{"id":"W2164620224","doi":"10.1093/bioinformatics/btm115","title":"SherLoc: high-accuracy prediction of protein subcellular localization by integrating text and protein sequence data","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":127,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sequence (biology); Protein sequencing; Artificial intelligence; Computational biology; Protein subcellular localization prediction; Data mining; Pattern recognition (psychology); Peptide sequence; Biology; Genetics; Gene","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":[0.001070518,0.0001998337,0.0001749212,0.00006875397,0.0001254872,0.00005264568,0.0003783803,0.0002136502,0.00001049287],"category_scores_gemma":[0.0009825751,0.0001804632,0.00002548696,0.00016855,0.0001504589,0.00006826115,0.0003090237,0.0001992147,0.000004310628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002310734,"about_ca_system_score_gemma":0.00007184323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006749696,"about_ca_topic_score_gemma":0.00001510447,"domain_scores_codex":[0.9984665,0.00004297691,0.0007794937,0.0001846281,0.0002705635,0.0002558643],"domain_scores_gemma":[0.9985701,0.00002576373,0.0004933398,0.0006863225,0.0001349817,0.00008941843],"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":[0.0001509318,0.0001200351,0.005353782,0.001747429,0.0001081649,0.00000183296,0.001376343,0.0002810404,0.9125117,0.001145522,0.004378585,0.07282461],"study_design_scores_gemma":[0.001125617,0.0008396425,0.0004412004,0.0003712785,0.00004562359,0.00003975186,0.001217991,0.4934039,0.4311437,0.00007527509,0.07076634,0.0005296674],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3825758,0.0002390887,0.6151128,0.00004481961,0.00006038992,0.0007799867,0.0002698641,0.0000407454,0.0008764815],"genre_scores_gemma":[0.8742926,0.00006316589,0.1214126,0.00009452315,0.00008244013,0.00001338955,0.003749633,0.00002696057,0.000264728],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4937002,"threshold_uncertainty_score":0.7359077,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01554791924248027,"score_gpt":0.2587434904356499,"score_spread":0.2431955711931696,"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."}}