{"url":"/dataset/mipe","name":"MIPE","full_name":"Improving Paratope and Epitope Prediction by Multi-Modal Contrastive Learning and Interaction Informativeness Estimation","description_markdown":"Datasets. From the publicly accessible Structural Antibody Database (SAbDab), we collected a total of 7571 antibodyantigen complexes, with the sequence data in FASTA format and structural data in PDB format. Following previous studies [Pittala and Bailey-Kellogg, 2020], we used CD-HIT [Li and Godzik, 2006] to remove high-homology antibody and antigen sequences with the thresholds of 95% and 90% sequence identity, respectively. Subsequently, we excluded antibodies and antigens with any residue type rather than 20 naturally occurring types. Finally, we compiled a dataset consisting of 626 binding antibody-antigen pairs, including their sequences, structures, and corresponding interaction maps. Noteworthy, antibodies primarily bind to antigens through their CDR regions. Most researchers use Euclidean distance to define paratopes and epitopes, and we follow the usual way in our dataset: within the CDR regions/antigen, a residue is labeled as a paratope/epitope if the Euclidean distance between its backbone atom and any backbone atom on the other antigen/CDR regions is less than 4.5 ˚ A.","description_withheld":null,"homepage":"https://www.ijcai.org/proceedings/2024/0669.pdf","introduced_date":"2024-05-31","introduced_date_note":null,"introduced_by":null,"license":{"name":"MIT","url":null},"modalities":[{"name":"Biology","url":"/datasets/modality/biology"},{"name":"Biomedical","url":"/datasets/modality/biomedical"}],"tasks":[{"name":"Antibody-antigen binding prediction","url":"/task/antibody-antigen-binding-prediction","datasets_with_task":"/datasets/task/antibody-antigen-binding-prediction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MIPE"],"data_loaders":[],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/antibody-antigen-binding-prediction-on-mipe","task":"Antibody-antigen binding prediction","dataset_variant":"MIPE","rows":7,"metrics":["AUC-PR","AUC-ROC"],"first_row_in_archive_order":{"model":"ParaSurf","paper":"/paper/parasurf-a-surface-based-deep-learning","metrics":{"AUC-PR":"0.781","AUC-ROC":"0.967"},"code_links":[{"title":"aggelos-michael-papadopoulos/ParaSurf","url":"https://github.com/aggelos-michael-papadopoulos/ParaSurf"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/parasurf-a-surface-based-deep-learning","title":"ParaSurf: A Surface-Based Deep Learning Approach for Paratope-Antigen Interaction Prediction","date":"2025-02-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-paratope-and-epitope-prediction-by","title":"Improving Paratope and Epitope Prediction by Multi-Modal Contrastive Learning and Interaction Informativeness Estimation","date":"2024-05-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pesto-parameter-free-geometric-deep-learning","title":"PeSTo: parameter-free geometric deep learning for accurate prediction of protein binding interfaces","date":"2023-04-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/paragraph-antibody-paratope-prediction-using","title":"Paragraph—antibody paratope prediction using graph neural networks with minimal feature vectors","date":"2022-10-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-context-aware-structural","title":"Learning context-aware structural representations to predict antigen and antibody binding interfaces","date":"2020-04-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/attentive-cross-modal-paratope-prediction","title":"Attentive cross-modal paratope prediction","date":"2018-06-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/parapred-antibody-paratope-prediction-using","title":"Parapred: antibody paratope prediction using convolutional and recurrent neural networks","date":"2018-04-16","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}