{"url":"/dataset/pecan","name":"PECAN","full_name":"Paratope-Epitope Complexes for Antibody Networks (PECAN)","description_markdown":"The PECAN dataset provides structural data for antibody-antigen interactions, specifically curated for paratope and epitope binding site prediction. It includes a diverse set of antibody-antigen complexes, ensuring a well-balanced and representative dataset for training and evaluating deep learning models in protein-protein interaction (PPI) tasks.\r\n\r\n**Characteristics:**\r\n- Focuses on **antibody-antigen binding site prediction**.\r\n- Derived from high-resolution **X-ray crystallography** structures.\r\n- Includes training, validation, and test splits.\r\n- Used as a **benchmark dataset** in multiple antibody binding site prediction studies.\r\n\r\n**Motivation and Use Cases:**\r\n- Facilitates the development of deep learning models for **paratope and epitope identification**.\r\n- Enables researchers to evaluate and compare methods for antibody-antigen interaction prediction.\r\n- Used in **ParaSurf**, a deep learning framework that achieves state-of-the-art results on this dataset.","description_withheld":null,"homepage":"https://figshare.com/articles/dataset/Training_validation_and_testing_sample_data_used_in_Antibody_interface_prediction_with_3D_Zernike_descriptors_and_SVM_/5442229","introduced_date":"2018-09-21","introduced_date_note":null,"introduced_by":null,"license":{"name":"CC0 1.0","url":null},"modalities":[{"name":"Biology","url":"/datasets/modality/biology"}],"tasks":[{"name":"Antibody-antigen binding prediction","url":"/task/antibody-antigen-binding-prediction","datasets_with_task":"/datasets/task/antibody-antigen-binding-prediction"}],"languages":[],"variants":["PECAN"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/antibody-antigen-binding-prediction-on-pecan","task":"Antibody-antigen binding prediction","dataset_variant":"PECAN","rows":5,"metrics":["AUC-PR","AUC-ROC"],"first_row_in_archive_order":{"model":"ParaSurf","paper":"/paper/parasurf-a-surface-based-deep-learning","metrics":{"AUC-PR":"0.733","AUC-ROC":"0.955"},"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/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/antibody-interface-prediction-with-3d-zernike","title":"Antibody interface prediction with 3D Zernike descriptors and SVM","date":"2018-10-05","rows_on_this_dataset":1,"code_links":1,"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."}