{"id":"W2289613708","doi":"10.1021/acs.jcim.5b00663","title":"Exploiting Multiple Descriptor Sets in QSAR Studies","year":2016,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; The Scarborough Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Quantitative structure–activity relationship; Molecular descriptor; Ranking (information retrieval); Computer science; Artificial intelligence; Machine learning; Partition (number theory); Training set; Set (abstract data type); Data mining; Pattern recognition (psychology); Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006277496,0.00005838502,0.0001300225,0.0001378838,0.00002023865,0.0000549387,0.0001488247,0.00002464085,6.698732e-7],"category_scores_gemma":[0.0005660493,0.00003828699,0.0000348111,0.00009006642,0.00001847347,0.003146153,0.00009999155,0.00007978553,0.000001567674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000527634,"about_ca_system_score_gemma":0.00004531211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001104086,"about_ca_topic_score_gemma":1.576222e-7,"domain_scores_codex":[0.9991175,0.000028339,0.0005152457,0.00004732929,0.0001955389,0.00009605647],"domain_scores_gemma":[0.9992482,0.0002489782,0.000184379,0.00005308663,0.0002124421,0.00005292094],"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":[0.00009061625,0.00005344252,0.0007440179,0.0001026029,0.00005806352,0.000007145952,0.01003575,0.1515247,0.04841434,0.009182359,0.0002751059,0.7795119],"study_design_scores_gemma":[0.0006386492,0.00001301802,0.00002036321,0.0001737608,0.000001894429,0.00003594497,0.0002288822,0.9807342,0.009058672,0.008879861,0.0001472504,0.00006752653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.489867,0.000135474,0.5093492,0.0005291468,0.00007289233,0.00001693658,2.902036e-7,0.000005843295,0.00002324075],"genre_scores_gemma":[0.9018221,0.0000996,0.09782581,0.0002210597,0.00002784756,0.00000100418,1.865121e-7,0.000001462051,9.360029e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8292094,"threshold_uncertainty_score":0.2280885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09843100805307531,"score_gpt":0.3412166612341577,"score_spread":0.2427856531810824,"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."}}