{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T07:57:11Z","timestamp":1790495831312,"version":"4.1.0"},"reference-count":26,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T00:00:00Z","timestamp":1788998400000},"content-version":"vor","delay-in-days":10,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12571532"],"award-info":[{"award-number":["12571532"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12426303"],"award-info":[{"award-number":["12426303"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin","doi-asserted-by":"publisher","award":["24JCYBJC01570"],"award-info":[{"award-number":["24JCYBJC01570"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Accurate prediction of antibody-antigen binding affinity is essential for therapeutic antibody design. Existing methods often model the dissociation constant (KD) and Gibbs free energy (\u0394G) independently, overlooking their thermodynamic relationship and complex paratope-epitope spatial interactions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We introduce Phys-AbGAT, a physics-informed multi-task graph attention network that represents the antibody-antigen interface as a spatial graph. It integrates ESM2 evolutionary embeddings with radial basis functions and employs a thermodynamically motivated auxiliary loss to encourage coupling between log10\u2061(KD) and \u0394G. On an independent 42-complex benchmark, Phys-AbGAT achieved Pearson correlation coefficients of 0.569 for log10\u2061(KD) and 0.573 for \u0394G. In matched-set comparisons, Phys-AbGAT achieved numerically lower RMSE and higher PCC than four baseline methods. The differences remained significant after Holm correction for MVSF-AB and PPA-Pred2, but not for AREA-AFFINITY or CSM-AB. Higher attention scores were assigned to several aromatic paratope residues, providing model-level hypotheses for structural inspection. These results support Phys-AbGAT as an interpretable multi-task geometric framework for joint prediction of two affinity-related quantities.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Code and data are available at https:\/\/github.com\/cliffgao\/Phys-AbGAT.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag669","type":"journal-article","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:51:29Z","timestamp":1789041089000},"source":"Crossref","is-referenced-by-count":0,"title":["Phys-AbGAT: a physics-informed multi-task graph attention network for robust antibody-antigen binding affinity prediction"],"prefix":"10.1093","volume":"42","author":[{"given":"Yifei","family":"Yang","sequence":"first","affiliation":[{"name":"School of Software, Nanchang University , Nanchang, Jiangxi 330047,","place":["China"]},{"name":"Jiangxi Provincial Key Laboratory of Data Security Technology , Nanchang, Jiangxi 330031,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linnan","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, AAIS and LPMC, Nankai University , Tianjin 300071,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junbiao","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, AAIS and LPMC, Nankai University , Tianjin 300071,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyan","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Microbiology, Tianjin Centers for Disease Control and Prevention , Tianjin 300011,","place":["China"]},{"name":"Tianjin Key Laboratory of Pathogenic Microbiology of Infectious Disease , Tianjin 300011,","place":["China"]},{"name":"Key Laboratory of Prevention and Control of Major Diseases in the Population, Ministry of Education, Tianjin Medical University , Tianjin 300020,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2984-9003","authenticated-orcid":false,"given":"Wei","family":"Zheng","sequence":"additional","affiliation":[{"name":"NITFID, School of Statistics and Data Science, AAIS, LPMC and KLMDASR, Nankai University , Tianjin 300071,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9943-4786","authenticated-orcid":false,"given":"Jianzhao","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, AAIS and LPMC, Nankai University , Tianjin 300071,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"2026092703014244500_btag669-B1","author":"Akiba","year":"2019"},{"key":"2026092703014244500_btag669-B2","doi-asserted-by":"publisher","first-page":"108257","DOI":"10.1016\/j.jsb.2025.108257","article-title":"Deep geometric framework to predict antibody\u2013antigen binding affinity","volume":"217","author":"Bandara","year":"2025","journal-title":"J Struct Biol"},{"key":"2026092703014244500_btag669-B3","doi-asserted-by":"publisher","first-page":"2102","DOI":"10.1093\/bioinformatics\/btac020","article-title":"ProteinBERT: a universal deep-learning model of protein sequence and function","volume":"38","author":"Brandes","year":"2022","journal-title":"Bioinformatics"},{"key":"2026092703014244500_btag669-B4","author":"Brody","year":"2022"},{"key":"2026092703014244500_btag669-B5","doi-asserted-by":"publisher","first-page":"D1140","DOI":"10.1093\/nar\/gkt1043","article-title":"SAbDab: the structural antibody database","volume":"42","author":"Dunbar","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2026092703014244500_btag669-B6","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","volume":"44","author":"Elnaggar","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2026092703014244500_btag669-B7","doi-asserted-by":"publisher","first-page":"3768","DOI":"10.1093\/bioinformatics\/btw549","article-title":"Predicting the errors of predicted local backbone angles and non-local solvent- accessibilities of proteins by deep neural networks","volume":"32","author":"Gao","year":"2016","journal-title":"Bioinformatics"},{"key":"2026092703014244500_btag669-B8","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1093\/bioinformatics\/btab616","article-title":"Precise estimation of residue relative solvent accessible area from