{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T04:10:51Z","timestamp":1780373451702,"version":"3.54.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1013576","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000}}],"reference-count":57,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Union \u2013 Next Generation EU","award":["ECS00000017"],"award-info":[{"award-number":["ECS00000017"]}]},{"DOI":"10.13039\/501100003196","name":"Ministero della Salute","doi-asserted-by":"publisher","award":["T4-AN-07"],"award-info":[{"award-number":["T4-AN-07"]}],"id":[{"id":"10.13039\/501100003196","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fondazione Toscana Life Sciences, Siena"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Antibodies are indispensable components of the immune system, known for their specific binding to antigens. Beyond their natural immunological functions, they are fundamental in developing vaccines and therapeutic interventions for infectious diseases. The complex architecture of antibodies, particularly their variable regions responsible for antigen recognition, presents significant challenges for computational modeling. Recent advancements in deep learning have markedly improved protein structure prediction; however, accurately modeling antibody-antigen (Ab-Ag) interactions remains challenging due to the inherent flexibility of antibodies and the dynamic nature of binding processes. In this study, we examine the use of predicted Local Distance Difference Test (pLDDT) scores as indicators of residue and side-chain flexibility to model Ab-Ag interactions through a fingerprint-based approach. We demonstrate the significance of flexibility in different antibody-specific tasks, enhancing the predictive accuracy of Ab-Ag interaction models by 4%, resulting in an AUC-ROC of 92%. In addition, we showcase state-of-the-art performance in paratope prediction. These results emphasize the importance of accounting for conformational flexibility in modeling antibody-antigen interactions and show that pLDDT can serve as a coarse proxy for these dynamic features. By optimizing antibody flexibility using pLDDT, they can be engineered to improve affinity or breadth for a specific target. This approach is particularly beneficial for addressing highly variable pathogens like HIV and SARS-CoV-2, as greater flexibility enhances tolerance to sequence variations in target antigens.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1013576","type":"journal-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T17:32:33Z","timestamp":1760376753000},"page":"e1013576","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing antibody-antigen interaction prediction with atomic flexibility"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1079-7204","authenticated-orcid":true,"given":"Sara","family":"Joubbi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5764-5238","authenticated-orcid":true,"given":"Alessio","family":"Micheli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Milazzo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giorgio","family":"Ciano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"St\u00e9phane M.","family":"Gagn\u00e9","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pietro","family":"Li\u00f2","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duccio","family":"Medini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2894-3583","authenticated-orcid":true,"given":"Giuseppe","family":"Maccari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"pcbi.1013576.ref001","volume-title":"Kuby immunology","author":"TJ Kindt","year":"2007"},{"issue":"1","key":"pcbi.1013576.ref002","doi-asserted-by":"crossref","first-page":"2153410","DOI":"10.1080\/19420862.2022.2153410","article-title":"Antibodies to watch in 2023","volume":"15","author":"H Kaplon","year":"2023","journal-title":"MAbs."},{"issue":"4","key":"pcbi.1013576.ref003","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbae307","article-title":"Antibody design using deep learning: From sequence and structure design to affinity maturation","volume":"25","author":"S Joubbi","year":"2024","journal-title":"Brief Bioinform."},{"issue":"4","key":"pcbi.1013576.ref004","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac267","article-title":"Machine-designed biotherapeutics: Opportunities, feasibility and advantages of deep learning in computational antibody discovery","volume":"23","author":"W Wilman","year":"2022","journal-title":"Brief Bioinform."},{"issue":"14","key":"pcbi.1013576.ref005","doi-asserted-by":"crossref","first-page":"3729","DOI":"10.3390\/cancers15143729","article-title":"Global impact of monoclonal antibodies (mAbs) in children: A focus on anti-GD2","volume":"15","author":"C Larrosa","year":"2023","journal-title":"Cancers."