{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002007649,0.001450935,0.0009944419,0.008045859,0.000565708,0.001253851,0.001118716,0.001126711,0.002855836],"category_scores_gemma":[0.01288191,0.0001940471,0.0009324187,0.006514451,0.0003617483,0.002703257,0.0007931159,0.001004739,0.002414657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005435321,"about_ca_system_score_gemma":0.001117004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003968887,"about_ca_topic_score_gemma":0.003404722,"domain_scores_codex":[0.9987503,0.0002881712,0.0002188842,0.0002438811,0.0004203841,0.00007834631],"domain_scores_gemma":[0.9877203,0.007587499,0.001231655,0.0005773404,0.002635563,0.000247623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009998189,0.000853808,0.04836559,0.001583748,0.0002391401,0.001003082,0.0002301733,0.02292502,0.05116407,0.001836316,0.0326584,0.8381408],"study_design_scores_gemma":[0.0003443963,0.0004985646,0.03478719,0.0002517288,0.0004897107,0.001057686,0.0004602916,0.8528111,0.07986943,0.01282649,0.01647674,0.0001266328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4635204,0.004625105,0.4768006,0.003845023,0.0006214717,0.0007719322,0.02144562,0.02108695,0.007283011],"genre_scores_gemma":[0.5031049,0.001775401,0.4554005,0.0004888122,0.0006628499,0.0004296032,0.03456951,0.0003276881,0.003240729],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008045859,"threshold_uncertainty_score":0.01061761,"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."}}