{"id":"W3005188734","doi":"10.1038/s41467-019-13825-8","title":"A deep learning system accurately classifies primary and metastatic cancers using passenger mutation patterns","year":2020,"lang":"en","type":"article","venue":"Nature Communications","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":238,"is_retracted":false,"has_abstract":true,"ca_institutions":"SickKids Foundation; BC Cancer Agency; University of British Columbia; Prostate Cancer Canada; Université de Montréal; Hospital for Sick Children; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; University of Calgary; Princess Margaret Cancer Centre; Simon Fraser University; University of Ottawa; McGill University; McGill University and Génome Québec Innovation Centre; Toronto General Hospital; University of Toronto; University Health Network; Genome Canada; Canada's Michael Smith Genome Sciences Centre; Vector Institute; Institute of Cancer Research; Ontario Institute for Cancer Research","funders":"National Institute of Environmental Health Sciences; Hrvatska Zaklada za Znanost; National Cancer Institute; Cancer Research UK; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Francis Crick Institute; Nvidia; European Commission; Silicon Valley Community Foundation","keywords":"Somatic cell; Classifier (UML); Genome; Computational biology; DNA sequencing; Primary tumor; Cancer; Biology; Metastasis; Gene; Bioinformatics; Cancer research; Genetics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006959362,0.00009963581,0.0001135451,0.00002277447,0.0001923758,0.00005167785,0.0002302949,0.0001124794,0.000001807572],"category_scores_gemma":[0.0001454703,0.0001037289,0.00003645759,0.00008551381,0.00005247369,0.000006342746,0.0002315932,0.0003150537,0.000001303392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006832943,"about_ca_system_score_gemma":0.0001012437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000048773,"about_ca_topic_score_gemma":0.0003289219,"domain_scores_codex":[0.9994036,0.00009214271,0.0001487446,0.0001793812,0.00006777843,0.0001083538],"domain_scores_gemma":[0.9993007,0.00007597051,0.000101047,0.0003594898,0.00009200312,0.00007083535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004106901,0.000203555,0.05662503,0.001891408,0.001383344,0.00004655723,0.006528056,0.03456617,0.8398024,0.01047312,0.005002369,0.04306728],"study_design_scores_gemma":[0.004816079,0.001048968,0.07565589,0.0004986496,0.001270156,0.0003053284,0.0201671,0.6142799,0.03245673,0.0001094483,0.2469073,0.00248437],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9321004,0.0437615,0.01907523,0.003090522,0.0001945548,0.000448208,0.00009606523,0.00005866323,0.001174838],"genre_scores_gemma":[0.9918172,0.00252557,0.004387577,0.0008089768,0.00008146615,0.00002241327,0.0003296172,0.00001852455,0.000008627556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8073457,"threshold_uncertainty_score":0.422994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04179888497081934,"score_gpt":0.3066536343427133,"score_spread":0.264854749371894,"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."}}