{"id":"W4402704193","doi":"10.1101/2024.09.12.612771","title":"Escaping the drug-bias trap: using debiasing design to improve interpretability and generalization of drug-target interaction prediction","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Interpretability; Computer science; Drug; Machine learning; Artificial intelligence; Virtual screening; Generalizability theory; Computational biology; Drug discovery; Data mining; Bioinformatics; Biology; Pharmacology; Mathematics","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":[0.002032693,0.00121994,0.0009816287,0.0006603801,0.0004065524,0.0008200259,0.001637318,0.0008551788,0.002296213],"category_scores_gemma":[0.004321289,0.0003696228,0.0007263944,0.0003642844,0.000709115,0.001200612,0.001331785,0.001657654,0.0004596068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001003518,"about_ca_system_score_gemma":0.001283047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004470179,"about_ca_topic_score_gemma":0.004886391,"domain_scores_codex":[0.9995297,0.0001455439,0.00003242612,0.0001545458,0.00007471181,0.00006305041],"domain_scores_gemma":[0.9987859,0.000591443,0.0001327998,0.0001815658,0.0002148241,0.00009358897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006283377,0.0002617073,0.006688292,0.0001902865,0.0001417825,0.0001852021,0.0001437174,0.7738973,0.01570497,0.006721356,0.005351866,0.1900851],"study_design_scores_gemma":[0.00001104607,0.00003713723,0.0001048281,0.00000441495,0.00000745882,0.000006645219,0.000004117031,0.99699,0.001129106,0.001487038,0.0002151778,0.000003080216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2603759,0.001727695,0.7245174,0.001422877,0.0001787208,0.0001774919,0.0004295399,0.005368707,0.005801658],"genre_scores_gemma":[0.871132,0.0003087526,0.1237001,0.0006705066,0.00006911327,0.000175332,0.00107154,0.0002335261,0.002639179],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004470179,"threshold_uncertainty_score":0.01075006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03420789716835802,"score_gpt":0.2763697439704992,"score_spread":0.2421618468021412,"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."}}