{"id":"W2598976994","doi":"10.1016/j.patrec.2017.03.011","title":"Feature selection by maximizing correlation information for integrated high-dimensional protein data","year":2017,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"Specialized Research Fund for the Doctoral Program of Higher Education of China; Natural Sciences and Engineering Research Council of Canada; Ministry of Industry and Information Technology of the People's Republic of China; National Natural Science Foundation of China","keywords":"Feature selection; Random forest; Computer science; Benchmark (surveying); Feature (linguistics); Pattern recognition (psychology); Correlation; Artificial intelligence; Support vector machine; Feature vector; Coding (social sciences); High dimensional; Data mining; Mathematics; Statistics","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":[0.001446915,0.0006898235,0.001297855,0.001733244,0.0004123814,0.0008473902,0.0008976785,0.0006671504,0.0007638653],"category_scores_gemma":[0.003036315,0.0003233952,0.001055547,0.002192417,0.0004318626,0.0007836624,0.000799898,0.0006647352,0.0004027114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004333497,"about_ca_system_score_gemma":0.0009833416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001445773,"about_ca_topic_score_gemma":0.00235045,"domain_scores_codex":[0.9993671,0.0001659948,0.00004726482,0.0001299495,0.0001907613,0.00009903969],"domain_scores_gemma":[0.9989247,0.0005563974,0.0001088609,0.0001417404,0.0002035795,0.00006463907],"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":[0.001046005,0.0006327356,0.011765,0.0002408294,0.0003995013,0.0004534984,0.00011058,0.182703,0.06003918,0.004352715,0.0088769,0.7293801],"study_design_scores_gemma":[0.00002665972,0.00007597016,0.002899753,0.000006012683,0.00004360353,0.000102902,0.00001302509,0.9873092,0.006259803,0.002715451,0.0005323377,0.00001535841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1579189,0.0005742073,0.83877,0.000291513,0.00003401039,0.00005654784,0.000374671,0.001415457,0.0005646882],"genre_scores_gemma":[0.8110133,0.000310729,0.1848232,0.0001086901,0.00010057,0.0001798455,0.002032679,0.0001659688,0.001265075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001733244,"threshold_uncertainty_score":0.007652104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01553518207091383,"score_gpt":0.2529235969522161,"score_spread":0.2373884148813023,"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."}}