{"id":"W2949244194","doi":"10.1186/s12859-017-1553-8","title":"MINT: a multivariate integrative method to identify reproducible molecular signatures across independent experiments and platforms","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":109,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Diamantina Institute, University of Queensland; National Health and Medical Research Council; Medical Research Council; Australian Research Council; University of Queensland; Australian Cancer Research Foundation","keywords":"Multivariate statistics; Overfitting; Computer science; Data mining; Computational biology; DNA microarray; Artificial intelligence; Machine learning; Biology; Gene; Genetics","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":[0.0004744626,0.0002001933,0.0001691005,0.00005040545,0.0003273946,0.0002577644,0.0004062725,0.000191614,0.000007384918],"category_scores_gemma":[0.0003274022,0.0001555081,0.00006865991,0.00004709475,0.00006557583,0.00003260624,0.0004997745,0.0001168374,0.00001685944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002125282,"about_ca_system_score_gemma":0.00006333346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003900558,"about_ca_topic_score_gemma":0.00002682058,"domain_scores_codex":[0.9988134,0.0000247513,0.0003246196,0.0003758597,0.0002088232,0.0002525266],"domain_scores_gemma":[0.9984134,0.000008642294,0.0002817938,0.001029051,0.0001173428,0.0001497722],"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":[0.0001645195,0.00005023303,0.001240857,0.00005730704,0.0000597439,0.000001440787,0.003459154,0.0002178145,0.9786595,0.0003818233,0.001540372,0.01416726],"study_design_scores_gemma":[0.0008788168,0.0001473998,0.01806644,0.00005892134,0.00001381794,0.000008885726,0.002783437,0.003468475,0.9666153,0.0003108237,0.00733797,0.0003097851],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4272137,0.000282809,0.5702626,0.0001060191,0.0002610961,0.0004951203,0.00003412819,0.00001828609,0.001326291],"genre_scores_gemma":[0.8250703,0.00003119709,0.1736016,0.0003411421,0.00006734709,0.00008683111,0.00005278378,0.00001859796,0.0007301535],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3978567,"threshold_uncertainty_score":0.6341437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04099443180788442,"score_gpt":0.4106003870872167,"score_spread":0.3696059552793323,"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."}}