{"id":"W4327747318","doi":"10.1038/s41591-023-02221-x","title":"Diagnostic classification of childhood cancer using multiscale transcriptomics","year":2023,"lang":"en","type":"article","venue":"Nature Medicine","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Sinai Health System; Princess Margaret Cancer Centre; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; SickKids Foundation; University of Toronto; Hospital for Sick Children","funders":"Garron Family Cancer Centre; Ontario Ministry of Research and Innovation; St. Baldrick's Foundation; Canadian Institutes of Health Research; Hospital for Sick Children; V Foundation for Cancer Research","keywords":"Childhood cancer; Optimal distinctiveness theory; Computational biology; Cancer; Transcriptome; Classifier (UML); Bioinformatics; Oncology; Medicine; Biology; Artificial intelligence; Computer science; Internal medicine; Genetics; Psychology; Gene expression; Gene","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":[0.000123698,0.0001068111,0.0001584945,0.0000708869,0.00003785984,0.000002870709,0.0001244127,0.0002342542,0.00004093308],"category_scores_gemma":[0.0005320035,0.00009299204,0.00004773522,0.0002314458,0.00009442012,0.000001606802,0.00002738452,0.0001586352,0.000003605082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002000146,"about_ca_system_score_gemma":0.0000821874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008246598,"about_ca_topic_score_gemma":0.0001038315,"domain_scores_codex":[0.9992789,0.00001599358,0.0001939134,0.0002187855,0.0001368638,0.0001555112],"domain_scores_gemma":[0.999462,0.00007628901,0.00008257756,0.0002254773,0.00009345866,0.00006021643],"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":[0.00003074646,0.00004224675,0.01142787,0.00004115683,0.00004549734,0.000002819835,0.0001913371,0.0002177226,0.972743,0.0001121609,0.01088047,0.004265016],"study_design_scores_gemma":[0.003678597,0.0004941352,0.5883734,0.0003654313,0.0002749933,0.00001721328,0.0005110695,0.002592959,0.3090629,0.0003368362,0.09382448,0.0004680447],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9897716,0.007323822,0.0004016032,0.001034239,0.0007982092,0.000187215,0.00009407548,0.00001433041,0.0003748941],"genre_scores_gemma":[0.9941834,0.00407071,0.0001670569,0.0003830248,0.0007655912,0.00001609313,0.0002427793,0.00002213288,0.0001492331],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6636801,"threshold_uncertainty_score":0.3792105,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01520289199090626,"score_gpt":0.3064505224690396,"score_spread":0.2912476304781334,"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."}}