{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:34:30Z","timestamp":1772138070959,"version":"3.50.1"},"reference-count":51,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T00:00:00Z","timestamp":1727913600000},"content-version":"vor","delay-in-days":2,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100009500","name":"BUET","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009500","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Proteins are responsible for most biological functions, many of which require the interaction of more than one protein molecule. However, accurately predicting protein\u2013protein interaction (PPI) sites (the interfacial residues of a protein that interact with other protein molecules) remains a challenge. The growing demand and cost associated with the reliable identification of PPI sites using conventional experimental methods call for computational tools for automated prediction and understanding of PPIs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We present Pair-EGRET, an edge-aggregated graph attention network that leverages the features extracted from pretrained transformer-like models to accurately predict PPI sites. Pair-EGRET works on a k-nearest neighbor graph, representing the 3D structure of a protein, and utilizes the cross-attention mechanism for accurate identification of interfacial residues of a pair of proteins. Through an extensive evaluation study using a diverse array of experimental data, evaluation metrics, and case studies on representative protein sequences, we demonstrate that Pair-EGRET can achieve remarkable performance in predicting PPI sites. Moreover, Pair-EGRET can provide interpretable insights from the learned cross-attention matrix.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Pair-EGRET is freely available in open source form at the GitHub Repository https:\/\/github.com\/1705004\/Pair-EGRET.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae588","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T23:21:18Z","timestamp":1727738478000},"source":"Crossref","is-referenced-by-count":8,"title":["Pair-EGRET: enhancing the prediction of protein\u2013protein interaction sites through graph attention networks and protein language models"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7735-8860","authenticated-orcid":false,"given":"Ramisa","family":"Alam","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology , Dhaka 1205,","place":["Bangladesh"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8667-3649","authenticated-orcid":false,"given":"Sazan","family":"Mahbub","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology , Dhaka 1205,","place":["Bangladesh"]},{"name":"Computational Biology Department, School of Computer Science, Carnegie Mellon University , Pittsburgh, PA 15213,","place":["United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5640-0615","authenticated-orcid":false,"given":"Md Shamsuzzoha","family":"Bayzid","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology , Dhaka 1205,","place":["Bangladesh"]}]}],"member":"286","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"2024102220523093400_btae588-B1","doi-asserted-by":"crossref","first-page":"1142","DOI":"10.1002\/prot.24479","article-title":"Pairpred: partner-specific prediction of interacting residues from sequence and structure","volume":"82","author":"Afsar Minhas","year":"2014","journal-title":"Proteins"},{"key":"2024102220523093400_btae588-B2","first-page":"1993","article-title":"Diffusion-convolutional neural networks","volume":"29","author":"Atwood","year":"2016","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024102220523093400_btae588-B3","doi-asserted-by":"publisher","author":"Ba","DOI":"10.48550\/arXiv.1607.06450"},{"key":"2024102220523093400_btae588-B4","doi-asserted-by":"crossref","first-page":"104024","DOI":"10.1016\/j.drudis.2024.104024","article-title":"Geometric deep learning methods and applications in 3d structure-based drug design","volume":"29","author":"Bai","year":"2024","journal-title":"Drug Discov Today"},{"key":"2024102220523093400_btae588-B5","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1093\/nar\/28.1.235","article-title":"The protein data bank","volume":"28","author":"Berman","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2024102220523093400_btae588-B6","doi-asserted-by":"crossref","first-page":"2580","DOI":"10.1093\/bioinformatics\/btab154","article-title":"Protein interaction interface region prediction by geometric deep learning","volume":"37","author":"Dai","year":"2021","journal-title":"Bioinformatics"},{"key":"2024102220523093400_btae588-B7","doi-asserted-by":"publisher","author":"Debnath","DOI":"10.48550\/arXiv.2203.12659"},{"key":"2024102220523093400_btae588-B8","first-page":"82","article-title":"Pymol:\u00a0 An open-source molecular graphics tool","volume":"40","author":"DeLano","year":"2002","journal-title":"Newsl Protein Crystallogr"},{"key":"2024102220523093400_btae588-B9","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","volume":"28","author":"Duvenaud","year":"2015","journal-title":"Adv Neur Inf Process Syst"},{"key":"2024102220523093400_btae588-B10","doi-asserted-by":"crossref","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"Prottrans: toward understanding the language of life through self-supervised learning","volume":"44","author":"Elnaggar","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2024102220523093400_btae588-B11","doi-asserted-by":"publisher","author":"Evans","year":"2022","DOI":"10.1101\/2021.10"},{"key":"2024102220523093400_btae588-B12","first-page":"6533","article-title":"Protein