{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007939746,0.003052964,0.00285962,0.006533224,0.001217324,0.002258032,0.00323925,0.001672757,0.02172057],"category_scores_gemma":[0.002686106,0.001065496,0.001355768,0.008036752,0.0003977705,0.003082542,0.002434626,0.001614091,0.03552193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007670328,"about_ca_system_score_gemma":0.001851895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002091134,"about_ca_topic_score_gemma":0.002785875,"domain_scores_codex":[0.9995394,0.00006237693,0.00005859133,0.0001139284,0.0001487628,0.00007706461],"domain_scores_gemma":[0.9991019,0.0001983955,0.0002072016,0.0001978563,0.0001469316,0.0001477354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.005007193,0.000466853,0.004514051,0.007946465,0.0004588479,0.002227195,0.0005136118,0.00327845,0.1527451,0.009713309,0.7149047,0.09822422],"study_design_scores_gemma":[0.0007171611,0.0003783021,0.01207626,0.0005468884,0.0003353319,0.002918461,0.0002733472,0.01675614,0.05518678,0.01358466,0.8969429,0.0002837827],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"software","genre_scores_codex":[0.02323746,0.004379123,0.05100923,0.0004626888,0.0003014687,0.0003841813,0.7724392,0.1361577,0.01162886],"genre_scores_gemma":[0.01756701,0.001865014,0.04193726,0.0001298096,0.00005706137,0.0004779654,0.9312389,0.004458534,0.002268415],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.02172057,"threshold_uncertainty_score":0.07266253,"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."}}