathways which effectively classified different breast cancer subtypes.</p><p id="p-22">New machine-learning methods have been developed to classify integrated multilayer heterogeneous genomic data (<a id="xref-ref-27-1" class="xref-bibr" href="#ref-27">27</a>). For example, for a given gene we might know the protein it encodes, the mRNA expression levels associated with the given gene for hundreds of patients, the occurrences of known or inferred transcription factor binding sites in the upstream region of that gene, and the identities of many of the proteins that interact with the given gene's protein product. Each of these distinct data types provides one view of the molecular machinery of the cell. Thus, integrating the multilayers of omics data could facilitate uncovering biological processes and capturing the interplay of multi-level genomic features. Several efforts have been made for multiple omics data integration in the context of SVM learning. Kim <em>et al.</em> (<a id="xref-ref-28-1" class="xref-bibr" href="#ref-28">28</a>) proposed a meta-analytic support vector machine (Meta-SVM) that can accommodate multiple omics data, making it possible to detect consensus genes associated with diseases across studies. The Meta-SVM method was applied to breast cancer expression profiles provided by TCGA including mRNA, copy number variation (CNV) and epigenetic DNA methylation. The three inter-omics features of breast cancer were aligned on identical protein coding regions. The results demonstrated that the Meta-SVM showed better performance in discovering the underlying true signals and in detecting gene sets enriched for cancer disease process validated as biologically significant.</p></div><div class="section" id="sec-3"><h2 class="">Biomarker/Signature Discovery</h2><p id="p-23">Biomarkers discovery involves selecting biologically meaningful or associated gene expression, SNPs, DNA methylation, or micro-RNA from high-dimensional data and modeling scores based on the selected features to help cancer diagnosis, prognosis or treatment response (<a id="xref-ref-29-1" class="xref-bibr" href="#ref-29">29</a>). This process can be viewed as selecting features for classifications (cancer <em>versus</em> none cancer, good <em>versus</em> poor outcome classes, drug response <em>versus</em> no response classes). There are two main methods for selecting features: filter methods and wrapper methods. In filter methods, the features (<em>i.e.</em> genes) are selected by predetermined ranking criteria and then are fitted into cancer classifier algorithms (<a id="xref-fig-3-1" class="xref-fig" href="#F3">Figure 3</a>). For example, genes can be ranked by correlation coefficients (<a id="xref-ref-9-4" class="xref-bibr" href="#ref-9">9</a>, <a id="xref-ref-12-2" class="xref-bibr" href="#ref-12">12</a>) and hypothesis testing statistics (<a id="xref-ref-30-1" class="xref-bibr" href="#ref-30">30</a>-<a id="xref-ref-33-1" class="xref-bibr" href="#ref-33">33</a>). The drawbacks with the gene-ranking methods are: (i) one has to specify the number of selected genes in advance and often subjectively and (ii) the selection is individual-based and hence ignores any significant gene-gene correlations that may occur in the data. Xu <em>et al.</em> (<a id="xref-ref-34-1" class="xref-bibr" href="#ref-34">34</a>) used differentially expressed genes (DEGs) and protein-protein interaction (PPI) network-based neighborhood scoring to select features and trained a SVM model of a 15-gene signature for prediction of colon cancer recurrence and prognosis. Hu <em>et al.</em> (<a id="xref-ref-35-1" class="xref-bibr" href="#ref-35">35</a>) built an SVM algorithm based on the structural risk minimization principle for the identification of thirty-eight markers involved in brain development from single-cell transcriptomic data. An SVM feature selection based on profiling of urinary RNA metabolites was applied to predict breast cancer (<a id="xref-ref-36-1" class="xref-bibr" href="#ref-36">36</a>). SVMs coupled with proteomics approaches were applied for detecting biomarkers predicting chemotherapy resistance in small cell lung cancer (<a id="xref-ref-37-1" class="xref-bibr" href="#ref-37">37</a>).</p><p id="p-24">In the wrapper methods, the gene selection and classifier modeling occur at the same time (<a id="xref-ref-38-1" class="xref-bibr" href="#ref-38">38</a>, <a id="xref-ref-39-1" class="xref-bibr" href="#ref-39">39</a>). Wrapper methods utilize the learning machine of interest as a black box to score subsets of variable according to their predictive power (<a id="xref-fig-3-2" class="xref-fig" href="#F3">Figure 3</a>). Based on the inferences drawn from the previous modeling, gene features will be added to or removed from the current subset. These methods are usually computationally expensive. Some common examples of wrapper methods are forward feature selection, backward feature elimination, and recursive feature elimination.</p><p id="p-25">One example is the SVM recursive feature elimination (SVM-RFE) proposed by Guyon <em>et al.</em> (<a id="xref-ref-39-2" class="xref-bibr" href="#ref-39">39</a>, <a id="xref-ref-40-1" class="xref-bibr" href="#ref-40">40</a>). The idea is that the orientation of the separating hyperplane modelled by the SVM can be used to select informative features, <em>i.e.</em> if the plane is orthogonal to a particular feature dimension, then that feature is informative, and vice versa. Thus, the SVM-RFE method could remove the least important features and select the most important features based on the weights of classifiers. Firstly, the SVM-RFE wrapper initializes the data set to contain all features. Then, it trains an SVM on the extended data set and applies a feature importance measure (<em>i.e.</em> criterion) to evaluate the importance of each feature. It ranks features in each iteration according to the criterion and constantly removes the lowest-ranked feature. Finally, the algorithm stops either when all features get confirmed or rejected.</p><p id="p-26">The SVM-RFE algorithm has been tested on both the AML/ALL and the colon cancer data sets (<a id="xref-ref-40-2" class="xref-bibr" href="#ref-40">40</a>). In the leukemia dataset, SVM-RFE selected two genes which together yielded zero leave-one-out error. In the colon cancer dataset, SVMRFE identified only 4 genes that yielded an accuracy of 98%. In addition, several other classification algorithms have been trained using the genes selected by SVM-RFE.</p><p id="p-27">In biomarker discovery using SVM-RFE, the sampling variation may greatly influence subsequent biological validations. Abeel <em>et al.</em> (<a id="xref-ref-38-2" class="xref-bibr" href="#ref-38">38</a>) addressed this issue by introducing the ensemble concept into the original RFE method. In the ensemble SVM-RFE method, bootstrap was used to resample K times from the training data. SVM-RFE was then applied to each of the K resamples and thus K marker sets were obtained. In the final phase, the output of these separate marker selectors was aggregated and returned as the final (ensemble) result. This ensemble SVM-RFE method was tested in four microarray datasets: a Leukemia dataset with acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL) tissues; a Colon Cancer dataset consisted of samples from 40 tumor and 22 normal colon tissues probed by an Affymetrix microarray chip measuring more than 6,500 genes; a lymphoma dataset from a study on diffuse large B-cell lymphoma; and a prostate dataset. The ensemble SVM-RFE was showing increases of up to almost 30% in robustness of the selected biomarkers, along with an improvement of about 15% in classification performance evaluated on the four microarray datasets compared to the original SVM-RFE. The stability improvement with ensemble methods is particularly noticeable for small signature sizes (a few dozens of genes), which is most relevant for the design of a diagnosis or prognosis model from a gene signature.</p><p id="p-28">Chen <em>et al.</em> (<a id="xref-ref-41-1" class="xref-bibr" href="#ref-41">41</a>) developed a network-constrained support vector machine (netSVM) for identifying biologically network biomarkers using integration of gene expression data and protein-protein interaction data. The netSVM was tested in two breast cancer gene expression data sets to identify prognostic signatures for predicting cancer metastasis. The results showed that the network biomarkers identified by netSVM were highly enriched in biological pathways associated with breast cancer progression and helped improve the prediction performance when tested across different data sets. Specifically, many of the identified genes were related to apoptosis, cell cycle, and cell proliferation, which are hallmark signatures of breast cancer metastasis. Importantly, several novel hub genes, biologically important with many interactions in Protein-protein interaction (PPI) network but often showing little change in expression when compared to their downstream genes, were also identified as network biomarkers; the genes were enriched in signaling pathways such as the TGF-beta signaling pathway, MAPK signaling pathway, and JAKSTAT signaling pathway. These signaling pathways may provide new insight to the underlying mechanism of breast cancer metastasis.</p></div><div class="section" id="sec-4"><h2 class="">Drug Discovery for Cancer Therapy</h2><p id="p-29">Drugs for a variety of deadly cancers remain limited. The major challenges in cancer drug discovery include side effects of drugs, high toxicity and drug resistance towards current anticancer drugs. The traditional drug discovery process involves an iterative procedure of finding compounds that are active against a biological target, which is time-consuming when selecting from a large collection of compounds. Experimental techniques used for drug discovery are costly and time-consuming (<a id="xref-ref-42-1" class="xref-bibr" href="#ref-42">42</a>). Today SVM can aid this screening process using the maximum margin hyperplanes. This hyperplane separates the active from the inactive compounds and has the largest possible distance from any labeled compound.</p><p id="p-30"><em>Selecting anticancer drugs.</em> Warmuth <em>et al.</em> (<a id="xref-ref-43-1" class="xref-bibr" href="#ref-43">43</a>) used active learning to develop an SVM model for selecting active compounds. Instead of separating the data into training set for deriving models and testing set for validating models, the learning set was incremented and a new, further improved model was learned with each round in active learning. Gupta <em>et al.</em> (<a id="xref-ref-44-1" class="xref-bibr" href="#ref-44">44</a>) applied an SVM model to prioritize anticancer drugs against a cancer using the genomic features of cancer cells. The drug profile of 24 anticancer drugs was tested against a large number of cell lines in order to understand the relation between drug resistance and altered genomic features of a cancer cell line. Bundela <em>et al.</em> (<a id="xref-ref-45-1" class="xref-bibr" href="#ref-45">45</a>) built an SVM-RBF model to identify potential therapeutic compounds for oral cancer from the large pool of compounds from the publicly available compound databases.</p><p id="p-31">Matsumoto <em>et al.</em> (<a id="xref-ref-46-1" class="xref-bibr" href="#ref-46">46</a>) used SVM for virtual screening of radiation protection function and toxicity for radioprotectors targeting p53. Radiation therapy is one of the main approaches against cancer cells, although this therapy has adverse side effects, including p53-induced apoptosis of normal tissues and cells (<a id="xref-ref-47-1" class="xref-bibr" href="#ref-47">47</a>). It is considered that p53 would be a target for therapeutic and mitigative radioprotection to avoid the apoptotic fate. It was found that SVM is better than other machine learning in the case that the target protein is known and we search for a compound that bond to the target protein.</p><p id="p-32"><em>Identifying novel cancer drug targets</em>. SVMs have been used for predicting druggability scores for targets (<a id="xref-ref-48-1" class="xref-bibr" href="#ref-48">48</a>). The model was trained using three to six global descriptors of protein binding sites accounting for size, compactness and physicochemical properties. With these descriptors, the druggability scores could be assigned to new targets (<a id="xref-ref-48-2" class="xref-bibr" href="#ref-48">48</a>). The SVM methodology was also used to prioritize docking poses. Li <em>et al.</em> (<a id="xref-ref-49-1" class="xref-bibr" href="#ref-49">49</a>) used a Support Vector Machine-based scoring function in regression mode (SVR) to assess target-ligand interactions. Knowledge-based pairwise potentials derived from complex crystal structures were used to develop the scoring function. In another study, a support vector regression (SVR) algorithm was derived from a set of descriptors and was applied to predict protein-ligand binding affinities (<a id="xref-ref-50-1" class="xref-bibr" href="#ref-50">50</a>).</p><p id="p-33">The identification of drug target proteins (DTP) plays a critical role in biometrics. Wang <em>et al.</em> (<a id="xref-ref-51-1" class="xref-bibr" href="#ref-51">51</a>) designed a novel framework to retrieve DTPs from a collected protein dataset, which represents an overwhelming task of great significance. Previously reported methodologies for this task generally employ protein-protein interactive networks but neglect informative biochemical attributes. A novel framework was formulated utilizing biochemical attributes to address this problem. In the framework, a biased support vector machine (BSVM) was combined with the deep embedded representation extracted using a deep learning model, stacked auto-encoders (SAEs). In cases of non-drug target proteins (NDTPs) contaminated by DTPs, the framework is beneficial due to the efficient representation of the SAE and relief of the imbalance effect by the BSVM. The experimental results demonstrated the effectiveness of this framework, and the generalization capability was confirmed <em>via</em> comparisons to other models. This study is the first to exploit a deep learning model for IDTP. In summary, nearly 23% of the NDTPs were predicted as likely DTPs, which are awaiting further verification based on biomedical experiments.</p><p id="p-34">Jeon <em>et al.</em> (<a id="xref-ref-52-1" class="xref-bibr" href="#ref-52">52</a>) utilized SVM to learn five genomic features from various types of high-throughput data for the genome-wide identification of cancer therapeutic targets. These features include gene essentiality, expression level, mutation, copy number and closeness in a PPI network. The SVM was trained by known cancer targets <em>versus</em> non-targets, and then used for novel target discovery.</p><p id="p-35"><em>Drug/nondrug classification.</em> Singh <em>et al.</em> (<a id="xref-ref-53-1" class="xref-bibr" href="#ref-53">53</a>) developed a hybrid method of SVM on thousands of anticancer and non-anticancer molecules tested against 60 National Cancer Institute (NCI) cancer cell lines. This highly accurate hybrid method can be used for classification of anticancer and non-anticancer molecules. Also a non-linear machine learning techniques has been used to generate robust multiomic signatures that predict cancer cellular response to 17-AAG, AZD0530, AZD6244, Erlotinib, Lapatinib, Nultin-3, Paclitaxel, PD0325901, PD0332991, PF02341066, and PLX4720 using data from the CCLE, CGP, and NCI60 databases(<a id="xref-ref-54-1" class="xref-bibr" href="#ref-54">54</a>).</p><p id="p-36"><em>Anticancer drug sensitivity prediction.</em> Computational models to predict the response of cancer cell lines to drug compounds facilitate cancer therapeutics development process. Hejase <em>et al.</em> (<a id="xref-ref-55-1" class="xref-bibr" href="#ref-55">55</a>) built an ensemble SVM model to predict the sensitivity of the breast cancer cell lines to previously untested drug compounds. The ensemble SVM model extracts features from different types of data (proteomic data, gene expression, RNA-seq, DNA methylation, and DNA copy number variation) rather than using different base algorithms on a single type of data. The ensemble model based on the different types of data enhanced and improved the accuracy of the overall model.</p><p id="p-37"><em>Predicting substrates of the cancer resistance.</em> Human breast cancer resistance protein (BCRP) is an ATP-binding cassette (ABC) efflux transporter that confers multidrug resistance in cancers and also plays an important role in the absorption, distribution and elimination of drugs. Hazai <em>et al.</em> (<a id="xref-ref-56-1" class="xref-bibr" href="#ref-56">56</a>) developed SVM models to predict wild-type BCRP substrates based on a total of 263 known BCRP substrates and non-substrates collected from literature. The final SVM model had an overall prediction accuracy of approximately 73% for an independent external validation data set of 40 compounds.</p></div><div class="section" id="sec-5"><h2 class="">Cancer Driver Gene Discovery</h2><p id="p-38">Cancer is initiated by somatic mutations, called cancer driver gene mutations. However, all various cancers cannot be explained by the handful number of driver genes currently reported. The continuing decline in the cost of genome sequencing, as well as the relative ease of interpreting the effects of mutations in many proteins <em>via</em> methods such as activity assays has led to a sustained drive to understand the effects of cancer derived mutations on cancer progression. The challenge of finding mechanistic links between mutations and cancer progression is made even more imperative by the fact that many cancer drugs target mutations that have specific effects, as well as the observation that many clinical trials fail due to patient cohorts that are not suitable for specific therapies (<a id="xref-ref-57-1" class="xref-bibr" href="#ref-57">57</a>). Sequencing efforts as well as the frequent failure of targeted therapies has led to an increasingly well-recognized principle that not all mutations confer selective advantage on cancer cells. These mutations are known as passenger mutations while mutations that confer some advantage are commonly referred to as driver mutations, because they can be seen as properties of the residues from the mutations. They showed that this classifier performs driving cancer progression (<a id="xref-ref-58-1" class="xref-bibr" href="#ref-58">58</a>).</p><p id="p-39">SVM is one of the most widely used techniques to classify mutations specific to cancer. This essentially geometric method tries to find combinations of features that are common to mutations of different classes so that mutations of unknown class (<em>i.e.</em> driver or passenger) can be classified (<a id="xref-ref-59-1" class="xref-bibr" href="#ref-59">59</a>). SVM classifiers were also trained to predict whether mutations occur across the whole genome (<a id="xref-ref-60-1" class="xref-bibr" href="#ref-60">60</a>) as well as in a specific class of proteins (<a id="xref-ref-61-1" class="xref-bibr" href="#ref-61">61</a>). These methods based on cross-validation showed high accurate predictions, high receiver operating characteristic area under the curve (AUC), or high probability of distinguishing between examples of different classes.</p><p id="p-40">Jordan <em>et al.</em> (<a id="xref-ref-59-2" class="xref-bibr" href="#ref-59">59</a>) developed an SVM method to predict the activation status of kinase domain mutations in cancer and the method showed it to be reliable with an accuracy of 78% when a balanced dataset was used. This method did not need to make any decisions in advance about which mutations are driver mutations, as many recent machine learning efforts have. It was also faster than molecular dynamics (MD) to predict the effect of kinase domain mutations which are ofted used to predict. Interestingly, the ability to affect salt bridge formation was demonstrated to be an important factor in determining whether a given mutation is likely to be a driver. Tan <em>et al.</em> (<a id="xref-ref-62-1" class="xref-bibr" href="#ref-62">62</a>) developed a novel missense-mutation-related feature extraction scheme for identifying driver mutations. A total of 126 features were investigated for each missense mutation, including (i) changes in the physiochemical properties of the residues from the mutations; (ii) substitution scoring matrix (SSM) features from published sources; (iii) protein sequence-specific (PSS) features, which extract various patterns of two consecutive amino acid residues or a six-letter exchange group in a protein sequence; and (iv) other annotated features derived from the UniProt KnowledgeBase, Swiss Prot variant page and COSMIC database. A classifier was derived based on the features using SVM. The classifier was then tested on a new data set using n-fold cross-validation. From the 126 candidate features, they were able to identify the top 70 features that were best able to discriminate between driver and passenger mutations. Most (61 of 70) of the top 70 features consisted of the SSM and PSS features rather than simple changes in the physiochemical better than the previous methods by comparing their ability (in terms of ROC and prediction precision) to identify 117 EGFR and 1029 TP53 missense mutations (<a id="xref-ref-58-2" class="xref-bibr" href="#ref-58">58</a>). Capriotti <em>et al.</em> (<a id="xref-ref-63-1" class="xref-bibr" href="#ref-63">63</a>) trained an SVM classifier on a set of 3163 cancer-causing variants and an equal number of neutral polymorphisms. The individual variants identified could be indicators of cancer risk. The method achieved 93% overall accuracy, a correlation coefficient of 0.86, and area under ROC curve of 0.98.