{"id":"W3186533172","doi":"10.1101/2021.07.27.21261075","title":"Small Patient Datasets Reveal Genetic Drivers of Non-Small Cell Lung Cancer Subtypes Using a Novel Machine Learning Approach","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University of Waterloo; University of Toronto","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Lung cancer; Set (abstract data type); Gene; Computational biology; Bioinformatics; Medicine; Oncology; Biology; 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":[0.002283604,0.0005770469,0.00067099,0.002468588,0.0003799981,0.001206955,0.0009761164,0.0007233229,0.0008472786],"category_scores_gemma":[0.005382476,0.0002412972,0.001196712,0.001643993,0.0003809934,0.0004514434,0.00075574,0.0009107427,0.0002515357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000483158,"about_ca_system_score_gemma":0.0007227407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001832133,"about_ca_topic_score_gemma":0.003377097,"domain_scores_codex":[0.9987199,0.000558847,0.0001175225,0.0003600519,0.0001608545,0.00008279077],"domain_scores_gemma":[0.9954006,0.003352092,0.0004713025,0.0004266684,0.0002191953,0.0001302225],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001211986,0.0008965306,0.6992267,0.0004128749,0.001583709,0.001112434,0.0002949985,0.07848334,0.02666953,0.001839511,0.003044443,0.1852239],"study_design_scores_gemma":[0.0001399634,0.0004511582,0.1929169,0.00006174234,0.0004897997,0.0009686953,0.0003494259,0.7810772,0.01101924,0.00840301,0.004056737,0.00006602379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8540591,0.001531049,0.1342418,0.0015646,0.00006163641,0.0002893739,0.0060557,0.0007717251,0.001425067],"genre_scores_gemma":[0.9377478,0.0001837114,0.0567235,0.0002129387,0.00008043893,0.0001508223,0.004500122,0.00002740727,0.000373183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002468588,"threshold_uncertainty_score":0.01207697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01870016543345622,"score_gpt":0.2422550356623732,"score_spread":0.223554870228917,"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."}}