{"id":"W840861454","doi":"10.1371/journal.pone.0129711","title":"The Discovery of Novel Biomarkers Improves Breast Cancer Intrinsic Subtype Prediction and Reconciles the Labels in the METABRIC Data Set","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Breast Cancer Treatment Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"BC Cancer Agency; Australian Research Council; Cancer Institute NSW; Cancer Research UK","keywords":"Breast cancer; Artificial intelligence; Classifier (UML); Computer science; Random forest; Machine learning; Ensemble learning; Computational biology; Discriminative model; Support vector machine; Transcriptome; Bioinformatics; Cancer; Medicine; Gene; Gene expression; Biology; Internal medicine","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003752238,0.00009610071,0.0001134823,0.00001301927,0.00007964756,0.00003025113,0.0002927415,0.00003738023,5.019322e-7],"category_scores_gemma":[0.0001001206,0.00004535879,0.00001645058,0.0001053783,0.0002001469,0.0000151233,0.0002434164,0.00005494028,3.179051e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001783245,"about_ca_system_score_gemma":0.00008574004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00090227,"about_ca_topic_score_gemma":0.001616225,"domain_scores_codex":[0.9993122,0.00006761531,0.000134524,0.0002074271,0.0001533016,0.0001248951],"domain_scores_gemma":[0.9992507,0.00006686152,0.00008681048,0.0005097691,0.00006846507,0.00001738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.002560948,0.002556408,0.3804658,0.0001994816,0.008843573,0.000002770083,0.002726805,0.00001068968,0.5330229,0.0002051832,0.01281062,0.05659479],"study_design_scores_gemma":[0.003076945,0.0002686034,0.9447034,0.0001400572,0.000967596,0.00003155859,0.003210637,0.0002804339,0.04475826,0.0001169447,0.002183169,0.0002623683],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9841663,0.01052954,0.000007463015,0.003606571,0.00006171613,0.0002562819,0.001297688,0.000003759795,0.00007074069],"genre_scores_gemma":[0.9956732,0.003777445,0.00005164103,0.0001157838,0.0001393246,0.00007053612,0.0001170661,0.000008473413,0.00004654187],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5642376,"threshold_uncertainty_score":0.1849678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08054890599048548,"score_gpt":0.2708805444404884,"score_spread":0.1903316384500029,"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."}}