</p><p id="p-41">Bari <em>et al.</em> (<a id="xref-ref-64-1" class="xref-bibr" href="#ref-64">64</a>) built SVM models to uncover a new class of cancer-related genes that are neither mutated nor differentially expressed. This SVM-Assisted Network Inference (MALANI) algorithm assesses all genes regardless of expression or mutational status in the context of cancer etiology. 8807 expression arrays corresponding to 9 cancer types were used to build more than 2×10<sup>8</sup> SVM models for reconstructing a cancer network. Approximately 3% of ~19,000 not differentially expressed genes are the new class of cancer gene candidates.</p></div><div class="section" id="sec-6"><h2 class="">Cancer Gene/Protein Interaction and Networks</h2><p id="p-42">Cancer is a complex disease of impacted biological processes with multiple genes or factors. Modeling the gene-gene interaction helps understand the underlying biological mechanisms. Traditional statistical tools are not appropriate for analyzing large-scale genetic data. However, it appears some of the computational limitations of detecting gene-gene interactions can be overcome using modern techniques, such as machine learning and data mining. The problem of detecting interactions among multiple genes can be considered as a combinatorial optimization problem: finding the best combination of gene features from a given dataset which can produce the highest prediction accuracy.</p><div id="T1" class="table pos-float"><div class="table-inline table-callout-links"><div class="callout"><span>View this table:</span><ul class="callout-links"><li class="view-inline first"><a href="" class="table-expand-inline" data-table-url="/highwire/markup/2981/expansion?postprocessors=highwire_tables%2Chighwire_reclass%2Chighwire_figures%2Chighwire_math%2Chighwire_inline_linked_media%2Chighwire_embed&table-expand-inline=1" data-icon-position="" data-hide-link-title="0">View inline</a></li><li class="view-popup"><a href="/highwire/markup/2981/expansion?width=1000&height=500&iframe=true&postprocessors=highwire_tables%2Chighwire_reclass%2Chighwire_figures%2Chighwire_math%2Chighwire_inline_linked_media%2Chighwire_embed" class="colorbox colorbox-load table-expand-popup" rel="gallery-fragment-tables" data-icon-position="" data-hide-link-title="0">View popup</a></li><li class="download-ppt last"><a href="/highwire/powerpoint/2981" class="highwire-figure-link highwire-figure-link-ppt" data-icon-position="" data-hide-link-title="0">Download powerpoint</a></li></ul></div></div><div class="table-caption"><span class="table-label">Table I.</span> <p id="p-43" class="first-child">Summary of typical applications of SVM in cancer genomics.</p><div class="sb-div caption-clear"></div></div></div><p id="p-44">A few early studies (<a id="xref-ref-40-3" class="xref-bibr" href="#ref-40">40</a>, <a id="xref-ref-65-1" class="xref-bibr" href="#ref-65">65</a>, <a id="xref-ref-66-1" class="xref-bibr" href="#ref-66">66</a>) have shown that SVMs are promising predictors for the detection of gene-gene interactions. Later an applicable computational SVM framework for detecting gene-gene interactions was described (<a id="xref-ref-67-1" class="xref-bibr" href="#ref-67">67</a>). SVM and combinatorial optimization techniques (local search and genetic algorithm) were tailored to fit within this framework. Although the proposed approach is computationally expensive, the results indicate this is a promising tool for the identification and characterization of high order gene-gene and gene-environment interactions. On one hand, several advantages of this method, including the strong power for classification, less concern for overfitting, and the ability to handle unbalanced data and achieve more stable models, have been demonstrated. On the other hand, this method was computationally expensive.</p><p id="p-45">In a study conducted by Guo <em>et al.</em> (<a id="xref-ref-68-1" class="xref-bibr" href="#ref-68">68</a>), SVM model derived from the primary sequences of proteins was used for predicting PPIs. The SVM model was developed with the aid of auto covariance (AC). AC was used to cover the information of interactions between amino acid residues a certain distance apart in the sequence. Thus, the neighboring effect was taken into consideration in this method. The AC and SVM combined method showed a very promising prediction result when performed on the yeast Saccharomyces cerevisiae PPI data. This method achieved an accuracy of 88.09% another independent data set of 11474 yeast PPIs. The superiority of this method over the existing sequence-based methods will make it useful for the study of protein networks. Chai <em>et al.</em> (<a id="xref-ref-69-1" class="xref-bibr" href="#ref-69">69</a>) built a new Net-SVM model which selected fewer but more relevant genes. This Net-SVM can be used to construct simple and informative PPI networks that are highly relevant to cancer.</p></div><div class="section" id="sec-7"><h2 class="">Perspective</h2><p id="p-46">Cancer genomic data are high-dimensional, heterogeneous and noisy. The application of SVM learning in cancer genomics is a popular and successful undertaking (<a id="xref-table-wrap-1-1" class="xref-table" href="#T1">Table I</a>). The appeal of SVM approach is due in part to the power of the SVM algorithm, and in part to the flexibility of the kernel approach to representing data. If the parameters C and r are appropriately chosen, SVMs can be robust, even when the training sample has some bias.</p><p id="p-47">Although SVMs with non-linear kernels are extremely powerful classifiers, they do have some downsides as following: 1). Finding the best model requires testing of various combinations of kernels and model parameters; 2). It can be slow to train, particularly if the input dataset has a large number of features or examples; 3). Their inner workings can be difficult to understand because the underlying models are based on complex mathematical systems and the results are difficult to interpret. The success or failure of machine learning approaches on a given problem may vary strongly with the expertise of the user. Of special concern with supervised applications is that all steps involved in the classifier design (selection of input variables, model training, <em>etc</em>.) should be cross-validated to obtain an unbiased estimate for classifier accuracy. For instance, selecting the features using all available data and subsequently cross-validating the classifier training will produce an optimistically biased error estimate (<a id="xref-ref-70-1" class="xref-bibr" href="#ref-70">70</a>).</p><p id="p-48">The cancer genomic and epigenomic data are exponentially increased as the new generation of sequencing technologies advances. The challenge in analyzing these large complex data motivates us to use artificial intelligent approaches. Developing new kernel functions will aid to discover new targets and new target drugs for various cancers, especially for those deadly and heterogeneous cancers, such as triple-negative breast cancers (TNBCs), soft tissue sarcomas (STS), <em>etc</em>.</p></div><div class="section ack" id="ack-1"><h2 class="">Acknowledgements</h2><p id="p-49">This study has been supported by University of Manitoba Faculty of Science Interdisciplinary/New Directions Research Collaboration Initiation Grant, and partially by the Canadian Breast Cancer Foundation, the Research Institute of Oncology and Hematology Summer student research fund, and CancerCare Manitoba Foundation (CCMF).</p></div><div class="section fn-group" id="fn-group-1"><h2>Footnotes</h2><ul><li class="fn" id="fn-1"><p id="p-50">This article is freely accessible online.</p></li></ul></div><ul class="history-list"><li xmlns:hwp="http://schema.highwire.org/Journal" class="received" hwp:start="2017-09-07"><span class="received-label">Received </span>September 7, 2017.</li><li xmlns:hwp="http://schema.highwire.org/Journal" class="rev-recd" hwp:start="2017-10-03"><span class="rev-recd-label">Revision received </span>October 3, 2017.</li><li xmlns:hwp="http://schema.highwire.org/Journal" class="accepted" hwp:start="2017-10-23"><span class="accepted-label">Accepted </span>October 23, 2017.</li></ul><ul class="copyright-statement"><li class="fn" id="copyright-statement-1">Copyright© 2018, International Institute of Anticancer Research (Dr. George J. Delinasios), All rights reserved</li></ul><div class="license" id="license-1"><p id="p-1"></p></div><div class="section ref-list" id="ref-list-1"><h2 class="">References</h2><ol class="cit-list"><li><a class="rev-xref-ref" href="#xref-ref-1-1" title="View reference 1 in text" id="ref-1">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.1"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Cruz</span> <span class="cit-name-given-names">JA</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wishart</span> <span class="cit-name-given-names">DS</span></span></li></ol><cite>: <span class="cit-article-title">Applications of machine learning in cancer prediction and prognosis</span>. <abbr class="cit-jnl-abbrev">Cancer Inform</abbr> <span class="cit-vol">2</span>: <span class="cit-fpage">59</span>-<span class="cit-lpage">77</span>, <span class="cit-pub-date">2006</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.stitle%253DCancer%2BInform%26rft.aulast%253DCruz%26rft.auinit1%253DJ.%2BA.%26rft.volume%253D2%26rft.spage%253D59%26rft.epage%253D77%26rft.atitle%253DApplications%2Bof%2Bmachine%2Blearning%2Bin%2Bcancer%2Bprediction%2Band%2Bprognosis.%26rft_id%253Dinfo%253Apmid%252F19458758%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=19458758&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-2-1" title="View reference 2 in text" id="ref-2">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.2"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Cicchetti</span> <span class="cit-name-given-names">D</span></span></li></ol><cite>: <span class="cit-article-title">Neural networks and diagnosis in the clinical laboratory: state of the art</span>. <abbr class="cit-jnl-abbrev">Clin Chem</abbr> <span class="cit-vol">38</span>(<span class="cit-issue">1</span>): <span class="cit-fpage">9</span>-<span class="cit-lpage">10</span>, <span class="cit-pub-date">1992</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DClinical%2BChemistry%26rft.stitle%253DClinical%2BChemistry%26rft.aulast%253DCicchetti%26rft.auinit1%253DD.%2BV.%26rft.volume%253D38%26rft.issue%253D1%26rft.spage%253D9%26rft.epage%253D10%26rft.atitle%253DNeural%2Bnetworks%2Band%2Bdiagnosis%2Bin%2Bthe%2Bclinical%2Blaboratory%253A%2Bstate%2Bof%2Bthe%2Bart%26rft_id%253Dinfo%253Apmid%252F1733613%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6MzoiUERGIjtzOjExOiJqb3VybmFsQ29kZSI7czo4OiJjbGluY2hlbSI7czo1OiJyZXNpZCI7czo2OiIzOC8xLzkiO3M6NDoiYXRvbSI7czoxNzoiL2NncC8xNS8xLzQxLmF0b20iO31zOjg6ImZyYWdtZW50IjtzOjA6IiI7fQ==/YTozOntzOjQ6InBhdGgiO3M6MjgzOiIvbG9va3VwL2lqbGluay9ZVG96T250ek9qUTZJbkJoZEdnaU8zTTZNVFE2SWk5c2IyOXJkWEF2YVdwc2FXNXJJanR6T2pVNkluRjFaWEo1SWp0aE9qUTZlM002T0RvaWJHbHVhMVI1Y0dVaU8zTTZNem9pVUVSR0lqdHpPakV4T2lKcWIzVnlibUZzUTI5a1pTSTdjem80T2lKamJHbHVZMmhsYlNJN2N6bzFPaUp5WlhOcFpDSTdjem8yT2lJek9DOHhMemtpTzNNNk5Eb2lZWFJ2YlNJN2N6b3hOem9pTDJObmNDOHhOUzh4THpReExtRjBiMjBpTzMxek9qZzZJbVp5WVdkdFpXNTBJanR6T2pBNklpSTdmUT09IjtzOjU6InF1ZXJ5IjthOjA6e31zOjg6ImZyYWdtZW50IjtzOjA6IiI7fQ==" class="cit-ref-sprinkles cit-ref-sprinkles-ijlink"><span><span class="cit-reflinks-full-text"><span class="free-full-text">FREE </span>Full Text</span></span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-3-1" title="View reference 3 in text" id="ref-3">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.3" data-doi="10.1016/0021-9681(85)90090-6"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Simes</span> <span class="cit-name-given-names">RJ</span></span></li></ol><cite>: <span class="cit-article-title">Treatment selection for cancer patients: application of statistical decision theory to the treatment of advanced ovarian cancer</span>. <abbr class="cit-jnl-abbrev">J Chronic Dis</abbr> <span class="cit-vol">38</span>(<span class="cit-issue">2</span>): <span class="cit-fpage">171</span>-<span class="cit-lpage">186</span>, <span class="cit-pub-date">1985</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DJournal%2Bof%2Bchronic%2Bdiseases%26rft.stitle%253DJ%2BChronic%2BDis%26rft.aulast%253DSimes%26rft.auinit1%253DR.%2BJ.%26rft.volume%253D38%26rft.issue%253D2%26rft.spage%253D171%26rft.epage%253D186%26rft.atitle%253DTreatment%2Bselection%2Bfor%2Bcancer%2Bpatients%253A%2Bapplication%2Bof%2Bstatistical%2Bdecision%2Btheory%2Bto%2Bthe%2Btreatment%2Bof%2Badvanced%2Bovarian%2Bcancer.%26rft_id%253Dinfo%253Adoi%252F10.1016%252F0021-9681%252885%252990090-6%26rft_id%253Dinfo%253Apmid%252F3882734%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1016/0021-9681(85)90090-6&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=3882734&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-4-1" title="View reference 4 in text" id="ref-4">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.4"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Aruna</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Rajagopalan</span> <span class="cit-name-given-names">SP</span></span></li></ol><cite>: <span class="cit-article-title">A novel SVM based CSSFFS feature selection algorithm for detecting breast cancer</span>. <abbr class="cit-jnl-abbrev">Int J Comput Appl</abbr> <span class="cit-vol">31</span>(<span class="cit-issue">8</span>): <span class="cit-fpage">14</span>-<span class="cit-lpage">20</span>, <span class="cit-pub-date">2011</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DInt%2BJ%2BComput%2BAppl%26rft.volume%253D31%26rft.spage%253D14%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-5-1" title="View reference 5 in text" id="ref-5">↵</a><div class="cit ref-cit ref-book" id="cit-15.1.41.5"><div class="cit-metadata"><ol class="duplicate"><li><span class="cit-ed"><span class="cit-name-surname">Schölkopf</span> <span class="cit-name-given-names">B</span></span>, </li><li><span class="cit-ed"><span class="cit-name-surname">Tsuda</span> <span class="cit-name-given-names">K</span></span>, </li><li><span class="cit-ed"><span class="cit-name-surname">Vert</span> <span class="cit-name-given-names">JP</span></span></li></ol><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Noble</span> <span class="cit-name-given-names">W</span></span></li></ol><cite>: <span class="cit-article-title">Support vector machine applications in computational biology</span>. <em>In</em>: <span class="cit-source">Kernel methods in computational biology</span>. <span class="cit-ed"><span class="cit-name-surname">Schölkopf</span> <span class="cit-name-given-names">B</span></span>, <span class="cit-ed"><span class="cit-name-surname">Tsuda</span> <span class="cit-name-given-names">K</span></span>, <span class="cit-ed"><span class="cit-name-surname">Vert</span> <span class="cit-name-given-names">JP</span></span> (eds.). <span class="cit-publ-loc">Cambridge, MA</span>, <span class="cit-publ-name">MIT Press</span>, pp. <span class="cit-fpage">71</span>-<span class="cit-lpage">92</span>, <span class="cit-pub-date">2004</span>. </cite></div><div class="cit-extra"></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-6-1" title="View reference 6 in text" id="ref-6">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.6" data-doi="10.1038/nbt1206-1565"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Noble</span> <span class="cit-name-given-names">WS</span></span></li></ol><cite>: <span class="cit-article-title">What is a support vector machine?</span> <abbr class="cit-jnl-abbrev">Nat biotechnol</abbr> <span class="cit-vol">24</span>(<span class="cit-issue">12</span>): <span class="cit-fpage">1565</span>-<span class="cit-lpage">1557</span>, <span class="cit-pub-date">2006</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DNature%2Bbiotechnology%26rft.stitle%253DNat%2BBiotechnol%26rft.aulast%253DNoble%26rft.auinit1%253DW.%2BS.%26rft.volume%253D24%26rft.issue%253D12%26rft.spage%253D1565%26rft.epage%253D1567%26rft.atitle%253DWhat%2Bis%2Ba%2Bsupport%2Bvector%2Bmachine%253F%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fnbt1206-1565%26rft_id%253Dinfo%253Apmid%252F17160063%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1038/nbt1206-1565&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=17160063&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-7-1" title="View reference 7 in text" id="ref-7">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.7"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Vapnik</span> <span class="cit-name-given-names">V</span></span></li></ol><cite>: <span class="cit-article-title">Pattern recognition using generalized portrait method</span>. <abbr class="cit-jnl-abbrev">Autom Remote Control</abbr> <span class="cit-vol">24</span>: <span class="cit-fpage">774</span>-<span class="cit-lpage">780</span>, <span class="cit-pub-date">1963</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DAutom%2BRemote%2BControl%26rft.volume%253D24%26rft.spage%253D774%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-8-1" title="View reference 8 in text" id="ref-8">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.8"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Aizerman</span> <span class="cit-name-given-names">MA</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Braverman</span> <span class="cit-name-given-names">EM</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Rozoner</span> <span class="cit-name-given-names">LI</span></span></li></ol><cite>: <span class="cit-article-title">Theoretical foundations of the potential function method in pattern recognition learning</span>. <abbr class="cit-jnl-abbrev">Autom Remote Control</abbr> <span class="cit-vol">25</span>: <span class="cit-fpage">821</span>-<span class="cit-lpage">837</span>, <span class="cit-pub-date">1964</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DAutom%2BRemote%2BControl%26rft.volume%253D25%26rft.spage%253D821%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-9-1" title="View reference 9 in text" id="ref-9">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.9" data-doi="10.1126/science.286.5439.531"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Golub</span> <span class="cit-name-given-names">TR</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Slonim</span> <span class="cit-name-given-names">DK</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Tamayo</span> <span class="cit-name-given-names">P</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Huard</span> <span class="cit-name-given-names">C</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Gaasenbeek</span> <span class="cit-name-given-names">M</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Mesirov</span> <span class="cit-name-given-names">JP</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Coller</span> <span class="cit-name-given-names">H</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Loh</span> <span class="cit-name-given-names">ML</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Downing</span> <span class="cit-name-given-names">JR</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Caligiuri</span> <span class="cit-name-given-names">MA</span></span></li></ol><cite>: <span class="cit-article-title">Molecular classification of cancer: class discovery and class prediction by gene expression monitoring</span>. <abbr class="cit-jnl-abbrev">Science</abbr> <span class="cit-vol">286</span>(<span class="cit-issue">5439</span>): <span class="cit-fpage">531</span>-<span class="cit-lpage">537</span>, <span class="cit-pub-date">1999</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DScience%26rft.stitle%253DScience%26rft.aulast%253DGolub%26rft.auinit1%253DT.%2BR.