{"id":"W2110841565","doi":"10.1109/tcbb.2011.31","title":"Using Kernel Alignment to Select Features of Molecular Descriptors in a QSAR Study","year":2011,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Toronto; Toronto Public Health","funders":"","keywords":"Quantitative structure–activity relationship; Molecular descriptor; Kernel (algebra); Artificial intelligence; Feature selection; Similarity (geometry); Pattern recognition (psychology); Computer science; Feature (linguistics); Data mining; Machine learning; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001821288,0.0006621649,0.001070436,0.001626112,0.0003785908,0.0007309441,0.0006723829,0.0006171462,0.0007604253],"category_scores_gemma":[0.00666084,0.0002739922,0.0004898027,0.001406934,0.0004021146,0.001148343,0.0006123871,0.000701647,0.0004383564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003375454,"about_ca_system_score_gemma":0.000800458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001573211,"about_ca_topic_score_gemma":0.001107844,"domain_scores_codex":[0.999099,0.0003769691,0.00007622781,0.0001330799,0.0002279933,0.0000867754],"domain_scores_gemma":[0.9966247,0.002183608,0.0004228986,0.0002154317,0.0004807167,0.00007258671],"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":[0.0008046858,0.0005054798,0.01541614,0.0001652052,0.0001570379,0.0002311011,0.0001884069,0.310482,0.06659876,0.006015818,0.0008464918,0.5985889],"study_design_scores_gemma":[0.00003363258,0.0001723137,0.002185336,0.000004841818,0.00003162292,0.00005483651,0.00002835509,0.9817523,0.01331801,0.001927989,0.0004728892,0.00001783981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1680084,0.0002195859,0.8303173,0.00006744221,0.00001061723,0.00009377149,0.00005176327,0.0008719078,0.0003591682],"genre_scores_gemma":[0.6923177,0.0001449571,0.3066544,0.00003093207,0.0000212807,0.00009977923,0.0002956925,0.0001049722,0.0003302678],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001821288,"threshold_uncertainty_score":0.009632051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06117062881534215,"score_gpt":0.3298003710050013,"score_spread":0.2686297421896592,"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."}}