{"id":"W2058015994","doi":"10.1021/jm500022q","title":"Using Matched Molecular Series as a Predictive Tool To Optimize Biological Activity","year":2014,"lang":"en","type":"article","venue":"Journal of Medicinal Chemistry","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nexen (Canada)","funders":"","keywords":"Series (stratigraphy); Tree (set theory); Set (abstract data type); Scale (ratio); Molecular descriptor; Chemistry; Generator (circuit theory); Data set; Computer science; Artificial intelligence; Machine learning; Data mining; Quantitative structure–activity relationship; Mathematics; Power (physics); Combinatorics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001359447,0.0001577413,0.0003542508,0.00005572183,0.00005512076,0.00006125979,0.0006717002,0.00009040518,0.00002885163],"category_scores_gemma":[0.00136064,0.0001243758,0.0001282241,0.0002580797,0.00007538561,0.0003573498,0.0002404965,0.0003489848,0.000003217814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001334275,"about_ca_system_score_gemma":0.000284121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003897693,"about_ca_topic_score_gemma":3.692455e-8,"domain_scores_codex":[0.9983582,0.000185509,0.0003540122,0.0002327607,0.0006565342,0.0002130189],"domain_scores_gemma":[0.9986394,0.0003033267,0.0003141414,0.0002392871,0.0002702211,0.0002336292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007235903,0.0001592677,0.0001672332,0.00006243576,0.0001173453,0.0003300405,0.0004974392,0.105891,0.8750636,0.0009464589,0.0001910658,0.01585051],"study_design_scores_gemma":[0.001636606,0.001428291,0.003317197,0.0004035419,0.00007414415,0.005498908,0.0002184614,0.19392,0.7696952,0.02228723,0.001007353,0.0005130833],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4955574,0.00002952397,0.5028686,0.0009166924,0.0001247598,0.00003267285,7.067237e-7,0.00001227103,0.0004573528],"genre_scores_gemma":[0.759041,0.00000415958,0.2402869,0.0003402406,0.0002975128,0.000001582867,3.058356e-7,0.000006083498,0.00002230416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2634836,"threshold_uncertainty_score":0.5071899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02977095711801334,"score_gpt":0.3258152013648571,"score_spread":0.2960442442468437,"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."}}