{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T18:00:38Z","timestamp":1773252038869,"version":"3.50.1"},"reference-count":22,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T00:00:00Z","timestamp":1747267200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Scientific and Technological Research Council of T\u00fcrkiye","award":["120C120"],"award-info":[{"award-number":["120C120"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Allostery, the process by which binding at one site perturbs a distant site, is being rendered as a key focus in the field of drug development with its substantial impact on protein function. The identification of allosteric pockets (sites) is a challenging task and several techniques have been developed, including Machine Learning to predict allosteric pockets that utilize both static and pocket features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our work, DeepAllo, is the first study that combines fine-tuned protein language model (pLM) with FPocket features and shows an increase in prediction performance of allosteric sites over previous studies. The pLM model was fine-tuned on AlloSteric Database (ASD) in Multitask Learning setting and was further used as a feature extractor to train XGBoost and AutoML models. The best model predicts allosteric pockets with 89.66% F1 score and 90.5% of allosteric pockets in the top 3 positions, outperforming previous results. A case study has been performed on proteins with known allosteric pockets, which shows the proof of our approach. Moreover, an effort was made to explain the pLM by visualizing its attention mechanism among allosteric and non-allosteric residues.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The source code is available on GitHub (https:\/\/github.com\/MoaazK\/deepallo) and archived on Zenodo (DOI: 10.5281\/zenodo.15255379). The trained model is hosted on Hugging Face (DOI: 10.57967\/hf\/5198). The dataset used for training and evaluation is archived on Zenodo (DOI: 10.5281\/zenodo.15255437).<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf294","type":"journal-article","created":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T08:03:23Z","timestamp":1747209803000},"source":"Crossref","is-referenced-by-count":11,"title":["DeepAllo: allosteric site prediction using protein language model (pLM) with multitask learning"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1977-2736","authenticated-orcid":false,"given":"Moaaz","family":"Khokhar","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Ko\u00e7 University , 34450 Istanbul,","place":["Turkey"]},{"name":"KUIS AI Center, Ko\u00e7 University , 34450 Istanbul,","place":["Turkey"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4202-4049","authenticated-orcid":false,"given":"Ozlem","family":"Keskin","sequence":"additional","affiliation":[{"name":"Department of Chemical and Biological Engineering, Ko\u00e7 University , 34450 Istanbul,","place":["Turkey"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2297-2113","authenticated-orcid":false,"given":"Attila","family":"Gursoy","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Ko\u00e7 University , 34450 Istanbul,","place":["Turkey"]},{"name":"KUIS AI Center, Ko\u00e7 University , 34450 Istanbul,","place":["Turkey"]}]}],"member":"286","published-online":{"date-parts":[[2025,5,15]]},"reference":[{"key":"2025070408272195000_btaf294-B1","doi-asserted-by":"crossref","first-page":"2605","DOI":"10.1021\/acs.molpharmaceut.9b00182","article-title":"Prediction of orthosteric and allosteric regulations on cannabinoid receptors using supervised machine learning classifiers","volume":"16","author":"Bian","year":"2019","journal-title":"Mol Pharm"},{"key":"2025070408272195000_btaf294-B2","doi-asserted-by":"publisher","author":"Elnaggar","year":"2020","DOI":"10.1101\/864405"},{"key":"2025070408272195000_btaf294-B3","doi-asserted-by":"publisher","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"Prottrans: Toward understanding the language of life through self-supervised learning.","author":"Elnaggar","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2025070408272195000_btaf294-B4","author":"Erickson","year":"2020"},{"key":"2025070408272195000_btaf294-B5","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1186\/s12859-015-0771-1","article-title":"Allopred: prediction of allosteric pockets on proteins using normal mode perturbation analysis","volume":"16","author":"Greener","year":"2015","journal-title":"BMC Bioinformatics"},{"key":"2025070408272195000_btaf294-B6","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1186\/1471-2105-10-168","article-title":"Fpocket: an open source