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 1–50 of 125 results for author: <span class="mathjax">Zhang, Z</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=Zhang%2C+Z">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="Zhang, Z"> </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=Zhang%2C+Z&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="Zhang, Z"> <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> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Zhang%2C+Z&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Zhang%2C+Z&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+Z&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+Z&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> </ul> </nav> <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/2502.07671">arXiv:2502.07671</a> <span> [<a href="https://arxiv.org/pdf/2502.07671">pdf</a>, <a href="https://arxiv.org/format/2502.07671">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"> Steering Protein Family Design through Profile Bayesian Flow </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Gong%2C+J">Jingjing Gong</a>, <a href="/search/q-bio?searchtype=author&query=Pei%2C+Y">Yu Pei</a>, <a href="/search/q-bio?searchtype=author&query=Long%2C+S">Siyu Long</a>, <a href="/search/q-bio?searchtype=author&query=Song%2C+Y">Yuxuan Song</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhe Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Huang%2C+W">Wenhao Huang</a>, <a href="/search/q-bio?searchtype=author&query=Cao%2C+Z">Ziyao Cao</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+S">Shuyi Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Zhou%2C+H">Hao Zhou</a>, <a href="/search/q-bio?searchtype=author&query=Ma%2C+W">Wei-Ying Ma</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="2502.07671v1-abstract-short" style="display: inline;"> Protein family design emerges as a promising alternative by combining the advantages of de novo protein design and mutation-based directed evolution.In this paper, we propose ProfileBFN, the Profile Bayesian Flow Networks, for specifically generative modeling of protein families. ProfileBFN extends the discrete Bayesian Flow Network from an MSA profile perspective, which can be trained on single p… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.07671v1-abstract-full').style.display = 'inline'; document.getElementById('2502.07671v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2502.07671v1-abstract-full" style="display: none;"> Protein family design emerges as a promising alternative by combining the advantages of de novo protein design and mutation-based directed evolution.In this paper, we propose ProfileBFN, the Profile Bayesian Flow Networks, for specifically generative modeling of protein families. ProfileBFN extends the discrete Bayesian Flow Network from an MSA profile perspective, which can be trained on single protein sequences by regarding it as a degenerate profile, thereby achieving efficient protein family design by avoiding large-scale MSA data construction and training. Empirical results show that ProfileBFN has a profound understanding of proteins. When generating diverse and novel family proteins, it can accurately capture the structural characteristics of the family. The enzyme produced by this method is more likely than the previous approach to have the corresponding function, offering better odds of generating diverse proteins with the desired functionality. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2502.07671v1-abstract-full').style.display = 'none'; document.getElementById('2502.07671v1-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 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/2501.18772">arXiv:2501.18772</a> <span> [<a href="https://arxiv.org/pdf/2501.18772">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Neurons and Cognition">q-bio.NC</span> </div> </div> <p class="title is-5 mathjax"> Dissociated Neuronal Cultures as Model Systems for Self-Organized Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Yaron%2C+A">Amit Yaron</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhuo Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Akita%2C+D">Dai Akita</a>, <a href="/search/q-bio?searchtype=author&query=Shiramatsu%2C+T+I">Tomoyo Isoguchi Shiramatsu</a>, <a href="/search/q-bio?searchtype=author&query=Chao%2C+Z">Zenas Chao</a>, <a href="/search/q-bio?searchtype=author&query=Takahashi%2C+H">Hirokazu Takahashi</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="2501.18772v1-abstract-short" style="display: inline;"> Dissociated neuronal cultures provide a simplified yet effective model system for investigating self-organized prediction and information processing in neural networks. This review consolidates current research demonstrating that these in vitro networks display fundamental computational capabilities, including predictive coding, adaptive learning, goal-directed behavior, and deviance detection. We… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18772v1-abstract-full').style.display = 'inline'; document.getElementById('2501.18772v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.18772v1-abstract-full" style="display: none;"> Dissociated neuronal cultures provide a simplified yet effective model system for investigating self-organized prediction and information processing in neural networks. This review consolidates current research demonstrating that these in vitro networks display fundamental computational capabilities, including predictive coding, adaptive learning, goal-directed behavior, and deviance detection. We examine how these cultures develop critical dynamics optimized for information processing, detail the mechanisms underlying learning and memory formation, and explore the relevance of the free energy principle within these systems. Building on these insights, we discuss how findings from dissociated neuronal cultures inform the design of neuromorphic and reservoir computing architectures, with the potential to enhance energy efficiency and adaptive functionality in artificial intelligence. The reduced complexity of neuronal cultures allows for precise manipulation and systematic investigation, bridging theoretical frameworks with practical implementations in bio-inspired computing. Finally, we highlight promising future directions, emphasizing advancements in three-dimensional culture techniques, multi-compartment models, and brain organoids that deepen our understanding of hierarchical and predictive processes in both biological and artificial systems. This review aims to provide a comprehensive overview of how dissociated neuronal cultures contribute to neuroscience and artificial intelligence, ultimately paving the way for biologically inspired computing solutions. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.18772v1-abstract-full').style.display = 'none'; document.getElementById('2501.18772v1-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </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">39 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/2501.05012">arXiv:2501.05012</a> <span> [<a href="https://arxiv.org/pdf/2501.05012">pdf</a>, <a href="https://arxiv.org/format/2501.05012">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</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"> SyNPar: Synthetic Null Data Parallelism for High-Power False Discovery Rate Control in High-Dimensional Variable Selection </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Wang%2C+C">Changhu Wang</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Ziheng Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Li%2C+J+J">Jingyi Jessica Li</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="2501.05012v1-abstract-short" style="display: inline;"> Balancing false discovery rate (FDR) and statistical power to ensure reliable discoveries is a key challenge in high-dimensional variable selection. Although several FDR control methods have been proposed, most involve perturbing the original data, either by concatenating knockoff variables or splitting the data into two halves, both of which can lead to a loss of power. In this paper, we introduc… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.05012v1-abstract-full').style.display = 'inline'; document.getElementById('2501.05012v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2501.05012v1-abstract-full" style="display: none;"> Balancing false discovery rate (FDR) and statistical power to ensure reliable discoveries is a key challenge in high-dimensional variable selection. Although several FDR control methods have been proposed, most involve perturbing the original data, either by concatenating knockoff variables or splitting the data into two halves, both of which can lead to a loss of power. In this paper, we introduce a novel approach called Synthetic Null Parallelism (SyNPar), which controls the FDR in high-dimensional variable selection while preserving the original data. SyNPar generates synthetic null data from a model fitted to the original data and modified to reflect the null hypothesis. It then applies the same estimation procedure in parallel to both the original and synthetic null data to estimate coefficients that indicate feature importance. By comparing the coefficients estimated from the null data with those from the original data, SyNPar effectively identifies false positives, functioning as a numerical analog of a likelihood ratio test. We provide theoretical guarantees for FDR control at any desired level while ensuring that the power approaches one with high probability asymptotically. SyNPar is straightforward to implement and can be applied to a wide range of statistical models, including high-dimensional linear regression, generalized linear models, Cox models, and Gaussian graphical models. Through extensive simulations and real data applications, we demonstrate that SyNPar outperforms state-of-the-art methods, including knockoffs and data-splitting methods, in terms of FDR control, power, and computational efficiency. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2501.05012v1-abstract-full').style.display = 'none'; document.getElementById('2501.05012v1-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 January, 2025; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2025. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2412.15560">arXiv:2412.15560</a> <span> [<a href="https://arxiv.org/pdf/2412.15560">pdf</a>, <a href="https://arxiv.org/format/2412.15560">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Machine Learning">cs.LG</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Sound">cs.SD</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Audio and Speech Processing">eess.AS</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Signal Processing">eess.SP</span> </div> </div> <p class="title is-5 mathjax"> Predicting Artificial Neural Network Representations to Learn Recognition Model for Music Identification from Brain Recordings </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Akama%2C+T">Taketo Akama</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhuohao Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Li%2C+P">Pengcheng Li</a>, <a href="/search/q-bio?searchtype=author&query=Hongo%2C+K">Kotaro Hongo</a>, <a href="/search/q-bio?searchtype=author&query=Kitano%2C+H">Hiroaki Kitano</a>, <a href="/search/q-bio?searchtype=author&query=Minamikawa%2C+S">Shun Minamikawa</a>, <a href="/search/q-bio?searchtype=author&query=Polouliakh%2C+N">Natalia Polouliakh</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="2412.15560v1-abstract-short" style="display: inline;"> Recent studies have demonstrated that the representations of artificial neural networks (ANNs) can exhibit notable similarities to cortical representations when subjected to identical auditory sensory inputs. In these studies, the ability to predict cortical representations is probed by regressing from ANN representations to cortical representations. Building upon this concept, our approach revers… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.15560v1-abstract-full').style.display = 'inline'; document.getElementById('2412.15560v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.15560v1-abstract-full" style="display: none;"> Recent studies have demonstrated that the representations of artificial neural networks (ANNs) can exhibit notable similarities to cortical representations when subjected to identical auditory sensory inputs. In these studies, the ability to predict cortical representations is probed by regressing from ANN representations to cortical representations. Building upon this concept, our approach reverses the direction of prediction: we utilize ANN representations as a supervisory signal to train recognition models using noisy brain recordings obtained through non-invasive measurements. Specifically, we focus on constructing a recognition model for music identification, where electroencephalography (EEG) brain recordings collected during music listening serve as input. By training an EEG recognition model to predict ANN representations-representations associated with music identification-we observed a substantial improvement in classification accuracy. This study introduces a novel approach to developing recognition models for brain recordings in response to external auditory stimuli. It holds promise for advancing brain-computer interfaces (BCI), neural decoding techniques, and our understanding of music cognition. Furthermore, it provides new insights into the relationship between auditory brain activity and ANN representations. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.15560v1-abstract-full').style.display = 'none'; document.getElementById('2412.15560v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">18 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/2412.01108">arXiv:2412.01108</a> <span> [<a href="https://arxiv.org/pdf/2412.01108">pdf</a>, <a href="https://arxiv.org/format/2412.01108">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"> Multi-Scale Representation Learning for Protein Fitness Prediction </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zuobai Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Notin%2C+P">Pascal Notin</a>, <a href="/search/q-bio?searchtype=author&query=Huang%2C+Y">Yining Huang</a>, <a href="/search/q-bio?searchtype=author&query=Lozano%2C+A">Aur茅lie Lozano</a>, <a href="/search/q-bio?searchtype=author&query=Chenthamarakshan%2C+V">Vijil Chenthamarakshan</a>, <a href="/search/q-bio?searchtype=author&query=Marks%2C+D">Debora Marks</a>, <a href="/search/q-bio?searchtype=author&query=Das%2C+P">Payel Das</a>, <a href="/search/q-bio?searchtype=author&query=Tang%2C+J">Jian Tang</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="2412.01108v1-abstract-short" style="display: inline;"> Designing novel functional proteins crucially depends on accurately modeling their fitness landscape. Given the limited availability of functional annotations from wet-lab experiments, previous methods have primarily relied on self-supervised models trained on vast, unlabeled protein sequence or structure datasets. While initial protein representation learning studies solely focused on either sequ… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.01108v1-abstract-full').style.display = 'inline'; document.getElementById('2412.01108v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2412.01108v1-abstract-full" style="display: none;"> Designing novel functional proteins crucially depends on accurately modeling their fitness landscape. Given the limited availability of functional annotations from wet-lab experiments, previous methods have primarily relied on self-supervised models trained on vast, unlabeled protein sequence or structure datasets. While initial protein representation learning studies solely focused on either sequence or structural features, recent hybrid architectures have sought to merge these modalities to harness their respective strengths. However, these sequence-structure models have so far achieved only incremental improvements when compared to the leading sequence-only approaches, highlighting unresolved challenges effectively leveraging these modalities together. Moreover, the function of certain proteins is highly dependent on the granular aspects of their surface topology, which have been overlooked by prior models. To address these limitations, we introduce the Sequence-Structure-Surface Fitness (S3F) model - a novel multimodal representation learning framework that integrates protein features across several scales. Our approach combines sequence representations from a protein language model with Geometric Vector Perceptron networks encoding protein backbone and detailed surface topology. The proposed method achieves state-of-the-art fitness prediction on the ProteinGym benchmark encompassing 217 substitution deep mutational scanning assays, and provides insights into the determinants of protein function. Our code is at https://github.com/DeepGraphLearning/S3F. