{"id":"W2147626660","doi":"10.1093/bioinformatics/btr591","title":"Optimized application of penalized regression methods to diverse genomic data","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":99,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Ontario Institute for Cancer Research","funders":"Division of Biological Infrastructure; National Science Foundation","keywords":"Elastic net regularization; Lasso (programming language); Feature selection; Computer science; Univariate; Regression; Data mining; R package; Predictive modelling; Regression analysis; Machine learning; Artificial intelligence; Statistics; Mathematics; Multivariate statistics","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":[0.0003387466,0.00009611569,0.0001244978,0.00006124253,0.00004057409,0.000007331182,0.0005013639,0.00008885902,0.00004083324],"category_scores_gemma":[0.00007266497,0.00007788065,0.0000374888,0.0001046099,0.00003176793,0.00001012625,0.0004159865,0.00003370193,0.0000264215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009185056,"about_ca_system_score_gemma":0.00005026263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001353331,"about_ca_topic_score_gemma":0.000001306539,"domain_scores_codex":[0.9992648,0.00004580021,0.0003149631,0.0001684298,0.00009748202,0.0001085102],"domain_scores_gemma":[0.998605,0.00000591201,0.0002189214,0.001011293,0.00007809938,0.00008079442],"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":[0.0003203118,0.00006059161,0.000235707,0.00004990523,0.00003153797,8.674088e-8,0.0006885687,0.00004618406,0.8884543,0.0001669556,0.010449,0.0994969],"study_design_scores_gemma":[0.001351966,0.0001833216,0.002883922,0.00003430721,0.00005702907,0.000004678059,0.0009143598,0.01947547,0.8100331,0.0001012935,0.1646476,0.0003128929],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01989065,0.0001340761,0.9735677,0.00003735232,0.0001386409,0.0003769694,0.0000489409,0.00001626511,0.005789418],"genre_scores_gemma":[0.09430418,0.0001341575,0.9045623,0.0002114171,0.00004714834,0.00003089934,0.0004509879,0.00001250201,0.0002464007],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1541986,"threshold_uncertainty_score":0.3175881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08353315231449081,"score_gpt":0.3586795711320192,"score_spread":0.2751464188175284,"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."}}