{"id":"W4225856506","doi":"10.1093/mutage/geac010","title":"Optimizing machine-learning models for mutagenicity prediction through better feature selection","year":2022,"lang":"en","type":"article","venue":"Mutagenesis","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Eisai Canada","keywords":"Machine learning; Artificial intelligence; Feature selection; Computer science; Benchmark (surveying); Context (archaeology); Cross-validation; Artificial neural network; Predictive modelling; Molecular descriptor; In silico; Model selection; Quantitative structure–activity relationship; Process (computing); Selection (genetic algorithm); Feature (linguistics); Data mining; Chemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002016254,0.001281622,0.00127369,0.0009313741,0.0002915543,0.0008423192,0.001020785,0.001090343,0.00103724],"category_scores_gemma":[0.004961988,0.0003631302,0.0009902442,0.0006996115,0.0003436163,0.001102275,0.0005297697,0.001328825,0.0003793251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007915097,"about_ca_system_score_gemma":0.001183425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004821368,"about_ca_topic_score_gemma":0.005384644,"domain_scores_codex":[0.9994536,0.0002451924,0.00003684991,0.0001184483,0.00008829554,0.00005770915],"domain_scores_gemma":[0.9981184,0.001366161,0.0001480641,0.0001064169,0.0002191443,0.0000418765],"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":[0.00006834447,0.0001172974,0.002245398,0.00004898013,0.00005648653,0.00004626072,0.00001203941,0.9508195,0.001453993,0.0007953375,0.0008935218,0.0434428],"study_design_scores_gemma":[0.000004823841,0.00002065023,0.000125115,0.000002926329,0.000005670543,0.000005202149,0.000001678673,0.998789,0.0003579827,0.0006111087,0.00007357405,0.000002235778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2123264,0.001900481,0.7795466,0.001445071,0.00008277252,0.0001245088,0.000565229,0.002425484,0.001583542],"genre_scores_gemma":[0.9028795,0.00036118,0.09411363,0.0002863473,0.00005649175,0.0001808475,0.0008984018,0.0000765361,0.001147023],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004821368,"threshold_uncertainty_score":0.01066303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03960028670017286,"score_gpt":0.2773120388961331,"score_spread":0.2377117521959602,"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."}}