{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/attentive-cross-modal-paratope-prediction","title":"Attentive cross-modal paratope prediction","arxiv_id":"1806.04398","date":"2018-06-12","proceeding":null,"authors":["Andreea Deac","Petar Veličković","Pietro Sormanni"],"abstract":"Antibodies are a critical part of the immune system, having the function of\ndirectly neutralising or tagging undesirable objects (the antigens) for future\ndestruction. Being able to predict which amino acids belong to the paratope,\nthe region on the antibody which binds to the antigen, can facilitate antibody\ndesign and contribute to the development of personalised medicine. The\nsuitability of deep neural networks has recently been confirmed for this task,\nwith Parapred outperforming all prior physical models. Our contribution is\ntwofold: first, we significantly outperform the computational efficiency of\nParapred by leveraging \\`a trous convolutions and self-attention. Secondly, we\nimplement cross-modal attention by allowing the antibody residues to attend\nover antigen residues. This leads to new state-of-the-art results on this task,\nalong with insightful interpretations.","url_abs":"http://arxiv.org/abs/1806.04398v1","url_pdf":"http://arxiv.org/pdf/1806.04398v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"antibody-antigen-binding-prediction","task_name":"Antibody-antigen binding prediction"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/antibody-antigen-binding-prediction-on-mipe","task":"Antibody-antigen binding prediction","dataset":"MIPE","model":"AG-Fast-Parapred","rank_in_archive_order":7,"of":7,"metrics":{"AUC-PR":"0.612","AUC-ROC":"0.883"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.04398","atlas_url":"https://app.syntology.ai/?focus=1806.04398","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}