Search | arXiv e-print repository

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"/> <meta name="viewport" content="width=device-width, initial-scale=1"/>  <link rel="apple-touch-icon" sizes="180x180" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/apple-touch-icon.png"> <link rel="icon" type="image/png" sizes="32x32" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-32x32.png"> <link rel="icon" type="image/png" sizes="16x16" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon-16x16.png"> <link rel="manifest" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/site.webmanifest"> <link rel="mask-icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/safari-pinned-tab.svg" color="#b31b1b"> <link rel="shortcut icon" href="https://static.arxiv.org/static/base/1.0.0a5/images/icons/favicon.ico"> <meta name="msapplication-TileColor" content="#b31b1b"> <meta name="msapplication-config" content="images/icons/browserconfig.xml"> <meta name="theme-color" content="#b31b1b">  <title>Search | arXiv e-print repository</title> <script defer src="https://static.arxiv.org/static/base/1.0.0a5/fontawesome-free-5.11.2-web/js/all.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/base/1.0.0a5/css/arxivstyle.css" /> <script type="text/x-mathjax-config"> MathJax.Hub.Config({ messageStyle: "none", extensions: ["tex2jax.js"], jax: ["input/TeX", "output/HTML-CSS"], tex2jax: { inlineMath: [ ['$','$'], ["\$","\$"] ], displayMath: [ ['$$','$$'], ["\\[","\\]"] ], processEscapes: true, ignoreClass: '.*', processClass: 'mathjax.*' }, TeX: { extensions: ["AMSmath.js", "AMSsymbols.js", "noErrors.js"], noErrors: { inlineDelimiters: ["$","$"], multiLine: false, style: { "font-size": "normal", "border": "" } } }, "HTML-CSS": { availableFonts: ["TeX"] } }); </script> <script src='//static.arxiv.org/MathJax-2.7.3/MathJax.js'></script> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/notification.js"></script> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/bulma-tooltip.min.css" /> <link rel="stylesheet" href="https://static.arxiv.org/static/search/0.5.6/css/search.css" /> <script src="https://code.jquery.com/jquery-3.2.1.slim.min.js" integrity="sha256-k2WSCIexGzOj3Euiig+TlR8gA0EmPjuc79OEeY5L45g=" crossorigin="anonymous"></script> <script src="https://static.arxiv.org/static/search/0.5.6/js/fieldset.js"></script> <style> radio#cf-customfield_11400 { display: none; } </style> </head> <body> <header><a href="#main-container" class="is-sr-only">Skip to main content</a>  <div class="attribution level is-marginless" role="banner"> <div class="level-left"> <a class="level-item" href="https://cornell.edu/"><img src="https://static.arxiv.org/static/base/1.0.0a5/images/cornell-reduced-white-SMALL.svg" alt="Cornell University" width="200" aria-label="logo" /></a> </div> <div class="level-right is-marginless"><p class="sponsors level-item is-marginless"><span id="support-ack-url">We gratefully acknowledge support from<br /> the Simons Foundation, <a href="https://info.arxiv.org/about/ourmembers.html">member institutions</a>, and all contributors. <a href="https://info.arxiv.org/about/donate.html">Donate</a></span></p></div> </div>  <div class="identity level is-marginless"> <div class="level-left"> <div class="level-item"> <a class="arxiv" href="https://arxiv.org/" aria-label="arxiv-logo"> <img src="https://static.arxiv.org/static/base/1.0.0a5/images/arxiv-logo-one-color-white.svg" aria-label="logo" alt="arxiv logo" width="85" style="width:85px;"/> </a> </div> </div> <div class="search-block level-right"> <form class="level-item mini-search" method="GET" action="https://arxiv.org/search"> <div class="field has-addons"> <div class="control"> <input class="input is-small" type="text" name="query" placeholder="Search..." aria-label="Search term or terms" /> <p class="help"><a href="https://info.arxiv.org/help">Help</a> | <a href="https://arxiv.org/search/advanced">Advanced Search</a></p> </div> <div class="control"> <div class="select is-small"> <select name="searchtype" aria-label="Field to search"> <option value="all" selected="selected">All fields</option> <option value="title">Title</option> <option value="author">Author</option> <option value="abstract">Abstract</option> <option value="comments">Comments</option> <option value="journal_ref">Journal reference</option> <option value="acm_class">ACM classification</option> <option value="msc_class">MSC classification</option> <option value="report_num">Report number</option> <option value="paper_id">arXiv identifier</option> <option value="doi">DOI</option> <option value="orcid">ORCID</option> <option value="author_id">arXiv author ID</option> <option value="help">Help pages</option> <option value="full_text">Full text</option> </select> </div> </div> <input type="hidden" name="source" value="header"> <button class="button is-small is-cul-darker">Search</button> </div> </form> </div> </div>  <div class="container"> <div class="user-tools is-size-7 has-text-right has-text-weight-bold" role="navigation" aria-label="User menu"> <a href="https://arxiv.org/login">Login</a> </div> </div> </header> <main class="container" id="main-container"> <div class="level is-marginless"> <div class="level-left"> <h1 class="title is-clearfix"> Showing 1–28 of 28 results for author: <span class="mathjax">Zitnik, M</span> </h1> </div> <div class="level-right is-hidden-mobile">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> <div class="content"> <form method="GET" action="/search/q-bio" aria-role="search"> Searching in archive <strong>q-bio</strong>. <a href="/search/?searchtype=author&query=Zitnik%2C+M">Search in all archives.</a> <div class="field has-addons-tablet"> <div class="control is-expanded"> <label for="query" class="hidden-label">Search term or terms</label> <input class="input is-medium" id="query" name="query" placeholder="Search term..." type="text" value="Zitnik, M"> </div> <div class="select control is-medium"> <label class="is-hidden" for="searchtype">Field</label> <select class="is-medium" id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> </div> <div class="control"> <button class="button is-link is-medium">Search</button> </div> </div> <div class="field"> <div class="control is-size-7"> <label class="radio"> <input checked id="abstracts-0" name="abstracts" type="radio" value="show"> Show abstracts </label> <label class="radio"> <input id="abstracts-1" name="abstracts" type="radio" value="hide"> Hide abstracts </label> </div> </div> <div class="is-clearfix" style="height: 2.5em"> <div class="is-pulled-right"> <a href="/search/advanced?terms-0-term=Zitnik%2C+M&terms-0-field=author&size=50&order=-announced_date_first">Advanced Search</a> </div> </div> <input type="hidden" name="order" value="-announced_date_first"> <input type="hidden" name="size" value="50"> </form> <div class="level breathe-horizontal"> <div class="level-left"> <form method="GET" action="/search/"> <div style="display: none;"> <select id="searchtype" name="searchtype"><option value="all">All fields</option><option value="title">Title</option><option selected value="author">Author(s)</option><option value="abstract">Abstract</option><option value="comments">Comments</option><option value="journal_ref">Journal reference</option><option value="acm_class">ACM classification</option><option value="msc_class">MSC classification</option><option value="report_num">Report number</option><option value="paper_id">arXiv identifier</option><option value="doi">DOI</option><option value="orcid">ORCID</option><option value="license">License (URI)</option><option value="author_id">arXiv author ID</option><option value="help">Help pages</option><option value="full_text">Full text</option></select> <input id="query" name="query" type="text" value="Zitnik, M"> <ul id="abstracts"><li><input checked id="abstracts-0" name="abstracts" type="radio" value="show"> <label for="abstracts-0">Show abstracts</label></li><li><input id="abstracts-1" name="abstracts" type="radio" value="hide"> <label for="abstracts-1">Hide abstracts</label></li></ul> </div> <div class="box field is-grouped is-grouped-multiline level-item"> <div class="control"> <span class="select is-small"> <select id="size" name="size"><option value="25">25</option><option selected value="50">50</option><option value="100">100</option><option value="200">200</option></select> </span> <label for="size">results per page</label>. </div> <div class="control"> <label for="order">Sort results by</label> <span class="select is-small"> <select id="order" name="order"><option selected value="-announced_date_first">Announcement date (newest first)</option><option value="announced_date_first">Announcement date (oldest first)</option><option value="-submitted_date">Submission date (newest first)</option><option value="submitted_date">Submission date (oldest first)</option><option value="">Relevance</option></select> </span> </div> <div class="control"> <button class="button is-small is-link">Go</button> </div> </div> </form> </div> </div> <ol class="breathe-horizontal" start="1"> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2502.03569">arXiv:2502.03569</a> <span> [<a href="https://arxiv.org/pdf/2502.03569">pdf</a>, <a href="https://arxiv.org/format/2502.03569">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Genomics">q-bio.GN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Populations and Evolution">q-bio.PE</span> </div> </div> <p class="title is-5 mathjax"> Controllable Sequence Editing for Counterfactual Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Li%2C+M+M">Michelle M. Li</a>, <a href="/search/q-bio?searchtype=author&query=Li%2C+K">Kevin Li</a>, <a href="/search/q-bio?searchtype=author&query=Ektefaie%2C+Y">Yasha Ektefaie</a>, <a href="/search/q-bio?searchtype=author&query=Messica%2C+S">Shvat Messica</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2502.03569v1-abstract-short" style="display: inline;"> Sequence models generate counterfactuals by modifying parts of a sequence based on a given condition, enabling reasoning about "what if" scenarios. While these models excel at conditional generation, they lack fine-grained control over when and where edits occur. Existing approaches either focus on univariate sequences or assume that interventions affect the entire sequence globally. However, many… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.03569v1-abstract-full').style.display = 'inline'; document.getElementById('2502.03569v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.03569v1-abstract-full" style="display: none;"> Sequence models generate counterfactuals by modifying parts of a sequence based on a given condition, enabling reasoning about "what if" scenarios. While these models excel at conditional generation, they lack fine-grained control over when and where edits occur. Existing approaches either focus on univariate sequences or assume that interventions affect the entire sequence globally. However, many applications require precise, localized modifications, where interventions take effect only after a specified time and impact only a subset of co-occurring variables. We introduce CLEF, a controllable sequence editing model for counterfactual reasoning about both immediate and delayed effects. CLEF learns temporal concepts that encode how and when interventions should influence a sequence. With these concepts, CLEF selectively edits relevant time steps while preserving unaffected portions of the sequence. We evaluate CLEF on cellular and patient trajectory datasets, where gene regulation affects only certain genes at specific time steps, or medical interventions alter only a subset of lab measurements. CLEF improves immediate sequence editing by up to 36.01% in MAE compared to baselines. Unlike prior methods, CLEF enables one-step generation of counterfactual sequences at any future time step, outperforming baselines by up to 65.71% in MAE. A case study on patients with type 1 diabetes mellitus shows that CLEF identifies clinical interventions that shift patient trajectories toward healthier outcomes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.03569v1-abstract-full').style.display = 'none'; document.getElementById('2502.03569v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.10720">arXiv:2411.10720</a> <span> [<a href="https://arxiv.org/pdf/2411.10720">pdf</a>, <a href="https://arxiv.org/format/2411.10720">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> </div> </div> <p class="title is-5 mathjax"> Multi Scale Graph Neural Network for Alzheimer's Disease </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Chauhan%2C+A">Anya Chauhan</a>, <a href="/search/q-bio?searchtype=author&query=Noori%2C+A">Ayush Noori</a>, <a href="/search/q-bio?searchtype=author&query=Li%2C+Z">Zhaozhi Li</a>, <a href="/search/q-bio?searchtype=author&query=He%2C+Y">Yingnan He</a>, <a href="/search/q-bio?searchtype=author&query=Li%2C+M+M">Michelle M Li</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Das%2C+S">Sudeshna Das</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2411.10720v1-abstract-short" style="display: inline;"> Alzheimer's disease (AD) is a complex, progressive neurodegenerative disorder characterized by extracellular A\b{eta} plaques, neurofibrillary tau tangles, glial activation, and neuronal degeneration, involving multiple cell types and pathways. Current models often overlook the cellular context of these pathways. To address this, we developed a multiscale graph neural network (GNN) model, ALZ PINN… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10720v1-abstract-full').style.display = 'inline'; document.getElementById('2411.10720v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.10720v1-abstract-full" style="display: none;"> Alzheimer's disease (AD) is a complex, progressive neurodegenerative disorder characterized by extracellular A\b{eta} plaques, neurofibrillary tau tangles, glial activation, and neuronal degeneration, involving multiple cell types and pathways. Current models often overlook the cellular context of these pathways. To address this, we developed a multiscale graph neural network (GNN) model, ALZ PINNACLE, using brain omics data from donors spanning the entire aging to AD spectrum. ALZ PINNACLE is based on the PINNACLE GNN framework, which learns context-aware protein, cell type, and tissue representations within a unified latent space. ALZ PINNACLE was trained on 14,951 proteins, 206,850 protein interactions, 7 cell types, and 48 cell subtypes or states. After pretraining, we investigated the learned embedding of APOE, the largest genetic risk factor for AD, across different cell types. Notably, APOE embeddings showed high similarity in microglial, neuronal, and CD8 cells, suggesting a similar role of APOE in these cell types. Fine tuning the model on AD risk genes revealed cell type contexts predictive of the role of APOE in AD. Our results suggest that ALZ PINNACLE may provide a valuable framework for uncovering novel insights into AD neurobiology. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.10720v1-abstract-full').style.display = 'none'; document.getElementById('2411.10720v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Findings paper presented at Machine Learning for Health (ML4H) symposium 2024, December 15-16, 2024, Vancouver, Canada, 9 pages</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2410.20354">arXiv:2410.20354</a> <span> [<a href="https://arxiv.org/pdf/2410.20354">pdf</a>, <a href="https://arxiv.org/format/2410.20354">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cryptography and Security">cs.CR</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Biomolecules">q-bio.BM</span> </div> </div> <p class="title is-5 mathjax"> FoldMark: Protecting Protein Generative Models with Watermarking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zaixi Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Jin%2C+R">Ruofan Jin</a>, <a href="/search/q-bio?searchtype=author&query=Fu%2C+K">Kaidi Fu</a>, <a href="/search/q-bio?searchtype=author&query=Cong%2C+L">Le Cong</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Wang%2C+M">Mengdi Wang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2410.20354v4-abstract-short" style="display: inline;"> Protein structure is key to understanding protein function and is essential for progress in bioengineering, drug discovery, and molecular biology. Recently, with the incorporation of generative AI, the power and accuracy of computational protein structure prediction/design have been improved significantly. However, ethical concerns such as copyright protection and harmful content generation (biose… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20354v4-abstract-full').style.display = 'inline'; document.getElementById('2410.20354v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.20354v4-abstract-full" style="display: none;"> Protein structure is key to understanding protein function and is essential for progress in bioengineering, drug discovery, and molecular biology. Recently, with the incorporation of generative AI, the power and accuracy of computational protein structure prediction/design have been improved significantly. However, ethical concerns such as copyright protection and harmful content generation (biosecurity) pose challenges to the wide implementation of protein generative models. Here, we investigate whether it is possible to embed watermarks into protein generative models and their outputs for copyright authentication and the tracking of generated structures. As a proof of concept, we propose a two-stage method FoldMark as a generalized watermarking strategy for protein generative models. FoldMark first pretrain watermark encoder and decoder, which can minorly adjust protein structures to embed user-specific information and faithfully recover the information from the encoded structure. In the second step, protein generative models are fine-tuned with watermark-conditioned Low-Rank Adaptation (LoRA) modules to preserve generation quality while learning to generate watermarked structures with high recovery rates. Extensive experiments are conducted on open-source protein structure prediction models (e.g., ESMFold and MultiFlow) and de novo structure design models (e.g., FrameDiff and FoldFlow) and we demonstrate that our method is effective across all these generative models. Meanwhile, our watermarking framework only exerts a negligible impact on the original protein structure quality and is robust under potential post-processing and adaptive attacks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.20354v4-abstract-full').style.display = 'none'; document.getElementById('2410.20354v4-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 27 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.19520">arXiv:2409.19520</a> <span> [<a href="https://arxiv.org/pdf/2409.19520">pdf</a>, <a href="https://arxiv.org/format/2409.19520">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Biomolecules">q-bio.BM</span> </div> </div> <p class="title is-5 mathjax"> Generalized Protein Pocket Generation with Prior-Informed Flow Matching </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zaixi Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Liu%2C+Q">Qi Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.19520v1-abstract-short" style="display: inline;"> Designing ligand-binding proteins, such as enzymes and biosensors, is essential in bioengineering and protein biology. One critical step in this process involves designing protein pockets, the protein interface binding with the ligand. Current approaches to pocket generation often suffer from time-intensive physical computations or template-based methods, as well as compromised generation quality… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19520v1-abstract-full').style.display = 'inline'; document.getElementById('2409.19520v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.19520v1-abstract-full" style="display: none;"> Designing ligand-binding proteins, such as enzymes and biosensors, is essential in bioengineering and protein biology. One critical step in this process involves designing protein pockets, the protein interface binding with the ligand. Current approaches to pocket generation often suffer from time-intensive physical computations or template-based methods, as well as compromised generation quality due to the overlooking of domain knowledge. To tackle these challenges, we propose PocketFlow, a generative model that incorporates protein-ligand interaction priors based on flow matching. During training, PocketFlow learns to model key types of protein-ligand interactions, such as hydrogen bonds. In the sampling, PocketFlow leverages multi-granularity guidance (overall binding affinity and interaction geometry constraints) to facilitate generating high-affinity and valid pockets. Extensive experiments show that PocketFlow outperforms baselines on multiple benchmarks, e.g., achieving an average improvement of 1.29 in Vina Score and 0.05 in scRMSD. Moreover, modeling interactions make PocketFlow a generalized generative model across multiple ligand modalities, including small molecules, peptides, and RNA. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19520v1-abstract-full').style.display = 'none'; document.getElementById('2409.19520v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted by NeurIPS 2024 as Spotlight</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.11654">arXiv:2409.11654</a> <span> [<a href="https://arxiv.org/pdf/2409.11654">pdf</a>, <a href="https://arxiv.org/format/2409.11654">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</span> </div> </div> <p class="title is-5 mathjax"> How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Bunne%2C+C">Charlotte Bunne</a>, <a href="/search/q-bio?searchtype=author&query=Roohani%2C+Y">Yusuf Roohani</a>, <a href="/search/q-bio?searchtype=author&query=Rosen%2C+Y">Yanay Rosen</a>, <a href="/search/q-bio?searchtype=author&query=Gupta%2C+A">Ankit Gupta</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+X">Xikun Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Roed%2C+M">Marcel Roed</a>, <a href="/search/q-bio?searchtype=author&query=Alexandrov%2C+T">Theo Alexandrov</a>, <a href="/search/q-bio?searchtype=author&query=AlQuraishi%2C+M">Mohammed AlQuraishi</a>, <a href="/search/q-bio?searchtype=author&query=Brennan%2C+P">Patricia Brennan</a>, <a href="/search/q-bio?searchtype=author&query=Burkhardt%2C+D+B">Daniel B. Burkhardt</a>, <a href="/search/q-bio?searchtype=author&query=Califano%2C+A">Andrea Califano</a>, <a href="/search/q-bio?searchtype=author&query=Cool%2C+J">Jonah Cool</a>, <a href="/search/q-bio?searchtype=author&query=Dernburg%2C+A+F">Abby F. Dernburg</a>, <a href="/search/q-bio?searchtype=author&query=Ewing%2C+K">Kirsty Ewing</a>, <a href="/search/q-bio?searchtype=author&query=Fox%2C+E+B">Emily B. Fox</a>, <a href="/search/q-bio?searchtype=author&query=Haury%2C+M">Matthias Haury</a>, <a href="/search/q-bio?searchtype=author&query=Herr%2C+A+E">Amy E. Herr</a>, <a href="/search/q-bio?searchtype=author&query=Horvitz%2C+E">Eric Horvitz</a>, <a href="/search/q-bio?searchtype=author&query=Hsu%2C+P+D">Patrick D. Hsu</a>, <a href="/search/q-bio?searchtype=author&query=Jain%2C+V">Viren Jain</a>, <a href="/search/q-bio?searchtype=author&query=Johnson%2C+G+R">Gregory R. Johnson</a>, <a href="/search/q-bio?searchtype=author&query=Kalil%2C+T">Thomas Kalil</a>, <a href="/search/q-bio?searchtype=author&query=Kelley%2C+D+R">David R. Kelley</a>, <a href="/search/q-bio?searchtype=author&query=Kelley%2C+S+O">Shana O. Kelley</a>, <a href="/search/q-bio?searchtype=author&query=Kreshuk%2C+A">Anna Kreshuk</a> , et al. (17 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2409.11654v2-abstract-short" style="display: inline;"> The cell is arguably the most fundamental unit of life and is central to understanding biology. Accurate modeling of cells is important for this understanding as well as for determining the root causes of disease. Recent advances in artificial intelligence (AI), combined with the ability to generate large-scale experimental data, present novel opportunities to model cells. Here we propose a vision… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.11654v2-abstract-full').style.display = 'inline'; document.getElementById('2409.11654v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.11654v2-abstract-full" style="display: none;"> The cell is arguably the most fundamental unit of life and is central to understanding biology. Accurate modeling of cells is important for this understanding as well as for determining the root causes of disease. Recent advances in artificial intelligence (AI), combined with the ability to generate large-scale experimental data, present novel opportunities to model cells. Here we propose a vision of leveraging advances in AI to construct virtual cells, high-fidelity simulations of cells and cellular systems under different conditions that are directly learned from biological data across measurements and scales. We discuss desired capabilities of such AI Virtual Cells, including generating universal representations of biological entities across scales, and facilitating interpretable in silico experiments to predict and understand their behavior using virtual instruments. We further address the challenges, opportunities and requirements to realize this vision including data needs, evaluation strategies, and community standards and engagement to ensure biological accuracy and broad utility. We envision a future where AI Virtual Cells help identify new drug targets, predict cellular responses to perturbations, as well as scale hypothesis exploration. With open science collaborations across the biomedical ecosystem that includes academia, philanthropy, and the biopharma and AI industries, a comprehensive predictive understanding of cell mechanisms and interactions has come into reach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.11654v2-abstract-full').style.display = 'none'; document.getElementById('2409.11654v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 17 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2408.13479">arXiv:2408.13479</a> <span> [<a href="https://arxiv.org/pdf/2408.13479">pdf</a>, <a href="https://arxiv.org/format/2408.13479">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantum Physics">quant-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Biomolecules">q-bio.BM</span> </div> </div> <p class="title is-5 mathjax"> Quantum-machine-assisted Drug Discovery: Survey and Perspective </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhou%2C+Y">Yidong Zhou</a>, <a href="/search/q-bio?searchtype=author&query=Chen%2C+J">Jintai Chen</a>, <a href="/search/q-bio?searchtype=author&query=Cheng%2C+J">Jinglei Cheng</a>, <a href="/search/q-bio?searchtype=author&query=Karemore%2C+G">Gopal Karemore</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Chong%2C+F+T">Frederic T. Chong</a>, <a href="/search/q-bio?searchtype=author&query=Liu%2C+J">Junyu Liu</a>, <a href="/search/q-bio?searchtype=author&query=Fu%2C+T">Tianfan Fu</a>, <a href="/search/q-bio?searchtype=author&query=Liang%2C+Z">Zhiding Liang</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2408.13479v3-abstract-short" style="display: inline;"> Drug discovery and development is a highly complex and costly endeavor, typically requiring over a decade and substantial financial investment to bring a new drug to market. Traditional computer-aided drug design (CADD) has made significant progress in accelerating this process, but the development of quantum computing offers potential due to its unique capabilities. This paper discusses the integ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13479v3-abstract-full').style.display = 'inline'; document.getElementById('2408.13479v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.13479v3-abstract-full" style="display: none;"> Drug discovery and development is a highly complex and costly endeavor, typically requiring over a decade and substantial financial investment to bring a new drug to market. Traditional computer-aided drug design (CADD) has made significant progress in accelerating this process, but the development of quantum computing offers potential due to its unique capabilities. This paper discusses the integration of quantum computing into drug discovery and development, focusing on how quantum technologies might accelerate and enhance various stages of the drug development cycle. Specifically, we explore the application of quantum computing in addressing challenges related to drug discovery, such as molecular simulation and the prediction of drug-target interactions, as well as the optimization of clinical trial outcomes. By leveraging the inherent capabilities of quantum computing, we might be able to reduce the time and cost associated with bringing new drugs to market, ultimately benefiting public health. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.13479v3-abstract-full').style.display = 'none'; document.getElementById('2408.13479v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 September, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 24 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">27 pages, 10 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.03403">arXiv:2406.03403</a> <span> [<a href="https://arxiv.org/pdf/2406.03403">pdf</a>, <a href="https://arxiv.org/format/2406.03403">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> </div> </div> <p class="title is-5 mathjax"> Structure-based Drug Design Benchmark: Do 3D Methods Really Dominate? </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zheng%2C+K">Kangyu Zheng</a>, <a href="/search/q-bio?searchtype=author&query=Lu%2C+Y">Yingzhou Lu</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zaixi Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Wan%2C+Z">Zhongwei Wan</a>, <a href="/search/q-bio?searchtype=author&query=Ma%2C+Y">Yao Ma</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Fu%2C+T">Tianfan Fu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2406.03403v1-abstract-short" style="display: inline;"> Currently, the field of structure-based drug design is dominated by three main types of algorithms: search-based algorithms, deep generative models, and reinforcement learning. While existing works have typically focused on comparing models within a single algorithmic category, cross-algorithm comparisons remain scarce. In this paper, to fill the gap, we establish a benchmark to evaluate the perfo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.03403v1-abstract-full').style.display = 'inline'; document.getElementById('2406.03403v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.03403v1-abstract-full" style="display: none;"> Currently, the field of structure-based drug design is dominated by three main types of algorithms: search-based algorithms, deep generative models, and reinforcement learning. While existing works have typically focused on comparing models within a single algorithmic category, cross-algorithm comparisons remain scarce. In this paper, to fill the gap, we establish a benchmark to evaluate the performance of sixteen models across these different algorithmic foundations by assessing the pharmaceutical properties of the generated molecules and their docking affinities with specified target proteins. We highlight the unique advantages of each algorithmic approach and offer recommendations for the design of future SBDD models. We emphasize that 1D/2D ligand-centric drug design methods can be used in SBDD by treating the docking function as a black-box oracle, which is typically neglected. The empirical results show that 1D/2D methods achieve competitive performance compared with 3D-based methods that use the 3D structure of the target protein explicitly. Also, AutoGrow4, a 2D molecular graph-based genetic algorithm, dominates SBDD in terms of optimization ability. The relevant code is available in https://github.com/zkysfls/2024-sbdd-benchmark. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.03403v1-abstract-full').style.display = 'none'; document.getElementById('2406.03403v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 4 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2310.02553">arXiv:2310.02553</a> <span> [<a href="https://arxiv.org/pdf/2310.02553">pdf</a>, <a href="https://arxiv.org/format/2310.02553">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Biomolecules">q-bio.BM</span> </div> </div> <p class="title is-5 mathjax"> Full-Atom Protein Pocket Design via Iterative Refinement </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zaixi Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Lu%2C+Z">Zepu Lu</a>, <a href="/search/q-bio?searchtype=author&query=Hao%2C+Z">Zhongkai Hao</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Liu%2C+Q">Qi Liu</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2310.02553v2-abstract-short" style="display: inline;"> The design of \emph{de novo} functional proteins that bind specific ligand molecules is paramount in therapeutics and bio-engineering. A critical yet formidable task in this endeavor is the design of the protein pocket, which is the cavity region of the protein where the ligand binds. Current methods are plagued by inefficient generation, inadequate context modeling of the ligand molecule, and the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.02553v2-abstract-full').style.display = 'inline'; document.getElementById('2310.02553v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2310.02553v2-abstract-full" style="display: none;"> The design of \emph{de novo} functional proteins that bind specific ligand molecules is paramount in therapeutics and bio-engineering. A critical yet formidable task in this endeavor is the design of the protein pocket, which is the cavity region of the protein where the ligand binds. Current methods are plagued by inefficient generation, inadequate context modeling of the ligand molecule, and the inability to generate side-chain atoms. Here, we present the Full-Atom Iterative Refinement (FAIR) method, designed to address these challenges by facilitating the co-design of protein pocket sequences, specifically residue types, and their corresponding 3D structures. FAIR operates in two steps, proceeding in a coarse-to-fine manner (transitioning from protein backbone to atoms, including side chains) for a full-atom generation. In each iteration, all residue types and structures are simultaneously updated, a process termed full-shot refinement. In the initial stage, the residue types and backbone coordinates are refined using a hierarchical context encoder, complemented by two structure refinement modules that capture both inter-residue and pocket-ligand interactions. The subsequent stage delves deeper, modeling the side-chain atoms of the pockets and updating residue types to ensure sequence-structure congruence. Concurrently, the structure of the binding ligand is refined across iterations to accommodate its inherent flexibility. Comprehensive experiments show that FAIR surpasses existing methods in designing superior pocket sequences and structures, producing average improvement exceeding 10\% in AAR and RMSD metrics. FAIR is available at \url{https://github.com/zaixizhang/FAIR}. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2310.02553v2-abstract-full').style.display = 'none'; document.getElementById('2310.02553v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 19 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 3 October, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">NeurIPS 2023 Spotlight</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2309.08478">arXiv:2309.08478</a> <span> [<a href="https://arxiv.org/pdf/2309.08478">pdf</a>, <a href="https://arxiv.org/format/2309.08478">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Molecular Networks">q-bio.MN</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1093/bioadv/vbae099">10.1093/bioadv/vbae099 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Current and future directions in network biology </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Li%2C+M+M">Michelle M. Li</a>, <a href="/search/q-bio?searchtype=author&query=Wells%2C+A">Aydin Wells</a>, <a href="/search/q-bio?searchtype=author&query=Glass%2C+K">Kimberly Glass</a>, <a href="/search/q-bio?searchtype=author&query=Gysi%2C+D+M">Deisy Morselli Gysi</a>, <a href="/search/q-bio?searchtype=author&query=Krishnan%2C+A">Arjun Krishnan</a>, <a href="/search/q-bio?searchtype=author&query=Murali%2C+T+M">T. M. Murali</a>, <a href="/search/q-bio?searchtype=author&query=Radivojac%2C+P">Predrag Radivojac</a>, <a href="/search/q-bio?searchtype=author&query=Roy%2C+S">Sushmita Roy</a>, <a href="/search/q-bio?searchtype=author&query=Baudot%2C+A">Ana茂s Baudot</a>, <a href="/search/q-bio?searchtype=author&query=Bozdag%2C+S">Serdar Bozdag</a>, <a href="/search/q-bio?searchtype=author&query=Chen%2C+D+Z">Danny Z. Chen</a>, <a href="/search/q-bio?searchtype=author&query=Cowen%2C+L">Lenore Cowen</a>, <a href="/search/q-bio?searchtype=author&query=Devkota%2C+K">Kapil Devkota</a>, <a href="/search/q-bio?searchtype=author&query=Gitter%2C+A">Anthony Gitter</a>, <a href="/search/q-bio?searchtype=author&query=Gosline%2C+S">Sara Gosline</a>, <a href="/search/q-bio?searchtype=author&query=Gu%2C+P">Pengfei Gu</a>, <a href="/search/q-bio?searchtype=author&query=Guzzi%2C+P+H">Pietro H. Guzzi</a>, <a href="/search/q-bio?searchtype=author&query=Huang%2C+H">Heng Huang</a>, <a href="/search/q-bio?searchtype=author&query=Jiang%2C+M">Meng Jiang</a>, <a href="/search/q-bio?searchtype=author&query=Kesimoglu%2C+Z+N">Ziynet Nesibe Kesimoglu</a>, <a href="/search/q-bio?searchtype=author&query=Koyuturk%2C+M">Mehmet Koyuturk</a>, <a href="/search/q-bio?searchtype=author&query=Ma%2C+J">Jian Ma</a>, <a href="/search/q-bio?searchtype=author&query=Pico%2C+A+R">Alexander R. Pico</a>, <a href="/search/q-bio?searchtype=author&query=Pr%C5%BEulj%2C+N">Nata拧a Pr啪ulj</a> , et al. (12 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2309.08478v2-abstract-short" style="display: inline;"> Network biology is an interdisciplinary field bridging computational and biological sciences that has proved pivotal in advancing the understanding of cellular functions and diseases across biological systems and scales. Although the field has been around for two decades, it remains nascent. It has witnessed rapid evolution, accompanied by emerging challenges. These challenges stem from various fa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.08478v2-abstract-full').style.display = 'inline'; document.getElementById('2309.08478v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2309.08478v2-abstract-full" style="display: none;"> Network biology is an interdisciplinary field bridging computational and biological sciences that has proved pivotal in advancing the understanding of cellular functions and diseases across biological systems and scales. Although the field has been around for two decades, it remains nascent. It has witnessed rapid evolution, accompanied by emerging challenges. These challenges stem from various factors, notably the growing complexity and volume of data together with the increased diversity of data types describing different tiers of biological organization. We discuss prevailing research directions in network biology and highlight areas of inference and comparison of biological networks, multimodal data integration and heterogeneous networks, higher-order network analysis, machine learning on networks, and network-based personalized medicine. Following the overview of recent breakthroughs across these five areas, we offer a perspective on the future directions of network biology. Additionally, we offer insights into scientific communities, educational initiatives, and the importance of fostering diversity within the field. This paper establishes a roadmap for an immediate and long-term vision for network biology. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2309.08478v2-abstract-full').style.display = 'none'; document.getElementById('2309.08478v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">52 pages, 6 figures, 1 table</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.11768">arXiv:2306.11768</a> <span> [<a href="https://arxiv.org/pdf/2306.11768">pdf</a>, <a href="https://arxiv.org/format/2306.11768">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Geometric Deep Learning for Structure-Based Drug Design: A Survey </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zaixi Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Yan%2C+J">Jiaxian Yan</a>, <a href="/search/q-bio?searchtype=author&query=Huang%2C+Y">Yining Huang</a>, <a href="/search/q-bio?searchtype=author&query=Liu%2C+Q">Qi Liu</a>, <a href="/search/q-bio?searchtype=author&query=Chen%2C+E">Enhong Chen</a>, <a href="/search/q-bio?searchtype=author&query=Wang%2C+M">Mengdi Wang</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2306.11768v6-abstract-short" style="display: inline;"> Structure-based drug design (SBDD) leverages the three-dimensional geometry of proteins to identify potential drug candidates. Traditional approaches, rooted in physicochemical modeling and domain expertise, are often resource-intensive. Recent advancements in geometric deep learning, which effectively integrate and process 3D geometric data, alongside breakthroughs in accurate protein structure p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.11768v6-abstract-full').style.display = 'inline'; document.getElementById('2306.11768v6-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.11768v6-abstract-full" style="display: none;"> Structure-based drug design (SBDD) leverages the three-dimensional geometry of proteins to identify potential drug candidates. Traditional approaches, rooted in physicochemical modeling and domain expertise, are often resource-intensive. Recent advancements in geometric deep learning, which effectively integrate and process 3D geometric data, alongside breakthroughs in accurate protein structure predictions from tools like AlphaFold, have significantly propelled the field forward. This paper systematically reviews the state-of-the-art in geometric deep learning for SBDD. We begin by outlining foundational tasks in SBDD, discussing prevalent 3D protein representations, and highlighting representative predictive and generative models. Next, we provide an in-depth review of key tasks, including binding site prediction, binding pose generation, de novo molecule generation, linker design, protein pocket generation, and binding affinity prediction. For each task, we present formal problem definitions, key methods, datasets, evaluation metrics, and performance benchmarks. Lastly, we explore current challenges and future opportunities in SBDD. Challenges include oversimplified problem formulations, limited out-of-distribution generalization, biosecurity concerns related to the misuse of structural data, insufficient evaluation metrics and large-scale benchmarks, and the need for experimental validation and enhanced model interpretability. Opportunities lie in leveraging multimodal datasets, integrating domain knowledge, developing comprehensive benchmarks, establishing criteria aligned with clinical outcomes, and designing foundation models to expand the scope of design tasks. We also curate \url{https://github.com/zaixizhang/Awesome-SBDD}, reflecting ongoing contributions and new datasets in SBDD. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.11768v6-abstract-full').style.display = 'none'; document.getElementById('2306.11768v6-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 15 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 June, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">28 pages, under review</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.12582">arXiv:2112.12582</a> <span> [<a href="https://arxiv.org/pdf/2112.12582">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Other Quantitative Biology">q-bio.OT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Beyond Low Earth Orbit: Biological Research, Artificial Intelligence, and Self-Driving Labs </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Sanders%2C+L+M">Lauren M. Sanders</a>, <a href="/search/q-bio?searchtype=author&query=Yang%2C+J+H">Jason H. Yang</a>, <a href="/search/q-bio?searchtype=author&query=Scott%2C+R+T">Ryan T. Scott</a>, <a href="/search/q-bio?searchtype=author&query=Qutub%2C+A+A">Amina Ann Qutub</a>, <a href="/search/q-bio?searchtype=author&query=Martin%2C+H+G">Hector Garcia Martin</a>, <a href="/search/q-bio?searchtype=author&query=Berrios%2C+D+C">Daniel C. Berrios</a>, <a href="/search/q-bio?searchtype=author&query=Hastings%2C+J+J+A">Jaden J. A. Hastings</a>, <a href="/search/q-bio?searchtype=author&query=Rask%2C+J">Jon Rask</a>, <a href="/search/q-bio?searchtype=author&query=Mackintosh%2C+G">Graham Mackintosh</a>, <a href="/search/q-bio?searchtype=author&query=Hoarfrost%2C+A+L">Adrienne L. Hoarfrost</a>, <a href="/search/q-bio?searchtype=author&query=Chalk%2C+S">Stuart Chalk</a>, <a href="/search/q-bio?searchtype=author&query=Kalantari%2C+J">John Kalantari</a>, <a href="/search/q-bio?searchtype=author&query=Khezeli%2C+K">Kia Khezeli</a>, <a href="/search/q-bio?searchtype=author&query=Antonsen%2C+E+L">Erik L. Antonsen</a>, <a href="/search/q-bio?searchtype=author&query=Babdor%2C+J">Joel Babdor</a>, <a href="/search/q-bio?searchtype=author&query=Barker%2C+R">Richard Barker</a>, <a href="/search/q-bio?searchtype=author&query=Baranzini%2C+S+E">Sergio E. Baranzini</a>, <a href="/search/q-bio?searchtype=author&query=Beheshti%2C+A">Afshin Beheshti</a>, <a href="/search/q-bio?searchtype=author&query=Delgado-Aparicio%2C+G+M">Guillermo M. Delgado-Aparicio</a>, <a href="/search/q-bio?searchtype=author&query=Glicksberg%2C+B+S">Benjamin S. Glicksberg</a>, <a href="/search/q-bio?searchtype=author&query=Greene%2C+C+S">Casey S. Greene</a>, <a href="/search/q-bio?searchtype=author&query=Haendel%2C+M">Melissa Haendel</a>, <a href="/search/q-bio?searchtype=author&query=Hamid%2C+A+A">Arif A. Hamid</a>, <a href="/search/q-bio?searchtype=author&query=Heller%2C+P">Philip Heller</a>, <a href="/search/q-bio?searchtype=author&query=Jamieson%2C+D">Daniel Jamieson</a> , et al. (31 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2112.12582v1-abstract-short" style="display: inline;"> Space biology research aims to understand fundamental effects of spaceflight on organisms, develop foundational knowledge to support deep space exploration, and ultimately bioengineer spacecraft and habitats to stabilize the ecosystem of plants, crops, microbes, animals, and humans for sustained multi-planetary life. To advance these aims, the field leverages experiments, platforms, data, and mode… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.12582v1-abstract-full').style.display = 'inline'; document.getElementById('2112.12582v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.12582v1-abstract-full" style="display: none;"> Space biology research aims to understand fundamental effects of spaceflight on organisms, develop foundational knowledge to support deep space exploration, and ultimately bioengineer spacecraft and habitats to stabilize the ecosystem of plants, crops, microbes, animals, and humans for sustained multi-planetary life. To advance these aims, the field leverages experiments, platforms, data, and model organisms from both spaceborne and ground-analog studies. As research is extended beyond low Earth orbit, experiments and platforms must be maximally autonomous, light, agile, and intelligent to expedite knowledge discovery. Here we present a summary of recommendations from a workshop organized by the National Aeronautics and Space Administration on artificial intelligence, machine learning, and modeling applications which offer key solutions toward these space biology challenges. In the next decade, the synthesis of artificial intelligence into the field of space biology will deepen the biological understanding of spaceflight effects, facilitate predictive modeling and analytics, support maximally autonomous and reproducible experiments, and efficiently manage spaceborne data and metadata, all with the goal to enable life to thrive in deep space. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.12582v1-abstract-full').style.display = 'none'; document.getElementById('2112.12582v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">28 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2112.12554">arXiv:2112.12554</a> <span> [<a href="https://arxiv.org/pdf/2112.12554">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Other Quantitative Biology">q-bio.OT</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Beyond Low Earth Orbit: Biomonitoring, Artificial Intelligence, and Precision Space Health </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Scott%2C+R+T">Ryan T. Scott</a>, <a href="/search/q-bio?searchtype=author&query=Antonsen%2C+E+L">Erik L. Antonsen</a>, <a href="/search/q-bio?searchtype=author&query=Sanders%2C+L+M">Lauren M. Sanders</a>, <a href="/search/q-bio?searchtype=author&query=Hastings%2C+J+J+A">Jaden J. A. Hastings</a>, <a href="/search/q-bio?searchtype=author&query=Park%2C+S">Seung-min Park</a>, <a href="/search/q-bio?searchtype=author&query=Mackintosh%2C+G">Graham Mackintosh</a>, <a href="/search/q-bio?searchtype=author&query=Reynolds%2C+R+J">Robert J. Reynolds</a>, <a href="/search/q-bio?searchtype=author&query=Hoarfrost%2C+A+L">Adrienne L. Hoarfrost</a>, <a href="/search/q-bio?searchtype=author&query=Sawyer%2C+A">Aenor Sawyer</a>, <a href="/search/q-bio?searchtype=author&query=Greene%2C+C+S">Casey S. Greene</a>, <a href="/search/q-bio?searchtype=author&query=Glicksberg%2C+B+S">Benjamin S. Glicksberg</a>, <a href="/search/q-bio?searchtype=author&query=Theriot%2C+C+A">Corey A. Theriot</a>, <a href="/search/q-bio?searchtype=author&query=Berrios%2C+D+C">Daniel C. Berrios</a>, <a href="/search/q-bio?searchtype=author&query=Miller%2C+J">Jack Miller</a>, <a href="/search/q-bio?searchtype=author&query=Babdor%2C+J">Joel Babdor</a>, <a href="/search/q-bio?searchtype=author&query=Barker%2C+R">Richard Barker</a>, <a href="/search/q-bio?searchtype=author&query=Baranzini%2C+S+E">Sergio E. Baranzini</a>, <a href="/search/q-bio?searchtype=author&query=Beheshti%2C+A">Afshin Beheshti</a>, <a href="/search/q-bio?searchtype=author&query=Chalk%2C+S">Stuart Chalk</a>, <a href="/search/q-bio?searchtype=author&query=Delgado-Aparicio%2C+G+M">Guillermo M. Delgado-Aparicio</a>, <a href="/search/q-bio?searchtype=author&query=Haendel%2C+M">Melissa Haendel</a>, <a href="/search/q-bio?searchtype=author&query=Hamid%2C+A+A">Arif A. Hamid</a>, <a href="/search/q-bio?searchtype=author&query=Heller%2C+P">Philip Heller</a>, <a href="/search/q-bio?searchtype=author&query=Jamieson%2C+D">Daniel Jamieson</a>, <a href="/search/q-bio?searchtype=author&query=Jarvis%2C+K+J">Katelyn J. Jarvis</a> , et al. (31 additional authors not shown) </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2112.12554v1-abstract-short" style="display: inline;"> Human space exploration beyond low Earth orbit will involve missions of significant distance and duration. To effectively mitigate myriad space health hazards, paradigm shifts in data and space health systems are necessary to enable Earth-independence, rather than Earth-reliance. Promising developments in the fields of artificial intelligence and machine learning for biology and health can address… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.12554v1-abstract-full').style.display = 'inline'; document.getElementById('2112.12554v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2112.12554v1-abstract-full" style="display: none;"> Human space exploration beyond low Earth orbit will involve missions of significant distance and duration. To effectively mitigate myriad space health hazards, paradigm shifts in data and space health systems are necessary to enable Earth-independence, rather than Earth-reliance. Promising developments in the fields of artificial intelligence and machine learning for biology and health can address these needs. We propose an appropriately autonomous and intelligent Precision Space Health system that will monitor, aggregate, and assess biomedical statuses; analyze and predict personalized adverse health outcomes; adapt and respond to newly accumulated data; and provide preventive, actionable, and timely insights to individual deep space crew members and iterative decision support to their crew medical officer. Here we present a summary of recommendations from a workshop organized by the National Aeronautics and Space Administration, on future applications of artificial intelligence in space biology and health. In the next decade, biomonitoring technology, biomarker science, spacecraft hardware, intelligent software, and streamlined data management must mature and be woven together into a Precision Space Health system to enable humanity to thrive in deep space. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2112.12554v1-abstract-full').style.display = 'none'; document.getElementById('2112.12554v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 22 December, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">31 pages, 4 figures</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2111.06247">arXiv:2111.06247</a> <span> [<a href="https://arxiv.org/pdf/2111.06247">pdf</a>, <a href="https://arxiv.org/format/2111.06247">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Genomics">q-bio.GN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Molecular Networks">q-bio.MN</span> </div> </div> <p class="title is-5 mathjax"> Sparse dictionary learning recovers pleiotropy from human cell fitness screens </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Pan%2C+J">Joshua Pan</a>, <a href="/search/q-bio?searchtype=author&query=Kwon%2C+J+J">Jason J. Kwon</a>, <a href="/search/q-bio?searchtype=author&query=Talamas%2C+J+A">Jessica A. Talamas</a>, <a href="/search/q-bio?searchtype=author&query=Borah%2C+A+A">Ashir A. Borah</a>, <a href="/search/q-bio?searchtype=author&query=Vazquez%2C+F">Francisca Vazquez</a>, <a href="/search/q-bio?searchtype=author&query=Boehm%2C+J+S">Jesse S. Boehm</a>, <a href="/search/q-bio?searchtype=author&query=Tsherniak%2C+A">Aviad Tsherniak</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=McFarland%2C+J+M">James M. McFarland</a>, <a href="/search/q-bio?searchtype=author&query=Hahn%2C+W+C">William C. Hahn</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2111.06247v1-abstract-short" style="display: inline;"> In high-throughput functional genomic screens, each gene product is commonly assumed to exhibit a singular biological function within a defined protein complex or pathway. In practice, a single gene perturbation may induce multiple cascading functional outcomes, a genetic principle known as pleiotropy. Here, we model pleiotropy in fitness screen collections by representing each gene perturbation a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.06247v1-abstract-full').style.display = 'inline'; document.getElementById('2111.06247v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2111.06247v1-abstract-full" style="display: none;"> In high-throughput functional genomic screens, each gene product is commonly assumed to exhibit a singular biological function within a defined protein complex or pathway. In practice, a single gene perturbation may induce multiple cascading functional outcomes, a genetic principle known as pleiotropy. Here, we model pleiotropy in fitness screen collections by representing each gene perturbation as the sum of multiple perturbations of biological functions, each harboring independent fitness effects inferred empirically from the data. Our approach ('Webster') recovered pleiotropic functions for DNA damage proteins from genotoxic fitness screens, untangled distinct signaling pathways upstream of shared effector proteins from cancer cell fitness screens, and learned aspects of the cellular hierarchy in an unsupervised manner. Modeling compound sensitivity profiles in terms of genetically defined functions recovered compound mechanisms of action. Our approach establishes a sparse approximation mechanism for unraveling complex genetic architectures underlying high-dimensional gene perturbation readouts. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2111.06247v1-abstract-full').style.display = 'none'; document.getElementById('2111.06247v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 11 November, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to the 16th Machine Learning in Computational Biology (MLCB) meeting 2021, and the Learning Meaningful Representations of Life (LMRL) Workshop at NeurIPS 2021</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2106.02246">arXiv:2106.02246</a> <span> [<a href="https://arxiv.org/pdf/2106.02246">pdf</a>, <a href="https://arxiv.org/format/2106.02246">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Molecular Networks">q-bio.MN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Tissues and Organs">q-bio.TO</span> </div> </div> <p class="title is-5 mathjax"> Deep Contextual Learners for Protein Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Li%2C+M+M">Michelle M. Li</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2106.02246v2-abstract-short" style="display: inline;"> Spatial context is central to understanding health and disease. Yet reference protein interaction networks lack such contextualization, thereby limiting the study of where protein interactions likely occur in the human body and how they may be altered in disease. Contextualized protein interactions could better characterize genes with disease-specific interactions and elucidate diseases' manifesta… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.02246v2-abstract-full').style.display = 'inline'; document.getElementById('2106.02246v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.02246v2-abstract-full" style="display: none;"> Spatial context is central to understanding health and disease. Yet reference protein interaction networks lack such contextualization, thereby limiting the study of where protein interactions likely occur in the human body and how they may be altered in disease. Contextualized protein interactions could better characterize genes with disease-specific interactions and elucidate diseases' manifestation in specific cell types. Here, we introduce AWARE, a graph neural message passing approach to inject cellular and tissue context into protein embeddings. AWARE optimizes for a multi-scale embedding space, whose structure reflects network topology at a single-cell resolution. We construct a multi-scale network of the Human Cell Atlas and apply AWARE to learn protein, cell type, and tissue embeddings that uphold cell type and tissue hierarchies. We demonstrate AWARE's utility on the novel task of predicting whether a protein is altered in disease and where that association most likely manifests in the human body. To this end, AWARE outperforms generic embeddings without contextual information by at least 12.5%, showing AWARE's potential to reveal context-dependent roles of proteins in disease. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.02246v2-abstract-full').style.display = 'none'; document.getElementById('2106.02246v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 16 July, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Accepted to the 2021 International Conference on Machine Learning (ICML) Workshop on Computational Biology (WCB)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2104.04883">arXiv:2104.04883</a> <span> [<a href="https://arxiv.org/pdf/2104.04883">pdf</a>, <a href="https://arxiv.org/format/2104.04883">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Biomolecules">q-bio.BM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Genomics">q-bio.GN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Molecular Networks">q-bio.MN</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1038/s41551-022-00942-x">10.1038/s41551-022-00942-x <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Graph Representation Learning in Biomedicine </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Li%2C+M+M">Michelle M. Li</a>, <a href="/search/q-bio?searchtype=author&query=Huang%2C+K">Kexin Huang</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2104.04883v3-abstract-short" style="display: inline;"> Biomedical networks (or graphs) are universal descriptors for systems of interacting elements, from molecular interactions and disease co-morbidity to healthcare systems and scientific knowledge. Advances in artificial intelligence, specifically deep learning, have enabled us to model, analyze, and learn with such networked data. In this review, we put forward an observation that long-standing pri… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.04883v3-abstract-full').style.display = 'inline'; document.getElementById('2104.04883v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2104.04883v3-abstract-full" style="display: none;"> Biomedical networks (or graphs) are universal descriptors for systems of interacting elements, from molecular interactions and disease co-morbidity to healthcare systems and scientific knowledge. Advances in artificial intelligence, specifically deep learning, have enabled us to model, analyze, and learn with such networked data. In this review, we put forward an observation that long-standing principles of systems biology and medicine -- while often unspoken in machine learning research -- provide the conceptual grounding for representation learning on graphs, explain its current successes and limitations, and even inform future advancements. We synthesize a spectrum of algorithmic approaches that, at their core, leverage graph topology to embed networks into compact vector spaces. We also capture the breadth of ways in which representation learning has dramatically improved the state-of-the-art in biomedical machine learning. Exemplary domains covered include identifying variants underlying complex traits, disentangling behaviors of single cells and their effects on health, assisting in diagnosis and treatment of patients, and developing safe and effective medicines. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2104.04883v3-abstract-full').style.display = 'none'; document.getElementById('2104.04883v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 June, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 April, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2102.09548">arXiv:2102.09548</a> <span> [<a href="https://arxiv.org/pdf/2102.09548">pdf</a>, <a href="https://arxiv.org/format/2102.09548">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computers and Society">cs.CY</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Biomolecules">q-bio.BM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> </div> </div> <p class="title is-5 mathjax"> Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Huang%2C+K">Kexin Huang</a>, <a href="/search/q-bio?searchtype=author&query=Fu%2C+T">Tianfan Fu</a>, <a href="/search/q-bio?searchtype=author&query=Gao%2C+W">Wenhao Gao</a>, <a href="/search/q-bio?searchtype=author&query=Zhao%2C+Y">Yue Zhao</a>, <a href="/search/q-bio?searchtype=author&query=Roohani%2C+Y">Yusuf Roohani</a>, <a href="/search/q-bio?searchtype=author&query=Leskovec%2C+J">Jure Leskovec</a>, <a href="/search/q-bio?searchtype=author&query=Coley%2C+C+W">Connor W. Coley</a>, <a href="/search/q-bio?searchtype=author&query=Xiao%2C+C">Cao Xiao</a>, <a href="/search/q-bio?searchtype=author&query=Sun%2C+J">Jimeng Sun</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2102.09548v2-abstract-short" style="display: inline;"> Therapeutics machine learning is an emerging field with incredible opportunities for innovatiaon and impact. However, advancement in this field requires formulation of meaningful learning tasks and careful curation of datasets. Here, we introduce Therapeutics Data Commons (TDC), the first unifying platform to systematically access and evaluate machine learning across the entire range of therapeuti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.09548v2-abstract-full').style.display = 'inline'; document.getElementById('2102.09548v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2102.09548v2-abstract-full" style="display: none;"> Therapeutics machine learning is an emerging field with incredible opportunities for innovatiaon and impact. However, advancement in this field requires formulation of meaningful learning tasks and careful curation of datasets. Here, we introduce Therapeutics Data Commons (TDC), the first unifying platform to systematically access and evaluate machine learning across the entire range of therapeutics. To date, TDC includes 66 AI-ready datasets spread across 22 learning tasks and spanning the discovery and development of safe and effective medicines. TDC also provides an ecosystem of tools and community resources, including 33 data functions and types of meaningful data splits, 23 strategies for systematic model evaluation, 17 molecule generation oracles, and 29 public leaderboards. All resources are integrated and accessible via an open Python library. We carry out extensive experiments on selected datasets, demonstrating that even the strongest algorithms fall short of solving key therapeutics challenges, including real dataset distributional shifts, multi-scale modeling of heterogeneous data, and robust generalization to novel data points. We envision that TDC can facilitate algorithmic and scientific advances and considerably accelerate machine-learning model development, validation and transition into biomedical and clinical implementation. TDC is an open-science initiative available at https://tdcommons.ai. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2102.09548v2-abstract-full').style.display = 'none'; document.getElementById('2102.09548v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 August, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 February, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published at NeurIPS 2021 Datasets and Benchmarks</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2010.03951">arXiv:2010.03951</a> <span> [<a href="https://arxiv.org/pdf/2010.03951">pdf</a>, <a href="https://arxiv.org/format/2010.03951">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Human-Computer Interaction">cs.HC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> MolDesigner: Interactive Design of Efficacious Drugs with Deep Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Huang%2C+K">Kexin Huang</a>, <a href="/search/q-bio?searchtype=author&query=Fu%2C+T">Tianfan Fu</a>, <a href="/search/q-bio?searchtype=author&query=Khan%2C+D">Dawood Khan</a>, <a href="/search/q-bio?searchtype=author&query=Abid%2C+A">Ali Abid</a>, <a href="/search/q-bio?searchtype=author&query=Abdalla%2C+A">Ali Abdalla</a>, <a href="/search/q-bio?searchtype=author&query=Abid%2C+A">Abubakar Abid</a>, <a href="/search/q-bio?searchtype=author&query=Glass%2C+L+M">Lucas M. Glass</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Xiao%2C+C">Cao Xiao</a>, <a href="/search/q-bio?searchtype=author&query=Sun%2C+J">Jimeng Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2010.03951v1-abstract-short" style="display: inline;"> The efficacy of a drug depends on its binding affinity to the therapeutic target and pharmacokinetics. Deep learning (DL) has demonstrated remarkable progress in predicting drug efficacy. We develop MolDesigner, a human-in-the-loop web user-interface (UI), to assist drug developers leverage DL predictions to design more effective drugs. A developer can draw a drug molecule in the interface. In the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.03951v1-abstract-full').style.display = 'inline'; document.getElementById('2010.03951v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2010.03951v1-abstract-full" style="display: none;"> The efficacy of a drug depends on its binding affinity to the therapeutic target and pharmacokinetics. Deep learning (DL) has demonstrated remarkable progress in predicting drug efficacy. We develop MolDesigner, a human-in-the-loop web user-interface (UI), to assist drug developers leverage DL predictions to design more effective drugs. A developer can draw a drug molecule in the interface. In the backend, more than 17 state-of-the-art DL models generate predictions on important indices that are crucial for a drug's efficacy. Based on these predictions, drug developers can edit the drug molecule and reiterate until satisfaction. MolDesigner can make predictions in real-time with a latency of less than a second. