{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T08:23:29Z","timestamp":1787905409629,"version":"build-2784847793"},"reference-count":54,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T00:00:00Z","timestamp":1748217600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of Henan","award":["242300421410"],"award-info":[{"award-number":["242300421410"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biomolecules"],"abstract":"<jats:p>Antibody lead discovery, crucial for immunotherapy development, requires identifying candidates with potent binding affinities to target antigens. Recent advances in protein language models have opened promising avenues to tackle this challenge by predicting antibody\u2013antigen interactions (AAIs). Despite their appeals, precisely detecting binding sites (i.e., paratopes and epitopes) within the complex landscape of long-sequence biomolecules remains challenging. Herein, we propose MambaAAI, a bio-inspired model built upon the Mamba architecture, designed to predict AAIs and identify binding sites through selective attention mechanisms. Technically, we employ ESM-2, a pre-trained protein language model to extract evolutionarily enriched representations from input antigen and antibody sequences, which are modeled as residue-level interaction matrixes. Subsequently, a dual-view Mamba encoder is devised to capture important binding patterns, by dynamically learning embeddings of interaction matrixes from both antibody and antigen perspectives. Finally, the learned embeddings are decoded using a multilayer perceptron to output interaction probabilities. MambaAAI provides a unique advantage, relative to prior techniques, in dynamically selecting bio-enhancing residue sites that contribute to AAI prediction. We evaluate MambaAAI on two large-scale antibody\u2013antigen neutralization datasets, and in silico results demonstrate that our method marginally outperforms the state-of-the-art baselines in terms of prediction accuracy, while maintaining robust generalization to unseen antibodies and antigens. In further analysis of the selective attention mechanism, we found that MambaAAI successfully uncovers critical epitope and paratope regions in the SARS-CoV-2 antibody examples. It is believed that MambaAAI holds great potential to discover lead candidates targeting specific antigens at a lower burden.<\/jats:p>","DOI":"10.3390\/biom15060764","type":"journal-article","created":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T03:30:19Z","timestamp":1748489419000},"page":"764","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Bio-Inspired Mamba for Antibody\u2013Antigen Interaction Prediction"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8684-9950","authenticated-orcid":false,"given":"Xuan","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer and Information Technology, Xinyang Normal University, Xinyang 464000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9673-6845","authenticated-orcid":false,"given":"Haitao","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Hubei University, Wuhan 430062, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqing","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Management, Xinyang Agriculture and Forestry University, Xinyang 464000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7155-7760","authenticated-orcid":false,"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer and Information Technology, Xinyang Normal University, Xinyang 464000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,5,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1146\/annurev-bioeng-071114-040733","article-title":"Advances in antibody design","volume":"17","author":"Tiller","year":"2015","journal-title":"Annu. Rev. Biomed. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1885","DOI":"10.1002\/jps.24430","article-title":"Developability assessment during the selection of novel therapeutic antibodies","volume":"104","author":"Jarasch","year":"2015","journal-title":"J. Pharm. Sci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2153410","DOI":"10.1080\/19420862.2022.2153410","article-title":"Antibodies to watch in 2023","volume":"15","author":"Kaplon","year":"2023","journal-title":"mAbs"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1111\/imm.12284","article-title":"Current approaches to fine mapping of antigen\u2013antibody interactions","volume":"142","author":"Abbott","year":"2014","journal-title":"Immunology"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Pucca, M.B., Cerni, F.A., Janke, R., Berm\u00fadez-M\u00e9ndez, E., Ledsgaard, L., Barbosa, J.E., and Laustsen, A.H. (2019). History of envenoming therapy and current perspectives. Front. Immunol., 10.","DOI":"10.3389\/fimmu.2019.01598"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.abb.2012.03.009","article-title":"Engineering antibodies by yeast display","volume":"526","author":"Boder","year":"2012","journal-title":"Arch. Biochem. Biophys."