{"id":"W3043189602","doi":"10.1038/s41598-020-68858-7","title":"Inferring disease subtypes from clusters in explanation space","year":2020,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital","funders":"Medical Research Council","keywords":"Classifier (UML); Cluster analysis; Computer science; Artificial intelligence; Biobank; Identification (biology); Machine learning; Disease; Computational biology; Data mining; Pattern recognition (psychology); Bioinformatics; Biology; Medicine","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":[0.0001417222,0.00006229897,0.00005349406,0.00003981201,0.00005157095,0.00006581433,0.00006880497,0.00003663876,0.0000372543],"category_scores_gemma":[0.000133681,0.00006098229,0.00003085345,0.0001541749,0.00003556354,0.000006819213,0.00005181408,0.00003594894,0.000008766572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001161067,"about_ca_system_score_gemma":0.00009035342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001446028,"about_ca_topic_score_gemma":0.00003123102,"domain_scores_codex":[0.9990808,0.00002592047,0.0001688267,0.0004700132,0.0001548776,0.0000995892],"domain_scores_gemma":[0.9994429,0.000002463151,0.00009143919,0.0003037557,0.00003552095,0.0001239042],"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":[0.00004170362,0.00001981397,0.0636835,0.00000786491,0.000004088167,0.00003219332,0.0002070128,0.0007125105,0.9172709,0.00001375653,0.01692064,0.001086009],"study_design_scores_gemma":[0.000388178,0.00003085872,0.08779397,0.00004114106,0.00001273324,0.000003564517,0.000425812,0.002020533,0.4989772,0.0009024434,0.4090903,0.0003132468],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9951605,0.0002876283,0.001439712,0.001266168,0.001085931,0.0001085117,0.000002544619,0.00001315556,0.0006358904],"genre_scores_gemma":[0.9987764,0.00001048432,0.0001295218,0.0001914378,0.0001012955,0.00001417793,0.0002772961,0.000006585517,0.0004927623],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4182937,"threshold_uncertainty_score":0.2486786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01734074709196928,"score_gpt":0.2482250143554381,"score_spread":0.2308842672634689,"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."}}