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2412.01108v1-abstract-full').style.display = 'none'; document.getElementById('2412.01108v1-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 December, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2411.15467">arXiv:2411.15467</a> <span> [<a href="https://arxiv.org/pdf/2411.15467">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Genomics">q-bio.GN</span> </div> </div> <p class="title is-5 mathjax"> The Updated Genome Warehouse: Enhancing Data Value, Security, and Usability to Address Data Expansion </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Ma%2C+Y">Yingke Ma</a>, <a href="/search/q-bio?searchtype=author&query=Zhao%2C+X">Xuetong Zhao</a>, <a href="/search/q-bio?searchtype=author&query=Jia%2C+Y">Yaokai Jia</a>, <a href="/search/q-bio?searchtype=author&query=Han%2C+Z">Zhenxian Han</a>, <a href="/search/q-bio?searchtype=author&query=Yu%2C+C">Caixia Yu</a>, <a href="/search/q-bio?searchtype=author&query=Fan%2C+Z">Zhuojing Fan</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhang Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Xiao%2C+J">Jingfa Xiao</a>, <a href="/search/q-bio?searchtype=author&query=Zhao%2C+W">Wenming Zhao</a>, <a href="/search/q-bio?searchtype=author&query=Bao%2C+Y">Yiming Bao</a>, <a href="/search/q-bio?searchtype=author&query=Chen%2C+M">Meili Chen</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="2411.15467v1-abstract-short" style="display: inline;"> The Genome Warehouse (GWH), accessible at https://ngdc.cncb.ac.cn/gwh, is an extensively utilized public repository dedicated to the deposition, management and sharing of genome assembly sequences, annotations, and metadata. This paper highlights noteworthy enhancements to the GWH since the 2021 version, emphasizing substantial advancements in web interfaces for data submission, database functiona… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15467v1-abstract-full').style.display = 'inline'; document.getElementById('2411.15467v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.15467v1-abstract-full" style="display: none;"> The Genome Warehouse (GWH), accessible at https://ngdc.cncb.ac.cn/gwh, is an extensively utilized public repository dedicated to the deposition, management and sharing of genome assembly sequences, annotations, and metadata. This paper highlights noteworthy enhancements to the GWH since the 2021 version, emphasizing substantial advancements in web interfaces for data submission, database functionality updates, and resource integration. Key updates include the reannotation of released prokaryotic genomes, mirroring of genome resources from National Center for Biotechnology Information (NCBI) GenBank and RefSeq, integration of Poxviridae sequences, implementation of an online batch submission system, enhancements to the quality control system, advanced search capabilities, and the introduction of a controlled-access mechanism for human genome data. These improvements collectively augment the ease and security of data submission and access as well as genome data value, thereby fostering heightened convenience and utility for researchers in the genomic field. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.15467v1-abstract-full').style.display = 'none'; document.getElementById('2411.15467v1-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> 23 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">17 pages, 2 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/2411.13280">arXiv:2411.13280</a> <span> [<a href="https://arxiv.org/pdf/2411.13280">pdf</a>, <a href="https://arxiv.org/format/2411.13280">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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Structure-Based Molecule Optimization via Gradient-Guided Bayesian Update </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Qiu%2C+K">Keyue Qiu</a>, <a href="/search/q-bio?searchtype=author&query=Song%2C+Y">Yuxuan Song</a>, <a href="/search/q-bio?searchtype=author&query=Yu%2C+J">Jie Yu</a>, <a href="/search/q-bio?searchtype=author&query=Ma%2C+H">Hongbo Ma</a>, <a href="/search/q-bio?searchtype=author&query=Cao%2C+Z">Ziyao Cao</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhilong Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Wu%2C+Y">Yushuai Wu</a>, <a href="/search/q-bio?searchtype=author&query=Zheng%2C+M">Mingyue Zheng</a>, <a href="/search/q-bio?searchtype=author&query=Zhou%2C+H">Hao Zhou</a>, <a href="/search/q-bio?searchtype=author&query=Ma%2C+W">Wei-Ying Ma</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="2411.13280v2-abstract-short" style="display: inline;"> Structure-based molecule optimization (SBMO) aims to optimize molecules with both continuous coordinates and discrete types against protein targets. A promising direction is to exert gradient guidance on generative models given its remarkable success in images, but it is challenging to guide discrete data and risks inconsistencies between modalities. To this end, we leverage a continuous and diffe… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13280v2-abstract-full').style.display = 'inline'; document.getElementById('2411.13280v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2411.13280v2-abstract-full" style="display: none;"> Structure-based molecule optimization (SBMO) aims to optimize molecules with both continuous coordinates and discrete types against protein targets. A promising direction is to exert gradient guidance on generative models given its remarkable success in images, but it is challenging to guide discrete data and risks inconsistencies between modalities. To this end, we leverage a continuous and differentiable space derived through Bayesian inference, presenting Molecule Joint Optimization (MolJO), the first gradient-based SBMO framework that facilitates joint guidance signals across different modalities while preserving SE(3)-equivariance. We introduce a novel backward correction strategy that optimizes within a sliding window of the past histories, allowing for a seamless trade-off between explore-and-exploit during optimization. Our proposed MolJO achieves state-of-the-art performance on CrossDocked2020 benchmark (Success Rate 51.3% , Vina Dock -9.05 and SA 0.78), more than 4x improvement in Success Rate compared to the gradient-based counterpart, and 2x "Me-Better" Ratio as much as 3D baselines. Furthermore, we extend MolJO to a wide range of optimization settings, including multi-objective optimization and challenging tasks in drug design such as R-group optimization and scaffold hopping, further underscoring its versatility and potential. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2411.13280v2-abstract-full').style.display = 'none'; document.getElementById('2411.13280v2-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> 21 November, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 20 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">27 pages, 17 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/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/2410.11224">arXiv:2410.11224</a> <span> [<a href="https://arxiv.org/pdf/2410.11224">pdf</a>, <a href="https://arxiv.org/format/2410.11224">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"> DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Docking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Yan%2C+J">Jiaxian Yan</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zaixi Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Zhu%2C+J">Jintao Zhu</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+K">Kai Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Pei%2C+J">Jianfeng Pei</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="2410.11224v2-abstract-short" style="display: inline;"> Molecular docking, a technique for predicting ligand binding poses, is crucial in structure-based drug design for understanding protein-ligand interactions. Recent advancements in docking methods, particularly those leveraging geometric deep learning (GDL), have demonstrated significant efficiency and accuracy advantages over traditional sampling methods. Despite these advancements, current method… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11224v2-abstract-full').style.display = 'inline'; document.getElementById('2410.11224v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.11224v2-abstract-full" style="display: none;"> Molecular docking, a technique for predicting ligand binding poses, is crucial in structure-based drug design for understanding protein-ligand interactions. Recent advancements in docking methods, particularly those leveraging geometric deep learning (GDL), have demonstrated significant efficiency and accuracy advantages over traditional sampling methods. Despite these advancements, current methods are often tailored for specific docking settings, and limitations such as the neglect of protein side-chain structures, difficulties in handling large binding pockets, and challenges in predicting physically valid structures exist. To accommodate various docking settings and achieve accurate, efficient, and physically reliable docking, we propose a novel two-stage docking framework, DeltaDock, consisting of pocket prediction and site-specific docking. We innovatively reframe the pocket prediction task as a pocket-ligand alignment problem rather than direct prediction in the first stage. Then we follow a bi-level coarse-to-fine iterative refinement process to perform site-specific docking. Comprehensive experiments demonstrate the superior performance of DeltaDock. Notably, in the blind docking setting, DeltaDock achieves a 31\% relative improvement over the docking success rate compared with the previous state-of-the-art GDL model. With the consideration of physical validity, this improvement increases to about 300\%. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.11224v2-abstract-full').style.display = 'none'; document.getElementById('2410.11224v2-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 14 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 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'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/2410.04351">arXiv:2410.04351</a> <span> [<a href="https://arxiv.org/pdf/2410.04351">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Tissues and Organs">q-bio.TO</span> </div> </div> <p class="title is-5 mathjax"> An asymmetric surface coating strategy for promotes rapid endothelialization in the rabbit carotid artery </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Tan%2C+L">Lili Tan</a>, <a href="/search/q-bio?searchtype=author&query=Ye%2C+Z">Zhiyi Ye</a>, <a href="/search/q-bio?searchtype=author&query=Yu%2C+S">Suhua Yu</a>, <a href="/search/q-bio?searchtype=author&query=Wang%2C+J">Jinxuan Wang</a>, <a href="/search/q-bio?searchtype=author&query=Ouyang%2C+C">Chenxi Ouyang</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhengcai Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Guidoin%2C+R">Robert Guidoin</a>, <a href="/search/q-bio?searchtype=author&query=Wang%2C+G">Guixue 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="2410.04351v1-abstract-short" style="display: inline;"> Studying surface modification has long been a key area for enhancing the effects of vascular stents after surgery. The study aimed to develop an asymmetric drug-eluting stent (ADES) with differential drug loading on its inner and outer surfaces, hypothesizing that this design would enhance drug delivery efficacy for percutaneous coronary interventions (PCIs) compared to uniformly coated drug-eluti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04351v1-abstract-full').style.display = 'inline'; document.getElementById('2410.04351v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.04351v1-abstract-full" style="display: none;"> Studying surface modification has long been a key area for enhancing the effects of vascular stents after surgery. The study aimed to develop an asymmetric drug-eluting stent (ADES) with differential drug loading on its inner and outer surfaces, hypothesizing that this design would enhance drug delivery efficacy for percutaneous coronary interventions (PCIs) compared to uniformly coated drug-eluting stents (UDES). An ultrasonic atomization spraying device was utilized to fabricate the ADES, which was subsequently evaluated for drug release patterns, hemocompatibility, and biocompatibility. In vitro, assessments demonstrated favorable hemocompatibility and showed targeted drug delivery capabilities of ADES within artificial blood vessels. Furthermore, in vivo testing using a rabbit carotid artery model revealed significant endothelialization on stented segments treated with the ADES. These findings suggest that the ADES holds promise as a minimally invasive platform for improving cardiovascular disease treatment outcomes by addressing thrombus formation and neointima proliferation more effectively than traditional stents. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.04351v1-abstract-full').style.display = 'none'; document.getElementById('2410.04351v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 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">24 pages,7 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/2410.01858">arXiv:2410.01858</a> <span> [<a href="https://arxiv.org/pdf/2410.01858">pdf</a>, <a href="https://arxiv.org/format/2410.01858">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Cell Behavior">q-bio.CB</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="Genomics">q-bio.GN</span> </div> </div> <p class="title is-5 mathjax"> Long-range gene expression prediction with token alignment of large language model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Honig%2C+E">Edouardo Honig</a>, <a href="/search/q-bio?searchtype=author&query=Zhan%2C+H">Huixin Zhan</a>, <a href="/search/q-bio?searchtype=author&query=Wu%2C+Y+N">Ying Nian Wu</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z+F">Zijun Frank Zhang</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="2410.01858v1-abstract-short" style="display: inline;"> Gene expression is a cellular process that plays a fundamental role in human phenotypical variations and diseases. Despite advances of deep learning models for gene expression prediction, recent benchmarks have revealed their inability to learn distal regulatory grammar. Here, we address this challenge by leveraging a pretrained large language model to enhance gene expression prediction. We introd… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01858v1-abstract-full').style.display = 'inline'; document.getElementById('2410.01858v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.01858v1-abstract-full" style="display: none;"> Gene expression is a cellular process that plays a fundamental role in human phenotypical variations and diseases. Despite advances of deep learning models for gene expression prediction, recent benchmarks have revealed their inability to learn distal regulatory grammar. Here, we address this challenge by leveraging a pretrained large language model to enhance gene expression prediction. We introduce Genetic sequence Token Alignment (GTA), which aligns genetic sequence features with natural language tokens, allowing for symbolic reasoning of genomic sequence features via the frozen language model. This cross-modal adaptation learns the regulatory grammar and allows us to further incorporate gene-specific human annotations as prompts, enabling in-context learning that is not possible with existing models. Trained on lymphoblastoid cells, GTA was evaluated on cells from the Geuvadis consortium and outperforms state-of-the-art models such as Enformer, achieving a Spearman correlation of 0.65, a 10\% improvement. Additionally, GTA offers improved interpretation of long-range interactions through the identification of the most meaningful sections of the input genetic context. GTA represents a powerful and novel cross-modal approach to gene expression prediction by utilizing a pretrained language model, in a paradigm shift from conventional gene expression models trained only on sequence data. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.01858v1-abstract-full').style.display = 'none'; document.getElementById('2410.01858v1-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 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 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">14 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/2410.00844">arXiv:2410.00844</a> <span> [<a href="https://arxiv.org/pdf/2410.00844">pdf</a>, <a href="https://arxiv.org/format/2410.00844">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="Optimization and Control">math.OC</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Computational Physics">physics.comp-ph</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"> Learning Stochastic Dynamics from Snapshots through Regularized Unbalanced Optimal Transport </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhenyi Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Li%2C+T">Tiejun Li</a>, <a href="/search/q-bio?searchtype=author&query=Zhou%2C+P">Peijie Zhou</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="2410.00844v2-abstract-short" style="display: inline;"> Reconstructing dynamics using samples from sparsely time-resolved snapshots is an important problem in both natural sciences and machine learning. Here, we introduce a new deep learning approach for solving regularized unbalanced optimal transport (RUOT) and inferring continuous unbalanced stochastic dynamics from observed snapshots. Based on the RUOT form, our method models these dynamics without… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00844v2-abstract-full').style.display = 'inline'; document.getElementById('2410.00844v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2410.00844v2-abstract-full" style="display: none;"> Reconstructing dynamics using samples from sparsely time-resolved snapshots is an important problem in both natural sciences and machine learning. Here, we introduce a new deep learning approach for solving regularized unbalanced optimal transport (RUOT) and inferring continuous unbalanced stochastic dynamics from observed snapshots. Based on the RUOT form, our method models these dynamics without requiring prior knowledge of growth and death processes or additional information, allowing them to be learned directly from data. Theoretically, we explore the connections between the RUOT and Schr枚dinger bridge problem and discuss the key challenges and potential solutions. The effectiveness of our method is demonstrated with a synthetic gene regulatory network, high-dimensional Gaussian Mixture Model, and single-cell RNA-seq data from blood development. Compared with other methods, our approach accurately identifies growth and transition patterns, eliminates false transitions, and constructs the Waddington developmental landscape. Our code is available at: https://github.com/zhenyiizhang/DeepRUOT. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2410.00844v2-abstract-full').style.display = 'none'; document.getElementById('2410.00844v2-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 February, 2025; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 October, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> October 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">Published as a conference paper at ICLR 2025 (oral)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.19645">arXiv:2409.19645</a> <span> [<a href="https://arxiv.org/pdf/2409.19645">pdf</a>, <a href="https://arxiv.org/format/2409.19645">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"> FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling </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=Wang%2C+M">Mengdi Wang</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="2409.19645v1-abstract-short" style="display: inline;"> Structure-based drug design (SBDD), which aims to generate 3D ligand molecules binding to target proteins, is a fundamental task in drug discovery. Existing SBDD methods typically treat protein as rigid and neglect protein structural change when binding with ligand molecules, leading to a big gap with real-world scenarios and inferior generation qualities (e.g., many steric clashes). To bridge the… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19645v1-abstract-full').style.display = 'inline'; document.getElementById('2409.19645v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2409.19645v1-abstract-full" style="display: none;"> Structure-based drug design (SBDD), which aims to generate 3D ligand molecules binding to target proteins, is a fundamental task in drug discovery. Existing SBDD methods typically treat protein as rigid and neglect protein structural change when binding with ligand molecules, leading to a big gap with real-world scenarios and inferior generation qualities (e.g., many steric clashes). To bridge the gap, we propose FlexSBDD, a deep generative model capable of accurately modeling the flexible protein-ligand complex structure for ligand molecule generation. FlexSBDD adopts an efficient flow matching framework and leverages E(3)-equivariant network with scalar-vector dual representation to model dynamic structural changes. Moreover, novel data augmentation schemes based on structure relaxation/sidechain repacking are adopted to boost performance. Extensive experiments demonstrate that FlexSBDD achieves state-of-the-art performance in generating high-affinity molecules and effectively modeling the protein's conformation change to increase favorable protein-ligand interactions (e.g., Hydrogen bonds) and decrease steric clashes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2409.19645v1-abstract-full').style.display = 'none'; document.getElementById('2409.19645v1-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> 29 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</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2409.19520">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/2408.16791">arXiv:2408.16791</a> <span> [<a href="https://arxiv.org/pdf/2408.16791">pdf</a>, <a href="https://arxiv.org/format/2408.16791">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> Multi-faceted Neuroimaging Data Integration via Analysis of Subspaces </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Ackerman%2C+A">Andrew Ackerman</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhengwu Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Hannig%2C+J">Jan Hannig</a>, <a href="/search/q-bio?searchtype=author&query=Prothero%2C+J">Jack Prothero</a>, <a href="/search/q-bio?searchtype=author&query=Marron%2C+J+S">J. S. Marron</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="2408.16791v1-abstract-short" style="display: inline;"> Neuroimaging studies, such as the Human Connectome Project (HCP), often collect multi-faceted and multi-block data to study the complex human brain. However, these data are often analyzed in a pairwise fashion, which can hinder our understanding of how different brain-related measures interact with each other. In this study, we comprehensively analyze the multi-block HCP data using the Data Integr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.16791v1-abstract-full').style.display = 'inline'; document.getElementById('2408.16791v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2408.16791v1-abstract-full" style="display: none;"> Neuroimaging studies, such as the Human Connectome Project (HCP), often collect multi-faceted and multi-block data to study the complex human brain. However, these data are often analyzed in a pairwise fashion, which can hinder our understanding of how different brain-related measures interact with each other. In this study, we comprehensively analyze the multi-block HCP data using the Data Integration via Analysis of Subspaces (DIVAS) method. We integrate structural and functional brain connectivity, substance use, cognition, and genetics in an exhaustive five-block analysis. This gives rise to the important finding that genetics is the single data modality most predictive of brain connectivity, outside of brain connectivity itself. Nearly 14\% of the variation in functional connectivity (FC) and roughly 12\% of the variation in structural connectivity (SC) is attributed to shared spaces with genetics. Moreover, investigations of shared space loadings provide interpretable associations between particular brain regions and drivers of variability, such as alcohol consumption in the substance-use data block. Novel Jackstraw hypothesis tests are developed for the DIVAS framework to establish statistically significant loadings. For example, in the (FC, SC, and Substance Use) shared space, these novel hypothesis tests highlight largely negative functional and structural connections suggesting the brain's role in physiological responses to increased substance use. Furthermore, our findings have been validated using a subset of genetically relevant siblings or twins not studied in the main analysis. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2408.16791v1-abstract-full').style.display = 'none'; document.getElementById('2408.16791v1-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, 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">38 pages, 6 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/2407.19349">arXiv:2407.19349</a> <span> [<a href="https://arxiv.org/pdf/2407.19349">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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Predicting T-Cell Receptor Specificity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Tu%2C+T">Tengyao Tu</a>, <a href="/search/q-bio?searchtype=author&query=Zeng%2C+W">Wei Zeng</a>, <a href="/search/q-bio?searchtype=author&query=Zhao%2C+K">Kun Zhao</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhenyu Zhang</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="2407.19349v1-abstract-short" style="display: inline;"> Researching the specificity of TCR contributes to the development of immunotherapy and provides new opportunities and strategies for personalized cancer immunotherapy. Therefore, we established a TCR generative specificity detection framework consisting of an antigen selector and a TCR classifier based on the Random Forest algorithm, aiming to efficiently screen out TCRs and target antigens and ac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.19349v1-abstract-full').style.display = 'inline'; document.getElementById('2407.19349v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2407.19349v1-abstract-full" style="display: none;"> Researching the specificity of TCR contributes to the development of immunotherapy and provides new opportunities and strategies for personalized cancer immunotherapy. Therefore, we established a TCR generative specificity detection framework consisting of an antigen selector and a TCR classifier based on the Random Forest algorithm, aiming to efficiently screen out TCRs and target antigens and achieve TCR specificity prediction. Furthermore, we used the k-fold validation method to compare the performance of our model with ordinary deep learning methods. The result proves that adding a classifier to the model based on the random forest algorithm is very effective, and our model generally outperforms ordinary deep learning methods. Moreover, we put forward feasible optimization suggestions for the shortcomings and challenges of our model found during model implementation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2407.19349v1-abstract-full').style.display = 'none'; document.getElementById('2407.19349v1-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 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/2406.13864">arXiv:2406.13864</a> <span> [<a href="https://arxiv.org/pdf/2406.13864">pdf</a>, <a href="https://arxiv.org/format/2406.13864">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"> Evaluating representation learning on the protein structure universe </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Jamasb%2C+A+R">Arian R. Jamasb</a>, <a href="/search/q-bio?searchtype=author&query=Morehead%2C+A">Alex Morehead</a>, <a href="/search/q-bio?searchtype=author&query=Joshi%2C+C+K">Chaitanya K. Joshi</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zuobai Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Didi%2C+K">Kieran Didi</a>, <a href="/search/q-bio?searchtype=author&query=Mathis%2C+S+V">Simon V. Mathis</a>, <a href="/search/q-bio?searchtype=author&query=Harris%2C+C">Charles Harris</a>, <a href="/search/q-bio?searchtype=author&query=Tang%2C+J">Jian Tang</a>, <a href="/search/q-bio?searchtype=author&query=Cheng%2C+J">Jianlin Cheng</a>, <a href="/search/q-bio?searchtype=author&query=Lio%2C+P">Pietro Lio</a>, <a href="/search/q-bio?searchtype=author&query=Blundell%2C+T+L">Tom L. Blundell</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="2406.13864v1-abstract-short" style="display: inline;"> We introduce ProteinWorkshop, a comprehensive benchmark suite for representation learning on protein structures with Geometric Graph Neural Networks. We consider large-scale pre-training and downstream tasks on both experimental and predicted structures to enable the systematic evaluation of the quality of the learned structural representation and their usefulness in capturing functional relations… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.13864v1-abstract-full').style.display = 'inline'; document.getElementById('2406.13864v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.13864v1-abstract-full" style="display: none;"> We introduce ProteinWorkshop, a comprehensive benchmark suite for representation learning on protein structures with Geometric Graph Neural Networks. We consider large-scale pre-training and downstream tasks on both experimental and predicted structures to enable the systematic evaluation of the quality of the learned structural representation and their usefulness in capturing functional relationships for downstream tasks. We find that: (1) large-scale pretraining on AlphaFold structures and auxiliary tasks consistently improve the performance of both rotation-invariant and equivariant GNNs, and (2) more expressive equivariant GNNs benefit from pretraining to a greater extent compared to invariant models. We aim to establish a common ground for the machine learning and computational biology communities to rigorously compare and advance protein structure representation learning. Our open-source codebase reduces the barrier to entry for working with large protein structure datasets by providing: (1) storage-efficient dataloaders for large-scale structural databases including AlphaFoldDB and ESM Atlas, as well as (2) utilities for constructing new tasks from the entire PDB. ProteinWorkshop is available at: github.com/a-r-j/ProteinWorkshop. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.13864v1-abstract-full').style.display = 'none'; document.getElementById('2406.13864v1-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 June, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> June 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">ICLR 2024</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/2406.00164">arXiv:2406.00164</a> <span> [<a href="https://arxiv.org/pdf/2406.00164">pdf</a>, <a href="https://arxiv.org/format/2406.00164">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Genomics">q-bio.GN</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> DYNA: Disease-Specific Language Model for Variant Pathogenicity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhan%2C+H">Huixin Zhan</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zijun Zhang</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="2406.00164v1-abstract-short" style="display: inline;"> Clinical variant classification of pathogenic versus benign genetic variants remains a challenge in clinical genetics. Recently, the proposition of genomic foundation models has improved the generic variant effect prediction (VEP) accuracy via weakly-supervised or unsupervised training. However, these VEPs are not disease-specific, limiting their adaptation at the point of care. To address this pr… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.00164v1-abstract-full').style.display = 'inline'; document.getElementById('2406.00164v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2406.00164v1-abstract-full" style="display: none;"> Clinical variant classification of pathogenic versus benign genetic variants remains a challenge in clinical genetics. Recently, the proposition of genomic foundation models has improved the generic variant effect prediction (VEP) accuracy via weakly-supervised or unsupervised training. However, these VEPs are not disease-specific, limiting their adaptation at the point of care. To address this problem, we propose DYNA: Disease-specificity fine-tuning via a Siamese neural network broadly applicable to all genomic foundation models for more effective variant effect predictions in disease-specific contexts. We evaluate DYNA in two distinct disease-relevant tasks. For coding VEPs, we focus on various cardiovascular diseases, where gene-disease relationships of loss-of-function vs. gain-of-function dictate disease-specific VEP. For non-coding VEPs, we apply DYNA to an essential post-transcriptional regulatory axis of RNA splicing, the most common non-coding pathogenic mechanism in established clinical VEP guidelines. In both cases, DYNA fine-tunes various pre-trained genomic foundation models on small, rare variant sets. The DYNA fine-tuned models show superior performance in the held-out rare variant testing set and are further replicated in large, clinically-relevant variant annotations in ClinVAR. Thus, DYNA offers a potent disease-specific variant effect prediction method, excelling in intra-gene generalization and generalization to unseen genetic variants, making it particularly valuable for disease associations and clinical applicability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2406.00164v1-abstract-full').style.display = 'none'; document.getElementById('2406.00164v1-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> 31 May, 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/2405.15489">arXiv:2405.15489</a> <span> [<a href="https://arxiv.org/pdf/2405.15489">pdf</a>, <a href="https://arxiv.org/format/2405.15489">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"> Out of Many, One: Designing and Scaffolding Proteins at the Scale of the Structural Universe with Genie 2 </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Lin%2C+Y">Yeqing Lin</a>, <a href="/search/q-bio?searchtype=author&query=Lee%2C+M">Minji Lee</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhao Zhang</a>, <a href="/search/q-bio?searchtype=author&query=AlQuraishi%2C+M">Mohammed AlQuraishi</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="2405.15489v1-abstract-short" style="display: inline;"> Protein diffusion models have emerged as a promising approach for protein design. One such pioneering model is Genie, a method that asymmetrically represents protein structures during the forward and backward processes, using simple Gaussian noising for the former and expressive SE(3)-equivariant attention for the latter. In this work we introduce Genie 2, extending Genie to capture a larger and m… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15489v1-abstract-full').style.display = 'inline'; document.getElementById('2405.15489v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2405.15489v1-abstract-full" style="display: none;"> Protein diffusion models have emerged as a promising approach for protein design. One such pioneering model is Genie, a method that asymmetrically represents protein structures during the forward and backward processes, using simple Gaussian noising for the former and expressive SE(3)-equivariant attention for the latter. In this work we introduce Genie 2, extending Genie to capture a larger and more diverse protein structure space through architectural innovations and massive data augmentation. Genie 2 adds motif scaffolding capabilities via a novel multi-motif framework that designs co-occurring motifs with unspecified inter-motif positions and orientations. This makes possible complex protein designs that engage multiple interaction partners and perform multiple functions. On both unconditional and conditional generation, Genie 2 achieves state-of-the-art performance, outperforming all known methods on key design metrics including designability, diversity, and novelty. Genie 2 also solves more motif scaffolding problems than other methods and does so with more unique and varied solutions. Taken together, these advances set a new standard for structure-based protein design. Genie 2 inference and training code, as well as model weights, are freely available at: https://github.com/aqlaboratory/genie2. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2405.15489v1-abstract-full').style.display = 'none'; document.getElementById('2405.15489v1-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.08023">arXiv:2404.08023</a> <span> [<a href="https://arxiv.org/pdf/2404.08023">pdf</a>, <a href="https://arxiv.org/format/2404.08023">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> Pathology-genomic fusion via biologically informed cross-modality graph learning for survival analysis </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zeyu Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Zhao%2C+Y">Yuanshen Zhao</a>, <a href="/search/q-bio?searchtype=author&query=Duan%2C+J">Jingxian Duan</a>, <a href="/search/q-bio?searchtype=author&query=Liu%2C+Y">Yaou Liu</a>, <a href="/search/q-bio?searchtype=author&query=Zheng%2C+H">Hairong Zheng</a>, <a href="/search/q-bio?searchtype=author&query=Liang%2C+D">Dong Liang</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhenyu Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Li%2C+Z">Zhi-Cheng Li</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="2404.08023v1-abstract-short" style="display: inline;"> The diagnosis and prognosis of cancer are typically based on multi-modal clinical data, including histology images and genomic data, due to the complex pathogenesis and high heterogeneity. Despite the advancements in digital pathology and high-throughput genome sequencing, establishing effective multi-modal fusion models for survival prediction and revealing the potential association between histo… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.08023v1-abstract-full').style.display = 'inline'; document.getElementById('2404.08023v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.08023v1-abstract-full" style="display: none;"> The diagnosis and prognosis of cancer are typically based on multi-modal clinical data, including histology images and genomic data, due to the complex pathogenesis and high heterogeneity. Despite the advancements in digital pathology and high-throughput genome sequencing, establishing effective multi-modal fusion models for survival prediction and revealing the potential association between histopathology and transcriptomics remains challenging. In this paper, we propose Pathology-Genome Heterogeneous Graph (PGHG) that integrates whole slide images (WSI) and bulk RNA-Seq expression data with heterogeneous graph neural network for cancer survival analysis. The PGHG consists of biological knowledge-guided representation learning network and pathology-genome heterogeneous graph. The representation learning network utilizes the biological prior knowledge of intra-modal and inter-modal data associations to guide the feature extraction. The node features of each modality are updated through attention-based graph learning strategy. Unimodal features and bi-modal fused features are extracted via attention pooling module and then used for survival prediction. We evaluate the model on low-grade gliomas, glioblastoma, and kidney renal papillary cell carcinoma datasets from the Cancer Genome Atlas (TCGA) and the First Affiliated Hospital of Zhengzhou University (FAHZU). Extensive experimental results demonstrate that the proposed method outperforms both unimodal and other multi-modal fusion models. For demonstrating the model interpretability, we also visualize the attention heatmap of pathological images and utilize integrated gradient algorithm to identify important tissue structure, biological pathways and key genes. