{"id":"W4411115338","doi":"10.1101/2025.06.05.658154","title":"Breast Cancer Clustering Integrating Complete Gene Expression Profiles and Genetic Ancestry","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill Genome Centre","funders":"","keywords":"Cluster analysis; Cancer; Breast cancer; Gene; Genetics; Computational biology; Biology; Expression (computer science); Gene expression; Bioinformatics; Oncology; Medicine; Computer science; Artificial intelligence","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":[0.0005500842,0.0004943656,0.0006412129,0.001176602,0.0003599039,0.0009050472,0.0002749921,0.000321351,0.0008962833],"category_scores_gemma":[0.001264736,0.0001563901,0.0006145666,0.001191018,0.0002437954,0.0001859417,0.00057377,0.0003591168,0.0006695272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003810081,"about_ca_system_score_gemma":0.0004726068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003445043,"about_ca_topic_score_gemma":0.003088155,"domain_scores_codex":[0.9995912,0.00008388846,0.00001656116,0.000173326,0.00007967336,0.00005533664],"domain_scores_gemma":[0.9996494,0.0001223538,0.00004567187,0.00007703393,0.00007876138,0.00002683411],"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":[0.001355062,0.0002199843,0.193919,0.0006469281,0.001160414,0.0006608739,0.0006871051,0.1317038,0.4509764,0.004532771,0.01395625,0.2001815],"study_design_scores_gemma":[0.00005319027,0.0001627441,0.2557008,0.00007937369,0.000396283,0.0006709989,0.0004895701,0.62845,0.07807306,0.01802289,0.01779422,0.000106891],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8372473,0.001343408,0.1451948,0.0003790871,0.00006276093,0.00008834039,0.01123627,0.001826873,0.002621121],"genre_scores_gemma":[0.9156972,0.0004311017,0.0666315,0.00009929527,0.00003818096,0.00008651723,0.01536552,0.0002575597,0.001393119],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003445043,"threshold_uncertainty_score":0.006849945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01939261941542887,"score_gpt":0.2545343668490302,"score_spread":0.2351417474336014,"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."}}