{"id":"W3115382283","doi":"10.1093/nar/gkaa1095","title":"PSORTdb 4.0: expanded and redesigned bacterial and archaeal protein subcellular localization database incorporating new secondary localizations","year":2020,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Biology; RefSeq; Proteome; Genome; Database; Hypothetical protein; Bacterial genome size; Computational biology; Annotation; Bacterial protein; Proteomics; Bioinformatics; Genetics; Bacteria; 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":[0.0006062329,0.0001564981,0.0001548615,0.00007857866,0.0002991458,0.0001383582,0.000197416,0.0001667002,0.0001173557],"category_scores_gemma":[0.0008339179,0.000156537,0.00002212368,0.0002538715,0.0002960519,0.00002597975,0.0005539336,0.0003457646,0.0000112503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001490404,"about_ca_system_score_gemma":0.0002771961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007223438,"about_ca_topic_score_gemma":0.00002673619,"domain_scores_codex":[0.998387,0.0002810415,0.0002985876,0.0003865806,0.000339481,0.0003072984],"domain_scores_gemma":[0.9991338,0.00002669743,0.00008099616,0.0002854064,0.0001380628,0.0003349863],"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":[0.0003619173,0.0000310777,0.005145872,0.0003321568,0.00003724043,0.00001209586,0.00108451,0.0001140544,0.9749083,0.0009711924,0.005440264,0.01156131],"study_design_scores_gemma":[0.008056339,0.00449268,0.002685189,0.0003134748,0.00005720341,0.0001182833,0.002060953,0.3482578,0.4677938,0.001768717,0.1628409,0.001554656],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.822408,0.0003173682,0.1738296,0.00143228,0.00003629561,0.0008484471,0.00004535751,0.00005049107,0.001032194],"genre_scores_gemma":[0.9842466,0.00008671272,0.01374121,0.0002574478,0.000380148,0.00002109373,0.000912223,0.00004280521,0.0003117665],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5071145,"threshold_uncertainty_score":0.6383392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03474046784770293,"score_gpt":0.3033790343090598,"score_spread":0.2686385664613569,"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."}}