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.08023v1-abstract-full').style.display = 'none'; document.getElementById('2404.08023v1-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 April, 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/2404.05553">arXiv:2404.05553</a> <span> [<a href="https://arxiv.org/pdf/2404.05553">pdf</a>, <a href="https://arxiv.org/format/2404.05553">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Artificial Intelligence">cs.AI</span> </div> </div> <p class="title is-5 mathjax"> Alljoined1 -- A dataset for EEG-to-Image decoding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Xu%2C+J">Jonathan Xu</a>, <a href="/search/q-bio?searchtype=author&query=Aristimunha%2C+B">Bruno Aristimunha</a>, <a href="/search/q-bio?searchtype=author&query=Feucht%2C+M+E">Max Emanuel Feucht</a>, <a href="/search/q-bio?searchtype=author&query=Qian%2C+E">Emma Qian</a>, <a href="/search/q-bio?searchtype=author&query=Liu%2C+C">Charles Liu</a>, <a href="/search/q-bio?searchtype=author&query=Shahjahan%2C+T">Tazik Shahjahan</a>, <a href="/search/q-bio?searchtype=author&query=Spyra%2C+M">Martyna Spyra</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+S+Z">Steven Zifan Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Short%2C+N">Nicholas Short</a>, <a href="/search/q-bio?searchtype=author&query=Kim%2C+J">Jioh Kim</a>, <a href="/search/q-bio?searchtype=author&query=Perdomo%2C+P">Paula Perdomo</a>, <a href="/search/q-bio?searchtype=author&query=Mao%2C+R+R">Ricky Renfeng Mao</a>, <a href="/search/q-bio?searchtype=author&query=Sabharwal%2C+Y">Yashvir Sabharwal</a>, <a href="/search/q-bio?searchtype=author&query=Shoura%2C+M+A+M">Michael Ahedor Moaz Shoura</a>, <a href="/search/q-bio?searchtype=author&query=Nestor%2C+A">Adrian Nestor</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="2404.05553v3-abstract-short" style="display: inline;"> We present Alljoined1, a dataset built specifically for EEG-to-Image decoding. Recognizing that an extensive and unbiased sampling of neural responses to visual stimuli is crucial for image reconstruction efforts, we collected data from 8 participants looking at 10,000 natural images each. We have currently gathered 46,080 epochs of brain responses recorded with a 64-channel EEG headset. The datas… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.05553v3-abstract-full').style.display = 'inline'; document.getElementById('2404.05553v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.05553v3-abstract-full" style="display: none;"> We present Alljoined1, a dataset built specifically for EEG-to-Image decoding. Recognizing that an extensive and unbiased sampling of neural responses to visual stimuli is crucial for image reconstruction efforts, we collected data from 8 participants looking at 10,000 natural images each. We have currently gathered 46,080 epochs of brain responses recorded with a 64-channel EEG headset. The dataset combines response-based stimulus timing, repetition between blocks and sessions, and diverse image classes with the goal of improving signal quality. For transparency, we also provide data quality scores. We publicly release the dataset and all code at https://linktr.ee/alljoined1. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.05553v3-abstract-full').style.display = 'none'; document.getElementById('2404.05553v3-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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">8 Pages, 6 Figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.5.1; I.6.3; I.2.6; K.3.2 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2404.00014">arXiv:2404.00014</a> <span> [<a href="https://arxiv.org/pdf/2404.00014">pdf</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Chemical Physics">physics.chem-ph</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="Biomolecules">q-bio.BM</span> </div> </div> <p class="title is-5 mathjax"> Deep Geometry Handling and Fragment-wise Molecular 3D Graph Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+O">Odin Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Huang%2C+Y">Yufei Huang</a>, <a href="/search/q-bio?searchtype=author&query=Cheng%2C+S">Shichen Cheng</a>, <a href="/search/q-bio?searchtype=author&query=Yu%2C+M">Mengyao Yu</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+X">Xujun Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Lin%2C+H">Haitao Lin</a>, <a href="/search/q-bio?searchtype=author&query=Zeng%2C+Y">Yundian Zeng</a>, <a href="/search/q-bio?searchtype=author&query=Wang%2C+M">Mingyang Wang</a>, <a href="/search/q-bio?searchtype=author&query=Wu%2C+Z">Zhenxing Wu</a>, <a href="/search/q-bio?searchtype=author&query=Zhao%2C+H">Huifeng Zhao</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zaixi Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Hua%2C+C">Chenqing Hua</a>, <a href="/search/q-bio?searchtype=author&query=Kang%2C+Y">Yu Kang</a>, <a href="/search/q-bio?searchtype=author&query=Cui%2C+S">Sunliang Cui</a>, <a href="/search/q-bio?searchtype=author&query=Pan%2C+P">Peichen Pan</a>, <a href="/search/q-bio?searchtype=author&query=Hsieh%2C+C">Chang-Yu Hsieh</a>, <a href="/search/q-bio?searchtype=author&query=Hou%2C+T">Tingjun Hou</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="2404.00014v1-abstract-short" style="display: inline;"> Most earlier 3D structure-based molecular generation approaches follow an atom-wise paradigm, incrementally adding atoms to a partially built molecular fragment within protein pockets. These methods, while effective in designing tightly bound ligands, often overlook other essential properties such as synthesizability. The fragment-wise generation paradigm offers a promising solution. However, a co… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.00014v1-abstract-full').style.display = 'inline'; document.getElementById('2404.00014v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2404.00014v1-abstract-full" style="display: none;"> Most earlier 3D structure-based molecular generation approaches follow an atom-wise paradigm, incrementally adding atoms to a partially built molecular fragment within protein pockets. These methods, while effective in designing tightly bound ligands, often overlook other essential properties such as synthesizability. The fragment-wise generation paradigm offers a promising solution. However, a common challenge across both atom-wise and fragment-wise methods lies in their limited ability to co-design plausible chemical and geometrical structures, resulting in distorted conformations. In response to this challenge, we introduce the Deep Geometry Handling protocol, a more abstract design that extends the design focus beyond the model architecture. Through a comprehensive review of existing geometry-related models and their protocols, we propose a novel hybrid strategy, culminating in the development of FragGen - a geometry-reliable, fragment-wise molecular generation method. FragGen marks a significant leap forward in the quality of generated geometry and the synthesis accessibility of molecules. The efficacy of FragGen is further validated by its successful application in designing type II kinase inhibitors at the nanomolar level. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2404.00014v1-abstract-full').style.display = 'none'; document.getElementById('2404.00014v1-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 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/2403.14358">arXiv:2403.14358</a> <span> [<a href="https://arxiv.org/pdf/2403.14358">pdf</a>, <a href="https://arxiv.org/format/2403.14358">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="Biomolecules">q-bio.BM</span> </div> </div> <p class="title is-5 mathjax"> Exploring the Potential of Large Language Models in Graph Generation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Yao%2C+Y">Yang Yao</a>, <a href="/search/q-bio?searchtype=author&query=Wang%2C+X">Xin Wang</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zeyang Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Qin%2C+Y">Yijian Qin</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Ziwei Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Chu%2C+X">Xu Chu</a>, <a href="/search/q-bio?searchtype=author&query=Yang%2C+Y">Yuekui Yang</a>, <a href="/search/q-bio?searchtype=author&query=Zhu%2C+W">Wenwu Zhu</a>, <a href="/search/q-bio?searchtype=author&query=Mei%2C+H">Hong Mei</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="2403.14358v1-abstract-short" style="display: inline;"> Large language models (LLMs) have achieved great success in many fields, and recent works have studied exploring LLMs for graph discriminative tasks such as node classification. However, the abilities of LLMs for graph generation remain unexplored in the literature. Graph generation requires the LLM to generate graphs with given properties, which has valuable real-world applications such as drug d… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.14358v1-abstract-full').style.display = 'inline'; document.getElementById('2403.14358v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.14358v1-abstract-full" style="display: none;"> Large language models (LLMs) have achieved great success in many fields, and recent works have studied exploring LLMs for graph discriminative tasks such as node classification. However, the abilities of LLMs for graph generation remain unexplored in the literature. Graph generation requires the LLM to generate graphs with given properties, which has valuable real-world applications such as drug discovery, while tends to be more challenging. In this paper, we propose LLM4GraphGen to explore the ability of LLMs for graph generation with systematical task designs and extensive experiments. Specifically, we propose several tasks tailored with comprehensive experiments to address key questions regarding LLMs' understanding of different graph structure rules, their ability to capture structural type distributions, and their utilization of domain knowledge for property-based graph generation. Our evaluations demonstrate that LLMs, particularly GPT-4, exhibit preliminary abilities in graph generation tasks, including rule-based and distribution-based generation. We also observe that popular prompting methods, such as few-shot and chain-of-thought prompting, do not consistently enhance performance. Besides, LLMs show potential in generating molecules with specific properties. These findings may serve as foundations for designing good LLMs based models for graph generation and provide valuable insights and further research. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.14358v1-abstract-full').style.display = 'none'; document.getElementById('2403.14358v1-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> 21 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2403.01433">arXiv:2403.01433</a> <span> [<a href="https://arxiv.org/pdf/2403.01433">pdf</a>, <a href="https://arxiv.org/format/2403.01433">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="Neurons and Cognition">q-bio.NC</span> </div> </div> <p class="title is-5 mathjax"> BrainMass: Advancing Brain Network Analysis for Diagnosis with Large-scale Self-Supervised Learning </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Yang%2C+Y">Yanwu Yang</a>, <a href="/search/q-bio?searchtype=author&query=Ye%2C+C">Chenfei Ye</a>, <a href="/search/q-bio?searchtype=author&query=Su%2C+G">Guinan Su</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Ziyao Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Chang%2C+Z">Zhikai Chang</a>, <a href="/search/q-bio?searchtype=author&query=Chen%2C+H">Hairui Chen</a>, <a href="/search/q-bio?searchtype=author&query=Chan%2C+P">Piu Chan</a>, <a href="/search/q-bio?searchtype=author&query=Yu%2C+Y">Yue Yu</a>, <a href="/search/q-bio?searchtype=author&query=Ma%2C+T">Ting Ma</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="2403.01433v1-abstract-short" style="display: inline;"> Foundation models pretrained on large-scale datasets via self-supervised learning demonstrate exceptional versatility across various tasks. Due to the heterogeneity and hard-to-collect medical data, this approach is especially beneficial for medical image analysis and neuroscience research, as it streamlines broad downstream tasks without the need for numerous costly annotations. However, there ha… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.01433v1-abstract-full').style.display = 'inline'; document.getElementById('2403.01433v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2403.01433v1-abstract-full" style="display: none;"> Foundation models pretrained on large-scale datasets via self-supervised learning demonstrate exceptional versatility across various tasks. Due to the heterogeneity and hard-to-collect medical data, this approach is especially beneficial for medical image analysis and neuroscience research, as it streamlines broad downstream tasks without the need for numerous costly annotations. However, there has been limited investigation into brain network foundation models, limiting their adaptability and generalizability for broad neuroscience studies. In this study, we aim to bridge this gap. In particular, (1) we curated a comprehensive dataset by collating images from 30 datasets, which comprises 70,781 samples of 46,686 participants. Moreover, we introduce pseudo-functional connectivity (pFC) to further generates millions of augmented brain networks by randomly dropping certain timepoints of the BOLD signal. (2) We propose the BrainMass framework for brain network self-supervised learning via mask modeling and feature alignment. BrainMass employs Mask-ROI Modeling (MRM) to bolster intra-network dependencies and regional specificity. Furthermore, Latent Representation Alignment (LRA) module is utilized to regularize augmented brain networks of the same participant with similar topological properties to yield similar latent representations by aligning their latent embeddings. Extensive experiments on eight internal tasks and seven external brain disorder diagnosis tasks show BrainMass's superior performance, highlighting its significant generalizability and adaptability. Nonetheless, BrainMass demonstrates powerful few/zero-shot learning abilities and exhibits meaningful interpretation to various diseases, showcasing its potential use for clinical applications. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2403.01433v1-abstract-full').style.display = 'none'; document.getElementById('2403.01433v1-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> March 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.18583">arXiv:2402.18583</a> <span> [<a href="https://arxiv.org/pdf/2402.18583">pdf</a>, <a href="https://arxiv.org/format/2402.18583">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"> Binding-Adaptive Diffusion Models for Structure-Based Drug Design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Huang%2C+Z">Zhilin Huang</a>, <a href="/search/q-bio?searchtype=author&query=Yang%2C+L">Ling Yang</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zaixi Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Zhou%2C+X">Xiangxin Zhou</a>, <a href="/search/q-bio?searchtype=author&query=Bao%2C+Y">Yu Bao</a>, <a href="/search/q-bio?searchtype=author&query=Zheng%2C+X">Xiawu Zheng</a>, <a href="/search/q-bio?searchtype=author&query=Yang%2C+Y">Yuwei Yang</a>, <a href="/search/q-bio?searchtype=author&query=Wang%2C+Y">Yu Wang</a>, <a href="/search/q-bio?searchtype=author&query=Yang%2C+W">Wenming Yang</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="2402.18583v1-abstract-short" style="display: inline;"> Structure-based drug design (SBDD) aims to generate 3D ligand molecules that bind to specific protein targets. Existing 3D deep generative models including diffusion models have shown great promise for SBDD. However, it is complex to capture the essential protein-ligand interactions exactly in 3D space for molecular generation. To address this problem, we propose a novel framework, namely Binding-… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.18583v1-abstract-full').style.display = 'inline'; document.getElementById('2402.18583v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.18583v1-abstract-full" style="display: none;"> Structure-based drug design (SBDD) aims to generate 3D ligand molecules that bind to specific protein targets. Existing 3D deep generative models including diffusion models have shown great promise for SBDD. However, it is complex to capture the essential protein-ligand interactions exactly in 3D space for molecular generation. To address this problem, we propose a novel framework, namely Binding-Adaptive Diffusion Models (BindDM). In BindDM, we adaptively extract subcomplex, the essential part of binding sites responsible for protein-ligand interactions. Then the selected protein-ligand subcomplex is processed with SE(3)-equivariant neural networks, and transmitted back to each atom of the complex for augmenting the target-aware 3D molecule diffusion generation with binding interaction information. We iterate this hierarchical complex-subcomplex process with cross-hierarchy interaction node for adequately fusing global binding context between the complex and its corresponding subcomplex. Empirical studies on the CrossDocked2020 dataset show BindDM can generate molecules with more realistic 3D structures and higher binding affinities towards the protein targets, with up to -5.92 Avg. Vina Score, while maintaining proper molecular properties. Our code is available at https://github.com/YangLing0818/BindDM <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.18583v1-abstract-full').style.display = 'none'; document.getElementById('2402.18583v1-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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 AAAI 2024. Project: https://github.com/YangLing0818/BindDM</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.10433">arXiv:2402.10433</a> <span> [<a href="https://arxiv.org/pdf/2402.10433">pdf</a>, <a href="https://arxiv.org/format/2402.10433">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> </div> </div> <p class="title is-5 mathjax"> Fusing Neural and Physical: Augment Protein Conformation Sampling with Tractable Simulations </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Lu%2C+J">Jiarui Lu</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zuobai Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Zhong%2C+B">Bozitao Zhong</a>, <a href="/search/q-bio?searchtype=author&query=Shi%2C+C">Chence Shi</a>, <a href="/search/q-bio?searchtype=author&query=Tang%2C+J">Jian Tang</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="2402.10433v2-abstract-short" style="display: inline;"> The protein dynamics are common and important for their biological functions and properties, the study of which usually involves time-consuming molecular dynamics (MD) simulations in silico. Recently, generative models has been leveraged as a surrogate sampler to obtain conformation ensembles with orders of magnitude faster and without requiring any simulation data (a "zero-shot" inference). Howev… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.10433v2-abstract-full').style.display = 'inline'; document.getElementById('2402.10433v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.10433v2-abstract-full" style="display: none;"> The protein dynamics are common and important for their biological functions and properties, the study of which usually involves time-consuming molecular dynamics (MD) simulations in silico. Recently, generative models has been leveraged as a surrogate sampler to obtain conformation ensembles with orders of magnitude faster and without requiring any simulation data (a "zero-shot" inference). However, being agnostic of the underlying energy landscape, the accuracy of such generative model may still be limited. In this work, we explore the few-shot setting of such pre-trained generative sampler which incorporates MD simulations in a tractable manner. Specifically, given a target protein of interest, we first acquire some seeding conformations from the pre-trained sampler followed by a number of physical simulations in parallel starting from these seeding samples. Then we fine-tuned the generative model using the simulation trajectories above to become a target-specific sampler. Experimental results demonstrated the superior performance of such few-shot conformation sampler at a tractable computational cost. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.10433v2-abstract-full').style.display = 'none'; document.getElementById('2402.10433v2-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 15 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 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">Published at the GEM workshop, ICLR 2024</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.08075">arXiv:2402.08075</a> <span> [<a href="https://arxiv.org/pdf/2402.08075">pdf</a>, <a href="https://arxiv.org/format/2402.08075">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Genomics">q-bio.GN</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> </div> </div> <p class="title is-5 mathjax"> Efficient and Scalable Fine-Tune of Language Models for Genome Understanding </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhan%2C+H">Huixin Zhan</a>, <a href="/search/q-bio?searchtype=author&query=Wu%2C+Y+N">Ying Nian Wu</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zijun Zhang</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="2402.08075v1-abstract-short" style="display: inline;"> Although DNA foundation models have advanced the understanding of genomes, they still face significant challenges in the limited scale and diversity of genomic data. This limitation starkly contrasts with the success of natural language foundation models, which thrive on substantially larger scales. Furthermore, genome understanding involves numerous downstream genome annotation tasks with inheren… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.08075v1-abstract-full').style.display = 'inline'; document.getElementById('2402.08075v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.08075v1-abstract-full" style="display: none;"> Although DNA foundation models have advanced the understanding of genomes, they still face significant challenges in the limited scale and diversity of genomic data. This limitation starkly contrasts with the success of natural language foundation models, which thrive on substantially larger scales. Furthermore, genome understanding involves numerous downstream genome annotation tasks with inherent data heterogeneity, thereby necessitating more efficient and robust fine-tuning methods tailored for genomics. Here, we present \textsc{Lingo}: \textsc{L}anguage prefix f\textsc{In}e-tuning for \textsc{G}en\textsc{O}mes. Unlike DNA foundation models, \textsc{Lingo} strategically leverages natural language foundation models' contextual cues, recalibrating their linguistic knowledge to genomic sequences. \textsc{Lingo} further accommodates numerous, heterogeneous downstream fine-tune tasks by an adaptive rank sampling method that prunes and stochastically reintroduces pruned singular vectors within small computational budgets. Adaptive rank sampling outperformed existing fine-tuning methods on all benchmarked 14 genome understanding tasks, while requiring fewer than 2\% of trainable parameters as genomic-specific adapters. Impressively, applying these adapters on natural language foundation models matched or even exceeded the performance of DNA foundation models. \textsc{Lingo} presents a new paradigm of efficient and scalable genome understanding via genomic-specific adapters on language models. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.08075v1-abstract-full').style.display = 'none'; document.getElementById('2402.08075v1-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.07955">arXiv:2402.07955</a> <span> [<a href="https://arxiv.org/pdf/2402.07955">pdf</a>, <a href="https://arxiv.org/format/2402.07955">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"> ProtIR: Iterative Refinement between Retrievers and Predictors for Protein Function Annotation </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zuobai Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Lu%2C+J">Jiarui Lu</a>, <a href="/search/q-bio?searchtype=author&query=Chenthamarakshan%2C+V">Vijil Chenthamarakshan</a>, <a href="/search/q-bio?searchtype=author&query=Lozano%2C+A">Aur茅lie Lozano</a>, <a href="/search/q-bio?searchtype=author&query=Das%2C+P">Payel Das</a>, <a href="/search/q-bio?searchtype=author&query=Tang%2C+J">Jian Tang</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="2402.07955v1-abstract-short" style="display: inline;"> Protein function annotation is an important yet challenging task in biology. Recent deep learning advancements show significant potential for accurate function prediction by learning from protein sequences and structures. Nevertheless, these predictor-based methods often overlook the modeling of protein similarity, an idea commonly employed in traditional approaches using sequence or structure ret… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07955v1-abstract-full').style.display = 'inline'; document.getElementById('2402.07955v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.07955v1-abstract-full" style="display: none;"> Protein function annotation is an important yet challenging task in biology. Recent deep learning advancements show significant potential for accurate function prediction by learning from protein sequences and structures. Nevertheless, these predictor-based methods often overlook the modeling of protein similarity, an idea commonly employed in traditional approaches using sequence or structure retrieval tools. To fill this gap, we first study the effect of inter-protein similarity modeling by benchmarking retriever-based methods against predictors on protein function annotation tasks. Our results show that retrievers can match or outperform predictors without large-scale pre-training. Building on these insights, we introduce a novel variational pseudo-likelihood framework, ProtIR, designed to improve function predictors by incorporating inter-protein similarity modeling. This framework iteratively refines knowledge between a function predictor and retriever, thereby combining the strengths of both predictors and retrievers. ProtIR showcases around 10% improvement over vanilla predictor-based methods. Besides, it achieves performance on par with protein language model-based methods, yet without the need for massive pre-training, highlighting the efficacy of our framework. Code will be released upon acceptance. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.07955v1-abstract-full').style.display = 'none'; document.getElementById('2402.07955v1-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2402.05856">arXiv:2402.05856</a> <span> [<a href="https://arxiv.org/pdf/2402.05856">pdf</a>, <a href="https://arxiv.org/format/2402.05856">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"> Structure-Informed Protein Language Model </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zuobai Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Lu%2C+J">Jiarui Lu</a>, <a href="/search/q-bio?searchtype=author&query=Chenthamarakshan%2C+V">Vijil Chenthamarakshan</a>, <a href="/search/q-bio?searchtype=author&query=Lozano%2C+A">Aur茅lie Lozano</a>, <a href="/search/q-bio?searchtype=author&query=Das%2C+P">Payel Das</a>, <a href="/search/q-bio?searchtype=author&query=Tang%2C+J">Jian Tang</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="2402.05856v1-abstract-short" style="display: inline;"> Protein language models are a powerful tool for learning protein representations through pre-training on vast protein sequence datasets. However, traditional protein language models lack explicit structural supervision, despite its relevance to protein function. To address this issue, we introduce the integration of remote homology detection to distill structural information into protein language… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.05856v1-abstract-full').style.display = 'inline'; document.getElementById('2402.05856v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2402.05856v1-abstract-full" style="display: none;"> Protein language models are a powerful tool for learning protein representations through pre-training on vast protein sequence datasets. However, traditional protein language models lack explicit structural supervision, despite its relevance to protein function. To address this issue, we introduce the integration of remote homology detection to distill structural information into protein language models without requiring explicit protein structures as input. We evaluate the impact of this structure-informed training on downstream protein function prediction tasks. Experimental results reveal consistent improvements in function annotation accuracy for EC number and GO term prediction. Performance on mutant datasets, however, varies based on the relationship between targeted properties and protein structures. This underscores the importance of considering this relationship when applying structure-aware training to protein function prediction tasks. Code and model weights are available at https://github.com/DeepGraphLearning/esm-s. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2402.05856v1-abstract-full').style.display = 'none'; document.getElementById('2402.05856v1-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> 7 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> February 2024. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2401.16544">arXiv:2401.16544</a> <span> [<a href="https://arxiv.org/pdf/2401.16544">pdf</a>, <a href="https://arxiv.org/format/2401.16544">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Statistical Mechanics">cond-mat.stat-mech</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/10.1063/5.0203335">10.1063/5.0203335 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Stochastic Distinguishability of Markovian Trajectories </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Pagare%2C+A">Asawari Pagare</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhongmin Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Zheng%2C+J">Jiming Zheng</a>, <a href="/search/q-bio?searchtype=author&query=Lu%2C+Z">Zhiyue Lu</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="2401.16544v2-abstract-short" style="display: inline;"> The ability to distinguish between stochastic systems based on their trajectories is crucial in thermodynamics, chemistry, and biophysics. The Kullback-Leibler (KL) divergence, $D_{\text{KL}}^{AB}(0,蟿)$, quantifies the distinguishability between the two ensembles of length-$蟿$ trajectories from Markov processes A and B. However, evaluating $D_{\text{KL}}^{AB}(0,蟿)$ from histograms of trajectories… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.16544v2-abstract-full').style.display = 'inline'; document.getElementById('2401.16544v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2401.16544v2-abstract-full" style="display: none;"> The ability to distinguish between stochastic systems based on their trajectories is crucial in thermodynamics, chemistry, and biophysics. The Kullback-Leibler (KL) divergence, $D_{\text{KL}}^{AB}(0,蟿)$, quantifies the distinguishability between the two ensembles of length-$蟿$ trajectories from Markov processes A and B. However, evaluating $D_{\text{KL}}^{AB}(0,蟿)$ from histograms of trajectories faces sufficient sampling difficulties, and no theory explicitly reveals what dynamical features contribute to the distinguishability. This letter provides a general formula that decomposes $D_{\text{KL}}^{AB}(0,蟿)$ in space and time for any Markov processes, arbitrarily far from equilibrium or steady state. It circumvents the sampling difficulty of evaluating $D_{\text{KL}}^{AB}(0,蟿)$. Furthermore, it explicitly connects trajectory KL divergence with individual transition events and their waiting time statistics. The results provide insights into understanding distinguishability between Markov processes, leading to new theoretical frameworks for designing biological sensors and optimizing signal transduction. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2401.16544v2-abstract-full').style.display = 'none'; document.getElementById('2401.16544v2-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 May, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> January 2024. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> J. Chem. Phys. 7 May 2024; 160 (17): 171101 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.17670">arXiv:2312.17670</a> <span> [<a href="https://arxiv.org/pdf/2312.17670">pdf</a>, <a href="https://arxiv.org/format/2312.17670">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link 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="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="Tissues and Organs">q-bio.TO</span> </div> </div> <p class="title is-5 mathjax"> Benchmarking the CoW with the TopCoW Challenge: Topology-Aware Anatomical Segmentation of the Circle of Willis for CTA and MRA </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Yang%2C+K">Kaiyuan Yang</a>, <a href="/search/q-bio?searchtype=author&query=Musio%2C+F">Fabio Musio</a>, <a href="/search/q-bio?searchtype=author&query=Ma%2C+Y">Yihui Ma</a>, <a href="/search/q-bio?searchtype=author&query=Juchler%2C+N">Norman Juchler</a>, <a href="/search/q-bio?searchtype=author&query=Paetzold%2C+J+C">Johannes C. Paetzold</a>, <a href="/search/q-bio?searchtype=author&query=Al-Maskari%2C+R">Rami Al-Maskari</a>, <a href="/search/q-bio?searchtype=author&query=H%C3%B6her%2C+L">Luciano H枚her</a>, <a href="/search/q-bio?searchtype=author&query=Li%2C+H+B">Hongwei Bran Li</a>, <a href="/search/q-bio?searchtype=author&query=Hamamci%2C+I+E">Ibrahim Ethem Hamamci</a>, <a href="/search/q-bio?searchtype=author&query=Sekuboyina%2C+A">Anjany Sekuboyina</a>, <a href="/search/q-bio?searchtype=author&query=Shit%2C+S">Suprosanna Shit</a>, <a href="/search/q-bio?searchtype=author&query=Huang%2C+H">Houjing Huang</a>, <a href="/search/q-bio?searchtype=author&query=Prabhakar%2C+C">Chinmay Prabhakar</a>, <a href="/search/q-bio?searchtype=author&query=de+la+Rosa%2C+E">Ezequiel de la Rosa</a>, <a href="/search/q-bio?searchtype=author&query=Waldmannstetter%2C+D">Diana Waldmannstetter</a>, <a href="/search/q-bio?searchtype=author&query=Kofler%2C+F">Florian Kofler</a>, <a href="/search/q-bio?searchtype=author&query=Navarro%2C+F">Fernando Navarro</a>, <a href="/search/q-bio?searchtype=author&query=Menten%2C+M">Martin Menten</a>, <a href="/search/q-bio?searchtype=author&query=Ezhov%2C+I">Ivan Ezhov</a>, <a href="/search/q-bio?searchtype=author&query=Rueckert%2C+D">Daniel Rueckert</a>, <a href="/search/q-bio?searchtype=author&query=Vos%2C+I">Iris Vos</a>, <a href="/search/q-bio?searchtype=author&query=Ruigrok%2C+Y">Ynte Ruigrok</a>, <a href="/search/q-bio?searchtype=author&query=Velthuis%2C+B">Birgitta Velthuis</a>, <a href="/search/q-bio?searchtype=author&query=Kuijf%2C+H">Hugo Kuijf</a>, <a href="/search/q-bio?searchtype=author&query=H%C3%A4mmerli%2C+J">Julien H盲mmerli</a> , et al. (59 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="2312.17670v3-abstract-short" style="display: inline;"> The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neuro-vascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two angiographic imaging modaliti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.17670v3-abstract-full').style.display = 'inline'; document.getElementById('2312.17670v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.17670v3-abstract-full" style="display: none;"> The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neuro-vascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited public datasets with annotations on CoW anatomy, especially for CTA. Therefore we organized the TopCoW Challenge in 2023 with the release of an annotated CoW dataset. The TopCoW dataset was the first public dataset with voxel-level annotations for thirteen possible CoW vessel components, enabled by virtual-reality (VR) technology. It was also the first large dataset with paired MRA and CTA from the same patients. TopCoW challenge formalized the CoW characterization problem as a multiclass anatomical segmentation task with an emphasis on topological metrics. We invited submissions worldwide for the CoW segmentation task, which attracted over 140 registered participants from four continents. The top performing teams managed to segment many CoW components to Dice scores around 90%, but with lower scores for communicating arteries and rare variants. There were also topological mistakes for predictions with high Dice scores. Additional topological analysis revealed further areas for improvement in detecting certain CoW components and matching CoW variant topology accurately. TopCoW represented a first attempt at benchmarking the CoW anatomical segmentation task for MRA and CTA, both morphologically and topologically. