{"id":"W1997967533","doi":"10.1021/pr900665y","title":"SherLoc2: A High-Accuracy Hybrid Method for Predicting Subcellular Localization of Proteins","year":2009,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":143,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Gene ontology; Subcellular localization; Data mining; Protein sequencing; Sequence (biology); Protein subcellular localization prediction; Feature (linguistics); Computational biology; Artificial intelligence; Gene; Biology; Peptide sequence; Genetics; Gene expression","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":[0.004703764,0.0001108259,0.0002405165,0.0002253786,0.0001205381,0.00004095391,0.0003677843,0.000113342,0.00001513093],"category_scores_gemma":[0.00407987,0.00009192916,0.0001301234,0.0002215762,0.00006198382,0.00001878038,0.00007217599,0.0004067624,0.000001221283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004043064,"about_ca_system_score_gemma":0.0002762497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001629571,"about_ca_topic_score_gemma":0.000001130354,"domain_scores_codex":[0.9979449,0.000320607,0.0006634813,0.0001370702,0.0006203809,0.0003135821],"domain_scores_gemma":[0.9977729,0.0001033441,0.0005265236,0.0002590124,0.00123204,0.0001061243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006430915,0.0001556692,0.0007160667,0.0003826229,0.000077524,0.000006824972,0.0001853774,0.004000987,0.9743302,0.0002006415,0.001150597,0.01815041],"study_design_scores_gemma":[0.00130928,0.005316718,0.0003854337,0.0001916581,0.00002056098,0.0001148666,0.00009668053,0.04395754,0.9347381,0.001714261,0.01201554,0.0001393487],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.214931,0.0002901596,0.7829453,0.0005553341,0.00005017483,0.001043419,0.000009418767,0.000004751059,0.0001703977],"genre_scores_gemma":[0.7734576,0.00007183758,0.2257353,0.00003764495,0.0004306118,0.00002512981,0.00002347561,0.00001988669,0.0001985268],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5585266,"threshold_uncertainty_score":0.4884281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02805623053856246,"score_gpt":0.3845717248430646,"score_spread":0.3565154943045022,"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."}}