{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003479529,0.00008771374,0.0002279153,0.00008187655,0.0001455506,0.00001856344,0.0004653893,0.000273239,0.00002889924],"category_scores_gemma":[0.00438204,0.00005800396,0.0001050661,0.0002720921,0.0003515655,0.000002255582,0.0003786887,0.0006185575,0.00001229483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003281685,"about_ca_system_score_gemma":0.0004993444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001207206,"about_ca_topic_score_gemma":0.000128545,"domain_scores_codex":[0.9981484,0.0004609738,0.0004138974,0.0003514959,0.0002894549,0.0003357732],"domain_scores_gemma":[0.9985757,0.0007248069,0.0000728712,0.0003887933,0.0001481697,0.00008969491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001160482,0.001576034,0.005081579,0.0004586439,0.0003074183,0.00001499487,0.006545336,0.00355234,0.1129492,0.0006220755,0.0454729,0.822259],"study_design_scores_gemma":[0.01569827,0.009147179,0.1153553,0.001797854,0.0003283793,0.00002353476,0.1310504,0.1215401,0.1218414,0.005181178,0.4762166,0.001819848],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9804657,0.003480406,0.006192497,0.001756304,0.0001192114,0.0004334134,0.00002715075,0.00002013757,0.007505154],"genre_scores_gemma":[0.9931019,0.0002808697,0.002408474,0.000357547,0.000133537,0.00017029,0.00003572503,0.00001063671,0.003501029],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8204392,"threshold_uncertainty_score":0.5246028,"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."}}