{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002039864,0.001772018,0.002093516,0.003555748,0.0009171474,0.002604032,0.003101169,0.001332541,0.01459812],"category_scores_gemma":[0.003262426,0.001306512,0.001885922,0.003883781,0.0003765018,0.002376149,0.002502719,0.002086151,0.01896702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008314053,"about_ca_system_score_gemma":0.002423055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002656203,"about_ca_topic_score_gemma":0.002776365,"domain_scores_codex":[0.9992898,0.00008918772,0.000146883,0.0001777998,0.0002103809,0.00008594048],"domain_scores_gemma":[0.9989467,0.0001866762,0.0001421016,0.0002244532,0.0003034172,0.0001966237],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.006115734,0.0004599969,0.008079239,0.006421946,0.0005680643,0.001547507,0.0005632727,0.005676762,0.1016651,0.00766369,0.6512657,0.2099731],"study_design_scores_gemma":[0.00089203,0.0004569162,0.009327239,0.0005215278,0.0003531853,0.002170393,0.0002008508,0.02159693,0.03897769,0.006684134,0.9184772,0.0003418537],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"software","genre_scores_codex":[0.03687532,0.007901163,0.1923801,0.001417917,0.001181489,0.0006330461,0.4891112,0.258817,0.01168274],"genre_scores_gemma":[0.02682608,0.002481616,0.138959,0.0005839277,0.00009973691,0.0004746351,0.8165163,0.008786673,0.005271963],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01459812,"threshold_uncertainty_score":0.04883564,"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."}}