{"id":"W2154202919","doi":"10.1093/bioinformatics/bti057","title":"PSORTb v.2.0: Expanded prediction of bacterial protein subcellular localization and insights gained from comparative proteome analysis","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":723,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University; Michael Smith Health Research BC","keywords":"Proteome; Computer science; n-gram; Subsequence; Support vector machine; Computational biology; MIT License; Subcellular localization; Biology; Artificial intelligence; Software; Bioinformatics; Genetics; Mathematics; Programming language; Language model","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":[0.0001318976,0.0001952533,0.0003072996,0.0001537749,0.00008893712,0.00004286896,0.0001316191,0.0001929874,0.00002051104],"category_scores_gemma":[0.00007239404,0.0001726256,0.00008702922,0.0002981585,0.0001201818,0.00003165229,0.00009198807,0.00009045011,0.000005622523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002532925,"about_ca_system_score_gemma":0.00007348062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004881129,"about_ca_topic_score_gemma":0.00003499744,"domain_scores_codex":[0.9987788,0.00004328842,0.0006427977,0.0001490246,0.0002288948,0.0001572],"domain_scores_gemma":[0.999035,0.000008216559,0.0004121903,0.000326562,0.000136688,0.00008131246],"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":[0.0009958898,0.0004800538,0.01294438,0.000900951,0.002956508,0.000003002774,0.03426037,0.05582236,0.8888124,0.001178999,0.0004682461,0.001176898],"study_design_scores_gemma":[0.004519755,0.001288405,0.008666976,0.0001425658,0.0006003722,0.000007425035,0.001898801,0.2525485,0.7246639,0.0006717031,0.004361083,0.0006305194],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8251913,0.00005990437,0.1736371,0.00001603046,0.00004891512,0.0005405703,0.0001013396,0.00002448163,0.0003802911],"genre_scores_gemma":[0.9697294,0.00002605553,0.027267,0.00003309084,0.0000804228,0.00002834466,0.002790982,0.00001064079,0.00003404932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1967262,"threshold_uncertainty_score":0.7039467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01112130957213176,"score_gpt":0.2311252125935061,"score_spread":0.2200039030213743,"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."}}