{"id":"W4305082653","doi":"10.1371/journal.pcbi.1010613","title":"A machine learning model trained on a high-throughput antibacterial screen increases the hit rate of drug discovery","year":2022,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Canadian Institutes of Health Research; Government of Canada; Cystic Fibrosis Canada; University of Manitoba; Cystic Fibrosis Foundation","keywords":"Antibacterial activity; Virtual screening; Drug discovery; Minimum inhibitory concentration; Machine learning; Antibiotics; Computer science; Bacteria; Artificial intelligence; Biology; Bioinformatics; Microbiology","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":[0.002383903,0.001118913,0.001193136,0.000947068,0.0002628418,0.000908491,0.0006692232,0.0009624789,0.001247423],"category_scores_gemma":[0.006331009,0.0003197049,0.0006223251,0.0006009733,0.0003662107,0.000961435,0.0005070188,0.001252646,0.0006165342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007010438,"about_ca_system_score_gemma":0.000911954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002382507,"about_ca_topic_score_gemma":0.002303015,"domain_scores_codex":[0.9993338,0.0002560337,0.00004803752,0.0001537987,0.0001373562,0.00007097902],"domain_scores_gemma":[0.9964586,0.002784946,0.0002451579,0.0001505145,0.0002926665,0.00006804556],"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":[0.0004638786,0.0004069286,0.01751529,0.0001813103,0.0002451316,0.0001148481,0.00002797365,0.8564306,0.008218225,0.0005647368,0.001311128,0.11452],"study_design_scores_gemma":[0.00001578032,0.0001886919,0.001798716,0.000009112122,0.00003308014,0.00002858044,0.000003698279,0.994922,0.002335047,0.0003878904,0.00026858,0.000008947843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6941046,0.001814891,0.2941152,0.001121537,0.0001457973,0.0001622118,0.0007454462,0.003363513,0.004426931],"genre_scores_gemma":[0.9677434,0.0003717222,0.02908387,0.0002958522,0.00005006338,0.0001158038,0.0007373438,0.00005141783,0.001550513],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002383903,"threshold_uncertainty_score":0.01260746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02729769639799109,"score_gpt":0.2747504262023792,"score_spread":0.2474527298043881,"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."}}