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 1–15 of 15 results for author: <span class="mathjax">Jha, S</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=Jha%2C+S">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="Jha, S"> </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=Jha%2C+S&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="Jha, S"> <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/2408.01869">arXiv:2408.01869</a> <span> [<a href="https://arxiv.org/pdf/2408.01869">pdf</a>, <a href="https://arxiv.org/format/2408.01869">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation and Language">cs.CL</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="Information Retrieval">cs.IR</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="Multiagent Systems">cs.MA</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"> MALADE: Orchestration of LLM-powered Agents with Retrieval Augmented Generation for Pharmacovigilance </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Choi%2C+J">Jihye Choi</a>, <a href="/search/q-bio?searchtype=author&query=Palumbo%2C+N">Nils Palumbo</a>, <a href="/search/q-bio?searchtype=author&query=Chalasani%2C+P">Prasad Chalasani</a>, <a href="/search/q-bio?searchtype=author&query=Engelhard%2C+M+M">Matthew M. Engelhard</a>, <a href="/search/q-bio?searchtype=author&query=Jha%2C+S">Somesh Jha</a>, <a href="/search/q-bio?searchtype=author&query=Kumar%2C+A">Anivarya Kumar</a>, <a href="/search/q-bio?searchtype=author&query=Page%2C+D">David Page</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="2408.01869v1-abstract-short" style="display: inline;"> In the era of Large Language Models (LLMs), given their remarkable text understanding and generation abilities, there is an unprecedented opportunity to develop new, LLM-based methods for trustworthy medical knowledge synthesis, extraction and summarization. This paper focuses on the problem of Pharmacovigilance (PhV), where the significance and challenges lie in identifying Adverse Drug Events (A… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01869v1-abstract-full').style.display = 'inline'; document.getElementById('2408.01869v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.01869v1-abstract-full" style="display: none;"> In the era of Large Language Models (LLMs), given their remarkable text understanding and generation abilities, there is an unprecedented opportunity to develop new, LLM-based methods for trustworthy medical knowledge synthesis, extraction and summarization. This paper focuses on the problem of Pharmacovigilance (PhV), where the significance and challenges lie in identifying Adverse Drug Events (ADEs) from diverse text sources, such as medical literature, clinical notes, and drug labels. Unfortunately, this task is hindered by factors including variations in the terminologies of drugs and outcomes, and ADE descriptions often being buried in large amounts of narrative text. We present MALADE, the first effective collaborative multi-agent system powered by LLM with Retrieval Augmented Generation for ADE extraction from drug label data. This technique involves augmenting a query to an LLM with relevant information extracted from text resources, and instructing the LLM to compose a response consistent with the augmented data. MALADE is a general LLM-agnostic architecture, and its unique capabilities are: (1) leveraging a variety of external sources, such as medical literature, drug labels, and FDA tools (e.g., OpenFDA drug information API), (2) extracting drug-outcome association in a structured format along with the strength of the association, and (3) providing explanations for established associations. Instantiated with GPT-4 Turbo or GPT-4o, and FDA drug label data, MALADE demonstrates its efficacy with an Area Under ROC Curve of 0.90 against the OMOP Ground Truth table of ADEs. Our implementation leverages the Langroid multi-agent LLM framework and can be found at https://github.com/jihyechoi77/malade. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.01869v1-abstract-full').style.display = 'none'; document.getElementById('2408.01869v1-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 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">Paper published at Machine Learning for Healthcare 2024 (MLHC'24)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2407.16584">arXiv:2407.16584</a> <span> [<a href="https://arxiv.org/pdf/2407.16584">pdf</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"> The need to implement FAIR principles in biomolecular simulations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Amaro%2C+R">Rommie Amaro</a>, <a href="/search/q-bio?searchtype=author&query=%C3%85qvist%2C+J">Johan 脜qvist</a>, <a href="/search/q-bio?searchtype=author&query=Bahar%2C+I">Ivet Bahar</a>, <a href="/search/q-bio?searchtype=author&query=Battistini%2C+F">Federica Battistini</a>, <a href="/search/q-bio?searchtype=author&query=Bellaiche%2C+A">Adam Bellaiche</a>, <a href="/search/q-bio?searchtype=author&query=Beltran%2C+D">Daniel Beltran</a>, <a href="/search/q-bio?searchtype=author&query=Biggin%2C+P+C">Philip C. Biggin</a>, <a href="/search/q-bio?searchtype=author&query=Bonomi%2C+M">Massimiliano Bonomi</a>, <a href="/search/q-bio?searchtype=author&query=Bowman%2C+G+R">Gregory R. Bowman</a>, <a href="/search/q-bio?searchtype=author&query=Bryce%2C+R">Richard Bryce</a>, <a href="/search/q-bio?searchtype=author&query=Bussi%2C+G">Giovanni Bussi</a>, <a href="/search/q-bio?searchtype=author&query=Carloni%2C+P">Paolo Carloni</a>, <a href="/search/q-bio?searchtype=author&query=Case%2C+D">David Case</a>, <a href="/search/q-bio?searchtype=author&query=Cavalli%2C+A">Andrea Cavalli</a>, <a href="/search/q-bio?searchtype=author&query=Chang%2C+C+A">Chie-En A. Chang</a>, <a href="/search/q-bio?searchtype=author&query=Cheatham%2C+T+E">Thomas E. Cheatham III</a>, <a href="/search/q-bio?searchtype=author&query=Cheung%2C+M+S">Margaret S. Cheung</a>, <a href="/search/q-bio?searchtype=author&query=Chipot%2C+C">Cris Chipot</a>, <a href="/search/q-bio?searchtype=author&query=Chong%2C+L+T">Lillian T. Chong</a>, <a href="/search/q-bio?searchtype=author&query=Choudhary%2C+P">Preeti Choudhary</a>, <a href="/search/q-bio?searchtype=author&query=Cisneros%2C+G+A">Gerardo Andres Cisneros</a>, <a href="/search/q-bio?searchtype=author&query=Clementi%2C+C">Cecilia Clementi</a>, <a href="/search/q-bio?searchtype=author&query=Collepardo-Guevara%2C+R">Rosana Collepardo-Guevara</a>, <a href="/search/q-bio?searchtype=author&query=Coveney%2C+P">Peter Coveney</a>, <a href="/search/q-bio?searchtype=author&query=Covino%2C+R">Roberto Covino</a> , et al. (101 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="2407.16584v3-abstract-short" style="display: inline;"> This letter illustrates the opinion of the molecular dynamics (MD) community on the need to adopt a new FAIR paradigm for