%26rft.volume%253D286%26rft.issue%253D5439%26rft.spage%253D531%26rft.epage%253D537%26rft.atitle%253DMolecular%2BClassification%2Bof%2BCancer%253A%2BClass%2BDiscovery%2Band%2BClass%2BPrediction%2Bby%2BGene%2BExpression%2BMonitoring%26rft_id%253Dinfo%253Adoi%252F10.1126%252Fscience.286.5439.531%26rft_id%253Dinfo%253Apmid%252F10521349%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6Mzoic2NpIjtzOjU6InJlc2lkIjtzOjEyOiIyODYvNTQzOS81MzEiO3M6NDoiYXRvbSI7czoxNzoiL2NncC8xNS8xLzQxLmF0b20iO31zOjg6ImZyYWdtZW50IjtzOjA6IiI7fQ==/YTozOntzOjQ6InBhdGgiO3M6Mjg3OiIvbG9va3VwL2lqbGluay9ZVG96T250ek9qUTZJbkJoZEdnaU8zTTZNVFE2SWk5c2IyOXJkWEF2YVdwc2FXNXJJanR6T2pVNkluRjFaWEo1SWp0aE9qUTZlM002T0RvaWJHbHVhMVI1Y0dVaU8zTTZORG9pUVVKVFZDSTdjem94TVRvaWFtOTFjbTVoYkVOdlpHVWlPM002TXpvaWMyTnBJanR6T2pVNkluSmxjMmxrSWp0ek9qRXlPaUl5T0RZdk5UUXpPUzgxTXpFaU8zTTZORG9pWVhSdmJTSTdjem94TnpvaUwyTm5jQzh4TlM4eEx6UXhMbUYwYjIwaU8zMXpPamc2SW1aeVlXZHRaVzUwSWp0ek9qQTZJaUk3ZlE9PSI7czo1OiJxdWVyeSI7YTowOnt9czo4OiJmcmFnbWVudCI7czowOiIiO30=" class="cit-ref-sprinkles cit-ref-sprinkles-ijlink"><span><span class="cit-reflinks-abstract">Abstract</span><span class="cit-sep cit-reflinks-variant-name-sep">/</span><span class="cit-reflinks-full-text"><span class="free-full-text">FREE </span>Full Text</span></span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-10-1" title="View reference 10 in text" id="ref-10">↵</a><div class="cit ref-cit ref-book" id="cit-15.1.41.10"><div class="cit-metadata"><ol class="duplicate"><li><span class="cit-ed"><span class="cit-name-surname">Leen</span> <span class="cit-name-given-names">T</span></span>, </li><li><span class="cit-ed"><span class="cit-name-surname">Solla</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-ed"><span class="cit-name-surname">Muller</span> <span class="cit-name-given-names">KR</span></span></li></ol><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Vapnik</span> <span class="cit-name-given-names">V</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Mukherjee</span> <span class="cit-name-given-names">S</span></span></li></ol><cite>: <span class="cit-article-title">Support VectorMachine for Multivariate Density Estimation</span>. <em>In</em>: <span class="cit-source">Advances in Neural Information Processing Systems</span>. <span class="cit-ed"><span class="cit-name-surname">Leen</span> <span class="cit-name-given-names">T</span></span>, <span class="cit-ed"><span class="cit-name-surname">Solla</span> <span class="cit-name-given-names">S</span></span>, <span class="cit-ed"><span class="cit-name-surname">Muller</span> <span class="cit-name-given-names">KR</span></span> (eds.). <span class="cit-publ-loc">Cambridge, MA</span>, <span class="cit-publ-name">MIT Press</span>, pp. <span class="cit-fpage">659</span>-<span class="cit-lpage">665</span>, <span class="cit-pub-date">2000</span>. </cite></div><div class="cit-extra"></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-11-1" title="View reference 11 in text" id="ref-11">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.11" data-doi="10.1006/geno.2000.6242"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Moler</span> <span class="cit-name-given-names">E</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Chow</span> <span class="cit-name-given-names">M</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Mian</span> <span class="cit-name-given-names">I</span></span></li></ol><cite>: <span class="cit-article-title">Analysis of molecular profile data using generative and discriminative methods</span>. <abbr class="cit-jnl-abbrev">Physiol Genomics</abbr> <span class="cit-vol">4</span>(<span class="cit-issue">2</span>): <span class="cit-fpage">109</span>-<span class="cit-lpage">126</span>, <span class="cit-pub-date">2000</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DPhysiological%2BGenomics%26rft.stitle%253DPhysiol.%2BGenomics%26rft.aulast%253DMoler%26rft.auinit1%253DE.%2BJ.%26rft.volume%253D4%26rft.issue%253D2%26rft.spage%253D109%26rft.epage%253D126%26rft.atitle%253DAnalysis%2Bof%2Bmolecular%2Bprofile%2Bdata%2Busing%2Bgenerative%2Band%2Bdiscriminative%2Bmethods%26rft_id%253Dinfo%253Adoi%252F10.1006%252Fgeno.2000.6242%26rft_id%253Dinfo%253Apmid%252F11120872%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6MTU6InBoeXNpb2xnZW5vbWljcyI7czo1OiJyZXNpZCI7czo3OiI0LzIvMTA5IjtzOjQ6ImF0b20iO3M6MTc6Ii9jZ3AvMTUvMS80MS5hdG9tIjt9czo4OiJmcmFnbWVudCI7czowOiIiO30=/YTozOntzOjQ6InBhdGgiO3M6Mjk1OiIvbG9va3VwL2lqbGluay9ZVG96T250ek9qUTZJbkJoZEdnaU8zTTZNVFE2SWk5c2IyOXJkWEF2YVdwc2FXNXJJanR6T2pVNkluRjFaWEo1SWp0aE9qUTZlM002T0RvaWJHbHVhMVI1Y0dVaU8zTTZORG9pUVVKVFZDSTdjem94TVRvaWFtOTFjbTVoYkVOdlpHVWlPM002TVRVNkluQm9lWE5wYjJ4blpXNXZiV2xqY3lJN2N6bzFPaUp5WlhOcFpDSTdjem8zT2lJMEx6SXZNVEE1SWp0ek9qUTZJbUYwYjIwaU8zTTZNVGM2SWk5alozQXZNVFV2TVM4ME1TNWhkRzl0SWp0OWN6bzRPaUptY21GbmJXVnVkQ0k3Y3pvd09pSWlPMzA9IjtzOjU6InF1ZXJ5IjthOjA6e31zOjg6ImZyYWdtZW50IjtzOjA6IiI7fQ==" class="cit-ref-sprinkles cit-ref-sprinkles-ijlink"><span><span class="cit-reflinks-abstract">Abstract</span><span class="cit-sep cit-reflinks-variant-name-sep">/</span><span class="cit-reflinks-full-text"><span class="free-full-text">FREE </span>Full Text</span></span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-12-1" title="View reference 12 in text" id="ref-12">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.12" data-doi="10.1093/bioinformatics/16.10.906"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Furey</span> <span class="cit-name-given-names">TS</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Cristianini</span> <span class="cit-name-given-names">N</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Duffy</span> <span class="cit-name-given-names">N</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Bednarski</span> <span class="cit-name-given-names">DW</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Schummer</span> <span class="cit-name-given-names">M</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Haussler</span> <span class="cit-name-given-names">D</span></span></li></ol><cite>: <span class="cit-article-title">Support vector machine classification and validation of cancer tissue samples using microarray expression data</span>. <abbr class="cit-jnl-abbrev">Bioinformatics</abbr> <span class="cit-vol">16</span>(<span class="cit-issue">10</span>): <span class="cit-fpage">906</span>-<span class="cit-lpage">914</span>, <span class="cit-pub-date">2000</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBioinformatics%26rft.stitle%253DBioinformatics%26rft.aulast%253DFurey%26rft.auinit1%253DT.%2BS.%26rft.volume%253D16%26rft.issue%253D10%26rft.spage%253D906%26rft.epage%253D914%26rft.atitle%253DSupport%2Bvector%2Bmachine%2Bclassification%2Band%2Bvalidation%2Bof%2Bcancer%2Btissue%2Bsamples%2Busing%2Bmicroarray%2Bexpression%2Bdata%26rft_id%253Dinfo%253Adoi%252F10.1093%252Fbioinformatics%252F16.10.906%26rft_id%253Dinfo%253Apmid%252F11120680%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1093/bioinformatics/16.10.906&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=11120680&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-13-1" title="View reference 13 in text" id="ref-13">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.13" data-doi="10.1200/JCO.2003.10.108"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Segal</span> <span class="cit-name-given-names">NH</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Pavlidis</span> <span class="cit-name-given-names">P</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Noble</span> <span class="cit-name-given-names">WS</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Antonescu</span> <span class="cit-name-given-names">CR</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Viale</span> <span class="cit-name-given-names">A</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wesley</span> <span class="cit-name-given-names">UV</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Busam</span> <span class="cit-name-given-names">K</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Gallardo</span> <span class="cit-name-given-names">H</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">DeSantis</span> <span class="cit-name-given-names">D</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Brennan</span> <span class="cit-name-given-names">MF</span></span></li></ol><cite>: <span class="cit-article-title">Classification of clear cell sarcoma as melanoma of soft parts by genomic profiling</span>. <abbr class="cit-jnl-abbrev">J Clin Oncol</abbr> <span class="cit-vol">21</span>: <span class="cit-fpage">1775</span>-<span class="cit-lpage">1781</span>, <span class="cit-pub-date">2003</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DJ%2BClin%2BOncol%26rft_id%253Dinfo%253Adoi%252F10.1200%252FJCO.2003.10.108%26rft_id%253Dinfo%253Apmid%252F12721254%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="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" class="cit-ref-sprinkles cit-ref-sprinkles-ijlink"><span><span class="cit-reflinks-abstract">Abstract</span><span class="cit-sep cit-reflinks-variant-name-sep">/</span><span class="cit-reflinks-full-text"><span class="free-full-text">FREE </span>Full Text</span></span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-14-1" title="View reference 14 in text" id="ref-14">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.14"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Segal</span> <span class="cit-name-given-names">NH</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Pavlidis</span> <span class="cit-name-given-names">P</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Antonescu</span> <span class="cit-name-given-names">CR</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Maki</span> <span class="cit-name-given-names">RG</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Noble</span> <span class="cit-name-given-names">WS</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">DeSantis</span> <span class="cit-name-given-names">D</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Woodruff</span> <span class="cit-name-given-names">JM</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Lewis</span> <span class="cit-name-given-names">JJ</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Brennan</span> <span class="cit-name-given-names">MF</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Houghton</span> <span class="cit-name-given-names">AN</span></span></li></ol><cite>: <span class="cit-article-title">Classification and subtype prediction of adult soft tissue sarcoma by functional genomics</span>. <abbr class="cit-jnl-abbrev">Am J Pathol</abbr> <span class="cit-vol">163</span>(<span class="cit-issue">2</span>): <span class="cit-fpage">691</span>-<span class="cit-lpage">700</span>, <span class="cit-pub-date">2003</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DAmerican%2BJournal%2BOf%2BPathology%26rft.stitle%253DAm.%2BJ.%2BPathol.%26rft.aulast%253DSegal%26rft.auinit1%253DN.%2BH.%26rft.volume%253D163%26rft.issue%253D2%26rft.spage%253D691%26rft.epage%253D700%26rft.atitle%253DClassification%2Band%2BSubtype%2BPrediction%2Bof%2BAdult%2BSoft%2BTissue%2BSarcoma%2Bby%2BFunctional%2BGenomics%26rft_id%253Dinfo%253Apmid%252F12875988%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=12875988&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-15-1" title="View reference 15 in text" id="ref-15">↵</a><div class="cit ref-cit ref-other" id="cit-15.1.41.15"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Tang</span> <span class="cit-name-given-names">Y</span></span></li></ol><cite>: <span class="cit-article-title">Deep learning using linear support vector machines</span>. <span class="cit-source">arXiv preprint 1306.0239</span>, <span class="cit-pub-date">2013</span>. </cite></div><div class="cit-extra"></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-16-1" title="View reference 16 in text" id="ref-16">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.16" data-doi="10.1093/bioinformatics/bth267"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Li</span> <span class="cit-name-given-names">T</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zhang</span> <span class="cit-name-given-names">C</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Ogihara</span> <span class="cit-name-given-names">M</span></span></li></ol><cite>: <span class="cit-article-title">A comparative study of feature selection and multiclass classification methods for tissue classification based on gene expression</span>. <abbr class="cit-jnl-abbrev">Bioinformatics</abbr> <span class="cit-vol">20</span>(<span class="cit-issue">15</span>): <span class="cit-fpage">2429</span>-<span class="cit-lpage">2437</span>, <span class="cit-pub-date">2004</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBioinformatics%26rft_id%253Dinfo%253Adoi%252F10.1093%252Fbioinformatics%252Fbth267%26rft_id%253Dinfo%253Apmid%252F15087314%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1093/bioinformatics/bth267&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=15087314&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-17-1" title="View reference 17 in text" id="ref-17">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.17" data-doi="10.1093/bioinformatics/17.suppl_1.S157"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Model</span> <span class="cit-name-given-names">F</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Adorjan</span> <span class="cit-name-given-names">P</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Olek</span> <span class="cit-name-given-names">A</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Piepenbrock</span> <span class="cit-name-given-names">C</span></span></li></ol><cite>: <span class="cit-article-title">Feature selection for DNA methylation based cancer classification</span>. <abbr class="cit-jnl-abbrev">Bioinformatics</abbr> <span class="cit-vol">17</span>(<span class="cit-issue">suppl 1</span>): <span class="cit-fpage">S157</span>-<span class="cit-lpage">164</span>, <span class="cit-pub-date">2001</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBioinformatics%26rft.stitle%253DBioinformatics%26rft.aulast%253DModel%26rft.auinit1%253DF.%26rft.volume%253D17%26rft.issue%253D90001%26rft.spage%253DS157%26rft.epage%253D164%26rft.atitle%253DFeature%2Bselection%2Bfor%2BDNA%2Bmethylation%2Bbased%2Bcancer%2Bclassification%26rft_id%253Dinfo%253Adoi%252F10.1093%252Fbioinformatics%252F17.suppl_1.S157%26rft_id%253Dinfo%253Apmid%252F11473005%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1093/bioinformatics/17.suppl_1.S157&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=11473005&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-18-1" title="View reference 18 in text" id="ref-18">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.18"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Kim</span> <span class="cit-name-given-names">S</span></span></li></ol><cite>: <span class="cit-article-title">Weighted K-means support vector machine for cancer prediction</span>. <abbr class="cit-jnl-abbrev">Springerplus</abbr> <span class="cit-vol">5</span>(<span class="cit-issue">1</span>): <span class="cit-fpage">1162</span>, <span class="cit-pub-date">2016</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DSpringerplus%26rft.volume%253D5%26rft.spage%253D1162%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-19-1" title="View reference 19 in text" id="ref-19">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.19"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Yang</span> <span class="cit-name-given-names">Z</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Jin</span> <span class="cit-name-given-names">M</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zhang</span> <span class="cit-name-given-names">Z</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Lu</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Hao</span> <span class="cit-name-given-names">K</span></span></li></ol><cite>: <span class="cit-article-title">Classification based on feature extraction for hepatocellular carcinoma diagnosis using high-throughput dna methylation sequencing data</span>. <abbr class="cit-jnl-abbrev">Procedia Comput Sci</abbr> <span class="cit-vol">107</span>: <span class="cit-fpage">412</span>-<span class="cit-lpage">417</span>, <span class="cit-pub-date">2017</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DProcedia%2BComput%2BSci%26rft.volume%253D107%26rft.spage%253D412%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-20-1" title="View reference 20 in text" id="ref-20">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.20"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Alkuhlani</span> <span class="cit-name-given-names">A</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Nassef</span> <span class="cit-name-given-names">M</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Farag</span> <span class="cit-name-given-names">I</span></span></li></ol><cite>: <span class="cit-article-title">Multistage feature selection approach for high-dimensional cancer data</span>. <abbr class="cit-jnl-abbrev">Soft Comput</abbr> <span class="cit-vol">21</span>: <span class="cit-fpage">6895</span>-<span class="cit-lpage">6906</span>, <span class="cit-pub-date">2017</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DSoft%2BComput%26rft.volume%253D21%26rft.spage%253D6895%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-21-1" title="View reference 21 in text" id="ref-21">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.21"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Guo</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Yan</span> <span class="cit-name-given-names">F</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Xu</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Bao</span> <span class="cit-name-given-names">Y</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zhu</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wang</span> <span class="cit-name-given-names">X</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wu</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Li</span> <span class="cit-name-given-names">Y</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Pu</span> <span class="cit-name-given-names">W</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Liu</span> <span class="cit-name-given-names">Y</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Jiang</span> <span class="cit-name-given-names">Z</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Ma</span> <span class="cit-name-given-names">Y</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Chen</span> <span class="cit-name-given-names">X</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Xiong</span> <span class="cit-name-given-names">M</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Jin</span> <span class="cit-name-given-names">L</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wang</span> <span class="cit-name-given-names">J</span></span></li></ol><cite>: <span class="cit-article-title">Identification and validation of the methylation biomarkers of non-small cell lung cancer (NSCLC)</span>. <abbr class="cit-jnl-abbrev">Clin Epigenetics</abbr> <span class="cit-vol">7</span>: <span class="cit-fpage">3</span>, <span class="cit-pub-date">2015</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DClin%2BEpigenetics%26rft.volume%253D7%26rft.spage%253D3%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-22-1" title="View reference 22 in text" id="ref-22">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.22"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Sun</span> <span class="cit-name-given-names">Z</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Fu</span> <span class="cit-name-given-names">X</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zhang</span> <span class="cit-name-given-names">L</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Yang</span> <span class="cit-name-given-names">X</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Liu</span> <span class="cit-name-given-names">F</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Hu</span> <span class="cit-name-given-names">G</span></span></li></ol><cite>: <span class="cit-article-title">A protein chip system for parallel analysis of multi-tumor markers and its application in cancer detection</span>. <abbr class="cit-jnl-abbrev">Anticancer Res</abbr> <span class="cit-vol">24</span>: <span class="cit-fpage">1159</span>-<span class="cit-lpage">1165</span>, <span class="cit-pub-date">2004</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DAnticancer%2BResearch%26rft.stitle%253DAnticancer%2BRes%26rft.aulast%253DSUN%26rft.auinit1%253DZ.