{"id":"W3048417086","doi":"10.1016/j.csbj.2020.08.005","title":"An integrative deep learning framework for classifying molecular subtypes of breast cancer","year":2020,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"Research Institute in Oncology and Hematology; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Manitoba Medical Service Foundation","keywords":"Deep learning; Artificial intelligence; Breast cancer; Computer science; Machine learning; Artificial neural network; Concatenation (mathematics); Cluster analysis; Deep neural networks; Cancer; Medicine; Internal medicine; Mathematics","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":[0.00004227107,0.00009806125,0.0001185687,0.000047316,0.0001406598,0.00002129193,0.0001271068,0.0001944204,0.00001509356],"category_scores_gemma":[0.00005631187,0.00007693887,0.0000493816,0.00008645021,0.0001260147,0.000007808853,0.00003140621,0.0002364573,1.45916e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008475918,"about_ca_system_score_gemma":0.00005213663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.480068e-7,"about_ca_topic_score_gemma":6.590236e-7,"domain_scores_codex":[0.9994174,0.00003800685,0.0001677893,0.0001967586,0.00007511023,0.0001049601],"domain_scores_gemma":[0.9995486,0.00001400393,0.0001604783,0.00005012432,0.0001518976,0.0000749664],"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":[0.0002509351,0.000007316823,0.003618755,0.00001866082,0.00007295826,0.00000113984,0.0001837696,0.01124735,0.8837708,0.009812816,0.00005832691,0.09095713],"study_design_scores_gemma":[0.00225976,0.002117532,0.08431257,0.0001545757,0.00009757234,0.0005767451,0.003265424,0.150924,0.6508253,0.1016671,0.003078649,0.0007206933],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6292114,0.00093704,0.365506,0.004201889,0.00006065067,0.00005537231,0.00001483156,0.000009510892,0.000003329568],"genre_scores_gemma":[0.9768934,0.0001998849,0.02241276,0.0003156648,0.0001282021,0.000005646104,0.00003351066,0.00000825248,0.000002661943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.347682,"threshold_uncertainty_score":0.3137476,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01034779644510691,"score_gpt":0.2895754871530358,"score_spread":0.2792276907079289,"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."}}