interface prediction using graph convolutional networks","volume":"30","author":"Fout","year":"2017","journal-title":"Adv Neur Inf Process Syst"},{"key":"2024102220523093400_btae588-B13","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1038\/s41592-019-0666-6","article-title":"Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning","volume":"17","author":"Gainza","year":"2019","journal-title":"Nat Methods"},{"key":"2024102220523093400_btae588-B14","doi-asserted-by":"crossref","first-page":"3932","DOI":"10.1021\/acs.chemrev.3c00550","article-title":"Computational approaches to predict protein\u2013protein interactions in crowded cellular environments","volume":"124","author":"Grassmann","year":"2024","journal-title":"Chem Rev"},{"key":"2024102220523093400_btae588-B15","doi-asserted-by":"crossref","first-page":"Vbad042","DOI":"10.1093\/bioadv\/vbad042","article-title":"Saint-angle: self-attention augmented inception-inside-inception network and transfer learning improve protein backbone torsion angle prediction","volume":"3","author":"Hasan","year":"2023","journal-title":"Bioinform Adv"},{"key":"2024102220523093400_btae588-B16","first-page":"770","author":"He","year":"2016"},{"key":"2024102220523093400_btae588-B17","doi-asserted-by":"crossref","first-page":"1479","DOI":"10.1093\/bioinformatics\/btx005","article-title":"Seeing the trees through the Forest: sequence-based homo-and heteromeric protein-protein interaction sites prediction using random Forest","volume":"33","author":"Hou","year":"2017","journal-title":"Bioinformatics"},{"key":"2024102220523093400_btae588-B18","first-page":"10217","author":"Jin","year":"2022"},{"key":"2024102220523093400_btae588-B19","author":"Jing","year":"2021"},{"key":"2024102220523093400_btae588-B20","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1002\/pro.3295","article-title":"Dockground: a comprehensive data resource for modeling of protein complexes","volume":"27","author":"Kundrotas","year":"2018","journal-title":"Protein Sci"},{"key":"2024102220523093400_btae588-B21","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1186\/gm441","article-title":"Protein-protein interaction networks: probing disease mechanisms using model systems","volume":"5","author":"Kuzmanov","year":"2013","journal-title":"Genome Med"},{"key":"2024102220523093400_btae588-B22","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1093\/bioinformatics\/btaa750","article-title":"Delphi: accurate deep ensemble model for protein interaction sites prediction","volume":"37","author":"Li","year":"2021","journal-title":"Bioinformatics"},{"key":"2024102220523093400_btae588-B23","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1038\/s42256-023-00741-2","article-title":"Protein\u2013protein contact prediction by geometric triangle-aware protein language models","volume":"5","author":"Lin","year":"2023","journal-title":"Nat Mach Intell"},{"key":"2024102220523093400_btae588-B24","doi-asserted-by":"publisher","first-page":"500902","DOI":"10.1101\/2022.07.20.500902","author":"Lin","year":"2022"},{"key":"2024102220523093400_btae588-B25","first-page":"679","author":"Liu","year":"2020"},{"key":"2024102220523093400_btae588-B26","doi-asserted-by":"crossref","first-page":"732","DOI":"10.1006\/jmbi.1996.0548","article-title":"Antibody-antigen interactions: contact analysis and binding site topography","volume":"262","author":"MacCallum","year":"1996","journal-title":"J Mol Biol"},{"key":"2024102220523093400_btae588-B27","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab578","article-title":"Egret: edge aggregated graph attention networks and transfer learning improve protein\u2013protein interaction site prediction","volume":"23","author":"Mahbub","year":"2022","journal-title":"Brief Bioinform"},{"key":"2024102220523093400_btae588-B28","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1038\/nmeth.2289","article-title":"Interactome3d: adding structural details to protein networks","volume":"10","author":"Mosca","year":"2013","journal-title":"Nat Methods"},{"key":"2024102220523093400_btae588-B29","first-page":"0240","article-title":"A transformer-based ensemble framework for the prediction of protein\u2013protein interaction sites","volume":"6","author":"Mou","year":"2023","journal-title":"Research (Wash D C)"},{"key":"2024102220523093400_btae588-B30","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1002\/wsbm.121","article-title":"Protein\u2013protein interaction networks and subnetworks in the biology of disease","volume":"3","author":"Nibbe","year":"2011","journal-title":"Wiley Interdiscip Rev Syst Biol Med"},{"key":"2024102220523093400_btae588-B31","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1093\/bioinformatics\/btx585","article-title":"Intpred: a structure-based predictor of protein\u2013protein interaction sites","volume":"34","author":"Northey","year":"2018","journal-title":"Bioinformatics"},{"key":"2024102220523093400_btae588-B32","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1093\/bioinformatics\/btu097","article-title":"Zdock server: interactive docking prediction of protein\u2013protein complexes and symmetric multimers","volume":"30","author":"Pierce","year":"2014","journal-title":"Bioinformatics"},{"key":"2024102220523093400_btae588-B33","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1002\/prot.21248","article-title":"Prediction-based