{"id":"W4385273941","doi":"10.37349/emed.2023.00153","title":"Small patient datasets reveal genetic drivers of non-small cell lung cancer subtypes using machine learning for hypothesis generation","year":2023,"lang":"en","type":"article","venue":"Exploration of Medicine","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; University of Waterloo; University of Toronto","funders":"","keywords":"Computational biology; Gene; Lung cancer; Set (abstract data type); Machine learning; Biology; Computer science; Bioinformatics; Medicine; Oncology; 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":[0.007832002,0.001142952,0.0009995607,0.003113346,0.0005017811,0.001220696,0.001438759,0.001067125,0.001417441],"category_scores_gemma":[0.02284487,0.0004187785,0.001952258,0.001685324,0.000821748,0.0007983765,0.001390429,0.00185106,0.00037411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006866018,"about_ca_system_score_gemma":0.00119629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001252231,"about_ca_topic_score_gemma":0.001664334,"domain_scores_codex":[0.9966653,0.002040552,0.0002320487,0.0006631874,0.0003002988,0.00009853599],"domain_scores_gemma":[0.9705254,0.02653706,0.001130984,0.001185606,0.00041875,0.0002021556],"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":[0.001739199,0.001103075,0.1758936,0.001525622,0.002062088,0.001354798,0.0007334336,0.3826597,0.01741681,0.004800205,0.006079224,0.4046323],"study_design_scores_gemma":[0.0001211322,0.0003002363,0.01511477,0.00006631125,0.0001923396,0.0002415832,0.0001490902,0.9611836,0.005108571,0.01561192,0.001873473,0.00003693907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3309133,0.002092578,0.6540053,0.002072424,0.00009680579,0.0006246265,0.006783879,0.00239207,0.001018929],"genre_scores_gemma":[0.746632,0.0002847868,0.2434246,0.0003293251,0.0001218696,0.0006834019,0.008138704,0.00007275937,0.0003125757],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007832002,"threshold_uncertainty_score":0.0414201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04868581669212042,"score_gpt":0.2768693298058275,"score_spread":0.228183513113707,"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."}}