{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001772015,0.001758799,0.0009770418,0.005406751,0.0005387202,0.001142384,0.001440819,0.001533326,0.003545513],"category_scores_gemma":[0.006913758,0.0003171204,0.0007025228,0.003367528,0.0003888097,0.002176547,0.001348807,0.0008123473,0.004256485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005050951,"about_ca_system_score_gemma":0.0007353626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001802921,"about_ca_topic_score_gemma":0.003486579,"domain_scores_codex":[0.9992455,0.0001821913,0.0000674243,0.0002309927,0.0002206871,0.00005312826],"domain_scores_gemma":[0.9950516,0.00267356,0.0006706187,0.0006248266,0.0007522199,0.0002272328],"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":[0.002418383,0.0006540655,0.06667293,0.002154649,0.0006075591,0.001300796,0.000273539,0.08322464,0.04676523,0.002449909,0.1727264,0.620752],"study_design_scores_gemma":[0.0002471506,0.0003644378,0.0162793,0.00008558876,0.00013358,0.001008239,0.0001248814,0.9176593,0.03986145,0.006826465,0.01730588,0.0001038025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3314142,0.004545487,0.416853,0.001622726,0.000380685,0.0003560547,0.08941814,0.1512052,0.00420453],"genre_scores_gemma":[0.4526826,0.001091543,0.4055614,0.0003850624,0.0002640551,0.000383117,0.133903,0.001559681,0.004169591],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005406751,"threshold_uncertainty_score":0.01186097,"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."}}