{"id":"W3102483160","doi":"10.1101/214494","title":"A deep learning system can accurately classify primary and metastatic cancers based on patterns of passenger mutations","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Cancer Research; University of Toronto; Ontario Institute for Cancer Research","funders":"Nvidia; Silicon Valley Community Foundation","keywords":"Classifier (UML); Somatic cell; Primary tumor; Metastasis; Cancer; Computational biology; Biology; Oncology; Gene; Medicine; Cancer research; Internal medicine; Artificial intelligence; Computer science; Genetics","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":[0.0009663592,0.001179744,0.0004996103,0.0007288706,0.0003168997,0.0009619485,0.0006455203,0.001357779,0.001652768],"category_scores_gemma":[0.002517082,0.0003418784,0.0005969412,0.0003804238,0.0003161145,0.0008371426,0.0007127835,0.001153752,0.001704747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006381125,"about_ca_system_score_gemma":0.0007950861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002983257,"about_ca_topic_score_gemma":0.004097922,"domain_scores_codex":[0.9996362,0.0000472245,0.00002442572,0.0001370694,0.00008434686,0.00007069119],"domain_scores_gemma":[0.9994179,0.0002387061,0.00006211594,0.00009236071,0.0001457362,0.00004322506],"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":[0.0005097781,0.000608199,0.05750921,0.000224108,0.0003274567,0.0004665092,0.0001474064,0.1437868,0.06849696,0.002738822,0.02782814,0.6973566],"study_design_scores_gemma":[0.00003417402,0.000128754,0.01027032,0.00005880919,0.00006100602,0.0002060774,0.00004103406,0.9517152,0.02438989,0.007977596,0.005081274,0.00003589363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4788548,0.002509191,0.4893031,0.003030651,0.000578536,0.0001630435,0.005952427,0.01066584,0.008942425],"genre_scores_gemma":[0.8915374,0.0006294426,0.09351177,0.0008184893,0.0001163732,0.0001220292,0.005671378,0.0001720912,0.007421092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002983257,"threshold_uncertainty_score":0.005931795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01786503802236345,"score_gpt":0.2423380959203044,"score_spread":0.224473057897941,"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."}}