%26rft.volume%253D24%26rft.issue%253D2C%26rft.spage%253D1159%26rft.epage%253D1166%26rft.atitle%253DA%2BProtein%2BChip%2BSystem%2Bfor%2BParallel%2BAnalysis%2Bof%2BMulti-tumor%2BMarkers%2Band%2Bits%2BApplication%2Bin%2BCancer%2BDetection%26rft_id%253Dinfo%253Apmid%252F15154641%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6MTA6ImFudGljYW5yZXMiO3M6NToicmVzaWQiO3M6MTA6IjI0LzJDLzExNTkiO3M6NDoiYXRvbSI7czoxNzoiL2NncC8xNS8xLzQxLmF0b20iO31zOjg6ImZyYWdtZW50IjtzOjA6IiI7fQ==/YTozOntzOjQ6InBhdGgiO3M6Mjk1OiIvbG9va3VwL2lqbGluay9ZVG96T250ek9qUTZJbkJoZEdnaU8zTTZNVFE2SWk5c2IyOXJkWEF2YVdwc2FXNXJJanR6T2pVNkluRjFaWEo1SWp0aE9qUTZlM002T0RvaWJHbHVhMVI1Y0dVaU8zTTZORG9pUVVKVFZDSTdjem94TVRvaWFtOTFjbTVoYkVOdlpHVWlPM002TVRBNkltRnVkR2xqWVc1eVpYTWlPM002TlRvaWNtVnphV1FpTzNNNk1UQTZJakkwTHpKREx6RXhOVGtpTzNNNk5Eb2lZWFJ2YlNJN2N6b3hOem9pTDJObmNDOHhOUzh4THpReExtRjBiMjBpTzMxek9qZzZJbVp5WVdkdFpXNTBJanR6T2pBNklpSTdmUT09IjtzOjU6InF1ZXJ5IjthOjA6e31zOjg6ImZyYWdtZW50IjtzOjA6IiI7fQ==" class="cit-ref-sprinkles cit-ref-sprinkles-ijlink"><span><span class="cit-reflinks-abstract">Abstract</span><span class="cit-sep cit-reflinks-variant-name-sep">/</span><span class="cit-reflinks-full-text"><span class="free-full-text">FREE </span>Full Text</span></span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-23-1" title="View reference 23 in text" id="ref-23">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.23" data-doi="10.1038/ncomms10259"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Tyanova</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Albrechtsen</span> <span class="cit-name-given-names">R</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Kronqvist</span> <span class="cit-name-given-names">P</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Cox</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Mann</span> <span class="cit-name-given-names">M</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Geiger</span> <span class="cit-name-given-names">T</span></span></li></ol><cite>: <span class="cit-article-title">Proteomic maps of breast cancer subtypes</span>. <abbr class="cit-jnl-abbrev">Nat Commun</abbr> <span class="cit-vol">7</span>: <span class="cit-fpage">10259</span>, <span class="cit-pub-date">2016</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DNat%2BCommun%26rft.volume%253D7%26rft.spage%253D10259%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fncomms10259%26rft_id%253Dinfo%253Apmid%252F26725330%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1038/ncomms10259&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=26725330&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-24-1" title="View reference 24 in text" id="ref-24">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.24" data-doi="10.1093/bioinformatics/btn188"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Rapaport</span> <span class="cit-name-given-names">F</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Barillot</span> <span class="cit-name-given-names">E</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Vert</span> <span class="cit-name-given-names">JP</span></span></li></ol><cite>: <span class="cit-article-title">Classification of arrayCGH data using fused SVM</span>. <abbr class="cit-jnl-abbrev">Bioinformatics</abbr> <span class="cit-vol">24</span>(<span class="cit-issue">13</span>): <span class="cit-fpage">i375</span>-<span class="cit-lpage">i382</span>, <span class="cit-pub-date">2008</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBioinformatics%26rft_id%253Dinfo%253Adoi%252F10.1093%252Fbioinformatics%252Fbtn188%26rft_id%253Dinfo%253Apmid%252F18586737%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1093/bioinformatics/btn188&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=18586737&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-25-1" title="View reference 25 in text" id="ref-25">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.25"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Vura</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wang</span> <span class="cit-name-given-names">X</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Guda</span> <span class="cit-name-given-names">C</span></span></li></ol><cite>: <span class="cit-article-title">Classification of breast cancer patients using somatic mutation profiles and machine learning approaches</span>. <abbr class="cit-jnl-abbrev">BMC Syst Biol</abbr> <span class="cit-vol">10</span>(<span class="cit-issue">suppl 3</span>): <span class="cit-fpage">62</span>, <span class="cit-pub-date">2016</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBMC%2BSyst%2BBiol%26rft.volume%253D10%26rft.spage%253D62%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-26-1" title="View reference 26 in text" id="ref-26">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.26"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Wu</span> <span class="cit-name-given-names">T</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wang</span> <span class="cit-name-given-names">Y</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Jiang</span> <span class="cit-name-given-names">R</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Lu</span> <span class="cit-name-given-names">X</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Tian</span> <span class="cit-name-given-names">J</span></span></li></ol><cite>: a<span class="cit-article-title">A pathways-based prediction model for classifying breast cancer subtypes</span>. <abbr class="cit-jnl-abbrev">Oncotarget</abbr> <span class="cit-vol">8</span>(<span class="cit-issue">35</span>): <span class="cit-fpage">58809</span>-<span class="cit-lpage">58822</span>, <span class="cit-pub-date">2017</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DOncotarget%26rft.volume%253D8%26rft.spage%253D58809%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-27-1" title="View reference 27 in text" id="ref-27">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.27"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Lin</span> <span class="cit-name-given-names">E</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Lane</span> <span class="cit-name-given-names">HY</span></span></li></ol><cite>: <span class="cit-article-title">Machine learning and systems genomics approaches for multi-omics data</span>. <abbr class="cit-jnl-abbrev">Biomark Res</abbr> <span class="cit-vol">5</span>(<span class="cit-issue">1</span>): <span class="cit-fpage">2</span>, <span class="cit-pub-date">2017</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBiomark%2BRes%26rft.volume%253D5%26rft.spage%253D2%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-28-1" title="View reference 28 in text" id="ref-28">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.28"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Kim</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Jhong</span> <span class="cit-name-given-names">JH</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Lee</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Koo</span> <span class="cit-name-given-names">JY</span></span></li></ol><cite>: <span class="cit-article-title">Meta-analytic support vector machine for integrating multiple omics data</span>. <abbr class="cit-jnl-abbrev">BioData Min</abbr> <span class="cit-vol">10</span>(<span class="cit-issue">1</span>): <span class="cit-fpage">2</span>, <span class="cit-pub-date">2017</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBioData%2BMin%26rft.volume%253D10%26rft.spage%253D2%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-29-1" title="View reference 29 in text" id="ref-29">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.29"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Yiu</span> <span class="cit-name-given-names">AJ</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Yiu</span> <span class="cit-name-given-names">CY</span></span></li></ol><cite>: <span class="cit-article-title">Biomarkers in colorectal cancer</span>. <abbr class="cit-jnl-abbrev">Anticancer Res</abbr> <span class="cit-vol">36</span>(<span class="cit-issue">3</span>): <span class="cit-fpage">1093</span>-<span class="cit-lpage">1102</span>, <span class="cit-pub-date">2016</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DAnticancer%2BResearch%26rft.stitle%253DAnticancer%2BRes%26rft.aulast%253DYIU%26rft.auinit1%253DA.%2BJ.%26rft.volume%253D36%26rft.issue%253D3%26rft.spage%253D1093%26rft.epage%253D1102%26rft.atitle%253DBiomarkers%2Bin%2BColorectal%2BCancer%26rft_id%253Dinfo%253Apmid%252F26977004%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6MTA6ImFudGljYW5yZXMiO3M6NToicmVzaWQiO3M6OToiMzYvMy8xMDkzIjtzOjQ6ImF0b20iO3M6MTc6Ii9jZ3AvMTUvMS80MS5hdG9tIjt9czo4OiJmcmFnbWVudCI7czowOiIiO30=/YTozOntzOjQ6InBhdGgiO3M6MjkxOiIvbG9va3VwL2lqbGluay9ZVG96T250ek9qUTZJbkJoZEdnaU8zTTZNVFE2SWk5c2IyOXJkWEF2YVdwc2FXNXJJanR6T2pVNkluRjFaWEo1SWp0aE9qUTZlM002T0RvaWJHbHVhMVI1Y0dVaU8zTTZORG9pUVVKVFZDSTdjem94TVRvaWFtOTFjbTVoYkVOdlpHVWlPM002TVRBNkltRnVkR2xqWVc1eVpYTWlPM002TlRvaWNtVnphV1FpTzNNNk9Ub2lNell2TXk4eE1Ea3pJanR6T2pRNkltRjBiMjBpTzNNNk1UYzZJaTlqWjNBdk1UVXZNUzgwTVM1aGRHOXRJanQ5Y3pvNE9pSm1jbUZuYldWdWRDSTdjem93T2lJaU8zMD0iO3M6NToicXVlcnkiO2E6MDp7fXM6ODoiZnJhZ21lbnQiO3M6MDoiIjt9" class="cit-ref-sprinkles cit-ref-sprinkles-ijlink"><span><span class="cit-reflinks-abstract">Abstract</span><span class="cit-sep cit-reflinks-variant-name-sep">/</span><span class="cit-reflinks-full-text"><span class="free-full-text">FREE </span>Full Text</span></span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-30-1" title="View reference 30 in text" id="ref-30">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.30" data-doi="10.1093/bioinformatics/bth339"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">He</span> <span class="cit-name-given-names">W</span></span></li></ol><cite>: <span class="cit-article-title">A spline function approach for detecting differentially expressed genes in microarray data analysis</span>. <abbr class="cit-jnl-abbrev">Bioinformatics</abbr> <span class="cit-vol">20</span>(<span class="cit-issue">17</span>): <span class="cit-fpage">2954</span>-<span class="cit-lpage">2963</span>, <span class="cit-pub-date">2004</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBioinformatics%26rft_id%253Dinfo%253Adoi%252F10.1093%252Fbioinformatics%252Fbth339%26rft_id%253Dinfo%253Apmid%252F15180936%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1093/bioinformatics/bth339&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=15180936&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><div class="cit ref-cit ref-journal no-rev-xref" id="cit-15.1.41.31" data-doi="10.1101/gr.165101"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Thomas</span> <span class="cit-name-given-names">JG</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Olson</span> <span class="cit-name-given-names">JM</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Tapscott</span> <span class="cit-name-given-names">SJ</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zhao</span> <span class="cit-name-given-names">LP</span></span></li></ol><cite>: <span class="cit-article-title">An efficient and robust statistical modeling approach to discover differentially expressed genes using genomic expression profiles</span>. <abbr class="cit-jnl-abbrev">Genome Res</abbr> <span class="cit-vol">11</span>(<span class="cit-issue">7</span>): <span class="cit-fpage">1227</span>-<span class="cit-lpage">1236</span>, <span class="cit-pub-date">2001</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DGenome%2BResearch%26rft.stitle%253DGenome%2BRes%26rft.aulast%253DThomas%26rft.auinit1%253DJ.%2BG.%26rft.volume%253D11%26rft.issue%253D7%26rft.spage%253D1227%26rft.epage%253D1236%26rft.atitle%253DAn%2BEfficient%2Band%2BRobust%2BStatistical%2BModeling%2BApproach%2Bto%2BDiscover%2BDifferentially%2BExpressed%2BGenes%2BUsing%2BGenomic%2BExpression%2BProfiles%26rft_id%253Dinfo%253Adoi%252F10.1101%252Fgr.165101%26rft_id%253Dinfo%253Apmid%252F11435405%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="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" class="cit-ref-sprinkles cit-ref-sprinkles-ijlink"><span><span class="cit-reflinks-abstract">Abstract</span><span class="cit-sep cit-reflinks-variant-name-sep">/</span><span class="cit-reflinks-full-text"><span class="free-full-text">FREE </span>Full Text</span></span></a></div></div></li><li><div class="cit ref-cit ref-journal no-rev-xref" id="cit-15.1.41.32" data-doi="10.1093/bioinformatics/18.4.546"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Pan</span> <span class="cit-name-given-names">W</span></span></li></ol><cite>: <span class="cit-article-title">A comparative review of statistical methods for discovering differentially expressed genes in replicated microarray experiments</span>. <abbr class="cit-jnl-abbrev">Bioinformatics</abbr> <span class="cit-vol">18</span>(<span class="cit-issue">4</span>): <span class="cit-fpage">546</span>-<span class="cit-lpage">554</span>, <span class="cit-pub-date">2002</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBioinformatics%26rft.stitle%253DBioinformatics%26rft.aulast%253DPan%26rft.auinit1%253DW.%26rft.volume%253D18%26rft.issue%253D4%26rft.spage%253D546%26rft.epage%253D554%26rft.atitle%253DA%2Bcomparative%2Breview%2Bof%2Bstatistical%2Bmethods%2Bfor%2Bdiscovering%2B%2Bdifferentially%2Bexpressed%2Bgenes%2Bin%2Breplicated%2Bmicroarray%2Bexperiments%26rft_id%253Dinfo%253Adoi%252F10.1093%252Fbioinformatics%252F18.4.546%26rft_id%253Dinfo%253Apmid%252F12016052%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1093/bioinformatics/18.4.546&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=12016052&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-33-1" title="View reference 33 in text" id="ref-33">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.33" data-doi="10.1093/bioinformatics/18.11.1454"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Troyanskaya</span> <span class="cit-name-given-names">OG</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Garber</span> <span class="cit-name-given-names">ME</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Brown</span> <span class="cit-name-given-names">PO</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Botstein</span> <span class="cit-name-given-names">D</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Altman</span> <span class="cit-name-given-names">RB</span></span></li></ol><cite>: <span class="cit-article-title">Nonparametric methods for identifying differentially expressed genes in microarray data</span>. <abbr class="cit-jnl-abbrev">Bioinformatics</abbr> <span class="cit-vol">18</span>(<span class="cit-issue">11</span>): <span class="cit-fpage">1454</span>-<span class="cit-lpage">1461</span>, <span class="cit-pub-date">2002</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBioinformatics%26rft.stitle%253DBioinformatics%26rft.aulast%253DTroyanskaya%26rft.auinit1%253DO.%2BG.%26rft.volume%253D18%26rft.issue%253D11%26rft.spage%253D1454%26rft.epage%253D1461%26rft.atitle%253DNonparametric%2Bmethods%2Bfor%2Bidentifying%2Bdifferentially%2Bexpressed%2Bgenes%2Bin%2Bmicroarray%2Bdata%26rft_id%253Dinfo%253Adoi%252F10.1093%252Fbioinformatics%252F18.11.1454%26rft_id%253Dinfo%253Apmid%252F12424116%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1093/bioinformatics/18.11.1454&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=12424116&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-34-1" title="View reference 34 in text" id="ref-34">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.34"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Xu</span> <span class="cit-name-given-names">G</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zhang</span> <span class="cit-name-given-names">M</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zhu</span> <span class="cit-name-given-names">H</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Xu</span> <span class="cit-name-given-names">J</span></span></li></ol><cite>: <span class="cit-article-title">A 15-gene signature for prediction of colon cancer recurrence and prognosis based on SVM</span>. <abbr class="cit-jnl-abbrev">Gene</abbr> <span class="cit-vol">604</span>: <span class="cit-fpage">33</span>-<span class="cit-lpage">40</span>, <span class="cit-pub-date">2017</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DGene%26rft.volume%253D604%26rft.spage%253D33%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-35-1" title="View reference 35 in text" id="ref-35">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.35"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Hu</span> <span class="cit-name-given-names">Y</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Hase</span> <span class="cit-name-given-names">T</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Li</span> <span class="cit-name-given-names">HP</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Prabhakar</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Kitano</span> <span class="cit-name-given-names">H</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Ng</span> <span class="cit-name-given-names">SK</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Ghosh</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wee</span> <span class="cit-name-given-names">LJ</span></span></li></ol><cite>: <span class="cit-article-title">A machine learning approach for the identification of key markers involved in brain development from single-cell transcriptomic data</span>. <abbr class="cit-jnl-abbrev">BMC Genomics</abbr> <span class="cit-vol">17</span>(<span class="cit-issue">suppl 13</span>): <span class="cit-fpage">1025</span>, <span class="cit-pub-date">2016</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBMC%2BGenomics%26rft.volume%253D17%26rft.spage%253D1025%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-36-1" title="View reference 36 in text" id="ref-36">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.36" data-doi="10.1186/1471-2407-9-104"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Henneges</span> <span class="cit-name-given-names">C</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Bullinger</span> <span class="cit-name-given-names">D</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Fux</span> <span class="cit-name-given-names">R</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Friese</span> <span class="cit-name-given-names">N</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Seeger</span> <span class="cit-name-given-names">H</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Neubauer</span> <span class="cit-name-given-names">H</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Laufer</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Gleiter</span> <span class="cit-name-given-names">CH</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Schwab</span> <span class="cit-name-given-names">M</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zell</span> <span class="cit-name-given-names">A</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Kammerer</span> <span class="cit-name-given-names">B</span></span></li></ol><cite>: <span class="cit-article-title">Prediction of breast cancer by profiling of urinary RNA metabolites using Support Vector Machine-based feature selection</span>. <abbr class="cit-jnl-abbrev">BMC Cancer</abbr> <span class="cit-vol">9</span>: <span class="cit-fpage">104</span>, <span class="cit-pub-date">2009</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBMC%2Bcancer%2B%255Belectronic%2Bresource%255D%26rft.stitle%253DBMC%2BCancer%26rft.aulast%253DHenneges%26rft.auinit1%253DC.%26rft.volume%253D9%26rft.spage%253D104%26rft.epage%253D104%26rft.atitle%253DPrediction%2Bof%2Bbreast%2Bcancer%2Bby%2Bprofiling%2Bof%2Burinary%2BRNA%2Bmetabolites%2Busing%2BSupport%2BVector%2BMachine-based%2Bfeature%2Bselection.%26rft_id%253Dinfo%253Adoi%252F10.1186%252F1471-2407-9-104%26rft_id%253Dinfo%253Apmid%252F19344524%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1186/1471-2407-9-104&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=19344524&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-37-1" title="View reference 37 in text" id="ref-37">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.37"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Han</span> <span class="cit-name-given-names">M</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Dai</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zhang</span> <span class="cit-name-given-names">Y</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Lin</span> <span class="cit-name-given-names">Q</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Jiang</span> <span class="cit-name-given-names">M</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Xu</span> <span class="cit-name-given-names">X</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Liu</span> <span class="cit-name-given-names">Q</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Jia</span> <span class="cit-name-given-names">J</span></span></li></ol><cite>: <span class="cit-article-title">Support vector machines coupled with proteomics approaches for detecting biomarkers predicting chemotherapy resistance in small cell lung cancer</span>. <abbr class="cit-jnl-abbrev">Oncol Rep</abbr> <span class="cit-vol">28</span>(<span class="cit-issue">6</span>): <span class="cit-fpage">2233</span>-<span class="cit-lpage">2238</span>, <span class="cit-pub-date">2012</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DOncology%2Breports%26rft.stitle%253DOncol%2BRep%26rft.aulast%253DHan%26rft.auinit1%253DM.%26rft.volume%253D28%26rft.issue%253D6%26rft.spage%253D2233%26rft.epage%253D2238%26rft.atitle%253DSupport%2Bvector%2Bmachines%2Bcoupled%2Bwith%2Bproteomics%2Bapproaches%2Bfor%2Bdetecting%2B%2B%2B%2B%2B%2B%2B%2B%2B%2B%2B%2B%2Bbiomarkers%2Bpredicting%2Bchemotherapy%2Bresistance%2Bin%2Bsmall%2Bcell%2Blung%2Bcancer.%26rft_id%253Dinfo%253Apmid%252F22992788%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=22992788&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-38-1" title="View reference 38 in text" id="ref-38">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.38"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Abeel</span> <span class="cit-name-given-names">T</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Helleputte</span> <span class="cit-name-given-names">T</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Van de Peer</span> <span class="cit-name-given-names">Y</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Dupont</span> <span class="cit-name-given-names">P</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Saeys</span> <span class="cit-name-given-names">Y</span></span></li></ol><cite>: <span class="cit-article-title">Robust biomarker identification for cancer diagnosis with ensemble feature selection methods</span>. <abbr class="cit-jnl-abbrev">Bioinformatics</abbr> <span class="cit-vol">26</span>(<span class="cit-issue">3</span>): <span class="cit-fpage">392</span>-<span class="cit-lpage">398</span>, <span class="cit-pub-date">2009</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBioinformatics%26rft.volume%253D26%26rft.spage%253D392%26rft_id%253Dinfo%253Apmid%252F19942583%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=19942583&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-39-1" title="View reference 39 in text" id="ref-39">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.39" data-doi="10.1162/153244303322753616"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Guyon</span> <span class="cit-name-given-names">I</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Elisseeff</span> <span class="cit-name-given-names">A</span></span></li></ol><cite>: <span class="cit-article-title">An introduction to variable and feature selection</span>. <abbr class="cit-jnl-abbrev">J Mach Learn Res</abbr> <span class="cit-vol">3</span>: <span class="cit-fpage">1157</span>-<span class="cit-lpage">1182</span>, <span class="cit-pub-date">2003</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DJ%2BMach%2BLearn%2BRes%26rft.volume%253D3%26rft.spage%253D1157%26rft_id%253Dinfo%253Adoi%252F10.1162%252F153244303322753616%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1162/153244303322753616&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-40-1" title="View reference 40 in text" id="ref-40">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.40" data-doi="10.1023/A:1012487302797"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Guyon</span> <span class="cit-name-given-names">I</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Weston</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Barnhill</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Vapnik</span> <span class="cit-name-given-names">V</span></span></li></ol><cite>: <span class="cit-article-title">Gene selection for cancer classification using support vector machines</span>. <abbr class="cit-jnl-abbrev">Mach Learn</abbr> <span class="cit-vol">46</span>(<span class="cit-issue">1</span>): <span class="cit-fpage">389</span>-<span class="cit-lpage">422</span>, <span class="cit-pub-date">2002</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DMach%2BLearn%26rft.volume%253D46%26rft.spage%253D389%26rft_id%253Dinfo%253Adoi%252F10.1023%252FA%253A1012487302797%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1023/A:1012487302797&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-41-1" title="View reference 41 in text" id="ref-41">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.41" data-doi="10.1186/1752-0509-5-161"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Chen</span> <span class="cit-name-given-names">L</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Xuan</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Riggins</span> <span class="cit-name-given-names">RB</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Clarke</span> <span class="cit-name-given-names">R</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wang</span> <span class="cit-name-given-names">Y</span></span></li></ol><cite>: <span class="cit-article-title">Identifying cancer biomarkers by network-constrained support vector machines</span>. <abbr class="cit-jnl-abbrev">BMC Syst Biol</abbr> <span class="cit-vol">5</span>(<span class="cit-issue">1</span>): <span class="cit-fpage">161</span>, <span class="cit-pub-date">2011</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.stitle%253DBMC%2BSyst%2BBiol%26rft.aulast%253DChen%26rft.auinit1%253DL.