{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001166368,0.0009815398,0.0009439721,0.001478544,0.0002601959,0.000754475,0.0009998893,0.0004714882,0.005727987],"category_scores_gemma":[0.002935206,0.000483201,0.0006899817,0.001200774,0.000158103,0.0007130182,0.0007933745,0.0006167167,0.003732609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002498478,"about_ca_system_score_gemma":0.0003918521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000865289,"about_ca_topic_score_gemma":0.0009131095,"domain_scores_codex":[0.9997168,0.00006561656,0.000025593,0.00007838855,0.00009099415,0.0000225043],"domain_scores_gemma":[0.9993617,0.0003039629,0.00008923634,0.00008446423,0.000113477,0.00004710117],"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":[0.004074526,0.0003218019,0.01593729,0.003199235,0.0004598754,0.001066672,0.0003615284,0.04210499,0.3341269,0.005094295,0.151509,0.4417439],"study_design_scores_gemma":[0.0005745821,0.0006620919,0.03235639,0.0003989735,0.0003264474,0.003753781,0.00008648938,0.6430902,0.1781543,0.009226647,0.1311671,0.0002029159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1380973,0.002320569,0.6610056,0.000498088,0.0001391324,0.0002469906,0.03089832,0.1616791,0.005114842],"genre_scores_gemma":[0.1903609,0.001248868,0.7235301,0.0001860744,0.00006903095,0.0005025039,0.07147302,0.009394811,0.003234725],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005727987,"threshold_uncertainty_score":0,"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."}}