{"id":"W2151790371","doi":"10.1093/bioinformatics/btg447","title":"Predicting subcellular localization of proteins using machine-learned classifiers","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":334,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Subcellular localization; Computer science; Artificial intelligence; Protein subcellular localization prediction; Machine learning; Computational biology; Pattern recognition (psychology); Chemistry; Biology; Biochemistry; Cytoplasm; Gene","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":[0.0003133821,0.0001994204,0.0001947118,0.0001035948,0.0001316998,0.00003310751,0.0002402075,0.0002159689,0.00001120961],"category_scores_gemma":[0.0002852633,0.0001886611,0.0001000356,0.0002058024,0.0001203016,0.00002319544,0.0001418608,0.0001553448,0.00001122326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004844045,"about_ca_system_score_gemma":0.0001683179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007791262,"about_ca_topic_score_gemma":0.00001987182,"domain_scores_codex":[0.9986153,0.0000298008,0.0006653707,0.0001263482,0.000288357,0.00027481],"domain_scores_gemma":[0.9989064,0.000007718168,0.0004562255,0.0004107606,0.000127815,0.00009113401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003232186,0.000387831,0.1186998,0.002958801,0.0004150221,0.000006481164,0.006011193,0.6570231,0.2049209,0.003479333,0.000292383,0.005481977],"study_design_scores_gemma":[0.001456546,0.0004485492,0.0002555183,0.0001440167,0.00005335089,0.00005091455,0.0006580178,0.7999644,0.1916935,0.0001321311,0.004751978,0.0003911357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.437516,0.0001175454,0.5592595,0.00004396578,0.0001404,0.0004145683,0.00002508152,0.00004635561,0.002436504],"genre_scores_gemma":[0.8751088,0.0000510268,0.1242062,0.0001646685,0.00008801662,0.000006408234,0.0002699748,0.00003352679,0.00007132959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4375928,"threshold_uncertainty_score":0.7693377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01636032850905748,"score_gpt":0.2565539395148381,"score_spread":0.2401936110057807,"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."}}