%26rft.volume%253D5%26rft.spage%253D161%26rft.epage%253D161%26rft.atitle%253DIdentifying%2Bcancer%2Bbiomarkers%2Bby%2Bnetwork-constrained%2Bsupport%2Bvector%2Bmachines.%26rft_id%253Dinfo%253Adoi%252F10.1186%252F1752-0509-5-161%26rft_id%253Dinfo%253Apmid%252F21992556%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1186/1752-0509-5-161&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=21992556&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-42-1" title="View reference 42 in text" id="ref-42">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.42"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Stagos</span> <span class="cit-name-given-names">D</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Karaberis</span> <span class="cit-name-given-names">E</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Kouretas</span> <span class="cit-name-given-names">D</span></span></li></ol><cite>: <span class="cit-article-title">Assessment of antioxidant/anticarcinogenic activity of plant extracts by a combination of molecular methods</span>. <abbr class="cit-jnl-abbrev">In Vivo</abbr> <span class="cit-vol">19</span>(<span class="cit-issue">4</span>): <span class="cit-fpage">741</span>-<span class="cit-lpage">747</span>, <span class="cit-pub-date">2005</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DIn%2BVivo%26rft.stitle%253DIn%2BVivo%26rft.aulast%253DSTAGOS%26rft.auinit1%253DD.%26rft.volume%253D19%26rft.issue%253D4%26rft.spage%253D741%26rft.epage%253D747%26rft.atitle%253DAssessment%2Bof%2BAntioxidant%2B%252F%2BAnticarcinogenic%2BActivity%2Bof%2BPlant%2BExtracts%2Bby%2Ba%2BCombination%2Bof%2BMolecular%2BMethods%26rft_id%253Dinfo%253Apmid%252F15999544%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6NjoiaW52aXZvIjtzOjU6InJlc2lkIjtzOjg6IjE5LzQvNzQxIjtzOjQ6ImF0b20iO3M6MTc6Ii9jZ3AvMTUvMS80MS5hdG9tIjt9czo4OiJmcmFnbWVudCI7czowOiIiO30=/YTozOntzOjQ6InBhdGgiO3M6MjgzOiIvbG9va3VwL2lqbGluay9ZVG96T250ek9qUTZJbkJoZEdnaU8zTTZNVFE2SWk5c2IyOXJkWEF2YVdwc2FXNXJJanR6T2pVNkluRjFaWEo1SWp0aE9qUTZlM002T0RvaWJHbHVhMVI1Y0dVaU8zTTZORG9pUVVKVFZDSTdjem94TVRvaWFtOTFjbTVoYkVOdlpHVWlPM002TmpvaWFXNTJhWFp2SWp0ek9qVTZJbkpsYzJsa0lqdHpPamc2SWpFNUx6UXZOelF4SWp0ek9qUTZJbUYwYjIwaU8zTTZNVGM2SWk5alozQXZNVFV2TVM4ME1TNWhkRzl0SWp0OWN6bzRPaUptY21GbmJXVnVkQ0k3Y3pvd09pSWlPMzA9IjtzOjU6InF1ZXJ5IjthOjA6e31zOjg6ImZyYWdtZW50IjtzOjA6IiI7fQ==" class="cit-ref-sprinkles cit-ref-sprinkles-ijlink"><span><span class="cit-reflinks-abstract">Abstract</span><span class="cit-sep cit-reflinks-variant-name-sep">/</span><span class="cit-reflinks-full-text"><span class="free-full-text">FREE </span>Full Text</span></span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-43-1" title="View reference 43 in text" id="ref-43">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.43"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Warmuth</span> <span class="cit-name-given-names">MK</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Liao</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Rätsch</span> <span class="cit-name-given-names">G</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Mathieson</span> <span class="cit-name-given-names">M</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Putta</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Lemmen</span> <span class="cit-name-given-names">C</span></span></li></ol><cite>: <span class="cit-article-title">Active learning with support vector machines in the drug discovery process</span>. <abbr class="cit-jnl-abbrev">J Chem Inf Comput Sci</abbr> <span class="cit-vol">43</span>(<span class="cit-issue">2</span>): <span class="cit-fpage">667</span>-<span class="cit-lpage">673</span>, <span class="cit-pub-date">2003</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DJournal%2Bof%2BChemical%2BInformation%2Band%2BComputer%2BSciences%26rft.stitle%253DJournal%2Bof%2BChemical%2BInformation%2Band%2BComputer%2BSciences%26rft.aulast%253DWarmuth%26rft.auinit1%253DM.%2BK.%26rft.volume%253D43%26rft.issue%253D2%26rft.spage%253D667%26rft.epage%253D673%26rft.atitle%253DActive%2Blearning%2Bwith%2Bsupport%2Bvector%2Bmachines%2Bin%2Bthe%2Bdrug%2Bdiscovery%2Bprocess.%26rft_id%253Dinfo%253Apmid%252F12653536%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=12653536&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-44-1" title="View reference 44 in text" id="ref-44">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.44"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Gupta</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Chaudhary</span> <span class="cit-name-given-names">K</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Kumar</span> <span class="cit-name-given-names">R</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Gautam</span> <span class="cit-name-given-names">G</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Nanda</span> <span class="cit-name-given-names">JS</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Dhanda</span> <span class="cit-name-given-names">SK</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Brahmachari</span> <span class="cit-name-given-names">SK</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Raghava</span> <span class="cit-name-given-names">GPS</span></span></li></ol><cite>: <span class="cit-article-title">Prioritization of anticancer drugs against a cancer using genomic features of cancer cells: A step towards personalized medicine</span>. <abbr class="cit-jnl-abbrev">Sci Rep</abbr> <span class="cit-vol">6</span>: <span class="cit-fpage">23857</span>, <span class="cit-pub-date">2016</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DSci%2BRep%26rft.volume%253D6%26rft.spage%253D23857%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-45-1" title="View reference 45 in text" id="ref-45">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.45"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Bundela</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Sharma</span> <span class="cit-name-given-names">A</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Bisen</span> <span class="cit-name-given-names">PS</span></span></li></ol><cite>: <span class="cit-article-title">Potential compounds for oral cancer treatment: resveratrol, nimbolide, lovastatin, bortezomib, vorinostat, berberine, pterostilbene, deguelin, andrographolide, and colchicine</span>. <abbr class="cit-jnl-abbrev">PLoS One</abbr> <span class="cit-vol">10</span>(<span class="cit-issue">11</span>): <span class="cit-fpage">e0141719</span>, <span class="cit-pub-date">2015</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DPLoS%2BOne%26rft.volume%253D10%26rft.spage%253De0141719%26rft_id%253Dinfo%253Apmid%252F26536350%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=26536350&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-46-1" title="View reference 46 in text" id="ref-46">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.46"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Matsumoto</span> <span class="cit-name-given-names">A</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Aoki</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Ohwada</span> <span class="cit-name-given-names">H</span></span></li></ol><cite>: <span class="cit-article-title">Comparison of random forest and SVM for raw data in drug discovery: prediction of radiation protection and toxicity case study</span>. <abbr class="cit-jnl-abbrev">Int J Mach Learn Comput</abbr> <span class="cit-vol">6</span>(<span class="cit-issue">2</span>): <span class="cit-fpage">145</span>-<span class="cit-lpage">148</span>, <span class="cit-pub-date">2016</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DInt%2BJ%2BMach%2BLearn%2BComput%26rft.volume%253D6%26rft.spage%253D145%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-47-1" title="View reference 47 in text" id="ref-47">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.47"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Morita</span> <span class="cit-name-given-names">A</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Ariyasu</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wang</span> <span class="cit-name-given-names">B</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Asanuma</span> <span class="cit-name-given-names">T</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Onoda</span> <span class="cit-name-given-names">T</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Sawa</span> <span class="cit-name-given-names">A</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Tanaka</span> <span class="cit-name-given-names">K</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Takahashi</span> <span class="cit-name-given-names">I</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Togami</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Nenoi</span> <span class="cit-name-given-names">M</span></span></li></ol><cite>: <span class="cit-article-title">AS-2, a novel inhibitor of p53-dependent apoptosis, prevents apoptotic mitochondrial dysfunction in a transcription-independent manner and protects mice from a lethal dose of ionizing radiation</span>. <abbr class="cit-jnl-abbrev">Biochem Biophys Res Commun</abbr> <span class="cit-vol">450</span>(<span class="cit-issue">4</span>): <span class="cit-fpage">1498</span>-<span class="cit-lpage">1504</span>, <span class="cit-pub-date">2014</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBiochem%2BBiophys%2BRes%2BCommun%26rft.volume%253D450%26rft.spage%253D1498%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-48-1" title="View reference 48 in text" id="ref-48">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.48" data-doi="10.1021/ci200454v"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Volkamer</span> <span class="cit-name-given-names">A</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Kuhn</span> <span class="cit-name-given-names">D</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Grombacher</span> <span class="cit-name-given-names">T</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Rippmann</span> <span class="cit-name-given-names">F</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Rarey</span> <span class="cit-name-given-names">M</span></span></li></ol><cite>: <span class="cit-article-title">Combining global and local measures for structure-based druggability predictions</span>. <abbr class="cit-jnl-abbrev">J Chem Inf Model</abbr> <span class="cit-vol">52</span>(<span class="cit-issue">2</span>): <span class="cit-fpage">360</span>-<span class="cit-lpage">372</span>, <span class="cit-pub-date">2012</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DJournal%2Bof%2Bchemical%2Binformation%2Band%2Bmodeling%26rft.stitle%253DJ%2BChem%2BInf%2BModel%26rft.aulast%253DVolkamer%26rft.auinit1%253DA.%26rft.volume%253D52%26rft.issue%253D2%26rft.spage%253D360%26rft.epage%253D372%26rft.atitle%253DCombining%2Bglobal%2Band%2Blocal%2Bmeasures%2Bfor%2Bstructure-based%2Bdruggability%2Bpredictions.%26rft_id%253Dinfo%253Adoi%252F10.1021%252Fci200454v%26rft_id%253Dinfo%253Apmid%252F22148551%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1021/ci200454v&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=22148551&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-49-1" title="View reference 49 in text" id="ref-49">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.49" data-doi="10.1021/ci200078f"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Li</span> <span class="cit-name-given-names">L</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wang</span> <span class="cit-name-given-names">B</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Meroueh</span> <span class="cit-name-given-names">SO</span></span></li></ol><cite>: <span class="cit-article-title">Support vector regression scoring of receptor-ligand complexes for rank-ordering and virtual screening of chemical libraries</span>. <abbr class="cit-jnl-abbrev">J Chem Inf Model</abbr> <span class="cit-vol">51</span>(<span class="cit-issue">9</span>): <span class="cit-fpage">2132</span>-<span class="cit-lpage">2138</span>, <span class="cit-pub-date">2011</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DJournal%2Bof%2Bchemical%2Binformation%2Band%2Bmodeling%26rft.stitle%253DJ%2BChem%2BInf%2BModel%26rft.aulast%253DLi%26rft.auinit1%253DL.%26rft.volume%253D51%26rft.issue%253D9%26rft.spage%253D2132%26rft.epage%253D2138%26rft.atitle%253DSupport%2Bvector%2Bregression%2Bscoring%2Bof%2Breceptor-ligand%2Bcomplexes%2Bfor%2Brank-ordering%2Band%2Bvirtual%2Bscreening%2Bof%2Bchemical%2Blibraries.%26rft_id%253Dinfo%253Adoi%252F10.1021%252Fci200078f%26rft_id%253Dinfo%253Apmid%252F21728360%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1021/ci200078f&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=21728360&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-50-1" title="View reference 50 in text" id="ref-50">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.50" data-doi="10.1021/ci300493w"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Li</span> <span class="cit-name-given-names">GB</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Yang</span> <span class="cit-name-given-names">LL</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wang</span> <span class="cit-name-given-names">WJ</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Li</span> <span class="cit-name-given-names">LL</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Yang</span> <span class="cit-name-given-names">SY</span></span></li></ol><cite>: <span class="cit-article-title">ID-Score: a new empirical scoring function based on a comprehensive set of descriptors related to protein-ligand interactions</span>. <abbr class="cit-jnl-abbrev">J Chem Inf Model</abbr> <span class="cit-vol">53</span>(<span class="cit-issue">3</span>): <span class="cit-fpage">592</span>-<span class="cit-lpage">600</span>, <span class="cit-pub-date">2013</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DJ%2BChem%2BInf%2BModel%26rft.volume%253D53%26rft.spage%253D592%26rft_id%253Dinfo%253Adoi%252F10.1021%252Fci300493w%26rft_id%253Dinfo%253Apmid%252F23394072%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1021/ci300493w&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=23394072&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-51-1" title="View reference 51 in text" id="ref-51">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.51"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Wang</span> <span class="cit-name-given-names">Q</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Feng</span> <span class="cit-name-given-names">Y</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Huang</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wang</span> <span class="cit-name-given-names">T</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Cheng</span> <span class="cit-name-given-names">G</span></span></li></ol><cite>: <span class="cit-article-title">A novel framework for the identification of drug target proteins: Combining stacked auto-encoders with a biased support vector machine</span>. <abbr class="cit-jnl-abbrev">PloS One</abbr> <span class="cit-vol">12</span>(<span class="cit-issue">4</span>): <span class="cit-fpage">e0176486</span>, <span class="cit-pub-date">2017</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DPloS%2BOne%26rft.volume%253D12%26rft.spage%253De0176486%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-52-1" title="View reference 52 in text" id="ref-52">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.52"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Jeon</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Nim</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Teyra</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Datti</span> <span class="cit-name-given-names">A</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wrana</span> <span class="cit-name-given-names">JL</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Sidhu</span> <span class="cit-name-given-names">SS</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Moffat</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Kim</span> <span class="cit-name-given-names">PM</span></span></li></ol><cite>: <span class="cit-article-title">A systematic approach to identify novel cancer drug targets using machine learning, inhibitor design and high-throughput screening</span>. <abbr class="cit-jnl-abbrev">Genome Med</abbr> <span class="cit-vol">6</span>(<span class="cit-issue">7</span>): <span class="cit-fpage">57</span>, <span class="cit-pub-date">2014</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DGenome%2BMed%26rft.volume%253D6%26rft.spage%253D57%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-53-1" title="View reference 53 in text" id="ref-53">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.53"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Singh</span> <span class="cit-name-given-names">H</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Kumar</span> <span class="cit-name-given-names">R</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Singh</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Chaudhary</span> <span class="cit-name-given-names">K</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Gautam</span> <span class="cit-name-given-names">A</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Raghava</span> <span class="cit-name-given-names">GP</span></span></li></ol><cite>: <span class="cit-article-title">Prediction of anticancer molecules using hybrid model developed on molecules screened against NCI-60 cancer cell lines</span>. <abbr class="cit-jnl-abbrev">BMC Cancer</abbr> <span class="cit-vol">16</span>(<span class="cit-issue">1</span>): <span class="cit-fpage">77</span>, <span class="cit-pub-date">2016</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBMC%2BCancer%26rft.volume%253D16%26rft.spage%253D77%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-54-1" title="View reference 54 in text" id="ref-54">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.54"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Stetson</span> <span class="cit-name-given-names">LC</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Pearl</span> <span class="cit-name-given-names">T</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Chen</span> <span class="cit-name-given-names">Y</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Barnholtz-Sloan</span> <span class="cit-name-given-names">JS</span></span></li></ol><cite>: <span class="cit-article-title">Computational identification of multi-omic correlates of anticancer therapeutic response</span>. <abbr class="cit-jnl-abbrev">BMC Genomics</abbr> <span class="cit-vol">15</span>(<span class="cit-issue">7</span>): <span class="cit-fpage">S2</span>, <span class="cit-pub-date">2014</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBMC%2BGenomics%26rft.volume%253D15%26rft.spage%253DS2%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-55-1" title="View reference 55 in text" id="ref-55">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.55"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Hejase</span> <span class="cit-name-given-names">HA</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Chan</span> <span class="cit-name-given-names">C</span></span></li></ol><cite>: <span class="cit-article-title">Improving Drug Sensitivity Prediction Using Different Types of Data</span>. <abbr class="cit-jnl-abbrev">CPT Pharmacometrics Syst Pharmacol</abbr> <span class="cit-vol">4</span>: <span class="cit-fpage">98</span>-<span class="cit-lpage">105</span>, <span class="cit-pub-date">2015</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DCPT%2BPharmacometrics%2BSyst%2BPharmacol%26rft.volume%253D4%26rft.spage%253D98%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-56-1" title="View reference 56 in text" id="ref-56">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.56" data-doi="10.1186/1471-2105-14-130"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Hazai</span> <span class="cit-name-given-names">E</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Hazai</span> <span class="cit-name-given-names">I</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Ragueneau-Majlessi</span> <span