{"id":"W2143801201","doi":"10.1093/bioinformatics/btn463","title":"Improving subcellular localization prediction using text classification and the gene ontology","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Gene ontology; Computer science; Hierarchy; Mechanism (biology); Protein function prediction; Ontology; Function (biology); Artificial intelligence; Data mining; Sequence (biology); Protein sequencing; Information retrieval; Natural language processing; Computational biology; Machine learning; Gene; Protein function; Biology; Peptide sequence; Genetics; 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":[0.0003535359,0.0001425012,0.0001342134,0.00005372347,0.0003621948,0.00003426738,0.000137027,0.000174403,0.000004565366],"category_scores_gemma":[0.0002243639,0.000106063,0.0000469305,0.0000998403,0.0003166257,0.00002212711,0.0000998583,0.0001164378,0.000008673292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000250998,"about_ca_system_score_gemma":0.00006843406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000342579,"about_ca_topic_score_gemma":0.000006019415,"domain_scores_codex":[0.9990371,0.00006193342,0.0004423009,0.0001147339,0.0001579327,0.00018602],"domain_scores_gemma":[0.9992217,0.00002146425,0.0002850642,0.0003259176,0.00009459635,0.0000513023],"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":[0.002537698,0.0004818216,0.3202045,0.002607818,0.0009923095,0.00001752978,0.03297545,0.08160797,0.430546,0.01989461,0.01324378,0.09489053],"study_design_scores_gemma":[0.001029105,0.00007759335,0.002534806,0.000007467267,0.00003193764,0.0002738232,0.0002443019,0.9870752,0.003830434,0.00002212465,0.004739525,0.0001337268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4083447,0.0003031119,0.5896429,0.00009061704,0.0001721613,0.0003378102,0.00001078227,0.00003576375,0.001062106],"genre_scores_gemma":[0.9660963,0.0003938427,0.03246188,0.0004178895,0.0001685895,0.00001221849,0.0002888367,0.00001898612,0.000141405],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9054672,"threshold_uncertainty_score":0.4325122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01576644824510354,"score_gpt":0.2292790754980813,"score_spread":0.2135126272529777,"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."}}