{"id":"W4403964068","doi":"10.26434/chemrxiv-2024-pf3ph","title":"Conformal Selection for Efficient and Accurate Compound Screening in Drug Discovery","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"","keywords":"Drug discovery; Selection (genetic algorithm); Conformal map; Drug; Computer science; Computational biology; Pharmacology; Mathematics; Medicine; Artificial intelligence; Biology; Bioinformatics","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":[0.007520679,0.0009840295,0.002145313,0.001853913,0.0008957018,0.001611222,0.001832795,0.001278499,0.002388417],"category_scores_gemma":[0.02846858,0.0007218451,0.001443143,0.001877736,0.002106589,0.001452021,0.003127189,0.002006638,0.000691106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001209966,"about_ca_system_score_gemma":0.001756731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002397764,"about_ca_topic_score_gemma":0.002063868,"domain_scores_codex":[0.9945129,0.002678271,0.0002281961,0.0005990642,0.001765085,0.0002164473],"domain_scores_gemma":[0.9863369,0.01037266,0.0007439997,0.001322376,0.0009655741,0.000258374],"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":[0.0002982894,0.0001121419,0.005027052,0.000403836,0.0002118549,0.0003280015,0.0002072147,0.6778035,0.007634985,0.08314991,0.004393946,0.2204293],"study_design_scores_gemma":[0.00005686424,0.00007550413,0.0004461098,0.00001714407,0.00002121679,0.00007454916,0.00001339693,0.9404901,0.002640726,0.05413505,0.002005518,0.00002383307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008822087,0.0003548893,0.9888203,0.0001744295,0.00003444391,0.00009586367,0.00007952481,0.000518203,0.001100306],"genre_scores_gemma":[0.4225301,0.0008885369,0.5726905,0.0005586195,0.0002312192,0.0006220011,0.0004997181,0.0003649827,0.001614268],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007520679,"threshold_uncertainty_score":0.03977358,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03431818453660575,"score_gpt":0.3222849342793785,"score_spread":0.2879667497427728,"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."}}