class="cit-name-given-names">I</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Chung</span> <span class="cit-name-given-names">SP</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Bikadi</span> <span class="cit-name-given-names">Z</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Mao</span> <span class="cit-name-given-names">Q</span></span></li></ol><cite>: <span class="cit-article-title">Predicting substrates of the human breast cancer resistance protein using a support vector machine method</span>. <abbr class="cit-jnl-abbrev">BMC Bioinformatics</abbr> <span class="cit-vol">14</span>: <span class="cit-fpage">130</span>, <span class="cit-pub-date">2013</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBMC%2BBioinformatics%26rft.volume%253D14%26rft.spage%253D130%26rft_id%253Dinfo%253Adoi%252F10.1186%252F1471-2105-14-130%26rft_id%253Dinfo%253Apmid%252F23586520%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1186/1471-2105-14-130&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=23586520&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-57-1" title="View reference 57 in text" id="ref-57">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.57" data-doi="10.1002/jcb.24401"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Normanno</span> <span class="cit-name-given-names">N</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Rachiglio</span> <span class="cit-name-given-names">AM</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Roma</span> <span class="cit-name-given-names">C</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Fenizia</span> <span class="cit-name-given-names">F</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Esposito</span> <span class="cit-name-given-names">C</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Pasquale</span> <span class="cit-name-given-names">R</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">La Porta</span> <span class="cit-name-given-names">ML</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Iannaccone</span> <span class="cit-name-given-names">A</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Micheli</span> <span class="cit-name-given-names">F</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Santangelo</span> <span class="cit-name-given-names">M</span></span></li></ol><cite>: <span class="cit-article-title">Molecular diagnostics and personalized medicine in oncology: challenges and opportunities</span>. <abbr class="cit-jnl-abbrev">J Cell Biochem</abbr> <span class="cit-vol">114</span>(<span class="cit-issue">3</span>): <span class="cit-fpage">514</span>-<span class="cit-lpage">524</span>, <span class="cit-pub-date">2013</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DJ%2BCell%2BBiochem%26rft.volume%253D114%26rft.spage%253D514%26rft_id%253Dinfo%253Adoi%252F10.1002%252Fjcb.24401%26rft_id%253Dinfo%253Apmid%252F22991232%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1002/jcb.24401&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=22991232&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-58-1" title="View reference 58 in text" id="ref-58">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.58" data-doi="10.1126/science.1235122"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Vogelstein</span> <span class="cit-name-given-names">B</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Papadopoulos</span> <span class="cit-name-given-names">N</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Velculescu</span> <span class="cit-name-given-names">VE</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zhou</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Diaz</span> <span class="cit-name-given-names">LA</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Kinzler</span> <span class="cit-name-given-names">KW</span></span></li></ol><cite>: <span class="cit-article-title">Cancer genome landscapes</span>. <abbr class="cit-jnl-abbrev">Science</abbr> <span class="cit-vol">339</span>(<span class="cit-issue">6127</span>): <span class="cit-fpage">1546</span>-<span class="cit-lpage">1558</span>, <span class="cit-pub-date">2013</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DScience%26rft.stitle%253DScience%26rft.aulast%253DVogelstein%26rft.auinit1%253DB.%26rft.volume%253D339%26rft.issue%253D6127%26rft.spage%253D1546%26rft.epage%253D1558%26rft.atitle%253DCancer%2BGenome%2BLandscapes%26rft_id%253Dinfo%253Adoi%252F10.1126%252Fscience.1235122%26rft_id%253Dinfo%253Apmid%252F23539594%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6Mzoic2NpIjtzOjU6InJlc2lkIjtzOjEzOiIzMzkvNjEyNy8xNTQ2IjtzOjQ6ImF0b20iO3M6MTc6Ii9jZ3AvMTUvMS80MS5hdG9tIjt9czo4OiJmcmFnbWVudCI7czowOiIiO30=/YTozOntzOjQ6InBhdGgiO3M6Mjg3OiIvbG9va3VwL2lqbGluay9ZVG96T250ek9qUTZJbkJoZEdnaU8zTTZNVFE2SWk5c2IyOXJkWEF2YVdwc2FXNXJJanR6T2pVNkluRjFaWEo1SWp0aE9qUTZlM002T0RvaWJHbHVhMVI1Y0dVaU8zTTZORG9pUVVKVFZDSTdjem94TVRvaWFtOTFjbTVoYkVOdlpHVWlPM002TXpvaWMyTnBJanR6T2pVNkluSmxjMmxrSWp0ek9qRXpPaUl6TXprdk5qRXlOeTh4TlRRMklqdHpPalE2SW1GMGIyMGlPM002TVRjNklpOWpaM0F2TVRVdk1TODBNUzVoZEc5dElqdDljem80T2lKbWNtRm5iV1Z1ZENJN2N6b3dPaUlpTzMwPSI7czo1OiJxdWVyeSI7YTowOnt9czo4OiJmcmFnbWVudCI7czowOiIiO30=" class="cit-ref-sprinkles cit-ref-sprinkles-ijlink"><span><span class="cit-reflinks-abstract">Abstract</span><span class="cit-sep cit-reflinks-variant-name-sep">/</span><span class="cit-reflinks-full-text"><span class="free-full-text">FREE </span>Full Text</span></span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-59-1" title="View reference 59 in text" id="ref-59">↵</a><div class="cit ref-cit ref-confproc" id="cit-15.1.41.59"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Jordan</span> <span class="cit-name-given-names">EJ</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Radhakrishnan</span> <span class="cit-name-given-names">R</span></span></li></ol><cite>: <span class="cit-source">Machine learning predictions of cancer driver mutations</span>. <span class="cit-conf-name">Proceedings of the 2014 6th International Advanced Research Workshop on In Silico Oncology and Cancer Investigation</span>, <span class="cit-conf-date">2014</span>. <span class="cit-comment">doi: 10.1109/IARWISOCI.2014.7034632</span> </cite></div><div class="cit-extra"></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-60-1" title="View reference 60 in text" id="ref-60">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.60" data-doi="10.1016/j.ygeno.2011.06.010"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Capriotti</span> <span class="cit-name-given-names">E</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Altman</span> <span class="cit-name-given-names">RB</span></span></li></ol><cite>: <span class="cit-article-title">A new disease-specific machine learning approach for the prediction of cancer-causing missense variants</span>. <abbr class="cit-jnl-abbrev">Genomics</abbr> <span class="cit-vol">98</span>(<span class="cit-issue">4</span>): <span class="cit-fpage">310</span>-<span class="cit-lpage">317</span>, <span class="cit-pub-date">2011</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DGenomics%26rft.stitle%253DGenomics%26rft.aulast%253DCapriotti%26rft.auinit1%253DE.%26rft.volume%253D98%26rft.issue%253D4%26rft.spage%253D310%26rft.epage%253D317%26rft.atitle%253DA%2Bnew%2Bdisease-specific%2Bmachine%2Blearning%2Bapproach%2Bfor%2Bthe%2Bprediction%2Bof%2Bcancer-causing%2Bmissense%2Bvariants.%26rft_id%253Dinfo%253Adoi%252F10.1016%252Fj.ygeno.2011.06.010%26rft_id%253Dinfo%253Apmid%252F21763417%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1016/j.ygeno.2011.06.010&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=21763417&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-61-1" title="View reference 61 in text" id="ref-61">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.61"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Izarzugaza</span> <span class="cit-name-given-names">JM</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">del Pozo</span> <span class="cit-name-given-names">A</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Vazquez</span> <span class="cit-name-given-names">M</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Valencia</span> <span class="cit-name-given-names">A</span></span></li></ol><cite>: <span class="cit-article-title">Prioritization of pathogenic mutations in the protein kinase superfamily</span>. <abbr class="cit-jnl-abbrev">BMC Genomics</abbr> <span class="cit-vol">13</span>(<span class="cit-issue">4</span>): <span class="cit-fpage">S3</span>, <span class="cit-pub-date">2012</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBMC%2BGenomics%26rft.volume%253D13%26rft.spage%253DS3%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-62-1" title="View reference 62 in text" id="ref-62">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.62" data-doi="10.1093/bioinformatics/bts558"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Tan</span> <span class="cit-name-given-names">H</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Bao</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zhou</span> <span class="cit-name-given-names">X</span></span></li></ol><cite>: <span class="cit-article-title">A novel missense-mutation-related feature extraction scheme for ‘driver’mutation identification</span>. <abbr class="cit-jnl-abbrev">Bioinformatics</abbr> <span class="cit-vol">28</span>(<span class="cit-issue">22</span>): <span class="cit-fpage">2948</span>-<span class="cit-lpage">2955</span>, <span class="cit-pub-date">2012</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DBioinformatics%26rft_id%253Dinfo%253Adoi%252F10.1093%252Fbioinformatics%252Fbts558%26rft_id%253Dinfo%253Apmid%252F23044540%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1093/bioinformatics/bts558&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=23044540&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-63-1" title="View reference 63 in text" id="ref-63">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.63" data-doi="10.1016/j.ygeno.2011.06.010"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Capriotti</span> <span class="cit-name-given-names">E</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Altman</span> <span class="cit-name-given-names">RB</span></span></li></ol><cite>: <span class="cit-article-title">A new disease-specific machine learning approach for the prediction of cancer-causing missense variants</span>. <abbr class="cit-jnl-abbrev">Genomics</abbr> <span class="cit-vol">98</span>(<span class="cit-issue">4</span>): <span class="cit-fpage">310</span>-<span class="cit-lpage">317</span>, <span class="cit-pub-date">2011</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DGenomics%26rft.stitle%253DGenomics%26rft.aulast%253DCapriotti%26rft.auinit1%253DE.%26rft.volume%253D98%26rft.issue%253D4%26rft.spage%253D310%26rft.epage%253D317%26rft.atitle%253DA%2Bnew%2Bdisease-specific%2Bmachine%2Blearning%2Bapproach%2Bfor%2Bthe%2Bprediction%2Bof%2Bcancer-causing%2Bmissense%2Bvariants.%26rft_id%253Dinfo%253Adoi%252F10.1016%252Fj.ygeno.2011.06.010%26rft_id%253Dinfo%253Apmid%252F21763417%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1016/j.ygeno.2011.06.010&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=21763417&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-64-1" title="View reference 64 in text" id="ref-64">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.64"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Bari</span> <span class="cit-name-given-names">MG</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Ung</span> <span class="cit-name-given-names">CY</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zhang</span> <span class="cit-name-given-names">C</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zhu</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Li</span> <span class="cit-name-given-names">H</span></span></li></ol><cite>: <span class="cit-article-title">Machine Learning-assisted network inference approach to identify a new class of genes that coordinate the functionality of cancer networks</span>. <abbr class="cit-jnl-abbrev">Sci Rep</abbr> <span class="cit-vol">7</span>: <span class="cit-fpage">6993</span>, <span class="cit-pub-date">2017</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DSci%2BRep%26rft.volume%253D7%26rft.spage%253D6993%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-65-1" title="View reference 65 in text" id="ref-65">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.65" data-doi="10.1158/1078-0432.CCR-1115-03"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Listgarten</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Damaraju</span> <span class="cit-name-given-names">S</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Poulin</span> <span class="cit-name-given-names">B</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Cook</span> <span class="cit-name-given-names">L</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Dufour</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Driga</span> <span class="cit-name-given-names">A</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Mackey</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wishart</span> <span class="cit-name-given-names">D</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Greiner</span> <span class="cit-name-given-names">R</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zanke</span> <span class="cit-name-given-names">B</span></span></li></ol><cite>: <span class="cit-article-title">Predictive models for breast cancer susceptibility from multiple single nucleotide polymorphisms</span>. <abbr class="cit-jnl-abbrev">Clin Cancer Res</abbr> <span class="cit-vol">10</span>(<span class="cit-issue">8</span>): <span class="cit-fpage">2725</span>-<span class="cit-lpage">2737</span>, <span class="cit-pub-date">2004</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DClinical%2BCancer%2BResearch%26rft.stitle%253DClin.%2BCancer%2BRes.%26rft.aulast%253DListgarten%26rft.auinit1%253DJ.%26rft.volume%253D10%26rft.issue%253D8%26rft.spage%253D2725%26rft.epage%253D2737%26rft.atitle%253DPredictive%2BModels%2Bfor%2BBreast%2BCancer%2BSusceptibility%2Bfrom%2BMultiple%2BSingle%2BNucleotide%2BPolymorphisms%26rft_id%253Dinfo%253Adoi%252F10.1158%252F1078-0432.CCR-1115-03%26rft_id%253Dinfo%253Apmid%252F15102677%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6MTA6ImNsaW5jYW5yZXMiO3M6NToicmVzaWQiO3M6OToiMTAvOC8yNzI1IjtzOjQ6ImF0b20iO3M6MTc6Ii9jZ3AvMTUvMS80MS5hdG9tIjt9czo4OiJmcmFnbWVudCI7czowOiIiO30=/YTozOntzOjQ6InBhdGgiO3M6MjkxOiIvbG9va3VwL2lqbGluay9ZVG96T250ek9qUTZJbkJoZEdnaU8zTTZNVFE2SWk5c2IyOXJkWEF2YVdwc2FXNXJJanR6T2pVNkluRjFaWEo1SWp0aE9qUTZlM002T0RvaWJHbHVhMVI1Y0dVaU8zTTZORG9pUVVKVFZDSTdjem94TVRvaWFtOTFjbTVoYkVOdlpHVWlPM002TVRBNkltTnNhVzVqWVc1eVpYTWlPM002TlRvaWNtVnphV1FpTzNNNk9Ub2lNVEF2T0M4eU56STFJanR6T2pRNkltRjBiMjBpTzNNNk1UYzZJaTlqWjNBdk1UVXZNUzgwTVM1aGRHOXRJanQ5Y3pvNE9pSm1jbUZuYldWdWRDSTdjem93T2lJaU8zMD0iO3M6NToicXVlcnkiO2E6MDp7fXM6ODoiZnJhZ21lbnQiO3M6MDoiIjt9" class="cit-ref-sprinkles cit-ref-sprinkles-ijlink"><span><span class="cit-reflinks-abstract">Abstract</span><span class="cit-sep cit-reflinks-variant-name-sep">/</span><span class="cit-reflinks-full-text"><span class="free-full-text">FREE </span>Full Text</span></span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-66-1" title="View reference 66 in text" id="ref-66">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.66" data-doi="10.1016/j.toxlet.2004.02.021"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Schwender</span> <span class="cit-name-given-names">H</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zucknick</span> <span class="cit-name-given-names">M</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Ickstadt</span> <span class="cit-name-given-names">K</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Bolt</span> <span class="cit-name-given-names">HM</span></span>, </li><li><span class="cit-auth cit-collab">The GENICA network</span></li></ol><cite>: <span class="cit-article-title">A pilot study on the application of statistical classification procedures to molecular epidemiological data</span>. <abbr class="cit-jnl-abbrev">Toxicol Lett</abbr> <span class="cit-vol">151</span>(<span class="cit-issue">1</span>): <span class="cit-fpage">291</span>-<span class="cit-lpage">299</span>, <span class="cit-pub-date">2004</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DToxicology%2Bletters%26rft.stitle%253DToxicol%2BLett%26rft.aulast%253DSchwender%26rft.auinit1%253DH.%26rft.volume%253D151%26rft.issue%253D1%26rft.spage%253D291%26rft.epage%253D299%26rft.atitle%253DA%2Bpilot%2Bstudy%2Bon%2Bthe%2Bapplication%2Bof%2Bstatistical%2Bclassification%2Bprocedures%2Bto%2Bmolecular%2Bepidemiological%2Bdata.%26rft_id%253Dinfo%253Adoi%252F10.1016%252Fj.toxlet.2004.02.021%26rft_id%253Dinfo%253Apmid%252F15177665%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1016/j.toxlet.2004.02.021&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=15177665&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-67-1" title="View reference 67 in text" id="ref-67">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.67" data-doi="10.1002/gepi.20272"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Chen</span> <span class="cit-name-given-names">SH</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Sun</span> <span class="cit-name-given-names">J</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Dimitrov</span> <span class="cit-name-given-names">L</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Turner</span> <span class="cit-name-given-names">AR</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Adams</span> <span class="cit-name-given-names">TS</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Meyers</span> <span class="cit-name-given-names">DA</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Chang</span> <span class="cit-name-given-names">BL</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Zheng</span> <span class="cit-name-given-names">SL</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Grönberg</span> <span class="cit-name-given-names">H</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Xu</span> <span class="cit-name-given-names">J</span></span></li></ol><cite>: <span class="cit-article-title">A support vector machine approach for detecting gene–gene interaction</span>. <abbr class="cit-jnl-abbrev">Genet Epidemiol</abbr> <span class="cit-vol">32</span>(<span class="cit-issue">2</span>): <span class="cit-fpage">152</span>-<span class="cit-lpage">67</span>, <span class="cit-pub-date">2008</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DGenetic%2Bepidemiology%26rft.stitle%253DGenet%2BEpidemiol%26rft.aulast%253DChen%26rft.auinit1%253DS.%2BH.%26rft.volume%253D32%26rft.issue%253D2%26rft.spage%253D152%26rft.epage%253D167%26rft.atitle%253DA%2Bsupport%2Bvector%2Bmachine%2Bapproach%2Bfor%2Bdetecting%2Bgene-gene%2Binteraction.%26rft_id%253Dinfo%253Adoi%252F10.1002%252Fgepi.20272%26rft_id%253Dinfo%253Apmid%252F17968988%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1002/gepi.20272&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=17968988&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-68-1" title="View reference 68 in text" id="ref-68">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.68" data-doi="10.1093/nar/gkn159"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Guo</span> <span class="cit-name-given-names">Y</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Yu</span> <span class="cit-name-given-names">L</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Wen</span> <span class="cit-name-given-names">Z</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Li</span> <span class="cit-name-given-names">M</span></span></li></ol><cite>: <span class="cit-article-title">Using support vector machine combined with auto covariance to predict protein–protein interactions from protein sequences</span>. <abbr class="cit-jnl-abbrev">Nucleic Acids Res</abbr> <span class="cit-vol">36</span>(<span class="cit-issue">9</span>): <span class="cit-fpage">3025</span>-<span class="cit-lpage">3030</span>, <span class="cit-pub-date">2008</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.jtitle%253DNucleic%2BAcids%2BRes%26rft_id%253Dinfo%253Adoi%252F10.1093%252Fnar%252Fgkn159%26rft_id%253Dinfo%253Apmid%252F18390576%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1093/nar/gkn159&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=18390576&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-69-1" title="View reference 69 in text" id="ref-69">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.69"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Chai</span> <span class="cit-name-given-names">H</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Huang</span> <span class="cit-name-given-names">HH</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Jiang</span> <span class="cit-name-given-names">HK</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Liang</span> <span class="cit-name-given-names">Y</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Xia</span> <span class="cit-name-given-names">LY</span></span></li></ol><cite>: <span class="cit-article-title">Protein-protein interaction network construction for cancer using a new L1/2-penalized Net-SVM model</span>. <abbr class="cit-jnl-abbrev">Genet Mol Res</abbr> <span class="cit-vol">15</span>(<span class="cit-issue">3</span>): <span class="cit-comment">gmr.15038794</span>, <span class="cit-pub-date">2016</span>. </cite></div><div class="cit-extra"></div></div></li><li><a class="rev-xref-ref" href="#xref-ref-70-1" title="View reference 70 in text" id="ref-70">↵</a><div class="cit ref-cit ref-journal" id="cit-15.1.41.70" data-doi="10.1371/journal.pcbi.0030116"><div class="cit-metadata"><ol class="cit-auth-list"><li><span class="cit-auth"><span class="cit-name-surname">Tarca</span> <span class="cit-name-given-names">AL</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Carey</span> <span class="cit-name-given-names">VJ</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Chen</span> <span class="cit-name-given-names">XW</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Romero</span> <span class="cit-name-given-names">R</span></span>, </li><li><span class="cit-auth"><span class="cit-name-surname">Drăghici</span> <span class="cit-name-given-names">S</span></span></li></ol><cite>: <span class="cit-article-title">Machine learning and its applications to biology</span>. <abbr class="cit-jnl-abbrev">PLoS Comput Biol</abbr> <span class="cit-vol">3</span>(<span class="cit-issue">6</span>): <span class="cit-fpage">e116</span>, <span class="cit-pub-date">2007</span>. </cite></div><div class="cit-extra"><a href="{openurl}?query=rft.stitle%253DPLoS%2BComput%2BBiol%26rft.aulast%253DTarca%26rft.auinit1%253DA.