{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T07:22:09Z","timestamp":1780471329440,"version":"3.54.1"},"reference-count":37,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,2,8]],"date-time":"2025-02-08T00:00:00Z","timestamp":1738972800000},"content-version":"vor","delay-in-days":7,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,2,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Identifying antibody binding sites, is crucial for developing vaccines and therapeutic antibodies, processes that are time-consuming and costly. Accurate prediction of the paratope\u2019s binding site can speed up the development by improving our understanding of antibody\u2013antigen interactions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We present ParaSurf, a deep learning model that significantly enhances paratope prediction by incorporating both surface geometric and non-geometric factors. Trained and tested on three prominent antibody\u2013antigen benchmarks, ParaSurf achieves state-of-the-art results across nearly all metrics. Unlike models restricted to the variable region, ParaSurf demonstrates the ability to accurately predict binding scores across the entire Fab region of the antibody. Additionally, we conducted an extensive analysis using the largest of the three datasets employed, focusing on three key components: (i) a detailed evaluation of paratope prediction for each complementarity-determining region loop, (ii) the performance of models trained exclusively on the heavy chain, and (iii) the results of training models solely on the light chain without incorporating data from the heavy chain.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Source code for ParaSurf, along with the datasets used, preprocessing pipeline, and trained model weights, are freely available at https:\/\/github.com\/aggelos-michael-papadopoulos\/ParaSurf.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf062","type":"journal-article","created":{"date-parts":[[2025,2,8]],"date-time":"2025-02-08T13:56:06Z","timestamp":1739022966000},"source":"Crossref","is-referenced-by-count":10,"title":["ParaSurf: a surface-based deep learning approach for paratope\u2013antigen interaction prediction"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8117-312X","authenticated-orcid":false,"given":"Angelos-Michael","family":"Papadopoulos","sequence":"first","affiliation":[{"name":"Information Technologies Institute, Centre for Research and Technology Hellas , Thessaloniki 57001,","place":["Greece"]},{"name":"Universidad Polit\u00e9cnica de Madrid , Madrid 28040,","place":["Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Apostolos","family":"Axenopoulos","sequence":"additional","affiliation":[{"name":"Information Technologies Institute, Centre for Research and Technology Hellas , Thessaloniki 57001,","place":["Greece"]},{"name":"Aristotle University of Thessaloniki , Thessaloniki 54124,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8995-4454","authenticated-orcid":false,"given":"Anastasia","family":"Iatrou","sequence":"additional","affiliation":[{"name":"Institute of Applied Biosciences, Centre for Research and Technology Hellas , Thessaloniki 57001,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kostas","family":"Stamatopoulos","sequence":"additional","affiliation":[{"name":"Institute of Applied Biosciences, Centre for Research and Technology Hellas , Thessaloniki 57001,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Alvarez","sequence":"additional","affiliation":[{"name":"Universidad Polit\u00e9cnica de Madrid , Madrid 28040,","place":["Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3814-6710","authenticated-orcid":false,"given":"Petros","family":"Daras","sequence":"additional","affiliation":[{"name":"Information Technologies Institute, Centre for Research and Technology Hellas , Thessaloniki 57001,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,2,8]]},"reference":[{"key":"2025030422250094200_btaf062-B1","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with alphafold 3","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"},{"key":"2025030422250094200_btaf062-B2","doi-asserted-by":"crossref","first-page":"btac732","DOI":"10.1093\/bioinformatics\/btac732","article-title":"Paragraph\u2014antibody paratope prediction using graph neural networks with minimal feature vectors","volume":"39","author":"Chinery","year":"2023","journal-title":"Bioinformatics"},{"key":"2025030422250094200_btaf062-B3","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/bs.mie.2022.11.003","article-title":"Multi-state