{"id":"W4406018731","doi":"10.1016/j.ccell.2024.12.002","title":"Classification of non-TCGA cancer samples to TCGA molecular subtypes using compact feature sets","year":2025,"lang":"en","type":"article","venue":"Cancer Cell","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; Eisai; National Cancer Institute; National Institutes of Health; Boston Scientific Corporation; Gilead Sciences; Pfizer","keywords":"Biology; Cancer research; Feature (linguistics); Computational biology; Oncology; Internal medicine; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00331227,0.0009490575,0.00112909,0.003965964,0.0007489031,0.002299836,0.001557558,0.0009015976,0.005458915],"category_scores_gemma":[0.0149376,0.0004894974,0.001596592,0.003843135,0.0004821996,0.001829933,0.002155512,0.001255272,0.003310835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001631906,"about_ca_system_score_gemma":0.002105067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01240043,"about_ca_topic_score_gemma":0.014956,"domain_scores_codex":[0.9976764,0.0004042061,0.0003218444,0.0006305405,0.0007423542,0.0002246198],"domain_scores_gemma":[0.9901702,0.003607143,0.0005717059,0.003651247,0.00173542,0.0002644218],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002495392,0.0009280787,0.2667906,0.0009990305,0.001036293,0.0008577326,0.0006588486,0.04707083,0.01958343,0.009378855,0.2029506,0.4472504],"study_design_scores_gemma":[0.001055198,0.0006886241,0.2117661,0.0006430611,0.0008321802,0.001650019,0.00112001,0.4757624,0.06409278,0.04373597,0.1982635,0.0003901341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5000309,0.002652194,0.1616505,0.003535343,0.0006559012,0.0006921255,0.2893825,0.02674125,0.01465938],"genre_scores_gemma":[0.5477715,0.0006826561,0.1170888,0.000646755,0.0001218467,0.001017152,0.3267823,0.0017472,0.00414184],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01240043,"threshold_uncertainty_score":0.02465647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02152446678870231,"score_gpt":0.3587207373482867,"score_spread":0.3371962705595844,"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."}}