{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002573659,0.000151978,0.00009789811,0.00005308566,0.0003813165,0.0002025695,0.0002964153,0.000155097,0.00002734154],"category_scores_gemma":[0.0003840194,0.0001505725,0.00003881847,0.00002790814,0.00004032018,0.0001216643,0.0001201746,0.0001796993,0.00005018377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002597084,"about_ca_system_score_gemma":0.00002497759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000765203,"about_ca_topic_score_gemma":0.00002350512,"domain_scores_codex":[0.9992195,0.00004118662,0.0002036903,0.0002126267,0.0001450994,0.0001779414],"domain_scores_gemma":[0.9989679,0.00001286549,0.0004072711,0.0004309076,0.0001384883,0.00004251516],"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":[0.0003454703,0.0000503152,0.00817791,0.0001838957,0.0001398881,5.131025e-7,0.00007197852,0.0005241443,0.3274461,0.000003509672,0.2903267,0.3727295],"study_design_scores_gemma":[0.008688975,0.0007936616,0.02367069,0.0005238118,0.0002249355,0.00009582178,0.0001034587,0.4539012,0.2110147,0.0001275028,0.298889,0.001966247],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5237016,0.000008015911,0.4697497,0.004660183,0.0003196854,0.0006623301,0.0007876513,0.00003889547,0.00007187906],"genre_scores_gemma":[0.888802,0.000005888275,0.02673474,0.004286834,0.000361874,0.0001360158,0.0794555,0.00003206493,0.0001851154],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4533771,"threshold_uncertainty_score":0.614017,"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."}}