{"id":"W4413337851","doi":"10.1038/s42256-025-01080-0","title":"The importance of negative training data for robust antibody binding prediction","year":2025,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Training (meteorology); Antibody; Training set; Computer science; Medicine; Immunology; Artificial intelligence; Geography; Meteorology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0101034,0.001415344,0.00149188,0.0009769654,0.0007708197,0.001817456,0.00217319,0.002665253,0.002207174],"category_scores_gemma":[0.03961251,0.0006849748,0.0006639533,0.0006241814,0.001690423,0.002574426,0.001335831,0.002605135,0.001541729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004058973,"about_ca_system_score_gemma":0.0008333304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001597202,"about_ca_topic_score_gemma":0.001920063,"domain_scores_codex":[0.995743,0.001965583,0.0002853081,0.000724447,0.001063039,0.0002184689],"domain_scores_gemma":[0.9654772,0.02696994,0.0009184101,0.003647283,0.002643835,0.0003433203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002540177,0.001030827,0.0288425,0.0008523677,0.000338209,0.0005308219,0.0001376466,0.204872,0.05774624,0.008220979,0.0238711,0.6710172],"study_design_scores_gemma":[0.00007305043,0.00026246,0.00479932,0.00008302191,0.0000821054,0.0003311363,0.00004530358,0.9539248,0.02577228,0.01146604,0.003130805,0.00002972444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2784455,0.004609252,0.6942207,0.004474094,0.0008646103,0.0002142134,0.002188155,0.004913395,0.01006999],"genre_scores_gemma":[0.9023183,0.0006106482,0.08841268,0.001347321,0.0003849444,0.0001087282,0.003065606,0.0003718268,0.003379912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0101034,"threshold_uncertainty_score":0.05343252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06454479274959338,"score_gpt":0.4149155629044256,"score_spread":0.3503707701548322,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}