},{"issue":"7873","key":"pcbi.1013576.ref006","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":"J Jumper","year":"2021","journal-title":"Nature."},{"key":"pcbi.1013576.ref007","first-page":"1","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","author":"J Abramson","year":"2024","journal-title":"Nature."},{"issue":"2","key":"pcbi.1013576.ref008","doi-asserted-by":"crossref","first-page":"12","DOI":"10.3390\/antib9020012","article-title":"A review of deep learning methods for antibodies","volume":"9","author":"J Graves","year":"2020","journal-title":"Antibodies (Basel)."},{"issue":"2","key":"pcbi.1013576.ref009","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":"P Gainza","year":"2020","journal-title":"Nat Methods."},{"key":"pcbi.1013576.ref010","doi-asserted-by":"crossref","unstructured":"Sverrisson F, Feydy J, Correia BE, Bronstein MM. Fast end-to-end learning on protein surfaces. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition; 2021. p. 15272\u201381.","DOI":"10.1101\/2020.12.28.424589"},{"issue":"1","key":"pcbi.1013576.ref011","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":"LF Krapp","year":"2023","journal-title":"Nat Commun."},{"key":"pcbi.1013576.ref012","unstructured":"Del Vecchio A, Deac A, Li\u00f2 P, Veli\u010dkovi\u0107 P. Neural message passing for joint paratope-epitope prediction. arXiv preprint. 2021. https:\/\/doi.org\/arXiv:210600757"},{"issue":"13","key":"pcbi.1013576.ref013","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":"S Pittala","year":"2020","journal-title":"Bioinformatics."},{"issue":"4","key":"pcbi.1013576.ref014","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btad196","article-title":"Surface ID: A geometry-aware system for protein molecular surface comparison","volume":"39","author":"S Riahi","year":"2023","journal-title":"Bioinformatics."},{"issue":"7","key":"pcbi.1013576.ref015","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae405","article-title":"Geometric epitope and paratope prediction","volume":"40","author":"M Pegoraro","year":"2024","journal-title":"Bioinformatics."},{"key":"pcbi.1013576.ref016","doi-asserted-by":"crossref","first-page":"102757","DOI":"10.1016\/j.sbi.2023.102757","article-title":"Modelling the assembly and flexibility of antibody structures","volume":"84","author":"D Guo","year":"2024","journal-title":"Curr Opin Struct Biol."},{"key":"pcbi.1013576.ref017","doi-asserted-by":"crossref","first-page":"928534","DOI":"10.3389\/fmolb.2022.928534","article-title":"Deep learning approaches for conformational flexibility and switching properties in protein design","volume":"9","author":"LSP Rudden","year":"2022","journal-title":"Front Mol Biosci."},{"issue":"17","key":"pcbi.1013576.ref018","doi-asserted-by":"crossref","first-page":"4912","DOI":"10.1021\/jp4010967","article-title":"Conformational selection and induced fit in specific antibody and antigen recognition: SPE7 as a case study","volume":"117","author":"W Wang","year":"2013","journal-title":"J Phys Chem B."},{"issue":"19","key":"pcbi.1013576.ref019","doi-asserted-by":"crossref","first-page":"7250","DOI":"10.1021\/bi047387t","article-title":"Induced fit in HIV-neutralizing antibody complexes: Evidence for alternative conformations of the gp120 V3 loop and the molecular basis for broad neutralization","volume":"44","author":"O Rosen","year":"2005","journal-title":"Biochemistry."},{"key":"pcbi.1013576.ref020","first-page":"2025","article-title":"Precise, specific, and sensitive de novo antibody design across multiple cases","author":"Y Bang","year":"2025","journal-title":"bioRxiv."},{"issue":"3","key":"pcbi.1013576.ref021","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae122","article-title":"AbFlex: Designing antibody complementarity determining regions with flexible CDR definition","volume":"40","author":"W Jeon","year":"2024","journal-title":"Bioinformatics."},{"issue":"1","key":"pcbi.1013576.ref022","doi-asserted-by":"crossref","first-page":"9597","DOI":"10.1038\/s41598-017-10246-9","article-title":"Elucidation of potential sites for antibody engineering by fluctuation editing","volume":"7","author":"S Yanaka","year":"2017","journal-title":"Sci Rep."},{"key":"pcbi.1013576.ref023","first-page":"2024","article-title":"Optimizing a human monoclonal antibody for better neutralization of SARS-CoV-2","author":"Q Wang","year":"2024","journal-title":"bioRxiv."},{"key":"pcbi.1013576.ref024","doi-asserted-by":"crossref","first-page":"1223802","DOI":"10.3389\/fimmu.2023.1223802","article-title":"Specific attributes of the VL domain influence both the structure and structural variability of CDR-H3 through steric effects","volume":"14","author":"B Guloglu","year":"2023","journal-title":"Front Immunol."