{"id":"W4406259803","doi":"10.1109/bibm62325.2024.10822432","title":"Gene function prediction using an AnnoTree-based genomic language model","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University; University of Waterloo","funders":"","keywords":"Computer science; Function (biology); Language model; Artificial intelligence; Natural language processing; Computational biology; Biology; 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":[0.0001374074,0.0001020411,0.00005565519,0.00005373741,0.00005468573,0.00005587189,0.00007312852,0.0001094493,0.00004359589],"category_scores_gemma":[0.00001079912,0.00009272217,0.00004695217,0.00005814146,0.00001899733,0.000008447889,0.00003187427,0.00008598401,0.00001590878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002340237,"about_ca_system_score_gemma":0.00008198112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002481194,"about_ca_topic_score_gemma":0.00001417672,"domain_scores_codex":[0.9994338,0.00002296173,0.0001411571,0.0001884645,0.00008304259,0.0001306307],"domain_scores_gemma":[0.999666,0.000002885767,0.000024344,0.0002375808,0.00002064379,0.00004849285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002445621,0.0000160552,0.0002814585,0.00002985594,0.00001797761,9.693026e-7,0.00005713414,0.3001204,0.6971544,0.00003455463,0.0003592913,0.001903384],"study_design_scores_gemma":[0.0001321989,0.0001448922,0.0002525655,0.000006450714,0.00002507192,0.000009651855,0.00003439078,0.9409277,0.05696528,0.00001749846,0.001383415,0.0001009094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5849841,0.000168797,0.4134537,0.00001735855,0.0001235916,0.00006143627,0.00002239476,0.00007485997,0.001093778],"genre_scores_gemma":[0.9784778,0.000006175685,0.01966145,0.0002863847,0.0002668909,0.000004357427,0.0006027251,0.00002499441,0.0006692025],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6408072,"threshold_uncertainty_score":0.37811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01251341949451856,"score_gpt":0.2651069880560296,"score_spread":0.2525935685615111,"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."}}