modeling of antibody-antigen complexes with saxs profiles and deep-learning models","volume":"678","author":"Cohen","year":"2023","journal-title":"Methods Enzymol"},{"key":"2025030422250094200_btaf062-B4","doi-asserted-by":"crossref","first-page":"1870","DOI":"10.1093\/bioinformatics\/bty918","article-title":"Antibody interface prediction with 3D zernike descriptors and SVM","volume":"35","author":"Daberdaku","year":"2019","journal-title":"Bioinformatics"},{"key":"2025030422250094200_btaf062-B5","doi-asserted-by":"crossref","first-page":"536","DOI":"10.1089\/cmb.2018.0175","article-title":"Attentive cross-modal paratope prediction","volume":"26","author":"Deac","year":"2019","journal-title":"J Comput Biol"},{"key":"2025030422250094200_btaf062-B6","doi-asserted-by":"crossref","first-page":"W665","DOI":"10.1093\/nar\/gkh381","article-title":"Pdb2pqr: an automated pipeline for the setup of poisson\u2013boltzmann electrostatics calculations","volume":"32","author":"Dolinsky","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2025030422250094200_btaf062-B7","doi-asserted-by":"crossref","first-page":"e8187","DOI":"10.1371\/journal.pone.0008187","article-title":"Antibody complementarity-determining regions (CDRS): a bridge between adaptive and innate immunity","volume":"4","author":"Gabrielli","year":"2009","journal-title":"PLoS One"},{"key":"2025030422250094200_btaf062-B8","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":"2020","journal-title":"Nat Methods"},{"key":"2025030422250094200_btaf062-B9","first-page":"770","author":"He","year":"2016"},{"key":"2025030422250094200_btaf062-B10","author":"H\u00f8ie","year":"2023"},{"key":"2025030422250094200_btaf062-B11","volume-title":"Immunobiology: the Immune System in Health and Disease","author":"Janeway","year":"2001","edition":"5th edn."},{"key":"2025030422250094200_btaf062-B12","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with alphafold","volume":"596","author":"Jumper","year":"2021","journal-title":"nature"},{"key":"2025030422250094200_btaf062-B13","doi-asserted-by":"crossref","first-page":"btae576","DOI":"10.1093\/bioinformatics\/btae576","article-title":"Abodybuilder3: improved and scalable antibody structure predictions","volume":"40","author":"Kenlay","year":"2024","journal-title":"Bioinformatics"},{"key":"2025030422250094200_btaf062-B14","doi-asserted-by":"crossref","first-page":"2175","DOI":"10.1038\/s41467-023-37701-8","article-title":"Pesto: parameter-free geometric deep learning for accurate prediction of protein binding interfaces","volume":"14","author":"Krapp","year":"2023","journal-title":"Nat Commun"},{"key":"2025030422250094200_btaf062-B15","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1093\/protein\/gzt043","article-title":"Antibody i-patch prediction of the antibody binding site improves rigid local antibody\u2013antigen docking","volume":"26","author":"Krawczyk","year":"2013","journal-title":"Protein Eng Des Sel"},{"key":"2025030422250094200_btaf062-B16","doi-asserted-by":"crossref","first-page":"D1006","DOI":"10.1093\/nar\/gkn838","article-title":"Jero\u02c6me lane, et al. Imgt\u00ae, the international immunogenetics information system\u00ae","volume":"37","author":"Lefranc","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2025030422250094200_btaf062-B17","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","article-title":"Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences","volume":"22","author":"Li","year":"2006","journal-title":"Bioinformatics"},{"key":"2025030422250094200_btaf062-B18","doi-asserted-by":"crossref","first-page":"2944","DOI":"10.1093\/bioinformatics\/bty305","article-title":"Parapred: antibody paratope prediction using convolutional and recurrent neural networks","volume":"34","author":"Liberis","year":"2018","journal-title":"Bioinformatics"},{"key":"2025030422250094200_btaf062-B19","doi-asserted-by":"crossref","first-page":"1681","DOI":"10.1093\/bioinformatics\/btab009","article-title":"Deepsurf: a surface-based deep learning approach for the prediction of ligand binding sites on proteins","volume":"37","author":"Mylonas","year":"2021","journal-title":"Bioinformatics"},{"key":"2025030422250094200_btaf062-B20","doi-asserted-by":"crossref","first-page":"3930","DOI":"10.1182\/blood-2023-188537","article-title":"Deepsurf2. 