{"id":"W4406663280","doi":"10.1101/2025.01.16.633372","title":"CPI-Pred: A deep learning framework for predicting functional parameters of compound-protein interactions","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institutes of Health; Genome Canada; Ontario Ministry of Research and Innovation; Mitacs; Adolph C. and Mary Sprague Miller Institute for Basic Research in Science, University of California Berkeley","keywords":"Artificial intelligence; Computer science; Machine learning; Econometrics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001077791,0.001299267,0.0009382667,0.0008652317,0.0003237018,0.0009600501,0.001967781,0.001678998,0.002254699],"category_scores_gemma":[0.002170016,0.0006187653,0.0009984823,0.0007959142,0.000599665,0.001182235,0.0009716391,0.002126767,0.0006151783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001408921,"about_ca_system_score_gemma":0.002112493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009265369,"about_ca_topic_score_gemma":0.0110819,"domain_scores_codex":[0.9997357,0.0000608216,0.0000140557,0.00009001898,0.00005791667,0.00004146992],"domain_scores_gemma":[0.9993475,0.0003385289,0.00008129929,0.00006043858,0.0001203752,0.00005199598],"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":[0.0001944174,0.0001630375,0.002727153,0.0001157347,0.00009812172,0.0000846598,0.00001517718,0.936678,0.003182889,0.003563205,0.003434331,0.04974334],"study_design_scores_gemma":[0.000004477967,0.00001975105,0.00007717575,0.000002855352,0.000003786459,0.000005401083,0.000001261598,0.9979832,0.0005504247,0.001118047,0.0002307928,0.000002815307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1636002,0.00252234,0.8155155,0.0009172356,0.0001039454,0.000158917,0.005310001,0.008077607,0.00379432],"genre_scores_gemma":[0.7968233,0.0008157683,0.188538,0.0005651387,0.00007145293,0.0003978315,0.008419477,0.0002568025,0.004112168],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009265369,"threshold_uncertainty_score":0.01842284,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02818041921952555,"score_gpt":0.2799788381501077,"score_spread":0.2517984189305821,"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."}}