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.03951v1-abstract-full').style.display = 'none'; document.getElementById('2010.03951v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 5 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">NeurIPS 2020 Demonstration Track</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2004.14949">arXiv:2004.14949</a> <span> [<a href="https://arxiv.org/pdf/2004.14949">pdf</a>, <a href="https://arxiv.org/format/2004.14949">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Molecular Networks">q-bio.MN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Huang%2C+K">Kexin Huang</a>, <a href="/search/q-bio?searchtype=author&query=Xiao%2C+C">Cao Xiao</a>, <a href="/search/q-bio?searchtype=author&query=Glass%2C+L">Lucas Glass</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Sun%2C+J">Jimeng Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2004.14949v2-abstract-short" style="display: inline;"> Molecular interaction networks are powerful resources for the discovery. They are increasingly used with machine learning methods to predict biologically meaningful interactions. While deep learning on graphs has dramatically advanced the prediction prowess, current graph neural network (GNN) methods are optimized for prediction on the basis of direct similarity between interacting nodes. In biolo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.14949v2-abstract-full').style.display = 'inline'; document.getElementById('2004.14949v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2004.14949v2-abstract-full" style="display: none;"> Molecular interaction networks are powerful resources for the discovery. They are increasingly used with machine learning methods to predict biologically meaningful interactions. While deep learning on graphs has dramatically advanced the prediction prowess, current graph neural network (GNN) methods are optimized for prediction on the basis of direct similarity between interacting nodes. In biological networks, however, similarity between nodes that do not directly interact has proved incredibly useful in the last decade across a variety of interaction networks. Here, we present SkipGNN, a graph neural network approach for the prediction of molecular interactions. SkipGNN predicts molecular interactions by not only aggregating information from direct interactions but also from second-order interactions, which we call skip similarity. In contrast to existing GNNs, SkipGNN receives neural messages from two-hop neighbors as well as immediate neighbors in the interaction network and non-linearly transforms the messages to obtain useful information for prediction. To inject skip similarity into a GNN, we construct a modified version of the original network, called the skip graph. We then develop an iterative fusion scheme that optimizes a GNN using both the skip graph and the original graph. Experiments on four interaction networks, including drug-drug, drug-target, protein-protein, and gene-disease interactions, show that SkipGNN achieves superior and robust performance, outperforming existing methods by up to 28.8\% of area under the precision recall curve (PR-AUC). Furthermore, we show that unlike popular GNNs, SkipGNN learns biologically meaningful embeddings and performs especially well on noisy, incomplete interaction networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.14949v2-abstract-full').style.display = 'none'; document.getElementById('2004.14949v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in Nature Scientific Reports: https://www.nature.com/articles/s41598-020-77766-9</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2004.08919">arXiv:2004.08919</a> <span> [<a href="https://arxiv.org/pdf/2004.08919">pdf</a>, <a href="https://arxiv.org/format/2004.08919">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1093/bioinformatics/btaa1005">10.1093/bioinformatics/btaa1005 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> DeepPurpose: a Deep Learning Library for Drug-Target Interaction Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Huang%2C+K">Kexin Huang</a>, <a href="/search/q-bio?searchtype=author&query=Fu%2C+T">Tianfan Fu</a>, <a href="/search/q-bio?searchtype=author&query=Glass%2C+L">Lucas Glass</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Xiao%2C+C">Cao Xiao</a>, <a href="/search/q-bio?searchtype=author&query=Sun%2C+J">Jimeng Sun</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2004.08919v3-abstract-short" style="display: inline;"> Accurate prediction of drug-target interactions (DTI) is crucial for drug discovery. Recently, deep learning (DL) models for show promising performance for DTI prediction. However, these models can be difficult to use for both computer scientists entering the biomedical field and bioinformaticians with limited DL experience. We present DeepPurpose, a comprehensive and easy-to-use deep learning lib… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.08919v3-abstract-full').style.display = 'inline'; document.getElementById('2004.08919v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2004.08919v3-abstract-full" style="display: none;"> Accurate prediction of drug-target interactions (DTI) is crucial for drug discovery. Recently, deep learning (DL) models for show promising performance for DTI prediction. However, these models can be difficult to use for both computer scientists entering the biomedical field and bioinformaticians with limited DL experience. We present DeepPurpose, a comprehensive and easy-to-use deep learning library for DTI prediction. DeepPurpose supports training of customized DTI prediction models by implementing 15 compound and protein encoders and over 50 neural architectures, along with providing many other useful features. We demonstrate state-of-the-art performance of DeepPurpose on several benchmark datasets. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.08919v3-abstract-full').style.display = 'none'; document.getElementById('2004.08919v3-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 December, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 19 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2020. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Published in Bioinformatics (2020)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2004.07229">arXiv:2004.07229</a> <span> [<a href="https://arxiv.org/pdf/2004.07229">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Molecular Networks">q-bio.MN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1073/pnas.2025581118">10.1073/pnas.2025581118 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Network Medicine Framework for Identifying Drug Repurposing Opportunities for COVID-19 </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Gysi%2C+D+M">Deisy Morselli Gysi</a>, <a href="/search/q-bio?searchtype=author&query=Valle%2C+%C3%8D+D">脥talo Do Valle</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Ameli%2C+A">Asher Ameli</a>, <a href="/search/q-bio?searchtype=author&query=Gan%2C+X">Xiao Gan</a>, <a href="/search/q-bio?searchtype=author&query=Varol%2C+O">Onur Varol</a>, <a href="/search/q-bio?searchtype=author&query=Ghiassian%2C+S+D">Susan Dina Ghiassian</a>, <a href="/search/q-bio?searchtype=author&query=Patten%2C+J">JJ Patten</a>, <a href="/search/q-bio?searchtype=author&query=Davey%2C+R">Robert Davey</a>, <a href="/search/q-bio?searchtype=author&query=Loscalzo%2C+J">Joseph Loscalzo</a>, <a href="/search/q-bio?searchtype=author&query=Barab%C3%A1si%2C+A">Albert-L谩szl贸 Barab谩si</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="2004.07229v2-abstract-short" style="display: inline;"> The current pandemic has highlighted the need for methodologies that can quickly and reliably prioritize clinically approved compounds for their potential effectiveness for SARS-CoV-2 infections. In the past decade, network medicine has developed and validated multiple predictive algorithms for drug repurposing, exploiting the sub-cellular network-based relationship between a drug's targets and di… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.07229v2-abstract-full').style.display = 'inline'; document.getElementById('2004.07229v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2004.07229v2-abstract-full" style="display: none;"> The current pandemic has highlighted the need for methodologies that can quickly and reliably prioritize clinically approved compounds for their potential effectiveness for SARS-CoV-2 infections. In the past decade, network medicine has developed and validated multiple predictive algorithms for drug repurposing, exploiting the sub-cellular network-based relationship between a drug's targets and disease genes. Here, we deployed algorithms relying on artificial intelligence, network diffusion, and network proximity, tasking each of them to rank 6,340 drugs for their expected efficacy against SARS-CoV-2. To test the predictions, we used as ground truth 918 drugs that had been experimentally screened in VeroE6 cells, and the list of drugs under clinical trial, that capture the medical community's assessment of drugs with potential COVID-19 efficacy. We find that while most algorithms offer predictive power for these ground truth data, no single method offers consistently reliable outcomes across all datasets and metrics. This prompted us to develop a multimodal approach that fuses the predictions of all algorithms, showing that a consensus among the different predictive methods consistently exceeds the performance of the best individual pipelines. We find that 76 of the 77 drugs that successfully reduced viral infection do not bind the proteins targeted by SARS-CoV-2, indicating that these drugs rely on network-based actions that cannot be identified using docking-based strategies. These advances offer a methodological pathway to identify repurposable drugs for future pathogens and neglected diseases underserved by the costs and extended timeline of de novo drug development. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2004.07229v2-abstract-full').style.display = 'none'; document.getElementById('2004.07229v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 9 August, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 April, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1808.01743">arXiv:1808.01743</a> <span> [<a href="https://arxiv.org/pdf/1808.01743">pdf</a>, <a href="https://arxiv.org/format/1808.01743">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> NIMFA: A Python Library for Nonnegative Matrix Factorization </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Zupan%2C+B">Blaz Zupan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1808.01743v1-abstract-short" style="display: inline;"> NIMFA is an open-source Python library that provides a unified interface to nonnegative matrix factorization algorithms. It includes implementations of state-of-the-art factorization methods, initialization approaches, and quality scoring. It supports both dense and sparse matrix representation. NIMFA's component-based implementation and hierarchical design should help the users to employ already… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1808.01743v1-abstract-full').style.display = 'inline'; document.getElementById('1808.01743v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1808.01743v1-abstract-full" style="display: none;"> NIMFA is an open-source Python library that provides a unified interface to nonnegative matrix factorization algorithms. It includes implementations of state-of-the-art factorization methods, initialization approaches, and quality scoring. It supports both dense and sparse matrix representation. NIMFA's component-based implementation and hierarchical design should help the users to employ already implemented techniques or design and code new strategies for matrix factorization tasks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1808.01743v1-abstract-full').style.display = 'none'; document.getElementById('1808.01743v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 6 August, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Journal of Machine Learning Research 13 (2012) 849-853 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1807.00123">arXiv:1807.00123</a> <span> [<a href="https://arxiv.org/pdf/1807.00123">pdf</a>, <a href="https://arxiv.org/format/1807.00123">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Engineering, Finance, and Science">cs.CE</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1016/j.inffus.2018.09.012">10.1016/j.inffus.2018.09.012 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Nguyen%2C+F">Francis Nguyen</a>, <a href="/search/q-bio?searchtype=author&query=Wang%2C+B">Bo Wang</a>, <a href="/search/q-bio?searchtype=author&query=Leskovec%2C+J">Jure