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.17670v3-abstract-full').style.display = 'none'; document.getElementById('2312.17670v3-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> 29 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 29 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">24 pages, 11 figures, 9 tables. Summary Paper for the MICCAI TopCoW 2023 Challenge</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.05063">arXiv:2312.05063</a> <span> [<a href="https://arxiv.org/pdf/2312.05063">pdf</a>, <a href="https://arxiv.org/format/2312.05063">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Medical Physics">physics.med-ph</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Numerical Analysis">math.NA</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"> Individualizing Glioma Radiotherapy Planning by Optimization of Data and Physics-Informed Discrete Loss </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Balcerak%2C+M">Michal Balcerak</a>, <a href="/search/q-bio?searchtype=author&query=Weidner%2C+J">Jonas Weidner</a>, <a href="/search/q-bio?searchtype=author&query=Karnakov%2C+P">Petr Karnakov</a>, <a href="/search/q-bio?searchtype=author&query=Ezhov%2C+I">Ivan Ezhov</a>, <a href="/search/q-bio?searchtype=author&query=Litvinov%2C+S">Sergey Litvinov</a>, <a href="/search/q-bio?searchtype=author&query=Koumoutsakos%2C+P">Petros Koumoutsakos</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+R+Z">Ray Zirui Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Lowengrub%2C+J+S">John S. Lowengrub</a>, <a href="/search/q-bio?searchtype=author&query=Wiestler%2C+B">Bene Wiestler</a>, <a href="/search/q-bio?searchtype=author&query=Menze%2C+B">Bjoern Menze</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="2312.05063v3-abstract-short" style="display: inline;"> Brain tumor growth is unique to each glioma patient and extends beyond what is visible in imaging scans, infiltrating surrounding brain tissue. Understanding these hidden patient-specific progressions is essential for effective therapies. Current treatment plans for brain tumors, such as radiotherapy, typically involve delineating a uniform margin around the visible tumor on pre-treatment scans to… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.05063v3-abstract-full').style.display = 'inline'; document.getElementById('2312.05063v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.05063v3-abstract-full" style="display: none;"> Brain tumor growth is unique to each glioma patient and extends beyond what is visible in imaging scans, infiltrating surrounding brain tissue. Understanding these hidden patient-specific progressions is essential for effective therapies. Current treatment plans for brain tumors, such as radiotherapy, typically involve delineating a uniform margin around the visible tumor on pre-treatment scans to target this invisible tumor growth. This "one size fits all" approach is derived from population studies and often fails to account for the nuances of individual patient conditions. We present the GliODIL framework, which infers the full spatial distribution of tumor cell concentration from available multi-modal imaging, leveraging a Fisher-Kolmogorov type physics model to describe tumor growth. This is achieved through the newly introduced method of Optimizing the Discrete Loss (ODIL), where both data and physics-based constraints are softly assimilated into the solution. Our test dataset comprises 152 glioblastoma patients with pre-treatment imaging and post-treatment follow-ups for tumor recurrence monitoring. By blending data-driven techniques with physics-based constraints, GliODIL enhances recurrence prediction in radiotherapy planning, challenging traditional uniform margins and strict adherence to the Fisher-Kolmogorov partial differential equation (PDE) model, which is adapted for complex cases. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.05063v3-abstract-full').style.display = 'none'; document.getElementById('2312.05063v3-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 April, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 8 December, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">22 pages, 7 figures, 1 table. Associated GitHub: https://github.com/m1balcerak/GliODIL</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2312.00080">arXiv:2312.00080</a> <span> [<a href="https://arxiv.org/pdf/2312.00080">pdf</a>, <a href="https://arxiv.org/format/2312.00080">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> PDB-Struct: A Comprehensive Benchmark for Structure-based Protein Design </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Wang%2C+C">Chuanrui Wang</a>, <a href="/search/q-bio?searchtype=author&query=Zhong%2C+B">Bozitao Zhong</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zuobai Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Chaudhary%2C+N">Narendra Chaudhary</a>, <a href="/search/q-bio?searchtype=author&query=Misra%2C+S">Sanchit Misra</a>, <a href="/search/q-bio?searchtype=author&query=Tang%2C+J">Jian Tang</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="2312.00080v1-abstract-short" style="display: inline;"> Structure-based protein design has attracted increasing interest, with numerous methods being introduced in recent years. However, a universally accepted method for evaluation has not been established, since the wet-lab validation can be overly time-consuming for the development of new algorithms, and the $\textit{in silico}$ validation with recovery and perplexity metrics is efficient but may not… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.00080v1-abstract-full').style.display = 'inline'; document.getElementById('2312.00080v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2312.00080v1-abstract-full" style="display: none;"> Structure-based protein design has attracted increasing interest, with numerous methods being introduced in recent years. However, a universally accepted method for evaluation has not been established, since the wet-lab validation can be overly time-consuming for the development of new algorithms, and the $\textit{in silico}$ validation with recovery and perplexity metrics is efficient but may not precisely reflect true foldability. To address this gap, we introduce two novel metrics: refoldability-based metric, which leverages high-accuracy protein structure prediction models as a proxy for wet lab experiments, and stability-based metric, which assesses whether models can assign high likelihoods to experimentally stable proteins. We curate datasets from high-quality CATH protein data, high-throughput $\textit{de novo}$ designed proteins, and mega-scale experimental mutagenesis experiments, and in doing so, present the $\textbf{PDB-Struct}$ benchmark that evaluates both recent and previously uncompared protein design methods. Experimental results indicate that ByProt, ProteinMPNN, and ESM-IF perform exceptionally well on our benchmark, while ESM-Design and AF-Design fall short on the refoldability metric. We also show that while some methods exhibit high sequence recovery, they do not perform as well on our new benchmark. Our proposed benchmark paves the way for a fair and comprehensive evaluation of protein design methods in the future. Code is available at https://github.com/WANG-CR/PDB-Struct. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2312.00080v1-abstract-full').style.display = 'none'; document.getElementById('2312.00080v1-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> 29 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> December 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">13 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/2311.18574">arXiv:2311.18574</a> <span> [<a href="https://arxiv.org/pdf/2311.18574">pdf</a>, <a href="https://arxiv.org/format/2311.18574">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"> Multi-scale Iterative Refinement towards Robust and Versatile Molecular Docking </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Yan%2C+J">Jiaxian Yan</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zaixi Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+K">Kai Zhang</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="2311.18574v1-abstract-short" style="display: inline;"> Molecular docking is a key computational tool utilized to predict the binding conformations of small molecules to protein targets, which is fundamental in the design of novel drugs. Despite recent advancements in geometric deep learning-based approaches leading to improvements in blind docking efficiency, these methods have encountered notable challenges, such as limited generalization performance… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.18574v1-abstract-full').style.display = 'inline'; document.getElementById('2311.18574v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.18574v1-abstract-full" style="display: none;"> Molecular docking is a key computational tool utilized to predict the binding conformations of small molecules to protein targets, which is fundamental in the design of novel drugs. Despite recent advancements in geometric deep learning-based approaches leading to improvements in blind docking efficiency, these methods have encountered notable challenges, such as limited generalization performance on unseen proteins, the inability to concurrently address the settings of blind docking and site-specific docking, and the frequent occurrence of physical implausibilities such as inter-molecular steric clash. In this study, we introduce DeltaDock, a robust and versatile framework designed for efficient molecular docking to overcome these challenges. DeltaDock operates in a two-step process: rapid initial complex structures sampling followed by multi-scale iterative refinement of the initial structures. In the initial stage, to sample accurate structures with high efficiency, we develop a ligand-dependent binding site prediction model founded on large protein models and graph neural networks. This model is then paired with GPU-accelerated sampling algorithms. The sampled structures are updated using a multi-scale iterative refinement module that captures both protein-ligand atom-atom interactions and residue-atom interactions in the following stage. Distinct from previous geometric deep learning methods that are conditioned on the blind docking setting, DeltaDock demonstrates superior performance in both blind docking and site-specific docking settings. Comprehensive experimental results reveal that DeltaDock consistently surpasses baseline methods in terms of docking accuracy. Furthermore, it displays remarkable generalization capabilities and proficiency for predicting physically valid structures, thereby attesting to its robustness and reliability in various scenarios. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.18574v1-abstract-full').style.display = 'none'; document.getElementById('2311.18574v1-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 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">13 pages, 8 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/2311.16536">arXiv:2311.16536</a> <span> [<a href="https://arxiv.org/pdf/2311.16536">pdf</a>, <a href="https://arxiv.org/format/2311.16536">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="Image and Video Processing">eess.IV</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"> Personalized Predictions of Glioblastoma Infiltration: Mathematical Models, Physics-Informed Neural Networks and Multimodal Scans </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+R+Z">Ray Zirui Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Ezhov%2C+I">Ivan Ezhov</a>, <a href="/search/q-bio?searchtype=author&query=Balcerak%2C+M">Michal Balcerak</a>, <a href="/search/q-bio?searchtype=author&query=Zhu%2C+A">Andy Zhu</a>, <a href="/search/q-bio?searchtype=author&query=Wiestler%2C+B">Benedikt Wiestler</a>, <a href="/search/q-bio?searchtype=author&query=Menze%2C+B">Bjoern Menze</a>, <a href="/search/q-bio?searchtype=author&query=Lowengrub%2C+J+S">John S. Lowengrub</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="2311.16536v3-abstract-short" style="display: inline;"> Predicting the infiltration of Glioblastoma (GBM) from medical MRI scans is crucial for understanding tumor growth dynamics and designing personalized radiotherapy treatment plans.Mathematical models of GBM growth can complement the data in the prediction of spatial distributions of tumor cells. However, this requires estimating patient-specific parameters of the model from clinical data, which is… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.16536v3-abstract-full').style.display = 'inline'; document.getElementById('2311.16536v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.16536v3-abstract-full" style="display: none;"> Predicting the infiltration of Glioblastoma (GBM) from medical MRI scans is crucial for understanding tumor growth dynamics and designing personalized radiotherapy treatment plans.Mathematical models of GBM growth can complement the data in the prediction of spatial distributions of tumor cells. However, this requires estimating patient-specific parameters of the model from clinical data, which is a challenging inverse problem due to limited temporal data and the limited time between imaging and diagnosis. This work proposes a method that uses Physics-Informed Neural Networks (PINNs) to estimate patient-specific parameters of a reaction-diffusion PDE model of GBM growth from a single 3D structural MRI snapshot. PINNs embed both the data and the PDE into a loss function, thus integrating theory and data. Key innovations include the identification and estimation of characteristic non-dimensional parameters, a pre-training step that utilizes the non-dimensional parameters and a fine-tuning step to determine the patient specific parameters. Additionally, the diffuse domain method is employed to handle the complex brain geometry within the PINN framework. Our method is validated both on synthetic and patient datasets, and shows promise for real-time parametric inference in the clinical setting for personalized GBM treatment. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.16536v3-abstract-full').style.display = 'none'; document.getElementById('2311.16536v3-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 August, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 28 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 2023. </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 92-08; 92C50; 35Q92 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> J.3; J.2; I.2.6 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.09261">arXiv:2311.09261</a> <span> [<a href="https://arxiv.org/pdf/2311.09261">pdf</a>, <a href="https://arxiv.org/format/2311.09261">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="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"> Emerging Drug Interaction Prediction Enabled by Flow-based Graph Neural Network with Biomedical Network </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Y">Yongqi Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Yao%2C+Q">Quanming Yao</a>, <a href="/search/q-bio?searchtype=author&query=Yue%2C+L">Ling Yue</a>, <a href="/search/q-bio?searchtype=author&query=Wu%2C+X">Xian Wu</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Ziheng Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Lin%2C+Z">Zhenxi Lin</a>, <a href="/search/q-bio?searchtype=author&query=Zheng%2C+Y">Yefeng Zheng</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="2311.09261v1-abstract-short" style="display: inline;"> Accurately predicting drug-drug interactions (DDI) for emerging drugs, which offer possibilities for treating and alleviating diseases, with computational methods can improve patient care and contribute to efficient drug development. However, many existing computational methods require large amounts of known DDI information, which is scarce for emerging drugs. In this paper, we propose EmerGNN, a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.09261v1-abstract-full').style.display = 'inline'; document.getElementById('2311.09261v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.09261v1-abstract-full" style="display: none;"> Accurately predicting drug-drug interactions (DDI) for emerging drugs, which offer possibilities for treating and alleviating diseases, with computational methods can improve patient care and contribute to efficient drug development. However, many existing computational methods require large amounts of known DDI information, which is scarce for emerging drugs. In this paper, we propose EmerGNN, a graph neural network (GNN) that can effectively predict interactions for emerging drugs by leveraging the rich information in biomedical networks. EmerGNN learns pairwise representations of drugs by extracting the paths between drug pairs, propagating information from one drug to the other, and incorporating the relevant biomedical concepts on the paths. The different edges on the biomedical network are weighted to indicate the relevance for the target DDI prediction. Overall, EmerGNN has higher accuracy than existing approaches in predicting interactions for emerging drugs and can identify the most relevant information on the biomedical network. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.09261v1-abstract-full').style.display = 'none'; document.getElementById('2311.09261v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">Accepted by Nature Computational Science</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2311.03429">arXiv:2311.03429</a> <span> [<a href="https://arxiv.org/pdf/2311.03429">pdf</a>, <a href="https://arxiv.org/format/2311.03429">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Genomics">q-bio.GN</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> </div> </div> <p class="title is-5 mathjax"> ProPath: Disease-Specific Protein Language Model for Variant Pathogenicity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhan%2C+H">Huixin Zhan</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zijun Zhang</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="2311.03429v2-abstract-short" style="display: inline;"> Clinical variant classification of pathogenic versus benign genetic variants remains a pivotal challenge in clinical genetics. Recently, the proposition of protein language models has improved the generic variant effect prediction (VEP) accuracy via weakly-supervised or unsupervised training. However, these VEPs are not disease-specific, limiting their adaptation at point-of-care. To address this… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.03429v2-abstract-full').style.display = 'inline'; document.getElementById('2311.03429v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2311.03429v2-abstract-full" style="display: none;"> Clinical variant classification of pathogenic versus benign genetic variants remains a pivotal challenge in clinical genetics. Recently, the proposition of protein language models has improved the generic variant effect prediction (VEP) accuracy via weakly-supervised or unsupervised training. However, these VEPs are not disease-specific, limiting their adaptation at point-of-care. To address this problem, we propose a disease-specific \textsc{pro}tein language model for variant \textsc{path}ogenicity, termed ProPath, to capture the pseudo-log-likelihood ratio in rare missense variants through a siamese network. We evaluate the performance of ProPath against pre-trained language models, using clinical variant sets in inherited cardiomyopathies and arrhythmias that were not seen during training. Our results demonstrate that ProPath surpasses the pre-trained ESM1b with an over $5\%$ improvement in AUC across both datasets. Furthermore, our model achieved the highest performances across all baselines for both datasets. Thus, our ProPath offers a potent disease-specific variant effect prediction, particularly valuable for disease associations and clinical applicability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2311.03429v2-abstract-full').style.display = 'none'; document.getElementById('2311.03429v2-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> 7 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 6 November, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> November 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">Accepted by MLCB 2023</span> </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/2308.05738">arXiv:2308.05738</a> <span> [<a href="https://arxiv.org/pdf/2308.05738">pdf</a>, <a href="https://arxiv.org/format/2308.05738">other</a>] </span> </p> <div class="tags is-inline-block"> <span class="tag is-small is-link tooltip is-tooltip-top" data-tooltip="Computation">stat.CO</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="Applications">stat.AP</span> <span class="tag is-small is-grey tooltip is-tooltip-top" data-tooltip="Methodology">stat.ME</span> </div> </div> <p class="title is-5 mathjax"> Continuous and Atlas-free Analysis of Brain Structural Connectivity </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Consagra%2C+W">William Consagra</a>, <a href="/search/q-bio?searchtype=author&query=Cole%2C+M">Martin Cole</a>, <a href="/search/q-bio?searchtype=author&query=Qiu%2C+X">Xing Qiu</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhengwu Zhang</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="2308.05738v1-abstract-short" style="display: inline;"> Brain structural networks are often represented as discrete adjacency matrices with elements summarizing the connectivity between pairs of regions of interest (ROIs). These ROIs are typically determined a-priori using a brain atlas. The choice of atlas is often arbitrary and can lead to a loss of important connectivity information at the sub-ROI level. This work introduces an atlas-free framework… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.05738v1-abstract-full').style.display = 'inline'; document.getElementById('2308.05738v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.05738v1-abstract-full" style="display: none;"> Brain structural networks are often represented as discrete adjacency matrices with elements summarizing the connectivity between pairs of regions of interest (ROIs). These ROIs are typically determined a-priori using a brain atlas. The choice of atlas is often arbitrary and can lead to a loss of important connectivity information at the sub-ROI level. This work introduces an atlas-free framework that overcomes these issues by modeling brain connectivity using smooth random functions. In particular, we assume that the observed pattern of white matter fiber tract endpoints is driven by a latent random function defined over a product manifold domain. To facilitate statistical analysis of these high dimensional functional data objects, we develop a novel algorithm to construct a data-driven reduced-rank function space that offers a desirable trade-off between computational complexity and flexibility. Using real data from the Human Connectome Project, we show that our method outperforms state-of-the-art approaches that use the traditional atlas-based structural connectivity representation on a variety of connectivity analysis tasks. We further demonstrate how our method can be used to detect localized regions and connectivity patterns associated with group differences. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.05738v1-abstract-full').style.display = 'none'; document.getElementById('2308.05738v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 2023. </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2308.04776">arXiv:2308.04776</a> <span> [<a href="https://arxiv.org/pdf/2308.04776">pdf</a>, <a href="https://arxiv.org/format/2308.04776">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="Statistical Mechanics">cond-mat.stat-mech</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/10.1103/PhysRevResearch.6.013035">10.1103/PhysRevResearch.6.013035 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> Universal scaling relation and criticality in metabolism and growth of Escherichia coli </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Guan%2C+S">Shaohua Guan</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhichao Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zihan Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Shi%2C+H">Hualin Shi</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="2308.04776v2-abstract-short" style="display: inline;"> The metabolic network plays a crucial role in regulating bacterial metabolism and growth, but it is subject to inherent molecular stochasticity. Previous studies have utilized flux balance analysis and the maximum entropy method to predict metabolic fluxes and growth rates, while the underlying principles governing bacterial metabolism and growth, especially the criticality hypothesis, remain uncl… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.04776v2-abstract-full').style.display = 'inline'; document.getElementById('2308.04776v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2308.04776v2-abstract-full" style="display: none;"> The metabolic network plays a crucial role in regulating bacterial metabolism and growth, but it is subject to inherent molecular stochasticity. Previous studies have utilized flux balance analysis and the maximum entropy method to predict metabolic fluxes and growth rates, while the underlying principles governing bacterial metabolism and growth, especially the criticality hypothesis, remain unclear. In this study, we employ a maximum entropy approach to investigate the universality in various constraint-based metabolic networks of Escherichia coli. Our findings reveal the existence of universal scaling relations across different nutritional environments and metabolic network models, similar to the universality observed in physics. By analyzing single-cell data, we confirm that metabolism of Escherichia coli operates close to the state with maximum Fisher information, which serves as a signature of criticality. This critical state provides functional advantages such as high sensitivity and long-range correlation. Moreover, we demonstrate that a metabolic system operating at criticality takes a compromise solution between growth and adaptation, thereby serving as a survival strategy in fluctuating environments. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2308.04776v2-abstract-full').style.display = 'none'; document.getElementById('2308.04776v2-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 January, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 9 August, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> August 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">10 pages, 6 figures</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">Journal ref:</span> Phys. Rev. Research 6, 013035 (2024) </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2307.08107">arXiv:2307.08107</a> <span> [<a href="https://arxiv.org/pdf/2307.08107">pdf</a>, <a href="https://arxiv.org/format/2307.08107">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> </div> </div> <p class="title is-5 mathjax"> Discovering a reaction-diffusion model for Alzheimer's disease by combining PINNs with symbolic regression </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhen Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Zou%2C+Z">Zongren Zou</a>, <a href="/search/q-bio?searchtype=author&query=Kuhl%2C+E">Ellen Kuhl</a>, <a href="/search/q-bio?searchtype=author&query=Karniadakis%2C+G+E">George Em Karniadakis</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="2307.08107v1-abstract-short" style="display: inline;"> Misfolded tau proteins play a critical role in the progression and pathology of Alzheimer's disease. Recent studies suggest that the spatio-temporal pattern of misfolded tau follows a reaction-diffusion type equation. However, the precise mathematical model and parameters that characterize the progression of misfolded protein across the brain remain incompletely understood. Here, we use deep learn… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.08107v1-abstract-full').style.display = 'inline'; document.getElementById('2307.08107v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2307.08107v1-abstract-full" style="display: none;"> Misfolded tau proteins play a critical role in the progression and pathology of Alzheimer's disease. Recent studies suggest that the spatio-temporal pattern of misfolded tau follows a reaction-diffusion type equation. However, the precise mathematical model and parameters that characterize the progression of misfolded protein across the brain remain incompletely understood. Here, we use deep learning and artificial intelligence to discover a mathematical model for the progression of Alzheimer's disease using longitudinal tau positron emission tomography from the Alzheimer's Disease Neuroimaging Initiative database. Specifically, we integrate physics informed neural networks (PINNs) and symbolic regression to discover a reaction-diffusion type partial differential equation for tau protein misfolding and spreading. First, we demonstrate the potential of our model and parameter discovery on synthetic data. Then, we apply our method to discover the best model and parameters to explain tau imaging data from 46 individuals who are likely to develop Alzheimer's disease and 30 healthy controls. Our symbolic regression discovers different misfolding models $f(c)$ for two groups, with a faster misfolding for the Alzheimer's group, $f(c) = 0.23c^3 - 1.34c^2 + 1.11c$, than for the healthy control group, $f(c) = -c^3 +0.62c^2 + 0.39c$. Our results suggest that PINNs, supplemented by symbolic regression, can discover a reaction-diffusion type model to explain misfolded tau protein concentrations in Alzheimer's disease. We expect our study to be the starting point for a more holistic analysis to provide image-based technologies for early diagnosis, and ideally early treatment of neurodegeneration in Alzheimer's disease and possibly other misfolding-protein based neurodegenerative disorders. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2307.08107v1-abstract-full').style.display = 'none'; document.getElementById('2307.08107v1-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, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> July 2023. </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/2306.03117">arXiv:2306.03117</a> <span> [<a href="https://arxiv.org/pdf/2306.03117">pdf</a>, <a href="https://arxiv.org/format/2306.03117">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="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"> Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Lu%2C+J">Jiarui Lu</a>, <a href="/search/q-bio?searchtype=author&query=Zhong%2C+B">Bozitao Zhong</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zuobai Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Tang%2C+J">Jian Tang</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="2306.03117v3-abstract-short" style="display: inline;"> The dynamic nature of proteins is crucial for determining their biological functions and properties, for which Monte Carlo (MC) and molecular dynamics (MD) simulations stand as predominant tools to study such phenomena. By utilizing empirically derived force fields, MC or MD simulations explore the conformational space through numerically evolving the system via Markov chain or Newtonian mechanics… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.03117v3-abstract-full').style.display = 'inline'; document.getElementById('2306.03117v3-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.03117v3-abstract-full" style="display: none;"> The dynamic nature of proteins is crucial for determining their biological functions and properties, for which Monte Carlo (MC) and molecular dynamics (MD) simulations stand as predominant tools to study such phenomena. By utilizing empirically derived force fields, MC or MD simulations explore the conformational space through numerically evolving the system via Markov chain or Newtonian mechanics. However, the high-energy barrier of the force fields can hamper the exploration of both methods by the rare event, resulting in inadequately sampled ensemble without exhaustive running. Existing learning-based approaches perform direct sampling yet heavily rely on target-specific simulation data for training, which suffers from high data acquisition cost and poor generalizability. Inspired by simulated annealing, we propose Str2Str, a novel structure-to-structure translation framework capable of zero-shot conformation sampling with roto-translation equivariant property. Our method leverages an amortized denoising score matching objective trained on general crystal structures and has no reliance on simulation data during both training and inference. Experimental results across several benchmarking protein systems demonstrate that Str2Str outperforms previous state-of-the-art generative structure prediction models and can be orders of magnitude faster compared to long MD simulations. Our open-source implementation is available at https://github.com/lujiarui/Str2Str <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.03117v3-abstract-full').style.display = 'none'; document.getElementById('2306.03117v3-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 March, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 5 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">Published as a conference paper at ICLR 2024, see https://openreview.net/forum?id=C4BikKsgmK</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.02532">arXiv:2306.02532</a> <span> [<a href="https://arxiv.org/pdf/2306.02532">pdf</a>, <a href="https://arxiv.org/format/2306.02532">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 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/10.1145/3580305.3599483">10.1145/3580305.3599483 <i class="fa fa-external-link" aria-hidden="true"></i></a></span> </div> </div> </div> <p class="title is-5 mathjax"> R-Mixup: Riemannian Mixup for Biological Networks </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Kan%2C+X">Xuan Kan</a>, <a href="/search/q-bio?searchtype=author&query=Li%2C+Z">Zimu Li</a>, <a href="/search/q-bio?searchtype=author&query=Cui%2C+H">Hejie Cui</a>, <a href="/search/q-bio?searchtype=author&query=Yu%2C+Y">Yue Yu</a>, <a href="/search/q-bio?searchtype=author&query=Xu%2C+R">Ran Xu</a>, <a href="/search/q-bio?searchtype=author&query=Yu%2C+S">Shaojun Yu</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zilong Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Guo%2C+Y">Ying Guo</a>, <a href="/search/q-bio?searchtype=author&query=Yang%2C+C">Carl Yang</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="2306.02532v1-abstract-short" style="display: inline;"> Biological networks are commonly used in biomedical and healthcare domains to effectively model the structure of complex biological systems with interactions linking biological entities. However, due to their characteristics of high dimensionality and low sample size, directly applying deep learning models on biological networks usually faces severe overfitting. In this work, we propose R-MIXUP, a… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.02532v1-abstract-full').style.display = 'inline'; document.getElementById('2306.02532v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.02532v1-abstract-full" style="display: none;"> Biological networks are commonly used in biomedical and healthcare domains to effectively model the structure of complex biological systems with interactions linking biological entities. However, due to their characteristics of high dimensionality and low sample size, directly applying deep learning models on biological networks usually faces severe overfitting. In this work, we propose R-MIXUP, a Mixup-based data augmentation technique that suits the symmetric positive definite (SPD) property of adjacency matrices from biological networks with optimized training efficiency. The interpolation process in R-MIXUP leverages the log-Euclidean distance metrics from the Riemannian manifold, effectively addressing the swelling effect and arbitrarily incorrect label issues of vanilla Mixup. We demonstrate the effectiveness of R-MIXUP with five real-world biological network datasets on both regression and classification tasks. Besides, we derive a commonly ignored necessary condition for identifying the SPD matrices of biological networks and empirically study its influence on the model performance. The code implementation can be found in Appendix E. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.02532v1-abstract-full').style.display = 'none'; document.getElementById('2306.02532v1-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, 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">Accepted to KDD 2023</span> </p> <p class="comments is-size-7"> <span class="has-text-black-bis has-text-weight-semibold">MSC Class:</span> 68T07; 68T05 <span class="has-text-black-bis has-text-weight-semibold">ACM Class:</span> I.2.6; J.3 </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.01794">arXiv:2306.01794</a> <span> [<a href="https://arxiv.org/pdf/2306.01794">pdf</a>, <a href="https://arxiv.org/format/2306.01794">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="Machine Learning">cs.LG</span> </div> </div> <p class="title is-5 mathjax"> DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Y">Yangtian Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zuobai Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Zhong%2C+B">Bozitao Zhong</a>, <a href="/search/q-bio?searchtype=author&query=Misra%2C+S">Sanchit Misra</a>, <a href="/search/q-bio?searchtype=author&query=Tang%2C+J">Jian Tang</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="2306.01794v2-abstract-short" style="display: inline;"> Proteins play a critical role in carrying out biological functions, and their 3D structures are essential in determining their functions. Accurately predicting the conformation of protein side-chains given their backbones is important for applications in protein structure prediction, design and protein-protein interactions. Traditional methods are computationally intensive and have limited accurac… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.01794v2-abstract-full').style.display = 'inline'; document.getElementById('2306.01794v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.01794v2-abstract-full" style="display: none;"> Proteins play a critical role in carrying out biological functions, and their 3D structures are essential in determining their functions. Accurately predicting the conformation of protein side-chains given their backbones is important for applications in protein structure prediction, design and protein-protein interactions. Traditional methods are computationally intensive and have limited accuracy, while existing machine learning methods treat the problem as a regression task and overlook the restrictions imposed by the constant covalent bond lengths and angles. In this work, we present DiffPack, a torsional diffusion model that learns the joint distribution of side-chain torsional angles, the only degrees of freedom in side-chain packing, by diffusing and denoising on the torsional space. To avoid issues arising from simultaneous perturbation of all four torsional angles, we propose autoregressively generating the four torsional angles from $蠂_1$ to $蠂_4$ and training diffusion models for each torsional angle. We evaluate the method on several benchmarks for protein side-chain packing and show that our method achieves improvements of $11.9\%$ and $13.5\%$ in angle accuracy on CASP13 and CASP14, respectively, with a significantly smaller model size ($60\times$ fewer parameters). Additionally, we show the effectiveness of our method in enhancing side-chain predictions in the AlphaFold2 model. Code is available at https://github.com/DeepGraphLearning/DiffPack. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.01794v2-abstract-full').style.display = 'none'; document.getElementById('2306.01794v2-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 February, 2024; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 1 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">37th Conference on Neural Information Processing Systems (NeurIPS 2023)</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2306.00548">arXiv:2306.00548</a> <span> [<a href="https://arxiv.org/pdf/2306.00548">pdf</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="Computer Vision and Pattern Recognition">cs.CV</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="Medical Physics">physics.med-ph</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"> Label- and slide-free tissue histology using 3D epi-mode quantitative phase imaging and virtual H&E staining </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Abraham%2C+T+M">Tanishq Mathew Abraham</a>, <a href="/search/q-bio?searchtype=author&query=Costa%2C+P+C">Paloma Casteleiro Costa</a>, <a href="/search/q-bio?searchtype=author&query=Filan%2C+C">Caroline Filan</a>, <a href="/search/q-bio?searchtype=author&query=Guang%2C+Z">Zhe Guang</a>, <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zhaobin Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Neill%2C+S">Stewart Neill</a>, <a href="/search/q-bio?searchtype=author&query=Olson%2C+J+J">Jeffrey J. Olson</a>, <a href="/search/q-bio?searchtype=author&query=Levenson%2C+R">Richard Levenson</a>, <a href="/search/q-bio?searchtype=author&query=Robles%2C+F+E">Francisco E. Robles</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="2306.00548v1-abstract-short" style="display: inline;"> Histological staining of tissue biopsies, especially hematoxylin and eosin (H&E) staining, serves as the benchmark for disease diagnosis and comprehensive clinical assessment of tissue. However, the process is laborious and time-consuming, often limiting its usage in crucial applications such as surgical margin assessment. To address these challenges, we combine an emerging 3D quantitative phase i… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.00548v1-abstract-full').style.display = 'inline'; document.getElementById('2306.00548v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2306.00548v1-abstract-full" style="display: none;"> Histological staining of tissue biopsies, especially hematoxylin and eosin (H&E) staining, serves as the benchmark for disease diagnosis and comprehensive clinical assessment of tissue. However, the process is laborious and time-consuming, often limiting its usage in crucial applications such as surgical margin assessment. To address these challenges, we combine an emerging 3D quantitative phase imaging technology, termed quantitative oblique back illumination microscopy (qOBM), with an unsupervised generative adversarial network pipeline to map qOBM phase images of unaltered thick tissues (i.e., label- and slide-free) to virtually stained H&E-like (vH&E) images. We demonstrate that the approach achieves high-fidelity conversions to H&E with subcellular detail using fresh tissue specimens from mouse liver, rat gliosarcoma, and human gliomas. We also show that the framework directly enables additional capabilities such as H&E-like contrast for volumetric imaging. The quality and fidelity of the vH&E images are validated using both a neural network classifier trained on real H&E images and tested on virtual H&E images, and a user study with neuropathologists. Given its simple and low-cost embodiment and ability to provide real-time feedback in vivo, this deep learning-enabled qOBM approach could enable new workflows for histopathology with the potential to significantly save time, labor, and costs in cancer screening, detection, treatment guidance, and more. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2306.00548v1-abstract-full').style.display = 'none'; document.getElementById('2306.00548v1-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, 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">30 pages, 9 main figures, 1 table, 5 supplementary 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/2305.13997">arXiv:2305.13997</a> <span> [<a href="https://arxiv.org/pdf/2305.13997">pdf</a>, <a href="https://arxiv.org/format/2305.13997">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"> Learning Subpocket Prototypes for Generalizable Structure-based Drug Design </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=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="2305.13997v1-abstract-short" style="display: inline;"> Generating molecules with high binding affinities to target proteins (a.k.a. structure-based drug design) is a fundamental and challenging task in drug discovery. Recently, deep generative models have achieved remarkable success in generating 3D molecules conditioned on the protein pocket. However, most existing methods consider molecular generation for protein pockets independently while neglecti… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.13997v1-abstract-full').style.display = 'inline'; document.getElementById('2305.13997v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.13997v1-abstract-full" style="display: none;"> Generating molecules with high binding affinities to target proteins (a.k.a. structure-based drug design) is a fundamental and challenging task in drug discovery. Recently, deep generative models have achieved remarkable success in generating 3D molecules conditioned on the protein pocket. However, most existing methods consider molecular generation for protein pockets independently while neglecting the underlying connections such as subpocket-level similarities. Subpockets are the local protein environments of ligand fragments and pockets with similar subpockets may bind the same molecular fragment (motif) even though their overall structures are different. Therefore, the trained models can hardly generalize to unseen protein pockets in real-world applications. In this paper, we propose a novel method DrugGPS for generalizable structure-based drug design. With the biochemical priors, we propose to learn subpocket prototypes and construct a global interaction graph to model the interactions between subpocket prototypes and molecular motifs. Moreover, a hierarchical graph transformer encoder and motif-based 3D molecule generation scheme are used to improve the model's performance. The experimental results show that our model consistently outperforms baselines in generating realistic drug candidates with high affinities in challenging out-of-distribution settings. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.13997v1-abstract-full').style.display = 'none'; document.getElementById('2305.13997v1-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 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">Accepted by ICML 2023</span> </p> </li> <li class="arxiv-result"> <div class="is-marginless"> <p class="list-title is-inline-block"><a href="https://arxiv.org/abs/2305.11917">arXiv:2305.11917</a> <span> [<a href="https://arxiv.org/pdf/2305.11917">pdf</a>, <a href="https://arxiv.org/format/2305.11917">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"> Interpretable neural architecture search and transfer learning for understanding CRISPR/Cas9 off-target enzymatic reactions </p> <p class="authors"> <span class="search-hit">Authors:</span> <a href="/search/q-bio?searchtype=author&query=Zhang%2C+Z">Zijun Zhang</a>, <a href="/search/q-bio?searchtype=author&query=Lamson%2C+A+R">Adam R. Lamson</a>, <a href="/search/q-bio?searchtype=author&query=Shelley%2C+M">Michael Shelley</a>, <a href="/search/q-bio?searchtype=author&query=Troyanskaya%2C+O">Olga Troyanskaya</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="2305.11917v2-abstract-short" style="display: inline;"> Finely-tuned enzymatic pathways control cellular processes, and their dysregulation can lead to disease. Creating predictive and interpretable models for these pathways is challenging because of the complexity of the pathways and of the cellular and genomic contexts. Here we introduce Elektrum, a deep learning framework which addresses these challenges with data-driven and biophysically interpreta… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.11917v2-abstract-full').style.display = 'inline'; document.getElementById('2305.11917v2-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2305.11917v2-abstract-full" style="display: none;"> Finely-tuned enzymatic pathways control cellular processes, and their dysregulation can lead to disease. Creating predictive and interpretable models for these pathways is challenging because of the complexity of the pathways and of the cellular and genomic contexts. Here we introduce Elektrum, a deep learning framework which addresses these challenges with data-driven and biophysically interpretable models for determining the kinetics of biochemical systems. First, it uses in vitro kinetic assays to rapidly hypothesize an ensemble of high-quality Kinetically Interpretable Neural Networks (KINNs) that predict reaction rates. It then employs a novel transfer learning step, where the KINNs are inserted as intermediary layers into deeper convolutional neural networks, fine-tuning the predictions for reaction-dependent in vivo outcomes. Elektrum makes effective use of the limited, but clean in vitro data and the complex, yet plentiful in vivo data that captures cellular context. We apply Elektrum to predict CRISPR-Cas9 off-target editing probabilities and demonstrate that Elektrum achieves state-of-the-art performance, regularizes neural network architectures, and maintains physical interpretability. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2305.11917v2-abstract-full').style.display = 'none'; document.getElementById('2305.11917v2-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> 29 September, 2023; <span class="has-text-black-bis has-text-weight-semibold">v1</span> submitted 18 May, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> May 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">23 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/2304.12436">arXiv:2304.12436</a> <span> [<a href="https://arxiv.org/pdf/2304.12436">pdf</a>, <a href="https://arxiv.org/format/2304.12436">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"> An Equivariant Generative Framework for Molecular Graph-Structure Co-Design </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=Liu%2C+Q">Qi Liu</a>, <a href="/search/q-bio?searchtype=author&query=Lee%2C+C">Chee-Kong Lee</a>, <a href="/search/q-bio?searchtype=author&query=Hsieh%2C+C">Chang-Yu Hsieh</a>, <a href="/search/q-bio?searchtype=author&query=Chen%2C+E">Enhong Chen</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="2304.12436v1-abstract-short" style="display: inline;"> Designing molecules with desirable physiochemical properties and functionalities is a long-standing challenge in chemistry, material science, and drug discovery. Recently, machine learning-based generative models have emerged as promising approaches for \emph{de novo} molecule design. However, further refinement of methodology is highly desired as most existing methods lack unified modeling of 2D… <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.12436v1-abstract-full').style.display = 'inline'; document.getElementById('2304.12436v1-abstract-short').style.display = 'none';">▽ More</a> </span> <span class="abstract-full has-text-grey-dark mathjax" id="2304.12436v1-abstract-full" style="display: none;"> Designing molecules with desirable physiochemical properties and functionalities is a long-standing challenge in chemistry, material science, and drug discovery. Recently, machine learning-based generative models have emerged as promising approaches for \emph{de novo} molecule design. However, further refinement of methodology is highly desired as most existing methods lack unified modeling of 2D topology and 3D geometry information and fail to effectively learn the structure-property relationship for molecule design. Here we present MolCode, a roto-translation equivariant generative framework for \underline{Mol}ecular graph-structure \underline{Co-de}sign. In MolCode, 3D geometric information empowers the molecular 2D graph generation, which in turn helps guide the prediction of molecular 3D structure. Extensive experimental results show that MolCode outperforms previous methods on a series of challenging tasks including \emph{de novo} molecule design, targeted molecule discovery, and structure-based drug design. Particularly, MolCode not only consistently generates valid (99.95$\%$ Validity) and diverse (98.75$\%$ Uniqueness) molecular graphs/structures with desirable properties, but also generate drug-like molecules with high affinity to target proteins (61.8$\%$ high-affinity ratio), which demonstrates MolCode's potential applications in material design and drug discovery. Our extensive investigation reveals that the 2D topology and 3D geometry contain intrinsically complementary information in molecule design, and provide new insights into machine learning-based molecule representation and generation. <a class="is-size-7" style="white-space: nowrap;" onclick="document.getElementById('2304.12436v1-abstract-full').style.display = 'none'; document.getElementById('2304.12436v1-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 April, 2023; <span class="has-text-black-bis has-text-weight-semibold">originally announced</span> April 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">Under review</span> </p> </li> </ol> <nav class="pagination is-small is-centered breathe-horizontal" role="navigation" aria-label="pagination"> <a href="" class="pagination-previous is-invisible">Previous </a> <a href="/search/?searchtype=author&query=Zhang%2C+Z&start=50" class="pagination-next" >Next </a> <ul class="pagination-list"> <li> <a href="/search/?searchtype=author&query=Zhang%2C+Z&start=0" class="pagination-link is-current" aria-label="Goto page 1">1 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+Z&start=50" class="pagination-link " aria-label="Page 2" aria-current="page">2 </a> </li> <li> <a href="/search/?searchtype=author&query=Zhang%2C+Z&start=100" class="pagination-link " aria-label="Page 3" aria-current="page">3 </a> </li> </ul> </nav> <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