%2BL.%26rft.volume%253D3%26rft.issue%253D6%26rft.spage%253De116%26rft.epage%253De116%26rft.atitle%253DMachine%2Blearning%2Band%2Bits%2Bapplications%2Bto%2Bbiology.%26rft_id%253Dinfo%253Adoi%252F10.1371%252Fjournal.pcbi.0030116%26rft_id%253Dinfo%253Apmid%252F17604446%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx" class="cit-ref-sprinkles cit-ref-sprinkles-openurl cit-ref-sprinkles-open-url"><span>OpenUrl</span></a><a href="/lookup/external-ref?access_num=10.1371/journal.pcbi.0030116&link_type=DOI" class="cit-ref-sprinkles cit-ref-sprinkles-doi cit-ref-sprinkles-crossref"><span>CrossRef</span></a><a href="/lookup/external-ref?access_num=17604446&link_type=MED&atom=%2Fcgp%2F15%2F1%2F41.atom" class="cit-ref-sprinkles cit-ref-sprinkles-medline"><span>PubMed</span></a></div></div></li></ol></div><span class="highwire-journal-article-marker-end"></span></div><span class="related-urls"></span></div></div> </div> </div> </div> </div> </div> </div></div> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-highwire-node-pager" > <div class="pane-content"> <div class="pager highwire-pager pager-mini clearfix highwire-node-pager highwire-article-pager"><span class="pager-prev"><a href="/content/15/1/17" title="The Role of micro RNAs in Breast Cancer Metastasis: Preclinical Validation and Potential Therapeutic Targets" rel="prev" class="pager-link-prev link-icon"><span class="icon-circle-arrow-left"></span> <span class="title">Previous</span></a></span><span class="pager-next"><a href="/content/15/1/53" title="Regulation of β-Catenin Phosphorylation by PR55β in Adenoid Cystic Carcinoma" rel="next" class="pager-link-next link-icon-right link-icon"><span class="title">Next</span> <span class="icon-circle-arrow-right"></span></a></span></div> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-highwire-back-to-top" > <div class="pane-content"> <a href="#page" class="back-to-top" data-icon-position="" data-hide-link-title="0"><span class="icon-chevron-up"></span> Back to top</a> </div> </div> </div> </div> </div> <div class="sidebar-right-wrapper grid-10 omega"> <div class="panel-panel panel-region-sidebar-right"> <div class="inside"><div class="panel-pane pane-panels-mini pane-jnl-iiar-art-issue pane-style-alt-content" > <h2 class="pane-title">In this issue</h2> <div class="pane-content"> <div class="panel-display panel-1col clearfix" id="mini-panel-jnl_iiar_art_issue"> <div class="panel-panel panel-col"> <div><div class="panel-pane pane-highwire-article-citation" > <div class="pane-content"> <div class="highwire-article-citation highwire-citation-type-highwire-issue node544" data-node-nid="544" id="node-544--21256978774" data-pisa="cgp;15/1" data-pisa-master="cgp;15/1" data-apath="/cgp/15/1.atom"><div class="highwire-cite highwire-cite-highwire-issue highwire-citation-jcore-issue-widget clearfix"> <div class="highwire-cite-col"> <a href="/content/15/1" class="highwire-cite-linked-title" data-icon-position="" data-hide-link-title="0"><span class="highwire-cite-title">Cancer Genomics & Proteomics</span></a> <div class="highwire-cite-metadata"><span class="highwire-cite-metadata-volume highwire-cite-metadata">Vol. 15</span>, <span class="highwire-cite-metadata-issue highwire-cite-metadata">Issue 1 </span><div class="highwire-cite-metadata-pubdate highwire-cite-metadata">January-February 2018 </div></div> <div class="highwire-cite-extras"><div class='highwire-article-citation-variant-list'><ul class="links variants-list"><li class="toc first"><a href="/content/15/1.toc" class="highwire-variant-link variant-toc " title="Table of Contents" rel="alternate" type="text/html" data-icon-position="" data-hide-link-title="0">Table of Contents</a></li><li class="tocpdf"><a href="/content/15/1.toc.pdf" class="highwire-variant-link variant-tocpdf " title="Table of Contents (PDF)" rel="alternate" type="application/pdf" data-icon-position="" data-hide-link-title="0">Table of Contents (PDF)</a></li><li class="index-by-author"><a href="/content/15/1.index-by-author" class="highwire-variant-link variant-index-by-author " title="Index by author" rel="alternate" data-icon-position="" data-hide-link-title="0">Index by author</a></li><li class="enclosure-back-matter"><a href="/content/cgp/15/1/local/back-matter.pdf" class="highwire-variant-link variant-enclosure" title="Back Matter (PDF)" rel="alternative" data-icon-position="" data-hide-link-title="0">Back Matter (PDF)</a></li><li class="enclosure-ed-board"><a href="/content/cgp/15/1/local/ed-board.pdf" class="highwire-variant-link variant-enclosure" title="Ed Board (PDF)" rel="alternative" data-icon-position="" data-hide-link-title="0">Ed Board (PDF)</a></li><li class="enclosure-front-matter last"><a href="/content/cgp/15/1/local/front-matter.pdf" class="highwire-variant-link variant-enclosure" title="Front Matter (PDF)" rel="alternative" data-icon-position="" data-hide-link-title="0">Front Matter (PDF)</a></li></ul></div></div> </div> </div></div> </div> </div> </div> </div> </div> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-panels-mini pane-jnl-iiar-art-tools" > <div class="pane-content"> <div id="mini-panel-jnl_iiar_art_tools" class="highwire-2col-stacked panel-display"> <div class="panel-row-wrapper clearfix"> <div class="content-left-wrapper content-column"> <div class="panel-panel panel-region-content-left"> <div class="inside"><div class="panel-pane pane-highwire-variant-link" > <div class="pane-content"> <a href="/content/cgp/15/1/41.full-text.print" target="_blank" rel="nofollow" class="link-icon"><span class="icon-print"></span> <span class="title">Print</span></a> </div> </div> <div class="panel-pane pane-highwire-variant-link text-no-wrap" > <div class="pane-content"> <a href="/content/cgp/15/1/41.full-text.pdf" target="_blank" class="link-icon"><span class="icon-download-alt"></span> <span class="title">Download PDF</span></a> </div> </div> <div class="panel-pane pane-minipanel-dialog-link pane-jnl-iiar-art-alert" > <div class="pane-content"> <div class='minipanel-dialog-wrapper'><div class='minipanel-dialog-link-link'><a href="/" oncontextmenu="javascript: return false;" class="minipanel-dialog-link-trigger link-icon" title="Alerts for this Article"><span class="icon-exclamation-sign"></span> <span class="title">Article Alerts</span></a></div><div class='minipanel-dialog-link-mini' style='display:none'><div class="panel-display panel-1col clearfix" id="mini-panel-jnl_iiar_art_alert"> <div class="panel-panel panel-col"> <div><div class="panel-pane pane-article-add-form" > <div class="pane-content"> <div id = "alerts-form-wrapper"><form action="/content/15/1/41" method="post" id="highwire-user-opportunity-login" accept-charset="UTF-8"><div><div class="form-item form-item-label-before form-type-textfield form-item-name"> <label for="edit-name">User Name <span class="form-required" title="This field is required.">*</span></label> <input type="text" id="edit-name" name="name" value="" size="60" maxlength="128" class="form-text required" /> </div> <div class="form-item form-item-label-before form-type-password form-item-pass"> <label for="edit-pass">Password <span class="form-required" title="This field is required.">*</span></label> <input type="password" id="edit-pass" name="pass" size="60" maxlength="128" class="form-text required" /> </div> <div id="alerts_email">Sign In to Email Alerts with your Email Address</div><div class="form-item form-item-label-before form-type-textfield form-item-highwire-alerts-email"> <label for="edit-highwire-alerts-email">Email <span class="form-required" title="This field is required.">*</span></label> <input type="text" id="edit-highwire-alerts-email" name="highwire_alerts_email" value="" size="60" maxlength="128" class="form-text required" /> </div> <input type="submit" id="edit-submit--3" name="op" value="Submit" class="form-submit" /><input type="hidden" name="form_build_id" value="form-Ow54yCiMt_yk9RhQA_aRxS6gLZC9QOSGtpbmGzkywS8" /> <input type="hidden" name="form_id" value="highwire_alerts_article_sign_up_form" /> <input type="hidden" name="current_path" value="content/15/1/41" /> </div></form></div> </div> </div> </div> </div> </div> </div></div> </div> </div> <div class="panel-pane pane-minipanel-dialog-link pane-jnl-iiar-art-email" > <div class="pane-content"> <div class='minipanel-dialog-wrapper'><div class='minipanel-dialog-link-link'><a href="/" oncontextmenu="javascript: return false;" class="minipanel-dialog-link-trigger link-icon" title="Email this Article"><span class="icon-envelope"></span> <span class="title">Email Article</span></a></div><div class='minipanel-dialog-link-mini' style='display:none'><div class="panel-display panel-1col clearfix" id="mini-panel-jnl_iiar_art_email"> <div class="panel-panel panel-col"> <div><div class="panel-pane pane-block pane-forward-form pane-forward" > <div class="pane-content"> <form action="/content/15/1/41" method="post" id="forward-form" accept-charset="UTF-8"><div><div id="edit-instructions" class="form-item form-item-label-before form-type-item"> <p>Thank you for your interest in spreading the word on Cancer Genomics & Proteomics.</p><p>NOTE: We only request your email address so that the person you are recommending the page to knows that you wanted them to see it, and that it is not junk mail. We do not capture any email address.</p> </div> <div class="form-item form-item-label-before form-type-textfield form-item-email"> <label for="edit-email">Your Email <span class="form-required" title="This field is required.">*</span></label> <input type="text" id="edit-email" name="email" value="" size="58" maxlength="256" class="form-text required" /> </div> <div class="form-item form-item-label-before form-type-textfield form-item-name"> <label for="edit-name--2">Your Name <span class="form-required" title="This field is required.">*</span></label> <input type="text" id="edit-name--2" name="name" value="" size="58" maxlength="256" class="form-text required" /> </div> <div class="form-item form-item-label-before form-type-textarea form-item-recipients"> <label for="edit-recipients">Send To <span class="form-required" title="This field is required.">*</span></label> <div class="form-textarea-wrapper resizable"><textarea id="edit-recipients" name="recipients" cols="50" rows="5" class="form-textarea required"></textarea></div> <div class="description">Enter multiple addresses on separate lines or separate them with commas.</div> </div> <div id="edit-page" class="form-item form-item-label-before form-type-item"> <label for="edit-page">You are going to email the following </label> <a href="/content/15/1/41" class="active" data-icon-position="" data-hide-link-title="0">Applications of Support Vector Machine (SVM) Learning in Cancer Genomics</a> </div> <div id="edit-subject" class="form-item form-item-label-before form-type-item"> <label for="edit-subject">Message Subject </label> (Your Name) has sent you a message from Cancer Genomics & Proteomics </div> <div id="edit-body" class="form-item form-item-label-before form-type-item"> <label for="edit-body">Message Body </label> (Your Name) thought you would like to see the Cancer Genomics & Proteomics web site. </div> <div class="form-item form-item-label-before form-type-textarea form-item-message"> <label for="edit-message--2">Your Personal Message </label> <div class="form-textarea-wrapper resizable"><textarea id="edit-message--2" name="message" cols="50" rows="10" class="form-textarea"></textarea></div> </div> <input type="hidden" name="path" value="node/1056" /> <input type="hidden" name="path_cid" value="" /> <input type="hidden" name="forward_footer" value="" /> <input type="hidden" name="form_build_id" value="form-wTkRweBpMY1mAWBcg3xcMnLxB1cKsj4DW6fJWelVNY8" /> <input type="hidden" name="form_id" value="forward_form" /> <fieldset class="captcha form-wrapper"><legend><span class="fieldset-legend">CAPTCHA</span></legend><div class="fieldset-wrapper"><div class="fieldset-description">This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.</div><input type="hidden" name="captcha_sid" value="3862766" /> <input type="hidden" name="captcha_token" value="beda29f10d46ba60811efa35e03398c0" /> <div class="form-item form-item-label-before form-type-textfield form-item-captcha-response"> <label for="edit-captcha-response">Math question <span class="form-required" title="This field is required.">*</span></label> <span class="field-prefix">2 + 9 = </span> <input type="text" id="edit-captcha-response" name="captcha_response" value="" size="4" maxlength="2" class="form-text required" /> <div class="description">Solve this simple math problem and enter the result. E.g. for 1+3, enter 4.</div> </div> </div></fieldset> <div class="form-actions form-wrapper" id="edit-actions"><input type="submit" id="edit-submit--4" name="op" value="Send Message" class="form-submit" /></div></div></form> </div> </div> </div> </div> </div> </div></div> </div> </div> <div class="panel-pane pane-minipanel-dialog-link pane-jnl-iiar-cite-tool" > <div class="pane-content"> <div class='minipanel-dialog-wrapper'><div class='minipanel-dialog-link-link'><a href="/highwire/citation/1056/download" oncontextmenu="javascript: return false;" class="minipanel-dialog-link-trigger link-icon" title="Citation Tools"><span class="icon-globe"></span> <span class="title">Citation Tools</span></a></div><div class='minipanel-dialog-link-mini' style='display:none'><div class="panel-display panel-1col clearfix" id="mini-panel-jnl_iiar_cite_tool"> <div class="panel-panel panel-col"> <div><div class="panel-pane pane-highwire-citation-export" > <div class="pane-content"> <div class="highwire-citation-export"> <div class="highwire-citation-info"> <div class="highwire-article-citation highwire-citation-type-highwire-article cite-tool-node1056" data-node-nid="1056" id="citation-node-1056--2663704392" data-pisa="cgp;15/1/41" data-pisa-master="cgp;15/1/41" data-apath="/cgp/15/1/41.atom"><div class="highwire-cite highwire-cite-highwire-article highwire-citation-jcore-standard clearfix"> <div class="highwire-cite-title">Applications of Support Vector Machine (SVM) Learning in Cancer Genomics</div> <div class="highwire-cite-authors"><span class="highwire-citation-authors"><span class="highwire-citation-author first" data-delta="0"><span class="nlm-given-names">SHUJUN</span> <span class="nlm-surname">HUANG</span></span>, <span class="highwire-citation-author" data-delta="1"><span class="nlm-given-names">NIANGUANG</span> <span class="nlm-surname">CAI</span></span>, <span class="highwire-citation-author" data-delta="2"><span class="nlm-given-names">PEDRO PENZUTI</span> <span class="nlm-surname">PACHECO</span></span>, <span class="highwire-citation-author" data-delta="3"><span class="nlm-given-names">SHAVIRA</span> <span class="nlm-surname">NARRANDES</span></span>, <span class="highwire-citation-author" data-delta="4"><span class="nlm-given-names">YANG</span> <span class="nlm-surname">WANG</span></span>, <span class="highwire-citation-author" data-delta="5"><span class="nlm-given-names">WAYNE</span> <span class="nlm-surname">XU</span></span></span></div> <div class="highwire-cite-metadata"><span class="highwire-cite-metadata-oa-ind highwire-cite-metadata"><i class="highwire-oa-indicator"></i> </span><span class="highwire-cite-metadata-journal highwire-cite-metadata">Cancer Genomics & Proteomics </span><span class="highwire-cite-metadata-date highwire-cite-metadata">Jan 2018, </span><span class="highwire-cite-metadata-volume highwire-cite-metadata">15 </span><span class="highwire-cite-metadata-issue highwire-cite-metadata">(1) </span><span class="highwire-cite-metadata-pages highwire-cite-metadata">41-51; </span></div> </div> </div> </div> <div class="highwire-citation-formats"> <h2>Citation Manager Formats</h2> <div class="highwire-citation-formats-links"> <span class="Z3988" title="ctx_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.spage=41&rft.epage=51&rft.atitle=Applications%20of%20Support%20Vector%20Machine%20%28SVM%29%20Learning%20in%20Cancer%20Genomics&rft.volume=15&rft.issue=1&rft.date=2018-01-01%2000%3A00%3A00&rft.stitle&rft.jtitle=Cancer%20Genomics%20%26%20Proteomics&rft.au=HUANG%2C+SHUJUN&rft.au=CAI%2C+NIANGUANG&rft.au=PACHECO%2C+PEDRO+PENZUTI&rft.au=NARRANDES%2C+SHAVIRA&rft.au=WANG%2C+YANG&rft.au=XU%2C+WAYNE"></span><ul class="hw-citation-links inline button button-alt button-grid clearfix"><li class="bibtext first"><a href="/highwire/citation/1056/bibtext" class="hw-download-citation-link" data-icon-position="" data-hide-link-title="0">BibTeX</a></li><li class="bookends"><a href="/highwire/citation/1056/bookends" class="hw-download-citation-link" data-icon-position="" data-hide-link-title="0">Bookends</a></li><li class="easybib"><a href="/highwire/citation/1056/easybib" class="hw-download-citation-link" data-icon-position="" data-hide-link-title="0">EasyBib</a></li><li class="endnote-tagged"><a href="/highwire/citation/1056/endnote-tagged" class="hw-download-citation-link" data-icon-position="" data-hide-link-title="0">EndNote (tagged)</a></li><li class="endnote-8-xml"><a href="/highwire/citation/1056/endnote-8-xml" class="hw-download-citation-link" data-icon-position="" data-hide-link-title="0">EndNote 8 (xml)</a></li><li class="medlars"><a href="/highwire/citation/1056/medlars" class="hw-download-citation-link" data-icon-position="" data-hide-link-title="0">Medlars</a></li><li class="mendeley"><a href="/highwire/citation/1056/mendeley" class="hw-download-citation-link" data-icon-position="" data-hide-link-title="0">Mendeley</a></li><li class="papers"><a href="/highwire/citation/1056/papers" class="hw-download-citation-link" data-icon-position="" data-hide-link-title="0">Papers</a></li><li class="refworks-tagged"><a href="/highwire/citation/1056/refworks-tagged" class="hw-download-citation-link" data-icon-position="" data-hide-link-title="0">RefWorks Tagged</a></li><li class="reference-manager"><a href="/highwire/citation/1056/reference-manager" class="hw-download-citation-link" data-icon-position="" data-hide-link-title="0">Ref Manager</a></li><li class="ris"><a href="/highwire/citation/1056/ris" class="hw-download-citation-link" data-icon-position="" data-hide-link-title="0">RIS</a></li><li class="zotero last"><a href="/highwire/citation/1056/zotero" class="hw-download-citation-link" data-icon-position="" data-hide-link-title="0">Zotero</a></li></ul> </div> </div> </div> </div> </div> </div> </div> </div> </div></div> </div> </div> <div class="panel-pane pane-highwire-permission-link" > <div class="pane-content"> <a href="https://www.copyright.com/openurl.do?contentIdType=doi&issn=17906295&contentId" target="_blank" class="highwire-permission-link link-icon"><span class="icon-copyright"></span> <span class="title">Reprints and Permissions</span></a> </div> </div> </div> </div> </div> <div class="content-right-wrapper content-column"> <div class="panel-panel panel-region-content-right"> <div class="inside"><div class="panel-pane pane-highwire-share-link highwire_clipboard_link_ajax" id="shareit"> <div class="pane-content"> <a href="/" class="link-icon"><span class="icon-share-alt"></span> <span class="title">Share</span></a> </div> </div> <div class="panel-pane pane-panels-mini pane-jnl-iiar-share highwire_clipboard_form_ajax_shareit" > <div class="pane-content"> <div class="panel-display panel-1col clearfix" id="mini-panel-jnl_iiar_share"> <div class="panel-panel panel-col"> <div><div class="panel-pane pane-highwire-article-citation large-margin-bottom" > <div class="pane-content"> <div class="highwire-article-citation highwire-citation-type-highwire-article node1056--3" data-node-nid="1056" id="share-node-1056--4585953759" data-pisa="cgp;15/1/41" data-pisa-master="cgp;15/1/41" data-apath="/cgp/15/1/41.atom"><div class="highwire-cite highwire-cite-highwire-article highwire-citation-jcore-standard clearfix"> <div class="highwire-cite-title">Applications of Support Vector Machine (SVM) Learning in Cancer Genomics</div> <div class="highwire-cite-authors"><span class="highwire-citation-authors"><span class="highwire-citation-author first" data-delta="0"><span class="nlm-given-names">SHUJUN</span> <span class="nlm-surname">HUANG</span></span>, <span class="highwire-citation-author" data-delta="1"><span class="nlm-given-names">NIANGUANG</span> <span class="nlm-surname">CAI</span></span>, <span class="highwire-citation-author" data-delta="2"><span class="nlm-given-names">PEDRO PENZUTI</span> <span class="nlm-surname">PACHECO</span></span>, <span class="highwire-citation-author" data-delta="3"><span class="nlm-given-names">SHAVIRA</span> <span class="nlm-surname">NARRANDES</span></span>, <span class="highwire-citation-author" data-delta="4"><span class="nlm-given-names">YANG</span> <span class="nlm-surname">WANG</span></span>, <span class="highwire-citation-author" data-delta="5"><span class="nlm-given-names">WAYNE</span> <span