{"id":"W4403793040","doi":"10.1101/2024.10.25.620288","title":"Preprocessing homologous regions in annotated protein sequences concerning machine-learning applications","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Homologous chromosome; Computer science; Protein superfamily; Artificial intelligence; Computational biology; Biology; Genetics; Gene","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007892437,0.0006080645,0.0004771549,0.0003331772,0.0002501685,0.0003286194,0.000735656,0.0007867365,0.00001588874],"category_scores_gemma":[0.0004806136,0.0006550823,0.0001516575,0.0006226037,0.0002400905,0.00001471283,0.00122615,0.002065722,0.00006362448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001601952,"about_ca_system_score_gemma":0.0008390757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001258664,"about_ca_topic_score_gemma":0.00001775042,"domain_scores_codex":[0.9968979,0.0002434937,0.0007696594,0.001174101,0.0003060323,0.0006087564],"domain_scores_gemma":[0.9978671,0.00003131752,0.0005726354,0.001052661,0.0003004289,0.0001758355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004165131,0.0001095374,0.009791714,0.002008786,0.000193224,0.00006961237,0.00007652839,0.008072714,0.978765,0.0007146873,0.0001299355,0.00002659652],"study_design_scores_gemma":[0.001806787,0.0005881123,0.00900348,0.00541982,0.0004046325,0.000001848406,0.00008833801,0.07515173,0.8014185,0.0001659907,0.1007109,0.00523994],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9782414,0.007962459,0.009897856,0.0003744168,0.0003598107,0.002092112,0.0001815057,0.0006355498,0.000254914],"genre_scores_gemma":[0.9869528,0.0002444802,0.01103162,0.0001043224,0.0003538497,0.001052045,0.0000116591,0.0001591687,0.00009003833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1773466,"threshold_uncertainty_score":0.99959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0106041803999528,"score_gpt":0.2411338556201119,"score_spread":0.230529675220159,"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."}}