the use of molecular simulations. It highlights the necessity of a collaborative effort to create, establish, and sustain a database that allows findability, accessibility, interoperability, and reusability of molecular dynamics simulation data. Such a development would democra… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.16584v3-abstract-full').style.display = 'inline'; document.getElementById('2407.16584v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.16584v3-abstract-full" style="display: none;"> This letter illustrates the opinion of the molecular dynamics (MD) community on the need to adopt a new FAIR paradigm for the use of molecular simulations. It highlights the necessity of a collaborative effort to create, establish, and sustain a database that allows findability, accessibility, interoperability, and reusability of molecular dynamics simulation data. Such a development would democratize the field and significantly improve the impact of MD simulations on life science research. This will transform our working paradigm, pushing the field to a new frontier. We invite you to support our initiative at the MDDB community (https://mddbr.eu/community/) <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.16584v3-abstract-full').style.display = 'none'; document.getElementById('2407.16584v3-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> 30 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 23 July, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2406.10893">arXiv:2406.10893</a> <span> [<a href="https://arxiv.org/pdf/2406.10893">pdf</a>, <a href="https://arxiv.org/format/2406.10893">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</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="Computer Vision and Pattern Recognition">cs.CV</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"> Development and Validation of Fully Automatic Deep Learning-Based Algorithms for Immunohistochemistry Reporting of Invasive Breast Ductal Carcinoma </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Jha%2C+S+K">Sumit Kumar Jha</a>, <a href="/search/q-bio?searchtype=author&query=Mishra%2C+P">Purnendu Mishra</a>, <a href="/search/q-bio?searchtype=author&query=Mathur%2C+S">Shubham Mathur</a>, <a href="/search/q-bio?searchtype=author&query=Singh%2C+G">Gursewak Singh</a>, <a href="/search/q-bio?searchtype=author&query=Kumar%2C+R">Rajiv Kumar</a>, <a href="/search/q-bio?searchtype=author&query=Aatre%2C+K">Kiran Aatre</a>, <a href="/search/q-bio?searchtype=author&query=Rengarajan%2C+S">Suraj Rengarajan</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="2406.10893v1-abstract-short" style="display: inline;"> Immunohistochemistry (IHC) analysis is a well-accepted and widely used method for molecular subtyping, a procedure for prognosis and targeted therapy of breast carcinoma, the most common type of tumor affecting women. There are four molecular biomarkers namely progesterone receptor (PR), estrogen receptor (ER), antigen Ki67, and human epidermal growth factor receptor 2 (HER2) whose assessment is n… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10893v1-abstract-full').style.display = 'inline'; document.getElementById('2406.10893v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.10893v1-abstract-full" style="display: none;"> Immunohistochemistry (IHC) analysis is a well-accepted and widely used method for molecular subtyping, a procedure for prognosis and targeted therapy of breast carcinoma, the most common type of tumor affecting women. There are four molecular biomarkers namely progesterone receptor (PR), estrogen receptor (ER), antigen Ki67, and human epidermal growth factor receptor 2 (HER2) whose assessment is needed under IHC procedure to decide prognosis as well as predictors of response to therapy. However, IHC scoring is based on subjective microscopic examination of tumor morphology and suffers from poor reproducibility, high subjectivity, and often incorrect scoring in low-score cases. In this paper, we present, a deep learning-based semi-supervised trained, fully automatic, decision support system (DSS) for IHC scoring of invasive ductal carcinoma. Our system automatically detects the tumor region removing artifacts and scores based on Allred standard. The system is developed using 3 million pathologist-annotated image patches from 300 slides, fifty thousand in-house cell annotations, and forty thousand pixels marking of HER2 membrane. We have conducted multicentric trials at four centers with three different types of digital scanners in terms of percentage agreement with doctors. And achieved agreements of 95, 92, 88 and 82 percent for Ki67, HER2, ER, and PR stain categories, respectively. In addition to overall accuracy, we found that there is 5 percent of cases where pathologist have changed their score in favor of algorithm score while reviewing with detailed algorithmic analysis. Our approach could improve the accuracy of IHC scoring and subsequent therapy decisions, particularly where specialist expertise is unavailable. Our system is highly modular. The proposed algorithm modules can be used to develop DSS for other cancer types. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.10893v1-abstract-full').style.display = 'none'; document.getElementById('2406.10893v1-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 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/2404.15293">arXiv:2404.15293</a> <span> [<a href="https://arxiv.org/pdf/2404.15293">pdf</a>, <a href="https://arxiv.org/format/2404.15293">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Image and Video Processing">eess.IV</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Graphics">cs.GR</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"> Interactive Manipulation and Visualization of 3D Brain MRI for Surgical Training </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Jha%2C+S">Siddharth Jha</a>, <a href="/search/q-bio?searchtype=author&query=Gui%2C+Z">Zichen Gui</a>, <a href="/search/q-bio?searchtype=author&query=Delbos%2C+B">Benjamin Delbos</a>, <a href="/search/q-bio?searchtype=author&query=Moreau%2C+R">Richard Moreau</a>, <a href="/search/q-bio?searchtype=author&query=Leleve%2C+A">Arnaud Leleve</a>, <a href="/search/q-bio?searchtype=author&query=Cheng%2C+I">Irene Cheng</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="2404.15293v1-abstract-short" style="display: inline;"> In modern medical diagnostics, magnetic resonance imaging (MRI) is an important technique that provides detailed insights into anatomical structures. In this paper, we present a comprehensive methodology focusing on streamlining the segmentation, reconstruction, and visualization process of 3D MRI data. Segmentation involves the extraction of anatomical regions with the help of state-of-the-art de… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.15293v1-abstract-full').style.display = 'inline'; document.getElementById('2404.15293v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.15293v1-abstract-full" style="display: none;"> In modern medical diagnostics, magnetic resonance imaging (MRI) is an important technique that provides detailed insights into anatomical structures. In this paper, we present a comprehensive methodology focusing on streamlining the segmentation, reconstruction, and visualization process of 3D MRI data. Segmentation involves the extraction of anatomical regions with the help of state-of-the-art deep learning algorithms. Then, 3D reconstruction converts segmented data from the previous step into multiple 3D representations. Finally, the visualization stage provides efficient and interactive presentations of both 2D and 3D MRI data. Integrating these three steps, the proposed system is able to augment the interpretability of the anatomical information from MRI scans according to our interviews with doctors. Even though this system was originally designed and implemented as part of human brain haptic feedback simulation for surgeon training, it can also provide experienced medical practitioners with an effective tool for clinical data analysis, surgical planning and other purposes <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.15293v1-abstract-full').style.display = 'none'; document.getElementById('2404.15293v1-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> 24 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2301.04093">arXiv:2301.04093</a> <span> [<a href="https://arxiv.org/pdf/2301.04093">pdf</a>, <a href="https://arxiv.org/format/2301.04093">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="Biomolecules">q-bio.BM</span> </div> </div> <p class="title is-5 mathjax"> On the Robustness of AlphaFold: A COVID-19 Case Study </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Alkhouri%2C+I">Ismail Alkhouri</a>, <a href="/search/q-bio?searchtype=author&query=Jha%2C+S">Sumit Jha</a>, <a href="/search/q-bio?searchtype=author&query=Beckus%2C+A">Andre Beckus</a>, <a href="/search/q-bio?searchtype=author&query=Atia%2C+G">George Atia</a>, <a href="/search/q-bio?searchtype=author&query=Velasquez%2C+A">Alvaro Velasquez</a>, <a href="/search/q-bio?searchtype=author&query=Ewetz%2C+R">Rickard Ewetz</a>, <a href="/search/q-bio?searchtype=author&query=Ramanathan%2C+A">Arvind Ramanathan</a>, <a href="/search/q-bio?searchtype=author&query=Jha%2C+S">Susmit Jha</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="2301.04093v2-abstract-short" style="display: inline;"> Protein folding neural networks (PFNNs) such as AlphaFold predict remarkably accurate structures of proteins compared to other approaches. However, the robustness of such networks has heretofore not been explored. This is particularly relevant given the broad social implications of such technologies and the fact that biologically small perturbations in the protein sequence do not generally lead to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.04093v2-abstract-full').style.display = 'inline'; document.getElementById('2301.04093v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2301.04093v2-abstract-full" style="display: none;"> Protein folding neural networks (PFNNs) such as AlphaFold predict remarkably accurate structures of proteins compared to other approaches. However, the robustness of such networks has heretofore not been explored. This is particularly relevant given the broad social implications of such technologies and the fact that biologically small perturbations in the protein sequence do not generally lead to drastic changes in the protein structure. In this paper, we demonstrate that AlphaFold does not exhibit such robustness despite its high accuracy. This raises the challenge of detecting and quantifying the extent to which these predicted protein structures can be trusted. To measure the robustness of the predicted structures, we utilize (i) the root-mean-square deviation (RMSD) and (ii) the Global Distance Test (GDT) similarity measure between the predicted structure of the original sequence and the structure of its adversarially perturbed version. We prove that the problem of minimally perturbing protein sequences to fool protein folding neural networks is NP-complete. Based on the well-established BLOSUM62 sequence alignment scoring matrix, we generate adversarial protein sequences and show that the RMSD between the predicted protein structure and the structure of the original sequence are very large when the adversarial changes are bounded by (i) 20 units in the BLOSUM62 distance, and (ii) five residues (out of hundreds or thousands of residues) in the given protein sequence. In our experimental evaluation, we consider 111 COVID-19 proteins in the Universal Protein resource (UniProt), a central resource for protein data managed by the European Bioinformatics Institute, Swiss Institute of Bioinformatics, and the US Protein Information Resource. These result in an overall GDT similarity test score average of around 34%, demonstrating a substantial drop in the performance of AlphaFold. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2301.04093v2-abstract-full').style.display = 'none'; document.getElementById('2301.04093v2-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> 12 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 10 January, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 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">arXiv admin note: text overlap with arXiv:2109.04460</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2207.05058">arXiv:2207.05058</a> <span> [<a href="https://arxiv.org/pdf/2207.05058">pdf</a>, <a href="https://arxiv.org/format/2207.05058">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</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"> Inferring and Conveying Intentionality: Beyond Numerical Rewards to Logical Intentions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Jha%2C+S">Susmit Jha</a>, <a href="/search/q-bio?searchtype=author&query=Rushby%2C+J">John Rushby</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="2207.05058v2-abstract-short" style="display: inline;"> Shared intentionality is a critical component in developing conscious AI agents capable of collaboration, self-reflection, deliberation, and reasoning. We formulate inference of shared intentionality as an inverse reinforcement learning problem with logical reward specifications. We show how the approach can infer task descriptions from demonstrations. We also extend our approach to actively conve… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.05058v2-abstract-full').style.display = 'inline'; document.getElementById('2207.05058v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2207.05058v2-abstract-full" style="display: none;"> Shared intentionality is a critical component in developing conscious AI agents capable of collaboration, self-reflection, deliberation, and reasoning. We formulate inference of shared intentionality as an inverse reinforcement learning problem with logical reward specifications. We show how the approach can infer task descriptions from demonstrations. We also extend our approach to actively convey intentionality. We demonstrate the approach on a simple grid-world example. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2207.05058v2-abstract-full').style.display = 'none'; document.getElementById('2207.05058v2-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> 13 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 July, 2022; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2022. </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 AAAI Spring Symposium on Towards Conscious AI Systems. 2019</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2109.04460">arXiv:2109.04460</a> <span> [<a href="https://arxiv.org/pdf/2109.04460">pdf</a>, <a href="https://arxiv.org/format/2109.04460">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> <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"> Protein Folding Neural Networks Are Not Robust </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Jha%2C+S+K">Sumit Kumar Jha</a>, <a href="/search/q-bio?searchtype=author&query=Ramanathan%2C+A">Arvind Ramanathan</a>, <a href="/search/q-bio?searchtype=author&query=Ewetz%2C+R">Rickard Ewetz</a>, <a href="/search/q-bio?searchtype=author&query=Velasquez%2C+A">Alvaro Velasquez</a>, <a href="/search/q-bio?searchtype=author&query=Jha%2C+S">Susmit Jha</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="2109.04460v2-abstract-short" style="display: inline;"> Deep neural networks such as AlphaFold and RoseTTAFold predict remarkably accurate structures of proteins compared to other algorithmic approaches. It is known that biologically small perturbations in the protein sequence do not lead to drastic changes in the protein structure. In this paper, we demonstrate that RoseTTAFold does not exhibit such a robustness despite its high accuracy, and biologic… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.04460v2-abstract-full').style.display = 'inline'; document.getElementById('2109.04460v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2109.04460v2-abstract-full" style="display: none;"> Deep neural networks such as AlphaFold and RoseTTAFold predict remarkably accurate structures of proteins compared to other algorithmic approaches. It is known that biologically small perturbations in the protein sequence do not lead to drastic changes in the protein structure. In this paper, we demonstrate that RoseTTAFold does not exhibit such a robustness despite its high accuracy, and biologically small perturbations for some input sequences result in radically different predicted protein structures. This raises the challenge of detecting when these predicted protein structures cannot be trusted. We define the robustness measure for the predicted structure of a protein sequence to be the inverse of the root-mean-square distance (RMSD) in the predicted structure and the structure of its adversarially perturbed sequence. We use adversarial attack methods to create adversarial protein sequences, and show that the RMSD in the predicted protein structure ranges from 0.119脜 to 34.162脜 when the adversarial perturbations are bounded by 20 units in the BLOSUM62 distance. This demonstrates very high variance in the robustness measure of the predicted structures. We show that the magnitude of the correlation (0.917) between our robustness measure and the RMSD between the predicted structure and the ground truth is high, that is, the predictions with low robustness measure cannot be trusted. This is the first paper demonstrating the susceptibility of RoseTTAFold to adversarial attacks. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2109.04460v2-abstract-full').style.display = 'none'; document.getElementById('2109.04460v2-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 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 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">8 pages, 5 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/2106.07036">arXiv:2106.07036</a> <span> [<a href="https://arxiv.org/pdf/2106.07036">pdf</a>, <a href="https://arxiv.org/format/2106.07036">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> <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"> Protein-Ligand Docking Surrogate Models: A SARS-CoV-2 Benchmark for Deep Learning Accelerated Virtual Screening </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Clyde%2C+A">Austin Clyde</a>, <a href="/search/q-bio?searchtype=author&query=Brettin%2C+T">Thomas Brettin</a>, <a href="/search/q-bio?searchtype=author&query=Partin%2C+A">Alexander Partin</a>, <a href="/search/q-bio?searchtype=author&query=Yoo%2C+H">Hyunseung Yoo</a>, <a href="/search/q-bio?searchtype=author&query=Babuji%2C+Y">Yadu Babuji</a>, <a href="/search/q-bio?searchtype=author&query=Blaiszik%2C+B">Ben Blaiszik</a>, <a href="/search/q-bio?searchtype=author&query=Merzky%2C+A">Andre Merzky</a>, <a href="/search/q-bio?searchtype=author&query=Turilli%2C+M">Matteo Turilli</a>, <a href="/search/q-bio?searchtype=author&query=Jha%2C+S">Shantenu Jha</a>, <a href="/search/q-bio?searchtype=author&query=Ramanathan%2C+A">Arvind Ramanathan</a>, <a href="/search/q-bio?searchtype=author&query=Stevens%2C+R">Rick Stevens</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="2106.07036v2-abstract-short" style="display: inline;"> We propose a benchmark to study surrogate model accuracy for protein-ligand docking. We share a dataset consisting of 200 million 3D complex structures and 2D structure scores across a consistent set of 13 million "in-stock" molecules over 15 receptors, or binding sites, across the SARS-CoV-2 proteome. Our work shows surrogate docking models have six orders of magnitude more throughput than standa… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.07036v2-abstract-full').style.display = 'inline'; document.getElementById('2106.07036v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2106.07036v2-abstract-full" style="display: none;"> We propose a benchmark to study surrogate model accuracy for protein-ligand docking. We share a dataset consisting of 200 million 3D complex structures and 2D structure scores across a consistent set of 13 million "in-stock" molecules over 15 receptors, or binding sites, across the SARS-CoV-2 proteome. Our work shows surrogate docking models have six orders of magnitude more throughput than standard docking protocols on the same supercomputer node types. We demonstrate the power of high-speed surrogate models by running each target against 1 billion molecules in under a day (50k predictions per GPU seconds). We showcase a workflow for docking utilizing surrogate ML models as a pre-filter. Our workflow is ten times faster at screening a library of compounds than the standard technique, with an error rate less than 0.01\% of detecting the underlying best scoring 0.1\% of compounds. Our analysis of the speedup explains that to screen more molecules under a docking paradigm, another order of magnitude speedup must come from model accuracy rather than computing speed (which, if increased, will not anymore alter our throughput to screen molecules). We believe this is strong evidence for the community to begin focusing on improving the accuracy of surrogate models to improve the ability to screen massive compound libraries 100x or even 1000x faster than current techniques. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2106.07036v2-abstract-full').style.display = 'none'; document.getElementById('2106.07036v2-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> 30 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 13 June, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 2021. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2103.02843">arXiv:2103.02843</a> <span> [<a href="https://arxiv.org/pdf/2103.02843">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</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="Biological Physics">physics.bio-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</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/10.1098/rsfs.2021.0018">10.1098/rsfs.2021.0018 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Pandemic Drugs at Pandemic Speed: Infrastructure for Accelerating COVID-19 Drug Discovery with Hybrid Machine Learning- and Physics-based Simulations on High Performance Computers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Bhati%2C+A+P">Agastya P. Bhati</a>, <a href="/search/q-bio?searchtype=author&query=Wan%2C+S">Shunzhou Wan</a>, <a href="/search/q-bio?searchtype=author&query=Alf%C3%A8%2C+D">Dario Alf猫</a>, <a href="/search/q-bio?searchtype=author&query=Clyde%2C+A+R">Austin R. Clyde</a>, <a href="/search/q-bio?searchtype=author&query=Bode%2C+M">Mathis Bode</a>, <a href="/search/q-bio?searchtype=author&query=Tan%2C+L">Li Tan</a>, <a href="/search/q-bio?searchtype=author&query=Titov%2C+M">Mikhail Titov</a>, <a href="/search/q-bio?searchtype=author&query=Merzky%2C+A">Andre Merzky</a>, <a href="/search/q-bio?searchtype=author&query=Turilli%2C+M">Matteo Turilli</a>, <a href="/search/q-bio?searchtype=author&query=Jha%2C+S">Shantenu Jha</a>, <a href="/search/q-bio?searchtype=author&query=Highfield%2C+R+R">Roger R. Highfield</a>, <a href="/search/q-bio?searchtype=author&query=Rocchia%2C+W">Walter Rocchia</a>, <a href="/search/q-bio?searchtype=author&query=Scafuri%2C+N">Nicola Scafuri</a>, <a href="/search/q-bio?searchtype=author&query=Succi%2C+S">Sauro Succi</a>, <a href="/search/q-bio?searchtype=author&query=Kranzlm%C3%BCller%2C+D">Dieter Kranzlm眉ller</a>, <a href="/search/q-bio?searchtype=author&query=Mathias%2C+G">Gerald Mathias</a>, <a href="/search/q-bio?searchtype=author&query=Wifling%2C+D">David Wifling</a>, <a href="/search/q-bio?searchtype=author&query=Donon%2C+Y">Yann Donon</a>, <a href="/search/q-bio?searchtype=author&query=Di+Meglio%2C+A">Alberto Di Meglio</a>, <a href="/search/q-bio?searchtype=author&query=Vallecorsa%2C+S">Sofia Vallecorsa</a>, <a href="/search/q-bio?searchtype=author&query=Ma%2C+H">Heng Ma</a>, <a href="/search/q-bio?searchtype=author&query=Trifan%2C+A">Anda Trifan</a>, <a href="/search/q-bio?searchtype=author&query=Ramanathan%2C+A">Arvind Ramanathan</a>, <a href="/search/q-bio?searchtype=author&query=Brettin%2C+T">Tom Brettin</a>, <a href="/search/q-bio?searchtype=author&query=Partin%2C+A">Alexander Partin</a> , et al. (4 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="2103.02843v2-abstract-short" style="display: inline;"> The race to meet the challenges of the global pandemic has served as a reminder that the existing drug discovery process is expensive, inefficient and slow. There is a major bottleneck screening the vast number of potential small molecules to shortlist lead compounds for antiviral drug development. New opportunities to accelerate drug discovery lie at the interface between machine learning methods… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.02843v2-abstract-full').style.display = 'inline'; document.getElementById('2103.02843v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2103.02843v2-abstract-full" style="display: none;"> The race to meet the challenges of the global pandemic has served as a reminder that the existing drug discovery process is expensive, inefficient and slow. There is a major bottleneck screening the vast number of potential small molecules to shortlist lead compounds for antiviral drug development. New opportunities to accelerate drug discovery lie at the interface between machine learning methods, in this case developed for linear accelerators, and physics-based methods. The two in silico methods, each have their own advantages and limitations which, interestingly, complement each other. Here, we present an innovative infrastructural development that combines both approaches to accelerate drug discovery. The scale of the potential resulting workflow is such that it is dependent on supercomputing to achieve extremely high throughput. We have demonstrated the viability of this workflow for the study of inhibitors for four COVID-19 target proteins and our ability to perform the required large-scale calculations to identify lead antiviral compounds through repurposing on a variety of supercomputers. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2103.02843v2-abstract-full').style.display = 'none'; document.getElementById('2103.02843v2-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 September, 2021; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 4 March, 2021; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2021. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Interface Focus. 2021. 