fingerprints of protein\u2013protein interactions","volume":"66","author":"Porollo","year":"2007","journal-title":"Proteins"},{"key":"2024102220523093400_btae588-B34","doi-asserted-by":"crossref","first-page":"4476","DOI":"10.1038\/s41467-024-48801-4","article-title":"A variational expectation-maximization framework for balanced multi-scale learning of protein and drug interactions","volume":"15","author":"Rao","year":"2024","journal-title":"Nat Commun"},{"key":"2024102220523093400_btae588-B35","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1039\/D2CB00207H","article-title":"Protein\u2013protein interfaces in molecular glue-induced ternary complexes: Classification, characterization, and prediction","volume":"4","author":"Rui","year":"2023","journal-title":"RSC Chem Biol"},{"key":"2024102220523093400_btae588-B36","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1093\/bioinformatics\/bty647","article-title":"Bipspi: a method for the prediction of partner-specific protein\u2013protein interfaces","volume":"35","author":"Sanchez-Garcia","year":"2019","journal-title":"Bioinformatics"},{"key":"2024102220523093400_btae588-B37","doi-asserted-by":"crossref","first-page":"167556","DOI":"10.1016\/j.jmb.2022.167556","article-title":"Bipspi+: mining type-specific datasets of protein complexes to improve protein binding site prediction","volume":"434","author":"Sanchez-Garcia","year":"2022","journal-title":"J Mol Biol"},{"key":"2024102220523093400_btae588-B38","first-page":"9323","author":"Satorras","year":"2021"},{"key":"2024102220523093400_btae588-B39","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2008","journal-title":"IEEE Trans Neural Netw"},{"key":"2024102220523093400_btae588-B40","doi-asserted-by":"crossref","first-page":"13890","DOI":"10.1038\/ncomms13890","article-title":"Quantum-chemical insights from deep tensor neural networks","volume":"8","author":"Sch\u00fctt","year":"2017","journal-title":"Nat Commun"},{"key":"2024102220523093400_btae588-B41","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1016\/j.bpj.2015.11.3519","article-title":"3diana: 3d domain interaction analysis: a toolbox for quaternary structure modeling","volume":"110","author":"Segura","year":"2016","journal-title":"Biophys J"},{"key":"2024102220523093400_btae588-B42","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1093\/nar\/29.1.228","article-title":"A database and tools for 3-D protein structure comparison and alignment using the combinatorial extension (CE) algorithm","volume":"29","author":"Shindyalov","year":"2001","journal-title":"Nucleic Acids Res"},{"key":"2024102220523093400_btae588-B43","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1007\/s10930-023-10121-9","article-title":"Deepbindppi: protein\u2013protein binding site prediction using attention based graph convolutional network","volume":"42","author":"Sunny","year":"2023","journal-title":"Protein J"},{"key":"2024102220523093400_btae588-B44","first-page":"15642","article-title":"End-to-end learning on 3d protein structure for interface prediction","volume":"32","author":"Townshend","year":"2019","journal-title":"Adv Neur Inf Process Syst"},{"key":"2024102220523093400_btae588-B45","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neur Inf Process Syst"},{"key":"2024102220523093400_btae588-B46","doi-asserted-by":"publisher","author":"Velickovic","year":"2018","DOI":"10.48550\/arXiv.1710.10903"},{"key":"2024102220523093400_btae588-B47","doi-asserted-by":"publisher","author":"Vig","year":"2021","DOI":"10.48550\/arXiv.2006.15222"},{"key":"2024102220523093400_btae588-B48","doi-asserted-by":"crossref","first-page":"3031","DOI":"10.1016\/j.jmb.2015.07.016","article-title":"Updates to the integrated protein\u2013protein interaction benchmarks: docking benchmark version 5 and affinity benchmark version 2","volume":"427","author":"Vreven","year":"2015","journal-title":"J Mol Biol"},{"key":"2024102220523093400_btae588-B49","doi-asserted-by":"crossref","first-page":"2395","DOI":"10.1093\/bioinformatics\/bty995","article-title":"Protein\u2013protein interaction sites prediction by ensemble random forests with synthetic minority oversampling technique","volume":"35","author":"Wang","year":"2019","journal-title":"Bioinformatics"},{"key":"2024102220523093400_btae588-B50","doi-asserted-by":"publisher","author":"Wu","year":"2023","DOI":"10.1101\/2023.01.05.522958"},{"key":"2024102220523093400_btae588-B51","doi-asserted-by":"crossref","first-page":"1829","DOI":"10.1038\/s41596-020-0312-x","article-title":"The hdock server for integrated protein\u2013protein docking","volume":"15","author":"Yan","year":"2020","journal-title":"Nat Protoc"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae588\/59554870\/btae588.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/10\/btae588\/59972763\/btae588.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/10\/btae588\/59972763\/btae588.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T16:52:51Z","timestamp":1729615971000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae588\/7808856"}},"subtitle":[],"editor":[{"given":"Arne","family":"Elofsson","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"references-count":51,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2024,10,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae588","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.12.25.572648","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,10]]},"published":{"date-parts":[[2024,10,1]]},"article-number":"btae588"}}