C\u03b1 atom distance matrix using a deep learning method","volume":"38","author":"Gao","year":"2021","journal-title":"Bioinformatics"},{"key":"2026092703014244500_btag669-B9","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1016\/j.str.2021.01.005","article-title":"An expanded benchmark for antibody-antigen docking and affinity prediction reveals insights into antibody recognition determinants","volume":"29","author":"Guest","year":"2021","journal-title":"Structure"},{"key":"2026092703014244500_btag669-B10","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1093\/bioinformatics\/btw006","article-title":"MMseqs software suite for fast and deep clustering and searching of large protein sequence sets","volume":"32","author":"Hauser","year":"2016","journal-title":"Bioinformatics"},{"key":"2026092703014244500_btag669-B11","doi-asserted-by":"publisher","first-page":"3365","DOI":"10.1038\/s41401-025-01608-5","article-title":"SAAINT-DB: a comprehensive structural antibody database for antibody modeling and design","volume":"46","author":"Huang","year":"2025","journal-title":"Acta Pharmacol Sin"},{"key":"2026092703014244500_btag669-B12","doi-asserted-by":"publisher","first-page":"e1013576","DOI":"10.1371\/journal.pcbi.1013576","article-title":"Enhancing antibody-antigen interaction prediction with atomic flexibility","volume":"21","author":"Joubbi","year":"2025","journal-title":"PLoS Comput Biol"},{"key":"2026092703014244500_btag669-B13","doi-asserted-by":"publisher","first-page":"btae579","DOI":"10.1093\/bioinformatics\/btae579","article-title":"MVSF-AB: accurate antibody-antigen binding affinity prediction via multi-view sequence feature learning","volume":"41","author":"Li","year":"2025","journal-title":"Bioinformatics"},{"key":"2026092703014244500_btag669-B14","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"2026092703014244500_btag669-B15","first-page":"11976","author":"Liu","year":"2022"},{"key":"2026092703014244500_btag669-B16","doi-asserted-by":"publisher","first-page":"2422","DOI":"10.1016\/j.str.2024.10.001","article-title":"ANTIPASTI: interpretable prediction of antibody binding affinity exploiting normal modes and deep learning","volume":"32","author":"Michalewicz","year":"2024","journal-title":"Structure"},{"key":"2026092703014244500_btag669-B17","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1093\/bioinformatics\/btab762","article-title":"CSM-AB: graph-based antibody\u2013antigen binding affinity prediction and docking scoring function","volume":"38","author":"Myung","year":"2022","journal-title":"Bioinformatics"},{"key":"2026092703014244500_btag669-B18","first-page":"809","author":"Nikam","year":"2018"},{"key":"2026092703014244500_btag669-B19","doi-asserted-by":"publisher","first-page":"vbac046","DOI":"10.1093\/bioadv\/vbac046","article-title":"AbLang: an antibody language model for completing antibody sequences","volume":"2","author":"Olsen","year":"2022","journal-title":"Bioinform Adv"},{"key":"2026092703014244500_btag669-B20","first-page":"9689","article-title":"Evaluating protein transfer learning with TAPE","volume":"32","author":"Rao","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026092703014244500_btag669-B21","doi-asserted-by":"publisher","first-page":"3230","DOI":"10.1021\/acs.jcim.2c01499","article-title":"AREA-AFFINITY: a web server for machine learning-Based prediction of protein-protein and antibody-protein antigen binding affinities","volume":"63","author":"Yang","year":"2023","journal-title":"J Chem Inf Model"},{"key":"2026092703014244500_btag669-B22","doi-asserted-by":"publisher","first-page":"108364","DOI":"10.1016\/j.jmgm.2022.108364","article-title":"Binding affinity prediction for antibody\u2013protein antigen complexes: a machine learning analysis based on interface and surface areas","volume":"118","author":"Yang","year":"2023","journal-title":"J Mol Graph Model"},{"key":"2026092703014244500_btag669-B23","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1186\/s12859-023-05562-z","article-title":"Dg-Affinity: predicting antigen\u2013antibody affinity with language models from sequences","volume":"24","author":"Yuan","year":"2023","journal-title":"BMC Bioinformatics"},{"key":"2026092703014244500_btag669-B24","doi-asserted-by":"publisher","first-page":"btad187","DOI":"10.1093\/bioinformatics\/btad187","article-title":"Identifying B-cell epitopes using AlphaFold2 predicted structures and pretrained language model","volume":"39","author":"Zeng","year":"2023","journal-title":"Bioinformatics"},{"key":"2026092703014244500_btag669-B25","doi-asserted-by":"publisher","first-page":"RP104934","DOI":"10.7554\/eLife.104934.3","article-title":"A comprehensive antigen-antibody complex database unlocking insights into interaction interface","volume":"14","author":"Zhou","year":"2025","journal-title":"Elife"},{"key":"2026092703014244500_btag669-B26","doi-asserted-by":"publisher","first-page":"8796","DOI":"10.1021\/acs.jcim.4c01850","article-title":"ProAffinity-GNN: a novel approach to structure-based protein-protein binding affinity prediction via a curated data set and graph neural networks","volume":"64","author":"Zhou","year":"2024","journal-title":"J Chem Inf Model"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag669\/71020973\/btag669.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/9\/btag669\/71020973\/btag669.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/9\/btag669\/71020973\/btag669.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T07:01:48Z","timestamp":1790492508000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag669\/8790036"}},"subtitle":[],"editor":[{"given":"Arne","family":"Elofsson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":26,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,8,31]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag669","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,8,31]]},"article-number":"btag669"}}