class="nlm-surname">XU</span></span></span></div> <div class="highwire-cite-metadata"><span class="highwire-cite-metadata-oa-ind highwire-cite-metadata"><i class="highwire-oa-indicator"></i> </span><span class="highwire-cite-metadata-journal highwire-cite-metadata">Cancer Genomics & Proteomics </span><span class="highwire-cite-metadata-date highwire-cite-metadata">Jan 2018, </span><span class="highwire-cite-metadata-volume highwire-cite-metadata">15 </span><span class="highwire-cite-metadata-issue highwire-cite-metadata">(1) </span><span class="highwire-cite-metadata-pages highwire-cite-metadata">41-51; </span></div> </div> </div> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-highwire-article-clipboard-copy large-margin-bottom" > <div class="pane-content"> <div class = "clipboard-copy"> <span class="label-url"> <label for="dynamic">Share This Article:</label> </span> <span class="input-text-url"> <input type="text" id="dynamic" value="https://cgp.iiarjournals.org/content/15/1/41" size="50"/> </span> <span class="copy-button button"> <button id="copy-dynamic" class="clipboardjs-button" data-clipboard-target="#dynamic" data-clipboard-alert-style="tooltip" data-clipboard-alert-text="Copied!">Copy</button> </span> </div> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-service-links" > <div class="pane-content"> <div class="service-links"><a href="https://twitter.com/share?url=https%3A//cgp.iiarjournals.org/content/15/1/41&text=Applications%20of%20Support%20Vector%20Machine%20%28SVM%29%20Learning%20in%20Cancer%20Genomics" id="twitter" title="Share this on Twitter" class="service-links-twitter" rel="nofollow" target="_blank" data-icon-position="" data-hide-link-title="0"><img src="https://cgp.iiarjournals.org/sites/all/modules/highwire/highwire/images/twitter.png" alt="Twitter logo" /></a> <a href="https://www.facebook.com/sharer.php?u=https%3A//cgp.iiarjournals.org/content/15/1/41&t=Applications%20of%20Support%20Vector%20Machine%20%28SVM%29%20Learning%20in%20Cancer%20Genomics" id="facebook" title="Share on Facebook" class="service-links-facebook" rel="nofollow" target="_blank" data-icon-position="" data-hide-link-title="0"><img src="https://cgp.iiarjournals.org/sites/all/modules/highwire/highwire/images/fb-blue.png" alt="Facebook logo" /></a> <a href="http://www.mendeley.com/import/?url=https%3A//cgp.iiarjournals.org/content/15/1/41&title=Applications%20of%20Support%20Vector%20Machine%20%28SVM%29%20Learning%20in%20Cancer%20Genomics" id="mendeley" title="Share on Mendeley" class="service-links-mendeley" rel="nofollow" target="_blank" data-icon-position="" data-hide-link-title="0"><img src="https://cgp.iiarjournals.org/sites/all/modules/highwire/highwire/images/mendeley.png" alt="Mendeley logo" /></a></div> </div> </div> </div> </div> </div> </div> </div> <div class="panel-pane pane-service-links" > <div class="pane-content"> <div class="service-links"><div class="item-list"><ul><li class="first"><a href="https://twitter.com/share?url=https%3A//cgp.iiarjournals.org/content/15/1/41&count=horizontal&via=&text=Applications%20of%20Support%20Vector%20Machine%20%28SVM%29%20Learning%20in%20Cancer%20Genomics&counturl=https%3A//cgp.iiarjournals.org/content/15/1/41" class="twitter-share-button service-links-twitter-widget" id="twitter_widget" title="Tweet This" rel="nofollow" target="_blank" data-icon-position="" data-hide-link-title="0"><span class="element-invisible">Tweet Widget</span></a></li><li><a href="https://www.facebook.com/plugins/like.php?href=https%3A//cgp.iiarjournals.org/content/15/1/41&layout=button_count&show_faces=false&action=like&colorscheme=light&width=100&height=21&font=&locale=" id="facebook_like" title="I Like it" class="service-links-facebook-like" rel="nofollow" target="_blank" data-icon-position="" data-hide-link-title="0"><span class="element-invisible">Facebook Like</span></a></li><li class="last"><a href="https://cgp.iiarjournals.org/content/15/1/41" id="google_plus_one" title="Plus it" class="service-links-google-plus-one" rel="nofollow" target="_blank" data-icon-position="" data-hide-link-title="0"><span class="element-invisible">Google Plus One</span></a></li></ul></div></div> </div> </div> </div> </div> </div> </div> <!-- /.panel-row-wrapper --> </div> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-highwire-article-nav mobile-hidden pane-style-alt-content" > <h2 class="pane-title">Jump to section</h2> <div class="pane-content"> <div class="highwire-list-wrapper highwire-article-nav highwire-nav-float"><div class="highwire-list"><ul data-highwire-float="1" data-highwire-float-class="grid-10 alpha omega"><li class="parent first odd"><a href="/content/15/1/41" class="highwire-article-nav-jumplink" data-panel-ajax-tab="jnl_iiar_tab_art" data-is-tab-link="true" data-icon-position="" data-hide-link-title="0">Article</a><div class="highwire-list"><ul><li class="first odd"><a href="#abstract-1" class="highwire-article-nav-jumplink first" data-panel-ajax-tab="jnl_iiar_tab_art" data-icon-position="" data-hide-link-title="0">Abstract</a></li><li class="even"><a href="#sec-1" class="highwire-article-nav-jumplink" data-panel-ajax-tab="jnl_iiar_tab_art" data-icon-position="" data-hide-link-title="0">SVM Model</a></li><li class="odd"><a href="#sec-2" class="highwire-article-nav-jumplink" data-panel-ajax-tab="jnl_iiar_tab_art" data-icon-position="" data-hide-link-title="0">Cancer Classification and Subtyping</a></li><li class="even"><a href="#sec-3" class="highwire-article-nav-jumplink" data-panel-ajax-tab="jnl_iiar_tab_art" data-icon-position="" data-hide-link-title="0">Biomarker/Signature Discovery</a></li><li class="odd"><a href="#sec-4" class="highwire-article-nav-jumplink" data-panel-ajax-tab="jnl_iiar_tab_art" data-icon-position="" data-hide-link-title="0">Drug Discovery for Cancer Therapy</a></li><li class="even"><a href="#sec-5" class="highwire-article-nav-jumplink" data-panel-ajax-tab="jnl_iiar_tab_art" data-icon-position="" data-hide-link-title="0">Cancer Driver Gene Discovery</a></li><li class="odd"><a href="#sec-6" class="highwire-article-nav-jumplink" data-panel-ajax-tab="jnl_iiar_tab_art" data-icon-position="" data-hide-link-title="0">Cancer Gene/Protein Interaction and Networks</a></li><li class="even"><a href="#sec-7" class="highwire-article-nav-jumplink" data-panel-ajax-tab="jnl_iiar_tab_art" data-icon-position="" data-hide-link-title="0">Perspective</a></li><li class="odd"><a href="#ack-1" class="highwire-article-nav-jumplink" data-panel-ajax-tab="jnl_iiar_tab_art" data-icon-position="" data-hide-link-title="0">Acknowledgements</a></li><li class="even"><a href="#fn-group-1" class="highwire-article-nav-jumplink" data-panel-ajax-tab="jnl_iiar_tab_art" data-icon-position="" data-hide-link-title="0">Footnotes</a></li><li class="last odd"><a href="#ref-list-1" class="highwire-article-nav-jumplink last" data-panel-ajax-tab="jnl_iiar_tab_art" data-icon-position="" data-hide-link-title="0">References</a></li></ul></div></li><li class="even"><a href="/content/15/1/41/tab-figures-data" class="highwire-article-nav-jumplink" data-panel-ajax-tab="jnl_iiar_tab_data" data-is-tab-link="true" data-icon-position="" data-hide-link-title="0">Figures & Data</a></li><li class="odd"><a href="/content/15/1/41/tab-article-info" class="highwire-article-nav-jumplink" data-panel-ajax-tab="jnl_iiar_tab_info" data-is-tab-link="true" data-icon-position="" data-hide-link-title="0">Info & Metrics</a></li><li class="last even"><a href="/content/15/1/41.full.pdf" class="highwire-article-nav-jumplink" data-icon-position="" data-hide-link-title="0"><i class="icon-file-alt"></i> PDF</a></li></ul></div></div> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-panels-mini pane-jnl-iiar-accordion" > <div class="pane-content"> <div class="panel-display panel-1col clearfix" id="mini-panel-jnl_iiar_accordion"> <div class="panel-panel panel-col"> <div><div id="highwire_article_accordion_container"><h3 ><i class="icon-caret-right"></i> Related Articles</h3><div><div class="highwire-list highwire-related-articles highwire-article-citation-list"><ul class="highwire-related-articles-list"><li class="first last odd"><div class="no-results">No related articles found.</div></li></ul></div><div class='highwire-list-footer'><div class="highwire-related-articles-footer"><ul class="links inline"><li class="related-pubmed first"><a href="/lookup/external-ref?link_type=MED_NBRS&access_num=29275361" target="_blank" class="" data-icon-position="" data-hide-link-title="0">PubMed</a></li><li class="related-google-scholar last"><a href="/lookup/google-scholar?link_type=googlescholar&gs_type=related&author%5B0%5D=SHUJUN%2BHUANG&author%5B1%5D=NIANGUANG%2BCAI&author%5B2%5D=PEDRO%2BPENZUTI%2BPACHECO&author%5B3%5D=SHAVIRA%2BNARRANDES&author%5B4%5D=YANG%2BWANG&author%5B5%5D=WAYNE%2BXU&title=Applications%2Bof%2BSupport%2BVector%2BMachine%2B%28SVM%29%2BLearning%2Bin%2BCancer%2BGenomics&publication_year=2017&path=content/15/1/41" target="_blank" class="" data-icon-position="" data-hide-link-title="0">Google Scholar</a></li></ul></div></div></div><h3 ><i class="icon-caret-right"></i> Cited By...</h3><div><div class="highwire-list highwire-cited-by"><ul><li class="first odd"><a href="http://medrxiv.org/cgi/content/full/2024.09.18.24313934v1" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Machine Learning and Bioinformatics Unravel Gene Signatures of Coronary Artery Disease Comorbidity with Periodontitis</div></a><div class="variant-links"></div></li><li class="even"><a href="http://biorxiv.org/cgi/content/full/2024.07.12.603253v1" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">A new alignment-free method: Subsequence Correlation Coefficient Vector(SCCFV) for influenza A comparison using virus genomes</div></a><div class="variant-links"></div></li><li class="odd"><a href="http://biorxiv.org/cgi/content/full/2024.06.21.600018v1" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Integrating Bioinformatics and Machine Learning to Investigate the Mechanisms by Which Three Major Respiratory Infectious Diseases Exacerbate Heart Failure</div></a><div class="variant-links"></div></li><li class="even"><a href="http://medrxiv.org/cgi/content/full/2024.03.12.24304158v2" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Gene Sequence to 2D Vector Transformation for Virus Classification</div></a><div class="variant-links"></div></li><li class="odd"><a href="http://biorxiv.org/cgi/content/full/2024.03.04.583279v1" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">SMOC2, OGN, FCN3, and SERPINA3 could be biomarkers for the evaluation of acute decompensated heart failure caused by venous congestion</div></a><div class="variant-links"></div></li><li class="even"><a href="http://biorxiv.org/cgi/content/full/2024.02.02.578674v1" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">DNA N-gram Analysis Framework (DNAnamer): A generalized N-gram frequency analysis framework for the supervised classification of DNA sequences</div></a><div class="variant-links"></div></li><li class="odd"><a href="http://biorxiv.org/cgi/content/full/2023.12.05.570061v1" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Identification and validation of aging-related genes in heart failure based on multiple machine learning algorithms</div></a><div class="variant-links"></div></li><li class="even"><a href="http://biorxiv.org/cgi/content/full/2023.12.05.570061v1" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Identification of immune-related genes for the diagnosis of ischaemic heart failure based on bioinformatics and three machine learning models</div></a><div class="variant-links"></div></li><li class="odd"><a href="https://cgp.iiarjournals.org/cgi/content/full/18/5/675" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">SOD2- and NRF2-associated Gene Signature to Predict Radioresistance in Head and Neck Cancer</div></a><div class="variant-links"></div></li><li class="even"><a href="http://biorxiv.org/cgi/content/full/2021.06.06.447291v2" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Combining Multi-Dimensional Molecular Fingerprints to Predict hERG Cardiotoxicity of Compounds</div></a><div class="variant-links"></div></li><li class="odd"><a href="http://biorxiv.org/cgi/content/full/2020.11.02.364612v1" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Do Support Vector Machines play a role in stratifying patient population based on cancer biomarkers?</div></a><div class="variant-links"></div></li><li class="even"><a href="http://bloodcancerdiscov.aacrjournals.org/cgi/content/full/1/3/244" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">PRPS-ST: A Protocol-Agnostic Self-training Method for Gene Expression-Based Classification of Blood Cancers</div></a><div class="variant-links"></div></li><li class="odd"><a href="http://biorxiv.org/cgi/content/full/2020.09.09.289413v1" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Machine learning-based investigation of the cancer protein secretory pathway</div></a><div class="variant-links"></div></li><li class="even"><a href="http://www.pnas.org/cgi/content/full/117/31/18869" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">A mechanism-aware and multiomic machine-learning pipeline characterizes yeast cell growth</div></a><div class="variant-links"></div></li><li class="odd"><a href="http://clincancerres.aacrjournals.org/cgi/content/full/26/10/2411" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Predicted Prognosis of Patients with Pancreatic Cancer by Machine Learning</div></a><div class="variant-links"></div></li><li class="even"><a href="http://biorxiv.org/cgi/content/full/2020.05.04.077263v1" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Fenchel duality of Cox partial likelihood and its application in survival kernel learning</div></a><div class="variant-links"></div></li><li class="odd"><a href="http://biorxiv.org/cgi/content/full/2020.04.28.051953v1" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Robust gene expression-based classification of cancers without normalization</div></a><div class="variant-links"></div></li><li class="even"><a href="http://ar.iiarjournals.org/cgi/content/full/40/1/271" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Prediction of Tumor Grade and Nodal Status in Oropharyngeal and Oral Cavity Squamous-cell Carcinoma Using a Radiomic Approach</div></a><div class="variant-links"></div></li><li class="odd"><a href="http://cancerimmunolres.aacrjournals.org/cgi/content/full/7/12/2065" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Tumor Immune Microenvironment and Chemosensitivity Signature for Predicting Response to Chemotherapy in Gastric Cancer</div></a><div class="variant-links"></div></li><li class="even"><a href="http://biorxiv.org/cgi/content/full/763722v2" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Software as a Service for the Genomic Prediction of Complex Diseases</div></a><div class="variant-links"></div></li><li class="odd"><a href="http://biorxiv.org/cgi/content/full/427716v3" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Uncertainty Reduction in Biochemical Kinetic Models: Enforcing Desired Model Properties</div></a><div class="variant-links"></div></li><li class="last even"><a href="http://biorxiv.org/cgi/content/full/618470v2" class="" data-icon-position="" data-hide-link-title="0"><div class="highwire-cite-title">Accurate ethnicity prediction from placental DNA methylation data</div></a><div class="variant-links"></div></li></ul></div><div class='highwire-list-footer'><ul class="links inline"><li class="citing-google-scholar first last"><a href="/lookup/google-scholar?link_type=googlescholar&gs_type=citedby&path=content/15/1/41" target="_blank" class="" data-icon-position="" data-hide-link-title="0">Google Scholar</a></li></ul></div></div><h3 ><i class="icon-caret-right"></i> Similar Articles</h3><div><div class="highwire-search-similar-ajax-wrapper" id="highwire-search-similar-articles-list-1"><div class="highwire-ajax-loading"><span class="icon-spinner icon-spin icon-2x"></span></div></div></div></div></div> </div> </div> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-highwire-term-full-title" > <h2 class="pane-title">Keywords</h2> <div class="pane-content"> <div class="highwire-list highwire-a-full-title"><ul class="field-items inline comma-separated"><li class="first odd"><a href="/keyword/machine-learning-ml" class="" data-icon-position="" data-hide-link-title="0"><span class="wrapper">Machine learning (ML)</span></a></li><li class="even"><a href="/keyword/support-vector-machine-svm" class="" data-icon-position="" data-hide-link-title="0"><span class="wrapper">support vector machine (SVM)</span></a></li><li class="odd"><a href="/keyword/classifier" class="" data-icon-position="" data-hide-link-title="0"><span class="wrapper">classifier</span></a></li><li class="even"><a href="/keyword/genomics" class="" data-icon-position="" data-hide-link-title="0"><span class="wrapper">Genomics</span></a></li><li class="odd"><a href="/keyword/kernel-function" class="" data-icon-position="" data-hide-link-title="0"><span class="wrapper">kernel function</span></a></li><li class="even"><a href="/keyword/gene-expression" class="" data-icon-position="" data-hide-link-title="0"><span class="wrapper">gene expression</span></a></li><li class="odd"><a href="/keyword/cancer-classification" class="" data-icon-position="" data-hide-link-title="0"><span class="wrapper">cancer classification</span></a></li><li class="even"><a href="/keyword/gene-selection" class="" data-icon-position="" data-hide-link-title="0"><span class="wrapper">gene selection</span></a></li><li class="odd"><a href="/keyword/biomarker-discovery" class="" data-icon-position="" data-hide-link-title="0"><span class="wrapper">biomarker discovery</span></a></li><li class="even"><a href="/keyword/drug-discovery" class="" data-icon-position="" data-hide-link-title="0"><span class="wrapper">drug discovery</span></a></li><li class="odd"><a href="/keyword/driver-gene" class="" data-icon-position="" data-hide-link-title="0"><span class="wrapper">driver gene</span></a></li><li class="even"><a href="/keyword/gene-gene-interaction" class="" data-icon-position="" data-hide-link-title="0"><span class="wrapper">gene-gene interaction</span></a></li><li class="last odd"><a href="/keyword/review" class="" data-icon-position="" data-hide-link-title="0"><span class="wrapper">review</span></a></li></ul></div> </div> </div> </div> </div> </div> </div> <!-- /.panel-row-wrapper --> </div> </div> </div> </div> </div> </div> </div> </section> <footer id="section-footer" class="section section-footer"> <div id="zone-footer" class="zone zone-footer clearfix container-30"> <div class="grid-28 suffix-1 prefix-1 region region-footer-first" id="region-footer-first"> <div class="region-inner region-footer-first-inner"> <div class="block block-panels-mini block-jnl-iiar-foot-info block-panels-mini-jnl-iiar-foot-info odd block-without-title" id="block-panels-mini-jnl-iiar-foot-info"> <div class="block-inner clearfix"> <div class="content clearfix"> <div class="panel-display panel-1col clearfix" id="mini-panel-jnl_iiar_foot_info"> <div class="panel-panel panel-col"> <div><div class="panel-pane pane-page-logo-footer" > <div class="pane-content"> <a href="/" class="linked-footer-logo active" data-icon-position="" data-hide-link-title="0"><img class="footer-logo" src="https://cgp.iiarjournals.org/sites/default/files/cgp-footer.png" width="600" height="36" alt="Cancer & Genome Proteomics" /></a> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-snippet pane-footer-copyright-text" > <div class="pane-content"> <div class="snippet footer-copyright-text" id="footer-copyright-text"> <div class="snippet-content"> <p>© 2024 Cancer Genomics & Proteomics</p> </div> </div> </div> </div> <div class="panel-separator"></div><div class="panel-pane pane-highwire-branding" > <div class="pane-content"> <a href="http://home.highwire.org" target="_blank" class="highwire-branding-link" data-icon-position="" data-hide-link-title="0"><img class="logo-highwire" src="https://cgp.iiarjournals.org/sites/all/modules/highwire/highwire/plugins/content_types/images/logo_small_hw_white.png" width="190" height="31" alt="Powered by HighWire" /></a> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> </div> </footer> </div> <div class="region region-page-bottom" id="region-page-bottom"> <div class="region-inner region-page-bottom-inner"> </div> </div><script type="text/javascript" src="/sites/default/files/advagg_js/js__LtnZ2PfApHDX23zxvARCG6h4ZaGtZCtIQI8G3skp9b4__GiiLfqWJC_yQYyAdigtc349YMNPfD3Uo1FENI4atQFc__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.js"></script> <script type="text/javascript" src="/sites/default/files/advagg_js/js__2WRbxlwOW0MEUc_hSWU5MBepQg6Lch6O5SZwefpJ6IE__HCL0YQJqLkOhrLPZZYGqosGvtFsEHMGghHIkSx4y9vA__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.js" defer="defer"></script> <script type="text/javascript" src="/sites/default/files/advagg_js/js__KK031NUSBfj3AOaMahsv5az44nEsBflLrGvUJDWj6T0__EZST6aelnPpZzrIvwteTv45QmGBTO_doYUJ6tHOHsW8__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.js"></script> <script type="text/javascript" src="/sites/default/files/advagg_js/js__Jd5dsvNznZMdglFu8sSni1wCsUfzvQbApHPAZwt5TY4__65Mqa1DMRwcSvPxjJEn6BXgMm-ckF3oOvkUTG9HRADI__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.js" defer="defer"></script> <script type="text/javascript" src="/sites/default/files/advagg_js/js__WcTpt-w0y1FyXrxZNriX8Ts1KjsFTDpdvZaw9yhRn24__aFJpdvsZPb1v9rWrq-WXbz_WQ9IThQN-mFTCdm1cfXc__BUE-77oZ9b7ju8egUDRLeURapp069HUD6yhoj0q3uMw.js"></script> <script type="text/javascript"> <!--//--><![CDATA[//><!-- function euCookieComplianceLoadScripts() {} //--><!]]> </script> <script type="text/javascript"> <!--//--><![CDATA[//><!-- var eu_cookie_compliance_cookie_name = ""; //--><!]]> </script> </body> </html>