{"id":"W4412163702","doi":"10.1158/1557-3265.aimachine-pr-05","title":"Abstract PR-05: Learning the Language of Somatic Mutations: A Large Language Model Approach to Precision Oncology","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Precision oncology; Somatic cell; Oncology; Medicine; Computational biology; Language model; Natural language processing; Internal medicine; Computer science; Artificial intelligence; Biology; Genetics; Cancer; Gene","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002080503,0.000896115,0.0006775644,0.0007803136,0.0004118903,0.001136397,0.001597664,0.001081826,0.003335639],"category_scores_gemma":[0.005732516,0.0004085092,0.001396922,0.0005872118,0.0005414258,0.001531806,0.001283238,0.002794811,0.0009451538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001325056,"about_ca_system_score_gemma":0.001374125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009736247,"about_ca_topic_score_gemma":0.009766894,"domain_scores_codex":[0.9990847,0.0004117967,0.00003954002,0.0003073185,0.00009985854,0.00005684843],"domain_scores_gemma":[0.9963983,0.002697942,0.0001545462,0.0002887089,0.0003393637,0.0001210576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005082619,0.0003735462,0.004715112,0.0002223607,0.0002813845,0.0003535635,0.000318928,0.6099889,0.005733816,0.0177134,0.02305162,0.3367392],"study_design_scores_gemma":[0.00001386908,0.00003257759,0.000160418,0.00000708528,0.00001347338,0.00002092441,0.00001160639,0.9909616,0.0004966686,0.007647577,0.0006279564,0.000006183746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09125699,0.0009942508,0.8897695,0.00441584,0.0002037588,0.0001513808,0.002347141,0.007580348,0.003280854],"genre_scores_gemma":[0.7638505,0.0004176434,0.2223413,0.001370077,0.0002496854,0.0002389213,0.005031324,0.0004783567,0.006022137],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009736247,"threshold_uncertainty_score":0.01935911,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1381308785094807,"score_gpt":0.5422115612473367,"score_spread":0.404080682737856,"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."}}