0: a deep learning approach for predicting interactions of b cell receptors with antigens","volume":"142","author":"Papadopoulos","year":"2023","journal-title":"Blood"},{"key":"2025030422250094200_btaf062-B21","doi-asserted-by":"crossref","first-page":"2228","DOI":"10.1182\/blood-2024-204732","article-title":"Deepsurf2-ff: introducing force fields in deep learning for improving in-silico prediction of bcr-antigen interactions in b cell lymphomas","volume":"144","author":"Papadopoulos","year":"2024","journal-title":"Blood"},{"key":"2025030422250094200_btaf062-B22","doi-asserted-by":"crossref","first-page":"3996","DOI":"10.1093\/bioinformatics\/btaa263","article-title":"Learning context-aware structural representations to predict antigen and antibody binding interfaces","volume":"36","author":"Pittala","year":"2020","journal-title":"Bioinformatics"},{"key":"2025030422250094200_btaf062-B23","doi-asserted-by":"crossref","first-page":"241","DOI":"10.3184\/003685017X14993478654307","article-title":"Magnetic resonance spectroscopy","volume":"100","author":"Rhodes","year":"2017","journal-title":"Sci Prog"},{"key":"2025030422250094200_btaf062-B24","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":"2025030422250094200_btaf062-B25","doi-asserted-by":"crossref","first-page":"D1368","DOI":"10.1093\/nar\/gkab1050","article-title":"Sabdab in the age of biotherapeutics: updates including sabdab-nano, the nanobody structure tracker","volume":"50","author":"Schneider","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2025030422250094200_btaf062-B26","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1136\/mp.53.1.8","article-title":"x ray crystallography","volume":"53","author":"Smyth","year":"2000","journal-title":"Mol Pathol"},{"key":"2025030422250094200_btaf062-B27","doi-asserted-by":"crossref","first-page":"3666","DOI":"10.1093\/bioinformatics\/bty374","article-title":"Development and evaluation of a deep learning model for protein\u2013ligand binding affinity prediction","volume":"34","author":"Stepniewska-Dziubinska","year":"2018","journal-title":"Bioinformatics"},{"key":"2025030422250094200_btaf062-B28","article-title":"End-to-end learning on 3d protein structure for interface prediction","volume":"32","author":"Townshend","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025030422250094200_btaf062-B29","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1002\/pro.2874","article-title":"The diversity of h 3 loops determines the antigen-binding tendencies of antibody CDR loops","volume":"25","author":"Tsuchiya","year":"2016","journal-title":"Protein Sci"},{"key":"2025030422250094200_btaf062-B30","author":"UCSF","year":"2024"},{"key":"2025030422250094200_btaf062-B31","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1042\/BST20210485","article-title":"Exploring cryo-electron microscopy with molecular dynamics","volume":"50","author":"Vant","year":"2022","journal-title":"Biochem Soc Trans"},{"key":"2025030422250094200_btaf062-B32","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025030422250094200_btaf062-B33","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":"2025030422250094200_btaf062-B34","author":"Wang"},{"key":"2025030422250094200_btaf062-B35","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1002\/jcc.540020311","article-title":"Amber: assisted model building with energy refinement. a general program for modeling molecules and their interactions","volume":"2","author":"Weiner","year":"1981","journal-title":"J Comput Chem"},{"key":"2025030422250094200_btaf062-B36","doi-asserted-by":"crossref","first-page":"btac797","DOI":"10.1093\/bioinformatics\/btac797","article-title":"Docknet: high-throughput protein\u2013protein interface contact prediction","volume":"39","author":"Williams","year":"2023","journal-title":"Bioinformatics"},{"key":"2025030422250094200_btaf062-B37","doi-asserted-by":"crossref","first-page":"btad724","DOI":"10.1093\/bioinformatics\/btad724","article-title":"Proteinmae: masked autoencoder for protein surface self-supervised learning","volume":"39","author":"Yuan","year":"2023","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf062\/61813119\/btaf062.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/2\/btaf062\/61813119\/btaf062.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/2\/btaf062\/61813119\/btaf062.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T17:25:26Z","timestamp":1741109126000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf062\/8005857"}},"subtitle":[],"editor":[{"given":"Arne","family":"Elofsson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf062","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.12.16.628621","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,2]]},"published":{"date-parts":[[2025,2]]},"article-number":"btaf062"}}