{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001443475,0.0001002062,0.0001629436,0.00008003683,0.00005360764,0.000003764479,0.00007467716,0.00006237592,0.00001050227],"category_scores_gemma":[0.0001651537,0.00009601627,0.00003814628,0.0001088554,0.00004620693,0.000004992948,0.00004271244,0.00003604525,5.56312e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001996626,"about_ca_system_score_gemma":0.0000865979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002343723,"about_ca_topic_score_gemma":0.0002634789,"domain_scores_codex":[0.999266,0.00002925309,0.0002908891,0.000198271,0.00009823352,0.0001174026],"domain_scores_gemma":[0.9993823,0.00004391969,0.0002333008,0.0001638444,0.0001337631,0.00004286964],"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":[0.00006086772,0.00002220911,0.003134379,0.000118197,0.000031077,8.83978e-7,0.0004661476,0.05238448,0.9352455,0.000004894546,0.004565525,0.003965866],"study_design_scores_gemma":[0.001765034,0.0009033227,0.001257684,0.00009993903,0.0001599944,9.360917e-7,0.0003890703,0.1127259,0.8749272,0.00002997666,0.007551166,0.0001898542],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9754273,0.001318344,0.02208877,0.000273667,0.0002861789,0.0003430425,0.000242581,0.000005438748,0.00001468427],"genre_scores_gemma":[0.9885751,0.00285918,0.005539954,0.0001125623,0.0005090542,0.00004958362,0.002258233,0.00002522968,0.0000710736],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06034138,"threshold_uncertainty_score":0.391543,"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."}}