{"id":"W4393397025","doi":"10.1038/s41598-024-54655-z","title":"AI is a viable alternative to high throughput screening: a 318-target study","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":120,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg; St. Boniface Hospital; Simon Fraser University; McGill University; Université du Québec à Montréal; McMaster University; University of Manitoba; St. Joseph’s Healthcare Hamilton; University of Toronto; Montreal Heart Institute; CancerCare Manitoba; Saskatchewan Cancer Agency; University of Alberta; Hospital for Sick Children; University of Saskatchewan; Université de Montréal","funders":"Biotechnology and Biological Sciences Research Council; National Institute of Diabetes and Digestive and Kidney Diseases; Medical Research Council","keywords":"Chemical space; Virtual screening; Computer science; Drug discovery; High-throughput screening; Small molecule; Throughput; Convolutional neural network; Cheminformatics; Chemical database; Computational biology; Machine learning; Artificial intelligence; Bioinformatics; Chemistry; 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":[0.002442959,0.0006547372,0.0008891493,0.0006990643,0.0003729115,0.001721929,0.0008568774,0.0007528003,0.005226196],"category_scores_gemma":[0.004073526,0.0001679367,0.0006189584,0.001199932,0.0008745106,0.003396792,0.0008583157,0.001310658,0.000926001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00133845,"about_ca_system_score_gemma":0.0008777734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001922333,"about_ca_topic_score_gemma":0.001968653,"domain_scores_codex":[0.9988742,0.0004494297,0.000028445,0.0001124723,0.0004274414,0.0001078659],"domain_scores_gemma":[0.9979766,0.00137558,0.0001620209,0.0002359845,0.0001587505,0.00009116502],"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":[0.003418428,0.001879129,0.02622216,0.001609851,0.0006159469,0.0005420473,0.000116241,0.1761597,0.04889088,0.1775643,0.01349955,0.5494818],"study_design_scores_gemma":[0.0003142928,0.004143488,0.01364573,0.0001962526,0.000349347,0.0007312673,0.0002235695,0.8200893,0.03589045,0.08983177,0.03450545,0.00007910938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6756501,0.03184025,0.1671056,0.01008943,0.0002955679,0.0005042175,0.001741684,0.001264106,0.1115091],"genre_scores_gemma":[0.9648023,0.007556565,0.0201939,0.0007565056,0.00009154935,0.0001597577,0.0006343771,0.00008089587,0.005724072],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005226196,"threshold_uncertainty_score":0.01748335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03060409017875283,"score_gpt":0.3462741309242043,"score_spread":0.3156700407454515,"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."}}