{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00785648,0.001423333,0.001223014,0.002613795,0.001526752,0.002797188,0.002346137,0.001457061,0.005483865],"category_scores_gemma":[0.02807064,0.0007864116,0.001000471,0.003173791,0.0009296435,0.002948689,0.002563233,0.002210724,0.004638798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009462021,"about_ca_system_score_gemma":0.00244827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001163639,"about_ca_topic_score_gemma":0.001434488,"domain_scores_codex":[0.9956211,0.001170031,0.000628962,0.0009547134,0.001384702,0.0002405054],"domain_scores_gemma":[0.9768877,0.009069523,0.002210187,0.008402918,0.003079388,0.0003503239],"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":[0.006511937,0.0006334708,0.05233374,0.005873263,0.0005066249,0.00308607,0.003200225,0.02631329,0.4001335,0.02063396,0.09293208,0.3878418],"study_design_scores_gemma":[0.0001736938,0.0003542496,0.02031155,0.0005918198,0.0002168294,0.001428622,0.001145898,0.1926418,0.625689,0.03350856,0.1237348,0.0002031521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2332059,0.002342984,0.5730717,0.001876233,0.0007160243,0.0009366956,0.03412247,0.1467265,0.007001467],"genre_scores_gemma":[0.3971934,0.0006355538,0.5287963,0.0008516678,0.0001546802,0.00066294,0.06024627,0.009032043,0.002427113],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00785648,"threshold_uncertainty_score":0.0415495,"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."}}