{"id":"W4412385716","doi":"10.26434/chemrxiv-2024-pf3ph-v3","title":"Conformal Selection for Efficient and Accurate Compound Screening in Drug Discovery","year":2025,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"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; Medicine; Pharmacology; Artificial intelligence; Mathematics; Bioinformatics; Biology","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":[0.009707207,0.0009428185,0.002048053,0.001656641,0.0008537662,0.001665315,0.0018724,0.001252441,0.00239043],"category_scores_gemma":[0.03457437,0.000701429,0.001455758,0.001824873,0.002453823,0.001595352,0.003431745,0.002248729,0.0006672645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001281525,"about_ca_system_score_gemma":0.001894885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001751645,"about_ca_topic_score_gemma":0.001594595,"domain_scores_codex":[0.9930136,0.003582715,0.0002659931,0.0006837972,0.002202465,0.0002514348],"domain_scores_gemma":[0.9839994,0.01197653,0.0008964667,0.001861117,0.0009614492,0.0003051034],"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":[0.0003544312,0.0001171872,0.005125401,0.0004454607,0.0002453021,0.0003444569,0.0002172603,0.6417423,0.009228115,0.1304237,0.004285392,0.207471],"study_design_scores_gemma":[0.00007067733,0.0001102,0.000527809,0.00002084922,0.00002717188,0.00009325521,0.00001498635,0.9141479,0.003907456,0.07859585,0.002455386,0.00002839946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008306006,0.0003278101,0.9892982,0.0001961343,0.00003480824,0.0000947825,0.00007375581,0.0004451181,0.001223418],"genre_scores_gemma":[0.4198347,0.0008923322,0.5755057,0.0006169868,0.0002102629,0.0006052968,0.0004156706,0.0003359274,0.001583078],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009707207,"threshold_uncertainty_score":0.05133724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03330237706079424,"score_gpt":0.3251577632510129,"score_spread":0.2918553861902186,"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."}}