{"id":"W2147335610","doi":"10.1093/nar/gki120","title":"PA-GOSUB: a searchable database of model organism protein sequences with their predicted Gene Ontology molecular function and subcellular localization","year":2004,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gene ontology; Biology; Proteome; Annotation; Function (biology); Subcellular localization; Computational biology; Model organism; Gene; Gene Annotation; Ontology; Database; Organism; Genome; Bioinformatics; Genetics; Computer science; Gene expression","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0007615407,0.0001624937,0.0001704559,0.0001444756,0.0001721109,0.00003395459,0.0002599872,0.0002058549,0.00002170187],"category_scores_gemma":[0.0001866704,0.000130719,0.00002647742,0.0003235753,0.0005123601,0.00002077198,0.0002657131,0.0003307291,0.000003563018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004281854,"about_ca_system_score_gemma":0.0003600575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000151776,"about_ca_topic_score_gemma":0.00004246754,"domain_scores_codex":[0.9983162,0.0001899303,0.0002445425,0.0003553558,0.0004957959,0.0003981699],"domain_scores_gemma":[0.9988698,0.00001223555,0.00008309104,0.000496095,0.0004136608,0.0001250919],"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":[0.0003163327,0.00008081163,0.001857806,0.0002157721,0.0000580275,0.000008375213,0.0002880426,0.0170479,0.9782842,0.001510873,0.00002854689,0.000303315],"study_design_scores_gemma":[0.001447631,0.002005929,0.0003839082,0.00009335284,0.00001722756,0.00004893399,0.0003214749,0.1143404,0.8787162,0.002000765,0.0004085135,0.0002157314],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7092549,0.0002172345,0.2895895,0.0001540744,0.000008010255,0.0004419826,0.0000321001,0.00001858209,0.0002836124],"genre_scores_gemma":[0.9854753,0.0001052556,0.01375,0.00005566999,0.00002968469,0.00004094609,0.0003749121,0.00003602395,0.0001321987],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2762204,"threshold_uncertainty_score":0.5330565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02075630728152151,"score_gpt":0.2810518104991162,"score_spread":0.2602955032175946,"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."}}