{"id":"W4317911177","doi":"10.1142/s021969132250045x","title":"Calibrating the classifier for protein family prediction with protein sequence using machine learning techniques: An empirical investigation","year":2023,"lang":"en","type":"article","venue":"International Journal of Wavelets Multiresolution and Information Processing","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Classifier (UML); Feature selection; Random forest; Artificial intelligence; Protein family; Computer science; Protein sequencing; Machine learning; Pattern recognition (psychology); Protein structure prediction; Computational biology; Data mining; Protein structure; Peptide sequence; Gene; 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":[0.000849671,0.0001245995,0.00009836674,0.0001962529,0.0002991844,0.0002418429,0.000178669,0.0001044143,0.000001405375],"category_scores_gemma":[0.0004380118,0.00008703042,0.00003697042,0.0001613284,0.0001032481,0.0005149273,0.00005357069,0.0002437645,6.001698e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005391501,"about_ca_system_score_gemma":0.0002087497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001358466,"about_ca_topic_score_gemma":0.000003322531,"domain_scores_codex":[0.9987423,0.00008129524,0.0005602043,0.00009240157,0.0003826765,0.0001411534],"domain_scores_gemma":[0.9983491,0.00001436961,0.0007556042,0.00006982542,0.0007488157,0.00006225105],"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":[0.0007178682,0.00003765495,0.0103482,0.0002395653,0.00009682869,0.000002184515,0.003558754,0.01352541,0.875163,0.0002640597,0.0001284249,0.09591808],"study_design_scores_gemma":[0.0007820853,0.0004935341,0.002420713,0.0003128574,0.00001472753,0.0001522857,0.0008632953,0.9435072,0.03723357,0.00006725529,0.01400139,0.000151088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8395057,0.00002941074,0.1591397,0.000721889,0.00006623608,0.0004061952,0.0000206588,0.0000446391,0.0000655074],"genre_scores_gemma":[0.9434081,0.00001754171,0.05555686,0.0004048235,0.0002308133,0.0000306038,0.0002912885,0.00001416314,0.00004584449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9299818,"threshold_uncertainty_score":0.3548998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03711071404583471,"score_gpt":0.3202827510113445,"score_spread":0.2831720369655097,"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."}}