platform for ligand pocket detection","volume":"10","author":"Guilloux","year":"2009","journal-title":"BMC Bioinform"},{"key":"2025070408272195000_btaf294-B7","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1002\/prot.20232","article-title":"Is allostery an intrinsic property of all dynamic proteins?","volume":"57","author":"Gunasekaran","year":"2004","journal-title":"Proteins Struct Funct Bioinf"},{"key":"2025070408272195000_btaf294-B8","doi-asserted-by":"publisher","first-page":"D376","DOI":"10.1093\/nar\/gkad915","article-title":"ASD2023: towards the integrating landscapes of allosteric knowledgebase","volume":"52","author":"He","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2025070408272195000_btaf294-B9","doi-asserted-by":"crossref","first-page":"2357","DOI":"10.1093\/bioinformatics\/btt399","article-title":"Allosite: a method for predicting allosteric sites","volume":"29","author":"Huang","year":"2013","journal-title":"Bioinformatics"},{"key":"2025070408272195000_btaf294-B10","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1016\/j.str.2008.11.009","article-title":"Comprehensive structural classification of ligand-binding motifs in proteins","volume":"17","author":"Kinjo","year":"2009","journal-title":"Structure"},{"key":"2025070408272195000_btaf294-B11","doi-asserted-by":"publisher","author":"Klausen","DOI":"10.1002\/prot.25674"},{"key":"2025070408272195000_btaf294-B12","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1016\/j.tips.2021.10.011","article-title":"Wandering beyond small molecules: peptides as allosteric protein modulators","volume":"43","author":"Mannes","year":"2022","journal-title":"Trends Pharmacol Sci"},{"key":"2025070408272195000_btaf294-B13","doi-asserted-by":"crossref","first-page":"1311","DOI":"10.2174\/138161212799436377","article-title":"The different ways through which specificity works in orthosteric and allosteric drugs","volume":"18","author":"Nussinov","year":"2012","journal-title":"Curr Pharm Des"},{"key":"2025070408272195000_btaf294-B14","doi-asserted-by":"crossref","first-page":"2358","DOI":"10.1021\/acs.jcim.7b00014","article-title":"Improved method for the identification and validation of allosteric sites","volume":"57","author":"Song","year":"2017","journal-title":"J Chem Inf Model"},{"key":"2025070408272195000_btaf294-B15","doi-asserted-by":"publisher","author":"Steinegger","year":"2018","DOI":"10.1038\/s41467-018-04964-5"},{"key":"2025070408272195000_btaf294-B16","doi-asserted-by":"crossref","first-page":"035015","DOI":"10.1088\/2632-2153\/abe6d6","article-title":"Passer: prediction of allosteric sites server","volume":"2","author":"Tian","year":"2021","journal-title":"Mach Learn Sci Technol"},{"key":"2025070408272195000_btaf294-B17","doi-asserted-by":"publisher","first-page":"W427","DOI":"10.1093\/nar\/gkad303","article-title":"PASSer: fast and accurate prediction of protein allosteric sites","volume":"51","author":"Tian","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2025070408272195000_btaf294-B18","doi-asserted-by":"publisher","author":"Tian","DOI":"10.1002\/jcc.27193"},{"key":"2025070408272195000_btaf294-B19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jmb.2008.02.034","article-title":"Allostery: absence of a change in shape does not imply that allostery is not at play","volume":"378","author":"Tsai","year":"2008","journal-title":"J Mol Biol"},{"key":"2025070408272195000_btaf294-B20","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2025070408272195000_btaf294-B21","doi-asserted-by":"publisher","author":"Vig","year":"2020","DOI":"10.1101\/2020.06.26.174417"},{"key":"2025070408272195000_btaf294-B22","doi-asserted-by":"crossref","first-page":"879251","DOI":"10.3389\/fmolb.2022.879251","article-title":"Passer2. 0: accurate prediction of protein allosteric sites through automated machine learning","volume":"9","author":"Xiao","year":"2022","journal-title":"Front Mol Biosci"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf294\/63196710\/btaf294.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/6\/btaf294\/63196710\/btaf294.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/6\/btaf294\/63196710\/btaf294.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T08:27:33Z","timestamp":1751617653000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf294\/8132950"}},"subtitle":[],"editor":[{"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,5,15]]},"references-count":22,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf294","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.10.09.617427","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,6]]},"published":{"date-parts":[[2025,5,15]]},"article-number":"btaf294"}}