},{"issue":"1","key":"pcbi.1013576.ref025","doi-asserted-by":"crossref","first-page":"2322533","DOI":"10.1080\/19420862.2024.2322533","article-title":"Do antibody CDR loops change conformation upon binding?","volume":"16","author":"C Liu","year":"2024","journal-title":"MAbs."},{"issue":"6","key":"pcbi.1013576.ref026","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0258173","article-title":"Simultaneous prediction of antibody backbone and side-chain conformations with deep learning","volume":"17","author":"D Akpinaroglu","year":"2022","journal-title":"PLoS One."},{"key":"pcbi.1013576.ref027","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.3389\/fimmu.2018.02278","article-title":"Understanding the significance and implications of antibody numbering and antigen-binding surface\/residue definition","volume":"9","author":"M Dondelinger","year":"2018","journal-title":"Front Immunol."},{"issue":"1","key":"pcbi.1013576.ref028","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/0022-2836(91)90617-F","article-title":"Structure, function and properties of antibody binding sites","volume":"217","author":"IS Mian","year":"1991","journal-title":"J Mol Biol."},{"key":"pcbi.1013576.ref029","doi-asserted-by":"crossref","first-page":"945808","DOI":"10.3389\/fmolb.2022.945808","article-title":"Antibody-antigen binding interface analysis in the big data era","volume":"9","author":"PBPS Reis","year":"2022","journal-title":"Front Mol Biosci."},{"issue":"6","key":"pcbi.1013576.ref030","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1002\/prot.26471","article-title":"Predicting protein flexibility with AlphaFold","volume":"91","author":"P Ma","year":"2023","journal-title":"Proteins."},{"issue":"44","key":"pcbi.1013576.ref031","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2304302120","article-title":"Systematic identification of conditionally folded intrinsically disordered regions by AlphaFold2","volume":"120","author":"TR Alderson","year":"2023","journal-title":"Proc Natl Acad Sci U S A."},{"issue":"6","key":"pcbi.1013576.ref032","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1002\/prot.26652","article-title":"Random, de novo, and conserved proteins: How structure and disorder predictors perform differently","volume":"92","author":"L Middendorf","year":"2024","journal-title":"Proteins."},{"issue":"2","key":"pcbi.1013576.ref033","doi-asserted-by":"crossref","first-page":"168900","DOI":"10.1016\/j.jmb.2024.168900","article-title":"Gradations in protein dynamics captured by experimental NMR are not well represented by AlphaFold2 models and other computational metrics","volume":"437","author":"J Gavalda-Garcia","year":"2025","journal-title":"J Mol Biol."},{"issue":"11","key":"pcbi.1013576.ref034","doi-asserted-by":"crossref","first-page":"1560","DOI":"10.3390\/cryst13111560","article-title":"pLDDT values in AlphaFold2 protein models are unrelated to globular protein local flexibility","volume":"13","author":"O Carugo","year":"2023","journal-title":"Crystals."},{"key":"pcbi.1013576.ref035","first-page":"2025","article-title":"Predicting the conformational flexibility of antibody and T-cell receptor CDRs","author":"FC Spoendlin","year":"2025","journal-title":"bioRxiv."},{"key":"pcbi.1013576.ref036","doi-asserted-by":"crossref","first-page":"1120370","DOI":"10.3389\/fbinf.2023.1120370","article-title":"Before and after AlphaFold2: An overview of protein structure prediction","volume":"3","author":"LMF Bertoline","year":"2023","journal-title":"Front Bioinform."},{"issue":"6637","key":"pcbi.1013576.ref037","doi-asserted-by":"crossref","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":"Z Lin","year":"2023","journal-title":"Science."},{"key":"pcbi.1013576.ref038","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkt1043","article-title":"SAbDab: The structural antibody database","volume":"42","author":"J Dunbar","year":"2014","journal-title":"Nucleic Acids Res."},{"issue":"1","key":"pcbi.1013576.ref039","doi-asserted-by":"crossref","first-page":"2276","DOI":"10.1038\/s41467-017-02258-w","article-title":"Protein conformational flexibility modulates kinetics and thermodynamics of drug binding","volume":"8","author":"M Amaral","year":"2017","journal-title":"Nat Commun."},{"issue":"1","key":"pcbi.1013576.ref040","doi-asserted-by":"crossref","first-page":"13696","DOI":"10.1038\/s41598-020-70680-0","article-title":"Antibody-protein binding and conformational changes: Identifying allosteric signalling pathways to engineer a better effector response","volume":"10","author":"MM Al Qaraghuli","year":"2020","journal-title":"Sci Rep."},{"issue":"3","key":"pcbi.1013576.ref041","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3507905","article-title":"DiffusionNet: Discretization agnostic learning on surfaces","volume":"41","author":"N Sharp","year":"2022","journal-title":"ACM Trans Graph."