{"id":"W2789426118","doi":"10.1111/cbdd.13188","title":"Rational design of isonicotinic acid hydrazide derivatives with antitubercular activity: Machine learning, molecular docking, synthesis and biological testing","year":2018,"lang":"en","type":"article","venue":"Chemical Biology & Drug Design","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Discovery Centre; University of Toronto; Ontario Institute for Cancer Research","funders":"Ontario Institute for Cancer Research","keywords":"INHA; Docking (animal); Virtual screening; Quantitative structure–activity relationship; Computational biology; Hydrazide; Isonicotinic acid; Chemistry; Drug discovery; Cheminformatics; Molecular descriptor; Mycobacterium tuberculosis; Computer science; Stereochemistry; Combinatorial chemistry; Machine learning; Biochemistry; Biology; Tuberculosis; Computational chemistry; Medicine; Organic chemistry","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":[0.0005332479,0.0007723483,0.001256102,0.000685724,0.0002420198,0.0006709071,0.0006781239,0.0003951826,0.001347189],"category_scores_gemma":[0.0007872671,0.0004091039,0.0008422173,0.0008165968,0.0002881572,0.0004378696,0.0003767546,0.0007372392,0.0004817496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006955572,"about_ca_system_score_gemma":0.0007822639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00137229,"about_ca_topic_score_gemma":0.003389517,"domain_scores_codex":[0.9998047,0.00006706572,0.00001579433,0.00002962802,0.00004894155,0.00003378093],"domain_scores_gemma":[0.9998645,0.00004888934,0.00002809375,0.00001628592,0.000021752,0.00002049741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00134985,0.001912028,0.002515635,0.002588351,0.0003237511,0.001014977,0.0001398952,0.5731681,0.2842951,0.01034883,0.001867952,0.1204754],"study_design_scores_gemma":[0.001046981,0.008810034,0.001742584,0.000246192,0.000627955,0.000577599,0.0001582061,0.5660723,0.3956972,0.003070409,0.02180644,0.0001441881],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8833874,0.02228432,0.07899395,0.0008245347,0.0001233081,0.0008830163,0.001579069,0.0008190158,0.01110541],"genre_scores_gemma":[0.946829,0.01143913,0.03846792,0.0001114905,0.00002086813,0.0002432368,0.0009161646,0.00005242196,0.001919841],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00137229,"threshold_uncertainty_score":0.005046666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04536358967745495,"score_gpt":0.2867550965639821,"score_spread":0.2413915068865271,"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."}}