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"103984","DOI":"10.1016\/j.drudis.2024.103984","article-title":"A new era of antibody discovery: An in-depth review of AI-driven approaches","volume":"6","author":"Cheng","year":"2024","journal-title":"Drug Discov. Today"},{"key":"ref_8","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":"ref_9","doi-asserted-by":"crossref","unstructured":"Liu, X., Luo, Y., Li, P., Song, S., and Peng, J. (2021). Deep geometric representations for modeling effects of mutations on protein-protein binding affinity. PLoS Comput. Biol., 17.","DOI":"10.1371\/journal.pcbi.1009284"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Davila, A., Xu, Z., Li, S., Rozewicki, J., Wilamowski, J., Kotelnikov, S., Kozakov, D., Teraguchi, S., and Standley, D.M. (2022). AbAdapt: An adaptive approach to predicting antibody\u2013antigen complex structures from sequence. Bioinform. Adv., 2.","DOI":"10.1093\/bioadv\/vbac015"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/S1074-7613(00)00006-6","article-title":"Diversity in the CDR3 region of VH is sufficient for most antibody specificities","volume":"13","author":"Xu","year":"2000","journal-title":"Immunity"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1093\/bioinformatics\/btab660","article-title":"DLAB: Deep learning methods for structure-based virtual screening of antibodies","volume":"38","author":"Schneider","year":"2022","journal-title":"Bioinformatics"},{"key":"ref_13","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":"ref_14","doi-asserted-by":"crossref","first-page":"e2410529121","DOI":"10.1073\/pnas.2410529121","article-title":"Improved deep learning prediction of antigen\u2013antibody interactions","volume":"121","author":"Gao","year":"2024","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_15","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":"ref_16","doi-asserted-by":"crossref","unstructured":"Asti, L., Uguzzoni, G., Marcatili, P., and Pagnani, A. (2016). Maximum-entropy models of sequenced immune repertoires predict antigen-antibody affinity. PLoS Comput. Biol., 12.","DOI":"10.1371\/journal.pcbi.1004870"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.1038\/s41587-022-01307-0","article-title":"Prediction of protein\u2013ligand binding affinity from sequencing data with interpretable machine learning","volume":"40","author":"Rube","year":"2022","journal-title":"Nat. Biotechnol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhang, K., Tao, Y., and Wang, F. (2025). AntiBinder: Utilizing bidirectional attention and hybrid encoding for precise antibody\u2013antigen interaction prediction. Briefings Bioinform., 26.","DOI":"10.1093\/bib\/bbaf008"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Jin, R., Ye, Q., Wang, J., Cao, Z., Jiang, D., Wang, T., Kang, Y., Xu, W., Hsieh, C.Y., and Hou, T. (2024). AttABseq: An attention-based deep learning prediction method for antigen\u2013antibody binding affinity changes based on protein sequences. Briefings Bioinform., 25.","DOI":"10.1093\/bib\/bbae304"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1038\/s42256-022-00553-w","article-title":"Predicting unseen antibodies\u2019 neutralizability via adaptive graph neural networks","volume":"4","author":"Zhang","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"ref_21","unstructured":"Lin, Z., Akin, H., Rao, R., Hie, B., Zhu, Z., Lu, W., Smetanin, N., dos Santos Costa, A., Fazel-Zarandi, M., and Sercu, T. (2022). Language models of protein sequences at the scale of evolution enable accurate structure prediction. bioRxiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Olsen, T.H., Moal, I.H., and Deane, C.M. (2022). AbLang: An antibody language model for completing antibody sequences. Bioinform. Adv., 2.","DOI":"10.1093\/bioadv\/vbac046"},{"key":"ref_23","unstructured":"Ruffolo, J.A., Gray, J.J., and Sulam, J. (2021). Deciphering antibody affinity maturation with language models and weakly supervised learning. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, Q., Mao, J., Li, G., and Pan, X. (2023). DG-Affinity: Predicting antigen\u2013antibody affinity with language models from sequences. BMC Bioinform., 24.","DOI":"10.1186\/s12859-023-05562-z"},{"key":"ref_25","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":"ref_26","doi-asserted-by":"crossref","first-page":"2412533","DOI":"10.1002\/advs.202412533","article-title":"DeepInterAware: Deep Interaction Interface-Aware Network for Improving Antigen-Antibody Interaction Prediction from Sequence Data","volume":"12","author":"Xia","year":"2025","journal-title":"Adv. Sci."},{"key":"ref_27","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":"ref_28","doi-asserted-by":"crossref","first-page":"1034","DOI":"10.1016\/j.drudis.2020.03.006","article-title":"Epitope-based vaccine design: A comprehensive overview of bioinformatics approaches","volume":"25","author":"Parvizpour","year":"2020","journal-title":"Drug Discovery Today"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., and Hovy, E. (2016, January 12\u201317). Hierarchical attention networks for document classification. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, CA, USA.","DOI":"10.18653\/v1\/N16-1174"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Villas-Boas, G.R., Rescia, V.C., Paes, M.M., Lavorato, S.N., Magalh\u00e3es-Filho, M.F.D., Cunha, M.S., and Oesterreich, S.A. (2020). The new coronavirus (SARS-CoV-2): A comprehensive review on immunity and the application of bioinformatics and molecular modeling to the discovery of potential anti-SARS-CoV-2 agents. Molecules, 25.","DOI":"10.3390\/molecules25184086"},{"key":"ref_31","unstructured":"Gu, A., Goel, K., and R\u00e9, C. (2021). Efficiently modeling long sequences with structured state spaces. arXiv."},{"key":"ref_32","first-page":"22982","article-title":"Diagonal state spaces are as effective as structured state spaces","volume":"35","author":"Gupta","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_33","first-page":"80690","article-title":"Convolutional state space models for long-range spatiotemporal modeling","volume":"36","author":"Smith","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_34","unstructured":"Gu, A., and Dao, T. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv."},{"key":"ref_35","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., and Wang, X. (2025, January 13\u201319). Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model. Proceedings of the Forty-first International Conference on Machine Learning, Vancouver, BC, Canada."},{"key":"ref_36","unstructured":"Ali, A., Zimerman, I., and Wolf, L. (2024). The hidden attention of mamba models. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"W213","DOI":"10.1093\/nar\/gkv404","article-title":"CATNAP: A tool to compile, analyze and tally neutralizing antibody panels","volume":"43","author":"Yoon","year":"2015","journal-title":"Nucleic Acids Res."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1093\/bioinformatics\/btaa739","article-title":"CoV-AbDab: The coronavirus antibody database","volume":"37","author":"Raybould","year":"2020","journal-title":"Bioinformatics"},{"key":"ref_39","unstructured":"Pitorro, H., and Treviso, M. (2025). LaTIM: Measuring Latent Token-to-Token Interactions in Mamba Models. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Vig, J., and Belinkov, Y. (August, January 28). Analyzing the Structure of Attention in a Transformer Language Model. Proceedings of the 2019 ACL Workshop, Florence, Italy.","DOI":"10.18653\/v1\/W19-4808"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"i305","DOI":"10.1093\/bioinformatics\/btz328","article-title":"Multifaceted protein\u2013protein interaction prediction based on Siamese residual RCNN","volume":"35","author":"Chen","year":"2019","journal-title":"Bioinformatics"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Gu, M., Yang, W., and Liu, M. (2024). Prediction of antibody-antigen interaction based on backbone aware with invariant point attention. BMC Bioinform., 25.","DOI":"10.1186\/s12859-024-05961-w"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"e01740-24","DOI":"10.1128\/jvi.01740-24","article-title":"Ultrapotent IgA dimeric antibodies neutralize emerging Omicron variants","volume":"99","author":"Zuo","year":"2025","journal-title":"J. Virol."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"2749","DOI":"10.1080\/22221751.2022.2140611","article-title":"Shared IGHV1-69-encoded neutralizing antibodies contribute to the emergence of L452R substitution in SARS-CoV-2 variants","volume":"11","author":"Yan","year":"2022","journal-title":"Emerg. Microbes Infect."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/S0145-305X(02)00039-3","article-title":"IMGT unique numbering for immunoglobulin and T cell receptor variable domains and Ig superfamily V-like domains","volume":"27","author":"Lefranc","year":"2003","journal-title":"Dev. Comp. Immunol."},{"key":"ref_46","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":"ref_47","doi-asserted-by":"crossref","first-page":"e2381","DOI":"10.1002\/rmv.2381","article-title":"Evolution of the SARS-CoV-2 omicron variants BA. 1 to BA. 5: Implications for immune escape and transmission","volume":"32","author":"Shrestha","year":"2022","journal-title":"Rev. Med. Virol."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"e1298","DOI":"10.1002\/wcms.1298","article-title":"Using PyMOL as a platform for computational drug design","volume":"7","author":"Yuan","year":"2017","journal-title":"Wiley Interdiscip. Rev. Comput. Mol. Sci."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1837","DOI":"10.1038\/s41467-024-46143-9","article-title":"Dispersion patterns of SARS-CoV-2 variants gamma, lambda and mu in Latin America and the Caribbean","volume":"15","author":"Martinez","year":"2024","journal-title":"Nat. Commun."},{"key":"ref_50","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":"Zhang","year":"2004","journal-title":"Proteins Struct. Funct. Bioinform."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1093\/bioinformatics\/btq066","article-title":"How significant is a protein structure similarity with TM-score = 0.5?","volume":"26","author":"Xu","year":"2010","journal-title":"Bioinformatics"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1517\/17460441.2015.1032936","article-title":"The MM\/PBSA and MM\/GBSA methods to estimate ligand-binding affinities","volume":"10","author":"Genheden","year":"2015","journal-title":"Expert Opin. Drug Discov."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, Y., and Zhang, W. (2024, January 3\u20139). Improving paratope and epitope prediction by multi-modal contrastive learning and interaction informativeness estimation. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, Jeju, Republic of Korea.","DOI":"10.24963\/ijcai.2024\/669"},{"key":"ref_54","unstructured":"Li, W., Zhou, H., Yu, J., Song, Z., and Yang, W. (2024). Coupled mamba: Enhanced multi-modal fusion with coupled state space model. arXiv."}],"container-title":["Biomolecules"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2218-273X\/15\/6\/764\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:40:36Z","timestamp":1760031636000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2218-273X\/15\/6\/764"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,26]]},"references-count":54,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["biom15060764"],"URL":"https:\/\/doi.org\/10.3390\/biom15060764","relation":{},"ISSN":["2218-273X"],"issn-type":[{"value":"2218-273X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,26]]}}}