{"id":"W2012352014","doi":"10.1101/gr.2650004","title":"Predicting Subcellular Localization via Protein Motif Co-Occurrence","year":2004,"lang":"en","type":"article","venue":"Genome Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":114,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Subcellular localization; Biology; Protein subcellular localization prediction; Computational biology; Protein Sorting Signals; Membrane protein; Organelle; Green fluorescent protein; Bioinformatics; Cell biology; Cytoplasm; Biochemistry; Gene; Peptide sequence; Signal peptide; Membrane","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":[0.0009403304,0.00048524,0.0005967214,0.002718962,0.0002803777,0.0004458642,0.000398372,0.0005705807,0.001176625],"category_scores_gemma":[0.003148808,0.0002329046,0.0005257025,0.001745223,0.000257027,0.0007612098,0.0004316422,0.0005698538,0.001117382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003583329,"about_ca_system_score_gemma":0.0005503275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002830203,"about_ca_topic_score_gemma":0.004097644,"domain_scores_codex":[0.9995066,0.0001243015,0.0000390274,0.0001408396,0.0001379025,0.00005135728],"domain_scores_gemma":[0.9980158,0.001153881,0.000362869,0.0001107435,0.0002612748,0.00009544679],"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":[0.002443559,0.0005251564,0.258823,0.0009823502,0.0005778181,0.001005844,0.000196631,0.2381268,0.1036281,0.004847045,0.009552156,0.3792915],"study_design_scores_gemma":[0.00003271604,0.000099693,0.02147644,0.00002292716,0.000061557,0.0004980967,0.00003399665,0.9577944,0.01347177,0.004649636,0.001832887,0.00002586339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5191103,0.00115293,0.4680123,0.0002933588,0.0000319863,0.00009702769,0.00476484,0.004802874,0.001734396],"genre_scores_gemma":[0.8658625,0.000377058,0.1263021,0.00004849457,0.00002437416,0.0001087081,0.006496864,0.0001008774,0.0006790838],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002830203,"threshold_uncertainty_score":0.005627453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02705706486612943,"score_gpt":0.337070739419401,"score_spread":0.3100136745532716,"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."}}