{"id":"W3216448540","doi":"10.1038/s41586-021-04278-5","title":"Multi-omic machine learning predictor of breast cancer therapy response","year":2021,"lang":"en","type":"article","venue":"Nature","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":642,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Trinity College, University of Cambridge; Medical Research Council; National Institute for Health and Care Research; University of Cambridge; Cancer Research UK; Cancer Research UK Cambridge Institute, University of Cambridge; NIHR Cambridge Biomedical Research Centre; Wellcome Trust","keywords":"Breast cancer; Medicine; Transcriptome; Disease; Oncology; Cancer; Digital pathology; Machine learning; Internal medicine; Bioinformatics; Pathology; Computer science; Biology","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":[0.00009403769,0.00009036016,0.0001037044,0.00001849433,0.00003430376,0.000009652457,0.00009428171,0.0004837519,0.00009043314],"category_scores_gemma":[0.0001441218,0.00008375556,0.00007039435,0.00006781713,0.00002812298,0.000001136155,0.00006248487,0.000454012,0.000001271457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001603669,"about_ca_system_score_gemma":0.000218339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004181529,"about_ca_topic_score_gemma":0.0001231939,"domain_scores_codex":[0.999445,0.00005595355,0.0001015538,0.0002036641,0.00007679412,0.0001170014],"domain_scores_gemma":[0.9995338,0.00002635085,0.00005618404,0.0001936914,0.0001464982,0.0000434324],"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":[0.0009159317,0.00006147686,0.01924028,0.000008728916,0.00005732578,0.000007013929,0.00004613162,0.0002436556,0.9745765,0.000008812051,0.002771185,0.002062979],"study_design_scores_gemma":[0.001958143,0.0001377276,0.1535229,0.00002690191,0.00001700131,0.00003670018,0.00003741662,0.0003718823,0.5804486,0.000009371644,0.2632483,0.0001849998],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9644289,0.03364787,0.0000560135,0.0009809023,0.0002613518,0.00006177769,0.000506538,0.000006256625,0.00005040421],"genre_scores_gemma":[0.9902275,0.006759075,0.0004180962,0.0009561688,0.0002272841,0.000007982952,0.0001390296,0.00001971674,0.001245103],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3941278,"threshold_uncertainty_score":0.3731138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005727007160292818,"score_gpt":0.262274046546969,"score_spread":0.2565470393866761,"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."}}