Leskovec</a>, <a href="/search/q-bio?searchtype=author&query=Goldenberg%2C+A">Anna Goldenberg</a>, <a href="/search/q-bio?searchtype=author&query=Hoffman%2C+M+M">Michael M. Hoffman</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1807.00123v2-abstract-short" style="display: inline;"> New technologies have enabled the investigation of biology and human health at an unprecedented scale and in multiple dimensions. These dimensions include a myriad of properties describing genome, epigenome, transcriptome, microbiome, phenotype, and lifestyle. No single data type, however, can capture the complexity of all the factors relevant to understanding a phenomenon such as a disease. Integ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1807.00123v2-abstract-full').style.display = 'inline'; document.getElementById('1807.00123v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1807.00123v2-abstract-full" style="display: none;"> New technologies have enabled the investigation of biology and human health at an unprecedented scale and in multiple dimensions. These dimensions include a myriad of properties describing genome, epigenome, transcriptome, microbiome, phenotype, and lifestyle. No single data type, however, can capture the complexity of all the factors relevant to understanding a phenomenon such as a disease. Integrative methods that combine data from multiple technologies have thus emerged as critical statistical and computational approaches. The key challenge in developing such approaches is the identification of effective models to provide a comprehensive and relevant systems view. An ideal method can answer a biological or medical question, identifying important features and predicting outcomes, by harnessing heterogeneous data across several dimensions of biological variation. In this Review, we describe the principles of data integration and discuss current methods and available implementations. We provide examples of successful data integration in biology and medicine. Finally, we discuss current challenges in biomedical integrative methods and our perspective on the future development of the field. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1807.00123v2-abstract-full').style.display = 'none'; document.getElementById('1807.00123v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 October, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 30 June, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Information Fusion 50 (2019) 71-91 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1805.03327">arXiv:1805.03327</a> <span> [<a href="https://arxiv.org/pdf/1805.03327">pdf</a>, <a href="https://arxiv.org/format/1805.03327">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Molecular Networks">q-bio.MN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1038/s41467-018-05469-x">10.1038/s41467-018-05469-x <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Network Enhancement: a general method to denoise weighted biological networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Wang%2C+B">Bo Wang</a>, <a href="/search/q-bio?searchtype=author&query=Pourshafeie%2C+A">Armin Pourshafeie</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Zhu%2C+J">Junjie Zhu</a>, <a href="/search/q-bio?searchtype=author&query=Bustamante%2C+C+D">Carlos D. Bustamante</a>, <a href="/search/q-bio?searchtype=author&query=Batzoglou%2C+S">Serafim Batzoglou</a>, <a href="/search/q-bio?searchtype=author&query=Leskovec%2C+J">Jure Leskovec</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1805.03327v2-abstract-short" style="display: inline;"> Networks are ubiquitous in biology where they encode connectivity patterns at all scales of organization, from molecular to the biome. However, biological networks are noisy due to the limitations of measurement technology and inherent natural variation, which can hamper discovery of network patterns and dynamics. We propose Network Enhancement (NE), a method for improving the signal-to-noise rati… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1805.03327v2-abstract-full').style.display = 'inline'; document.getElementById('1805.03327v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1805.03327v2-abstract-full" style="display: none;"> Networks are ubiquitous in biology where they encode connectivity patterns at all scales of organization, from molecular to the biome. However, biological networks are noisy due to the limitations of measurement technology and inherent natural variation, which can hamper discovery of network patterns and dynamics. We propose Network Enhancement (NE), a method for improving the signal-to-noise ratio of undirected, weighted networks. NE uses a doubly stochastic matrix operator that induces sparsity and provides a closed-form solution that increases spectral eigengap of the input network. As a result, NE removes weak edges, enhances real connections, and leads to better downstream performance. Experiments show that NE improves gene function prediction by denoising tissue-specific interaction networks, alleviates interpretation of noisy Hi-C contact maps from the human genome, and boosts fine-grained identification accuracy of species. Our results indicate that NE is widely applicable for denoising biological networks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1805.03327v2-abstract-full').style.display = 'none'; document.getElementById('1805.03327v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 1 June, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 May, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Nature Communications, 9:3108, 2018 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1805.02411">arXiv:1805.02411</a> <span> [<a href="https://arxiv.org/pdf/1805.02411">pdf</a>, <a href="https://arxiv.org/format/1805.02411">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Molecular Networks">q-bio.MN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Applications">stat.AP</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1038/s41467-018-04948-5">10.1038/s41467-018-04948-5 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Prioritizing network communities </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Sosic%2C+R">Rok Sosic</a>, <a href="/search/q-bio?searchtype=author&query=Leskovec%2C+J">Jure Leskovec</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1805.02411v2-abstract-short" style="display: inline;"> Uncovering modular structure in networks is fundamental for systems in biology, physics, and engineering. Community detection identifies candidate modules as hypotheses, which then need to be validated through experiments, such as mutagenesis in a biological laboratory. Only a few communities can typically be validated, and it is thus important to prioritize which communities to select for downstr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1805.02411v2-abstract-full').style.display = 'inline'; document.getElementById('1805.02411v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1805.02411v2-abstract-full" style="display: none;"> Uncovering modular structure in networks is fundamental for systems in biology, physics, and engineering. Community detection identifies candidate modules as hypotheses, which then need to be validated through experiments, such as mutagenesis in a biological laboratory. Only a few communities can typically be validated, and it is thus important to prioritize which communities to select for downstream experimentation. Here we develop CRank, a mathematically principled approach for prioritizing network communities. CRank efficiently evaluates robustness and magnitude of structural features of each community and then combines these features into the community prioritization. CRank can be used with any community detection method. It needs only information provided by the network structure and does not require any additional metadata or labels. However, when available, CRank can incorporate domain-specific information to further boost performance. Experiments on many large networks show that CRank effectively prioritizes communities, yielding a nearly 50-fold improvement in community prioritization. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1805.02411v2-abstract-full').style.display = 'none'; document.getElementById('1805.02411v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 28 May, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 7 May, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Nature Communications, 9:2544, 2018 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1802.00543">arXiv:1802.00543</a> <span> [<a href="https://arxiv.org/pdf/1802.00543">pdf</a>, <a href="https://arxiv.org/format/1802.00543">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Molecular Networks">q-bio.MN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1093/bioinformatics/bty294">10.1093/bioinformatics/bty294 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Modeling polypharmacy side effects with graph convolutional networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Agrawal%2C+M">Monica Agrawal</a>, <a href="/search/q-bio?searchtype=author&query=Leskovec%2C+J">Jure Leskovec</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1802.00543v2-abstract-short" style="display: inline;"> The use of drug combinations, termed polypharmacy, is common to treat patients with complex diseases and co-existing conditions. However, a major consequence of polypharmacy is a much higher risk of adverse side effects for the patient. Polypharmacy side effects emerge because of drug-drug interactions, in which activity of one drug may change if taken with another drug. The knowledge of drug inte… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1802.00543v2-abstract-full').style.display = 'inline'; document.getElementById('1802.00543v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1802.00543v2-abstract-full" style="display: none;"> The use of drug combinations, termed polypharmacy, is common to treat patients with complex diseases and co-existing conditions. However, a major consequence of polypharmacy is a much higher risk of adverse side effects for the patient. Polypharmacy side effects emerge because of drug-drug interactions, in which activity of one drug may change if taken with another drug. The knowledge of drug interactions is limited because these complex relationships are rare, and are usually not observed in relatively small clinical testing. Discovering polypharmacy side effects thus remains an important challenge with significant implications for patient mortality. Here, we present Decagon, an approach for modeling polypharmacy side effects. The approach constructs a multimodal graph of protein-protein interactions, drug-protein target interactions, and the polypharmacy side effects, which are represented as drug-drug interactions, where each side effect is an edge of a different type. Decagon is developed specifically to handle such multimodal graphs with a large number of edge types. Our approach develops a new graph convolutional neural network for multirelational link prediction in multimodal networks. Decagon predicts the exact side effect, if any, through which a given drug combination manifests clinically. Decagon accurately predicts polypharmacy side effects, outperforming baselines by up to 69%. We find that it automatically learns representations of side effects indicative of co-occurrence of polypharmacy in patients. Furthermore, Decagon models particularly well side effects with a strong molecular basis, while on predominantly non-molecular side effects, it achieves good performance because of effective sharing of model parameters across edge types. Decagon creates opportunities to use large pharmacogenomic and patient data to flag and prioritize side effects for follow-up analysis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1802.00543v2-abstract-full').style.display = 'none'; document.getElementById('1802.00543v2-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 26 April, 2018; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 February, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2018. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">Presented at ISMB 2018</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Bioinformatics, 34:13, 457-466, 2018 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1712.00843">arXiv:1712.00843</a> <span> [<a href="https://arxiv.org/pdf/1712.00843">pdf</a>, <a href="https://arxiv.org/format/1712.00843">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Molecular Networks">q-bio.MN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> </div> </div> <p class="title is-5 mathjax"> Large-scale analysis of disease pathways in the human interactome </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Agrawal%2C+M">Monica Agrawal</a>, <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Leskovec%2C+J">Jure Leskovec</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1712.00843v1-abstract-short" style="display: inline;"> Discovering disease pathways, which can be defined as sets of proteins associated with a given disease, is an important problem that has the potential to provide clinically actionable insights for disease diagnosis, prognosis, and treatment. Computational methods aid the discovery by relying on protein-protein interaction (PPI) networks. They start with a few known disease-associated proteins and… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1712.00843v1-abstract-full').style.display = 'inline'; document.getElementById('1712.00843v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1712.00843v1-abstract-full" style="display: none;"> Discovering disease pathways, which can be defined as sets of proteins associated with a given disease, is an important problem that has the potential to provide clinically actionable insights for disease diagnosis, prognosis, and treatment. Computational methods aid the discovery by relying on protein-protein interaction (PPI) networks. They start with a few known disease-associated proteins and aim to find the rest of the pathway by exploring the PPI network around the known disease proteins. However, the success of such methods has been limited, and failure cases have not been well understood. Here we study the PPI network structure of 519 disease pathways. We find that 90% of pathways do not correspond to single well-connected components in the PPI network. Instead, proteins associated with a single disease tend to form many separate connected components/regions in the network. We then evaluate state-of-the-art disease pathway discovery methods and show that their performance is especially poor on diseases with disconnected pathways. Thus, we conclude that network connectivity structure alone may not be sufficient for disease pathway discovery. However, we show that higher-order network structures, such as small subgraphs of the pathway, provide a promising direction for the development of new methods. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1712.00843v1-abstract-full').style.display = 'none'; document.getElementById('1712.00843v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 3 December, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2017. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Pacific Symposium on Biocomputing 23:111-122(2018) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1708.03392">arXiv:1708.03392</a> <span> [<a href="https://arxiv.org/pdf/1708.03392">pdf</a>, <a href="https://arxiv.org/format/1708.03392">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Molecular Networks">q-bio.MN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> </div> <p class="title is-5 mathjax"> Jumping across biomedical contexts using compressive data fusion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Zupan%2C+B">Blaz Zupan</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1708.03392v1-abstract-short" style="display: inline;"> Motivation: The rapid growth of diverse biological data allows us to consider interactions between a variety of objects, such as genes, chemicals, molecular signatures, diseases, pathways and environmental exposures. Often, any pair of objects--such as a gene and a disease--can be related in different ways, for example, directly via gene-disease associations or indirectly via functional annotation… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1708.03392v1-abstract-full').style.display = 'inline'; document.getElementById('1708.03392v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1708.03392v1-abstract-full" style="display: none;"> Motivation: The rapid growth of diverse biological data allows us to consider interactions between a variety of objects, such as genes, chemicals, molecular signatures, diseases, pathways and environmental exposures. Often, any pair of objects--such as a gene and a disease--can be related in different ways, for example, directly via gene-disease associations or indirectly via functional annotations, chemicals and pathways. Different ways of relating these objects carry different semantic meanings. However, traditional methods disregard these semantics and thus cannot fully exploit their value in data modeling. Results: We present Medusa, an approach to detect size-k modules of objects that, taken together, appear most significant to another set of objects. Medusa operates on large-scale collections of heterogeneous data sets and explicitly distinguishes between diverse data semantics. It advances research along two dimensions: it builds on collective matrix factorization to derive different semantics, and it formulates the growing of the modules as a submodular optimization program. Medusa is flexible in choosing or combining semantic meanings and provides theoretical guarantees about detection quality. In a systematic study on 310 complex diseases, we show the effectiveness of Medusa in associating genes with diseases and detecting disease modules. We demonstrate that in predicting gene-disease associations Medusa compares favorably to methods that ignore diverse semantic meanings. We find that the utility of different semantics depends on disease categories and that, overall, Medusa recovers disease modules more accurately when combining different semantics. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1708.03392v1-abstract-full').style.display = 'none'; document.getElementById('1708.03392v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 10 August, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2017. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">In Proceedings of the 24th International Conference on Intelligent Systems for Molecular Biology (ISMB), 2016</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Bioinformatics, 32 (12): i90-i100 (2016) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1707.04638">arXiv:1707.04638</a> <span> [<a href="https://arxiv.org/pdf/1707.04638">pdf</a>, <a href="https://arxiv.org/format/1707.04638">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Social and Information Networks">cs.SI</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Molecular Networks">q-bio.MN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Machine Learning">stat.ML</span> </div> <div class="is-inline-block" style="margin-left: 0.5rem"> <div class="tags has-addons"> <span class="tag is-dark is-size-7">doi</span> <span class="tag is-light is-size-7"><a class="" href="https://doi.org/10.1093/bioinformatics/btx252">10.1093/bioinformatics/btx252 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Predicting multicellular function through multi-layer tissue networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zitnik%2C+M">Marinka Zitnik</a>, <a href="/search/q-bio?searchtype=author&query=Leskovec%2C+J">Jure Leskovec</a> </p> <p class="abstract mathjax"> <span class="has-text-black-bis has-text-weight-semibold">Abstract</span>: <span class="abstract-short has-text-grey-dark mathjax" id="1707.04638v1-abstract-short" style="display: inline;"> Motivation: Understanding functions of proteins in specific human tissues is essential for insights into disease diagnostics and therapeutics, yet prediction of tissue-specific cellular function remains a critical challenge for biomedicine. Results: Here we present OhmNet, a hierarchy-aware unsupervised node feature learning approach for multi-layer networks. We build a multi-layer network, wher… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1707.04638v1-abstract-full').style.display = 'inline'; document.getElementById('1707.04638v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1707.04638v1-abstract-full" style="display: none;"> Motivation: Understanding functions of proteins in specific human tissues is essential for insights into disease diagnostics and therapeutics, yet prediction of tissue-specific cellular function remains a critical challenge for biomedicine. Results: Here we present OhmNet, a hierarchy-aware unsupervised node feature learning approach for multi-layer networks. We build a multi-layer network, where each layer represents molecular interactions in a different human tissue. OhmNet then automatically learns a mapping of proteins, represented as nodes, to a neural embedding based low-dimensional space of features. OhmNet encourages sharing of similar features among proteins with similar network neighborhoods and among proteins activated in similar tissues. The algorithm generalizes prior work, which generally ignores relationships between tissues, by modeling tissue organization with a rich multiscale tissue hierarchy. We use OhmNet to study multicellular function in a multi-layer protein interaction network of 107 human tissues. In 48 tissues with known tissue-specific cellular functions, OhmNet provides more accurate predictions of cellular function than alternative approaches, and also generates more accurate hypotheses about tissue-specific protein actions. We show that taking into account the tissue hierarchy leads to improved predictive power. Remarkably, we also demonstrate that it is possible to leverage the tissue hierarchy in order to effectively transfer cellular functions to a functionally uncharacterized tissue. Overall, OhmNet moves from flat networks to multiscale models able to predict a range of phenotypes spanning cellular subsystems <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1707.04638v1-abstract-full').style.display = 'none'; document.getElementById('1707.04638v1-abstract-short').style.display = 'inline';">△ Less</a> </span> </p> <p class="is-size-7"><span class="has-text-black-bis has-text-weight-semibold">Submitted</span> 14 July, 2017; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2017. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Comments:</span> <span class="has-text-grey-dark mathjax">In Proceedings of the 25th International Conference on Intelligent Systems for Molecular Biology (ISMB), 2017</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Bioinformatics 2017, 33 (14): i190-i198 </p> </li> </ol> <div class="is-hidden-tablet">  <span class="help" style="display: inline-block;"><a href="https://github.com/arXiv/arxiv-search/releases">Search v0.5.6 released 2020-02-24</a>  </span> </div> </div> </main> <footer> <div class="columns is-desktop" role="navigation" aria-label="Secondary">  <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/about">About</a></li> <li><a href="https://info.arxiv.org/help">Help</a></li> </ul> </div> <div class="column"> <ul class="nav-spaced"> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>contact arXiv</title><desc>Click here to contact arXiv</desc><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg> <a href="https://info.arxiv.org/help/contact.html"> Contact</a> </li> <li> <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><title>subscribe to arXiv mailings</title><desc>Click here to subscribe</desc><path d="M476 3.2L12.5 270.6c-18.1 10.4-15.8 35.6 2.2 43.2L121 358.4l287.3-253.2c5.5-4.9 13.3 2.6 8.6 8.3L176 407v80.5c0 23.6 28.5 32.9 42.5 15.8L282 426l124.6 52.2c14.2 6 30.4-2.9 33-18.2l72-432C515 7.8 493.3-6.8 476 3.2z"/></svg> <a href="https://info.arxiv.org/help/subscribe"> Subscribe</a> </li> </ul> </div> </div> </div>   <div class="column"> <div class="columns"> <div class="column"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/license/index.html">Copyright</a></li> <li><a href="https://info.arxiv.org/help/policies/privacy_policy.html">Privacy Policy</a></li> </ul> </div> <div class="column sorry-app-links"> <ul class="nav-spaced"> <li><a href="https://info.arxiv.org/help/web_accessibility.html">Web Accessibility Assistance</a></li> <li> <p class="help"> <a class="a11y-main-link" href="https://status.arxiv.org" target="_blank">arXiv Operational Status <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 256 512" class="icon filter-dark_grey" role="presentation"><path d="M224.3 273l-136 136c-9.4 9.4-24.6 9.4-33.9 0l-22.6-22.6c-9.4-9.4-9.4-24.6 0-33.9l96.4-96.4-96.4-96.4c-9.4-9.4-9.4-24.6 0-33.9L54.3 103c9.4-9.4 24.6-9.4 33.9 0l136 136c9.5 9.4 9.5 24.6.1 34z"/></svg></a><br> Get status notifications via <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/email/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" class="icon filter-black" role="presentation"><path d="M502.3 190.8c3.9-3.1 9.7-.2 9.7 4.7V400c0 26.5-21.5 48-48 48H48c-26.5 0-48-21.5-48-48V195.6c0-5 5.7-7.8 9.7-4.7 22.4 17.4 52.1 39.5 154.1 113.6 21.1 15.4 56.7 47.8 92.2 47.6 35.7.3 72-32.8 92.3-47.6 102-74.1 131.6-96.3 154-113.7zM256 320c23.2.4 56.6-29.2 73.4-41.4 132.7-96.3 142.8-104.7 173.4-128.7 5.8-4.5 9.2-11.5 9.2-18.9v-19c0-26.5-21.5-48-48-48H48C21.5 64 0 85.5 0 112v19c0 7.4 3.4 14.3 9.2 18.9 30.6 23.9 40.7 32.4 173.4 128.7 16.8 12.2 50.2 41.8 73.4 41.4z"/></svg>email</a> or <a class="is-link" href="https://subscribe.sorryapp.com/24846f03/slack/new" target="_blank"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512" class="icon filter-black" role="presentation"><path d="M94.12 315.1c0 25.9-21.16 47.06-47.06 47.06S0 341 0 315.1c0-25.9 21.16-47.06 47.06-47.06h47.06v47.06zm23.72 0c0-25.9 21.16-47.06 47.06-47.06s47.06 21.16 47.06 47.06v117.84c0 25.9-21.16 47.06-47.06 47.06s-47.06-21.16-47.06-47.06V315.1zm47.06-188.98c-25.9 0-47.06-21.16-47.06-47.06S139 32 164.9 32s47.06 21.16 47.06 47.06v47.06H164.9zm0 23.72c25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06H47.06C21.16 243.96 0 222.8 0 196.9s21.16-47.06 47.06-47.06H164.9zm188.98 47.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06s-21.16 47.06-47.06 47.06h-47.06V196.9zm-23.72 0c0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06V79.06c0-25.9 21.16-47.06 47.06-47.06 25.9 0 47.06 21.16 47.06 47.06V196.9zM283.1 385.88c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06-25.9 0-47.06-21.16-47.06-47.06v-47.06h47.06zm0-23.72c-25.9 0-47.06-21.16-47.06-47.06 0-25.9 21.16-47.06 47.06-47.06h117.84c25.9 0 47.06 21.16 47.06 47.06 0 25.9-21.16 47.06-47.06 47.06H283.1z"/></svg>slack</a> </p> </li> </ul> </div> </div> </div>  </div> </footer> <script src="https://static.arxiv.org/static/base/1.0.0a5/js/member_acknowledgement.js"></script> </body> </html>

CINXE.COM

Search | arXiv e-print repository