{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001168235,0.0001191818,0.00009620529,0.0001133571,0.000275747,0.00006128826,0.0003448311,0.0001486977,0.00004899503],"category_scores_gemma":[0.0003602326,0.0001180506,0.00004199158,0.0002664397,0.0001558367,0.000006755328,0.0002006467,0.0003562742,0.000178014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006659705,"about_ca_system_score_gemma":0.0001753138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005819823,"about_ca_topic_score_gemma":0.00001074508,"domain_scores_codex":[0.9983727,0.0001406688,0.0002372032,0.0002793694,0.0004934769,0.0004765954],"domain_scores_gemma":[0.9991591,0.00001108056,0.00005952839,0.0004250182,0.0002203593,0.0001248962],"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":[0.00006943875,0.0001228889,0.01364599,0.000322653,0.00004303486,0.00001269989,0.0006099165,0.02303077,0.9587982,0.0002930976,0.0002509138,0.002800406],"study_design_scores_gemma":[0.002661247,0.002391763,0.005145958,0.0001759451,0.00001637067,0.00009947511,0.0004868635,0.02841743,0.7854591,0.001601702,0.1725303,0.001013785],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8382422,0.0004188408,0.1567396,0.0001831562,0.00005143682,0.0007498476,0.00004391629,0.00004322366,0.003527777],"genre_scores_gemma":[0.9967285,0.00005114415,0.001754246,0.00003426232,0.0001827573,0.00004536254,0.0007965934,0.00001940301,0.0003876801],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1733391,"threshold_uncertainty_score":0.4813965,"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."}}