{"id":"W4411509101","doi":"10.1007/978-981-96-8197-6_18","title":"The Use of Large Language Models to Cluster Genomic Data","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Cluster (spacecraft); Natural language processing; Theoretical computer science; Programming language; Artificial intelligence","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":[0.0005416806,0.0002048135,0.0001868533,0.0001253249,0.0001134549,0.0001127791,0.001966777,0.0001820947,0.000003812679],"category_scores_gemma":[0.0002029625,0.0001501636,0.00004637468,0.00009571508,0.0002049268,0.00001320675,0.003426453,0.0002848782,0.000004746468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002718159,"about_ca_system_score_gemma":0.0002272359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001997195,"about_ca_topic_score_gemma":0.0002652527,"domain_scores_codex":[0.9986581,0.00002217324,0.0003046407,0.000485616,0.0002499269,0.0002795384],"domain_scores_gemma":[0.9977297,0.0001453733,0.0001416706,0.001844645,0.00008861548,0.00005002712],"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":[0.00008764305,0.00003085549,0.0001125166,0.0001613014,0.00007669973,0.000007271773,0.001343783,0.5673842,0.004952693,0.003285266,0.004971719,0.417586],"study_design_scores_gemma":[0.0001836344,0.0001005329,0.00002709745,0.0001394548,0.00001269154,0.000008787491,5.71369e-7,0.8950064,0.001497422,0.001089146,0.1016422,0.0002920286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008440235,0.0003719306,0.9964485,0.0003307803,0.0003485168,0.0002785198,0.0001131721,0.000008862529,0.001255703],"genre_scores_gemma":[0.1521007,0.0003704756,0.8184546,0.01520275,0.0009505546,0.00001205532,0.0007392278,0.00009263357,0.01207703],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.417294,"threshold_uncertainty_score":0.6123494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02440632938278499,"score_gpt":0.2802765917107655,"score_spread":0.2558702623279805,"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."}}