{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004104051,0.001135426,0.001065626,0.00257499,0.001236094,0.002847645,0.00209099,0.001011935,0.002641804],"category_scores_gemma":[0.01496386,0.0009919769,0.002694369,0.003354842,0.001274783,0.003860938,0.002087433,0.00292203,0.002225818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001372596,"about_ca_system_score_gemma":0.001591937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009305673,"about_ca_topic_score_gemma":0.01336828,"domain_scores_codex":[0.9981033,0.0009687108,0.0001266161,0.000370239,0.0003351864,0.0000959869],"domain_scores_gemma":[0.9857019,0.01133641,0.0003266059,0.001537886,0.0008975434,0.0001996342],"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":[0.0003716095,0.000290345,0.003905623,0.0003435587,0.0004996036,0.0005011951,0.000758507,0.2357528,0.005728524,0.08230804,0.03278212,0.636758],"study_design_scores_gemma":[0.00001394275,0.00001784274,0.0002674578,0.00001729208,0.00003313296,0.00005844019,0.00005148424,0.889345,0.001366585,0.1047538,0.004050799,0.00002413411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004076847,0.0004014974,0.9904568,0.0003738671,0.0001000119,0.00003796122,0.000486159,0.003181051,0.0008859652],"genre_scores_gemma":[0.1183954,0.0007682088,0.8681142,0.0004686695,0.0002513263,0.0003225954,0.004901321,0.001751649,0.005026595],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009305673,"threshold_uncertainty_score":0.02170455,"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."}}