},{"issue":"17","key":"pcbi.1013576.ref042","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":"B Dai","year":"2021","journal-title":"Bioinformatics."},{"key":"pcbi.1013576.ref043","first-page":"2024","article-title":"Chai-1: Decoding the molecular interactions of life","author":"C Discovery","year":"2024","journal-title":"bioRxiv."},{"key":"pcbi.1013576.ref044","article-title":"Boltz-1 democratizing biomolecular interaction modeling","author":"J Wohlwend","year":"2025","journal-title":"bioRxiv."},{"key":"pcbi.1013576.ref045","first-page":"2021","article-title":"Protein complex prediction with AlphaFold-Multimer","author":"R Evans","year":"2021","journal-title":"biorxiv."},{"key":"pcbi.1013576.ref046","first-page":"2024","article-title":"What does AlphaFold3 learn about antigen and nanobody docking, and what remains unsolved?","author":"FN Hitawala","year":"2024","journal-title":"bioRxiv."},{"issue":"1","key":"pcbi.1013576.ref047","doi-asserted-by":"crossref","DOI":"10.1093\/bioadv\/vbaf056","article-title":"Challenges in predicting PROTAC-mediated protein-protein interfaces with AlphaFold reveal a general limitation on small interfaces","volume":"5","author":"GP Pereira","year":"2025","journal-title":"Bioinform Adv."},{"key":"pcbi.1013576.ref048","doi-asserted-by":"crossref","unstructured":"Passaro S, Corso G, Wohlwend J, Reveiz M, Thaler S, Ram SomnathV, et al. Boltz-2: Towards accurate and efficient binding affinity prediction. BioRxiv; 2025. p. 2025\u201306.","DOI":"10.1101\/2025.06.14.659707"},{"key":"pcbi.1013576.ref049","first-page":"2022","article-title":"A penultimate classification of canonical antibody CDR conformations","author":"S Kelow","year":"2022","journal-title":"bioRxiv."},{"key":"pcbi.1013576.ref050","doi-asserted-by":"crossref","unstructured":"Ge L, Cui X, Zhao K, Zhou X, Zhang Y, Zhang G. AlphaFlex: Accuracy modeling of protein multiple conformations via predicted flexible residues. Cold Spring Harbor Laboratory; 2025. https:\/\/doi.org\/10.1101\/2025.07.11.664327","DOI":"10.1101\/2025.07.11.664327"},{"key":"pcbi.1013576.ref051","doi-asserted-by":"crossref","unstructured":"Joubbi S, Maccari G, Ciano G, Micheli A, Milazzo P, Medini D. Improving antibody-antigen interaction prediction through flexibility with ESMFold. In: Proceedings of the 18th international joint conference on biomedical engineering systems and technologies; 2025. p. 603\u201310. http:\/\/dx.doi.org\/10.5220\/0013189500003911","DOI":"10.5220\/0013189500003911"},{"issue":"4","key":"pcbi.1013576.ref052","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1002\/prot.20264","article-title":"Scoring function for automated assessment of protein structure template quality","volume":"57","author":"Y Zhang","year":"2004","journal-title":"Proteins."},{"issue":"16","key":"pcbi.1013576.ref053","doi-asserted-by":"crossref","first-page":"2288","DOI":"10.1093\/bioinformatics\/btu190","article-title":"Improving B-cell epitope prediction and its application to global antibody-antigen docking","volume":"30","author":"K Krawczyk","year":"2014","journal-title":"Bioinformatics."},{"issue":"19","key":"pcbi.1013576.ref054","doi-asserted-by":"crossref","first-page":"3031","DOI":"10.1016\/j.jmb.2015.07.016","article-title":"Updates to the integrated protein-protein interaction benchmarks: Docking benchmark version 5 and affinity benchmark version 2","volume":"427","author":"T Vreven","year":"2015","journal-title":"J Mol Biol."},{"issue":"15","key":"pcbi.1013576.ref055","doi-asserted-by":"crossref","first-page":"7065","DOI":"10.1021\/acs.chemrev.9b00785","article-title":"Relativistic heavy-neighbor-atom effects on NMR shifts: Concepts and trends across the periodic table","volume":"120","author":"J V\u0131 Cha","year":"2020","journal-title":"Chem Rev."},{"key":"pcbi.1013576.ref056","doi-asserted-by":"crossref","first-page":"413","DOI":"10.3389\/fimmu.2018.00413","article-title":"Repertoire analysis of antibody CDR-H3 loops suggests affinity maturation does not typically result in rigidification","volume":"9","author":"JR Jeliazkov","year":"2018","journal-title":"Front Immunol."},{"key":"pcbi.1013576.ref057","unstructured":"Kouba P, Planas-\/Iglesias J, Damborsky J, Sedlar J, Mazurenko S, Sivic J. Learning to engineer protein flexibility. arXiv preprint. 2024. https:\/\/doi.org\/10.48550\/arXiv.2412.18275"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1013576","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T17:52:21Z","timestamp":1760637141000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013576"}},"subtitle":[],"editor":[{"given":"Nir","family":"Ben-Tal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":57,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1013576","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1013576","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]}}}