11 (6): 20210018 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2010.06574">arXiv:2010.06574</a> <span> [<a href="https://arxiv.org/pdf/2010.06574">pdf</a>, <a href="https://arxiv.org/format/2010.06574">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</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="Quantitative Methods">q-bio.QM</span> </div> </div> <p class="title is-5 mathjax"> IMPECCABLE: Integrated Modeling PipelinE for COVID Cure by Assessing Better LEads </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Saadi%2C+A+A">Aymen Al Saadi</a>, <a href="/search/q-bio?searchtype=author&query=Alfe%2C+D">Dario Alfe</a>, <a href="/search/q-bio?searchtype=author&query=Babuji%2C+Y">Yadu Babuji</a>, <a href="/search/q-bio?searchtype=author&query=Bhati%2C+A">Agastya Bhati</a>, <a href="/search/q-bio?searchtype=author&query=Blaiszik%2C+B">Ben Blaiszik</a>, <a href="/search/q-bio?searchtype=author&query=Brettin%2C+T">Thomas Brettin</a>, <a href="/search/q-bio?searchtype=author&query=Chard%2C+K">Kyle Chard</a>, <a href="/search/q-bio?searchtype=author&query=Chard%2C+R">Ryan Chard</a>, <a href="/search/q-bio?searchtype=author&query=Coveney%2C+P">Peter Coveney</a>, <a href="/search/q-bio?searchtype=author&query=Trifan%2C+A">Anda Trifan</a>, <a href="/search/q-bio?searchtype=author&query=Brace%2C+A">Alex Brace</a>, <a href="/search/q-bio?searchtype=author&query=Clyde%2C+A">Austin Clyde</a>, <a href="/search/q-bio?searchtype=author&query=Foster%2C+I">Ian Foster</a>, <a href="/search/q-bio?searchtype=author&query=Gibbs%2C+T">Tom Gibbs</a>, <a href="/search/q-bio?searchtype=author&query=Jha%2C+S">Shantenu Jha</a>, <a href="/search/q-bio?searchtype=author&query=Keipert%2C+K">Kristopher Keipert</a>, <a href="/search/q-bio?searchtype=author&query=Kurth%2C+T">Thorsten Kurth</a>, <a href="/search/q-bio?searchtype=author&query=Kranzlm%C3%BCller%2C+D">Dieter Kranzlm眉ller</a>, <a href="/search/q-bio?searchtype=author&query=Lee%2C+H">Hyungro Lee</a>, <a href="/search/q-bio?searchtype=author&query=Li%2C+Z">Zhuozhao Li</a>, <a href="/search/q-bio?searchtype=author&query=Ma%2C+H">Heng Ma</a>, <a href="/search/q-bio?searchtype=author&query=Merzky%2C+A">Andre Merzky</a>, <a href="/search/q-bio?searchtype=author&query=Mathias%2C+G">Gerald Mathias</a>, <a href="/search/q-bio?searchtype=author&query=Partin%2C+A">Alexander Partin</a>, <a href="/search/q-bio?searchtype=author&query=Yin%2C+J">Junqi Yin</a> , et al. (11 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="2010.06574v1-abstract-short" style="display: inline;"> The drug discovery process currently employed in the pharmaceutical industry typically requires about 10 years and $2-3 billion to deliver one new drug. This is both too expensive and too slow, especially in emergencies like the COVID-19 pandemic. In silicomethodologies need to be improved to better select lead compounds that can proceed to later stages of the drug discovery protocol accelerating… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.06574v1-abstract-full').style.display = 'inline'; document.getElementById('2010.06574v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2010.06574v1-abstract-full" style="display: none;"> The drug discovery process currently employed in the pharmaceutical industry typically requires about 10 years and $2-3 billion to deliver one new drug. This is both too expensive and too slow, especially in emergencies like the COVID-19 pandemic. In silicomethodologies need to be improved to better select lead compounds that can proceed to later stages of the drug discovery protocol accelerating the entire process. No single methodological approach can achieve the necessary accuracy with required efficiency. Here we describe multiple algorithmic innovations to overcome this fundamental limitation, development and deployment of computational infrastructure at scale integrates multiple artificial intelligence and simulation-based approaches. Three measures of performance are:(i) throughput, the number of ligands per unit time; (ii) scientific performance, the number of effective ligands sampled per unit time and (iii) peak performance, in flop/s. The capabilities outlined here have been used in production for several months as the workhorse of the computational infrastructure to support the capabilities of the US-DOE National Virtual Biotechnology Laboratory in combination with resources from the EU Centre of Excellence in Computational Biomedicine. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2010.06574v1-abstract-full').style.display = 'none'; document.getElementById('2010.06574v1-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> 13 October, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 2020. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2006.02431">arXiv:2006.02431</a> <span> [<a href="https://arxiv.org/pdf/2006.02431">pdf</a>, <a href="https://arxiv.org/format/2006.02431">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> <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> <p class="title is-5 mathjax"> Targeting SARS-CoV-2 with AI- and HPC-enabled Lead Generation: A First Data Release </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Babuji%2C+Y">Yadu Babuji</a>, <a href="/search/q-bio?searchtype=author&query=Blaiszik%2C+B">Ben Blaiszik</a>, <a href="/search/q-bio?searchtype=author&query=Brettin%2C+T">Tom Brettin</a>, <a href="/search/q-bio?searchtype=author&query=Chard%2C+K">Kyle Chard</a>, <a href="/search/q-bio?searchtype=author&query=Chard%2C+R">Ryan Chard</a>, <a href="/search/q-bio?searchtype=author&query=Clyde%2C+A">Austin Clyde</a>, <a href="/search/q-bio?searchtype=author&query=Foster%2C+I">Ian Foster</a>, <a href="/search/q-bio?searchtype=author&query=Hong%2C+Z">Zhi Hong</a>, <a href="/search/q-bio?searchtype=author&query=Jha%2C+S">Shantenu Jha</a>, <a href="/search/q-bio?searchtype=author&query=Li%2C+Z">Zhuozhao Li</a>, <a href="/search/q-bio?searchtype=author&query=Liu%2C+X">Xuefeng Liu</a>, <a href="/search/q-bio?searchtype=author&query=Ramanathan%2C+A">Arvind Ramanathan</a>, <a href="/search/q-bio?searchtype=author&query=Ren%2C+Y">Yi Ren</a>, <a href="/search/q-bio?searchtype=author&query=Saint%2C+N">Nicholaus Saint</a>, <a href="/search/q-bio?searchtype=author&query=Schwarting%2C+M">Marcus Schwarting</a>, <a href="/search/q-bio?searchtype=author&query=Stevens%2C+R">Rick Stevens</a>, <a href="/search/q-bio?searchtype=author&query=van+Dam%2C+H">Hubertus van Dam</a>, <a href="/search/q-bio?searchtype=author&query=Wagner%2C+R">Rick Wagner</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="2006.02431v1-abstract-short" style="display: inline;"> Researchers across the globe are seeking to rapidly repurpose existing drugs or discover new drugs to counter the the novel coronavirus disease (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). One promising approach is to train machine learning (ML) and artificial intelligence (AI) tools to screen large numbers of small molecules. As a contribution to that effort,… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.02431v1-abstract-full').style.display = 'inline'; document.getElementById('2006.02431v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2006.02431v1-abstract-full" style="display: none;"> Researchers across the globe are seeking to rapidly repurpose existing drugs or discover new drugs to counter the the novel coronavirus disease (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). One promising approach is to train machine learning (ML) and artificial intelligence (AI) tools to screen large numbers of small molecules. As a contribution to that effort, we are aggregating numerous small molecules from a variety of sources, using high-performance computing (HPC) to computer diverse properties of those molecules, using the computed properties to train ML/AI models, and then using the resulting models for screening. In this first data release, we make available 23 datasets collected from community sources representing over 4.2 B molecules enriched with pre-computed: 1) molecular fingerprints to aid similarity searches, 2) 2D images of molecules to enable exploration and application of image-based deep learning methods, and 3) 2D and 3D molecular descriptors to speed development of machine learning models. This data release encompasses structural information on the 4.2 B molecules and 60 TB of pre-computed data. Future releases will expand the data to include more detailed molecular simulations, computed models, and other products. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2006.02431v1-abstract-full').style.display = 'none'; document.getElementById('2006.02431v1-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> 27 May, 2020; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 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">11 pages, 5 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/1908.00496">arXiv:1908.00496</a> <span> [<a href="https://arxiv.org/pdf/1908.00496">pdf</a>, <a href="https://arxiv.org/format/1908.00496">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"> Deep Generative Model Driven Protein Folding Simulation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Ma%2C+H">Heng Ma</a>, <a href="/search/q-bio?searchtype=author&query=Bhowmik%2C+D">Debsindhu Bhowmik</a>, <a href="/search/q-bio?searchtype=author&query=Lee%2C+H">Hyungro Lee</a>, <a href="/search/q-bio?searchtype=author&query=Turilli%2C+M">Matteo Turilli</a>, <a href="/search/q-bio?searchtype=author&query=Young%2C+M+T">Michael T. Young</a>, <a href="/search/q-bio?searchtype=author&query=Jha%2C+S">Shantenu Jha</a>, <a href="/search/q-bio?searchtype=author&query=Ramanathan%2C+A">Arvind Ramanathan</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="1908.00496v1-abstract-short" style="display: inline;"> Significant progress in computer hardware and software have enabled molecular dynamics (MD) simulations to model complex biological phenomena such as protein folding. However, enabling MD simulations to access biologically relevant timescales (e.g., beyond milliseconds) still remains challenging. These limitations include (1) quantifying which set of states have already been (sufficiently) sampled… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1908.00496v1-abstract-full').style.display = 'inline'; document.getElementById('1908.00496v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1908.00496v1-abstract-full" style="display: none;"> Significant progress in computer hardware and software have enabled molecular dynamics (MD) simulations to model complex biological phenomena such as protein folding. However, enabling MD simulations to access biologically relevant timescales (e.g., beyond milliseconds) still remains challenging. These limitations include (1) quantifying which set of states have already been (sufficiently) sampled in an ensemble of MD runs, and (2) identifying novel states from which simulations can be initiated to sample rare events (e.g., sampling folding events). With the recent success of deep learning and artificial intelligence techniques in analyzing large datasets, we posit that these techniques can also be used to adaptively guide MD simulations to model such complex biological phenomena. Leveraging our recently developed unsupervised deep learning technique to cluster protein folding trajectories into partially folded intermediates, we build an iterative workflow that enables our generative model to be coupled with all-atom MD simulations to fold small protein systems on emerging high performance computing platforms. We demonstrate our approach in folding Fs-peptide and the $尾尾伪$ (BBA) fold, FSD-EY. Our adaptive workflow enables us to achieve an overall root-mean squared deviation (RMSD) to the native state of 1.6$~脜$ and 4.4~$脜$ respectively for Fs-peptide and FSD-EY. We also highlight some emerging challenges in the context of designing scalable workflows when data intensive deep learning techniques are coupled to compute intensive MD simulations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1908.00496v1-abstract-full').style.display = 'none'; document.getElementById('1908.00496v1-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 August, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2019. </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">3 figures, 2 tables</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1907.06954">arXiv:1907.06954</a> <span> [<a href="https://arxiv.org/pdf/1907.06954">pdf</a>, <a href="https://arxiv.org/format/1907.06954">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 Physics">physics.comp-ph</span> </div> </div> <p class="title is-5 mathjax"> Extensible and Scalable Adaptive Sampling on Supercomputers </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Hruska%2C+E">Eugen Hruska</a>, <a href="/search/q-bio?searchtype=author&query=Balasubramanian%2C+V">Vivekanandan Balasubramanian</a>, <a href="/search/q-bio?searchtype=author&query=Lee%2C+H">Hyungro Lee</a>, <a href="/search/q-bio?searchtype=author&query=Jha%2C+S">Shantenu Jha</a>, <a href="/search/q-bio?searchtype=author&query=Clementi%2C+C">Cecilia Clementi</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="1907.06954v2-abstract-short" style="display: inline;"> The accurate sampling of protein dynamics is an ongoing challenge despite the utilization of High-Performance Computers (HPC) systems. Utilizing only "brute force" MD simulations requires an unacceptably long time to solution. Adaptive sampling methods allow a more effective sampling of protein dynamics than standard MD simulations. Depending on the restarting strategy the speed up can be more tha… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1907.06954v2-abstract-full').style.display = 'inline'; document.getElementById('1907.06954v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1907.06954v2-abstract-full" style="display: none;"> The accurate sampling of protein dynamics is an ongoing challenge despite the utilization of High-Performance Computers (HPC) systems. Utilizing only "brute force" MD simulations requires an unacceptably long time to solution. Adaptive sampling methods allow a more effective sampling of protein dynamics than standard MD simulations. Depending on the restarting strategy the speed up can be more than one order of magnitude. One challenge limiting the utilization of adaptive sampling by domain experts is the relatively high complexity of efficiently running adaptive sampling on HPC systems. We discuss how the ExTASY framework can set up new adaptive sampling strategies, and reliably execute resulting workflows at scale on HPC platforms. Here the folding dynamics of four proteins are predicted with no a priori information. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1907.06954v2-abstract-full').style.display = 'none'; document.getElementById('1907.06954v2-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> 24 September, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 16 July, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2019. </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">17 pages, 9 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/1907.00097">arXiv:1907.00097</a> <span> [<a href="https://arxiv.org/pdf/1907.00097">pdf</a>, <a href="https://arxiv.org/format/1907.00097">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Distributed, Parallel, and Cluster Computing">cs.DC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Quantitative Methods">q-bio.QM</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/10.1002/CPE.5789">10.1002/CPE.5789 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Parallel Performance of Molecular Dynamics Trajectory Analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Khoshlessan%2C+M">Mahzad Khoshlessan</a>, <a href="/search/q-bio?searchtype=author&query=Paraskevakos%2C+I">Ioannis Paraskevakos</a>, <a href="/search/q-bio?searchtype=author&query=Fox%2C+G+C">Geoffrey C. Fox</a>, <a href="/search/q-bio?searchtype=author&query=Jha%2C+S">Shantenu Jha</a>, <a href="/search/q-bio?searchtype=author&query=Beckstein%2C+O">Oliver Beckstein</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="1907.00097v4-abstract-short" style="display: inline;"> The performance of biomolecular molecular dynamics simulations has steadily increased on modern high performance computing resources but acceleration of the analysis of the output trajectories has lagged behind so that analyzing simulations is becoming a bottleneck. To close this gap, we studied the performance of parallel trajectory analysis with MPI and the Python MDAnalysis library on three dif… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1907.00097v4-abstract-full').style.display = 'inline'; document.getElementById('1907.00097v4-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1907.00097v4-abstract-full" style="display: none;"> The performance of biomolecular molecular dynamics simulations has steadily increased on modern high performance computing resources but acceleration of the analysis of the output trajectories has lagged behind so that analyzing simulations is becoming a bottleneck. To close this gap, we studied the performance of parallel trajectory analysis with MPI and the Python MDAnalysis library on three different XSEDE supercomputers where trajectories were read from a Lustre parallel file system. Strong scaling performance was impeded by stragglers, MPI processes that were slower than the typical process. Stragglers were less prevalent for compute-bound workloads, thus pointing to file reading as a bottleneck for scaling. However, a more complicated picture emerged in which both the computation and the data ingestion exhibited close to ideal strong scaling behavior whereas stragglers were primarily caused by either large MPI communication costs or long times to open the single shared trajectory file. We improved overall strong scaling performance by either subfiling (splitting the trajectory into separate files) or MPI-IO with Parallel HDF5 trajectory files. The parallel HDF5 approach resulted in near ideal strong scaling on up to 384 cores (16 nodes), thus reducing trajectory analysis times by two orders of magnitude compared to the serial approach. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1907.00097v4-abstract-full').style.display = 'none'; document.getElementById('1907.00097v4-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> 27 March, 2020; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 June, 2019; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2019. </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 manuscript, to appear in 'Concurrency and Computation: Practice and Experience'</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> D.1.3; J.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/1809.04804">arXiv:1809.04804</a> <span> [<a href="https://arxiv.org/pdf/1809.04804">pdf</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 Physics">physics.comp-ph</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.sbi.2018.09.005">10.1016/j.sbi.2018.09.005 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Adaptive ensemble simulations of biomolecules </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Kasson%2C+P+M">Peter M. Kasson</a>, <a href="/search/q-bio?searchtype=author&query=Jha%2C+S">Shantenu Jha</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="1809.04804v1-abstract-short" style="display: inline;"> Recent advances in both theory and computational power have created opportunities to simulate biomolecular processes more efficiently using adaptive ensemble simulations. Ensemble simulations are now widely used to compute a number of individual simulation trajectories and analyze statistics across them. Adaptive ensemble simulations offer a further level of sophistication and flexibility by enabl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1809.04804v1-abstract-full').style.display = 'inline'; document.getElementById('1809.04804v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="1809.04804v1-abstract-full" style="display: none;"> Recent advances in both theory and computational power have created opportunities to simulate biomolecular processes more efficiently using adaptive ensemble simulations. Ensemble simulations are now widely used to compute a number of individual simulation trajectories and analyze statistics across them. Adaptive ensemble simulations offer a further level of sophistication and flexibility by enabling high-level algorithms to control simulations based on intermediate results. We review some of the adaptive ensemble algorithms and software infrastructure currently in use and outline where the complexities of implementing adaptive simulation have limited algorithmic innovation to date. We describe an adaptive ensemble API to overcome some of these barriers and more flexibly and simply express adaptive simulation algorithms to help realize the power of this type of simulation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('1809.04804v1-abstract-full').style.display = 'none'; document.getElementById('1809.04804v1-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> 13 September, 2018; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> September 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">Manuscript accepted for publication in Current Opinion in Structural Biology</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Current Opinion in Structural Biology 2018. 52:87-94 </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