{"id":"W2040630248","doi":"10.1371/journal.pcbi.0010066","title":"Refining Protein Subcellular Localization","year":2005,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":123,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Proteome; Computational biology; Subcellular localization; Protein subcellular localization prediction; Protein–protein interaction; Biology; Protein targeting; Function (biology); Organelle; Proteomics; Computer science; Bioinformatics; Membrane protein; Cell biology; Biochemistry; Gene; Cytoplasm","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":[0.0001242831,0.0001135578,0.00009939144,0.00005121989,0.00009080691,0.00001414486,0.0001341817,0.0001342474,0.00006384312],"category_scores_gemma":[0.0001469631,0.0001101523,0.00003929477,0.00007137127,0.00006724418,0.000004384018,0.00007813574,0.00009287261,0.0001283948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001678171,"about_ca_system_score_gemma":0.00004884321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003731347,"about_ca_topic_score_gemma":0.000005700257,"domain_scores_codex":[0.9992263,0.00007525981,0.0002407908,0.0001979981,0.00008993675,0.0001697355],"domain_scores_gemma":[0.9995936,0.00001911829,0.0001027946,0.0001370371,0.000102678,0.00004474115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001185902,0.0002343737,0.02710129,0.0000761304,0.000171476,0.000001721067,0.0001789757,0.5606968,0.3668637,0.02389838,0.002274871,0.01838364],"study_design_scores_gemma":[0.0009507938,0.0005340412,0.001215355,0.00002903102,0.00001839194,0.00003079709,0.00001781939,0.67119,0.03924868,0.001659943,0.2846359,0.000469286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5605589,0.0002657296,0.4328955,0.0009310202,0.00007526208,0.0002006433,0.00002304922,0.00007616141,0.004973693],"genre_scores_gemma":[0.9513955,0.00000334927,0.04539203,0.0008156717,0.0002799416,0.00001984797,0.00166315,0.00001579392,0.0004146897],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3908366,"threshold_uncertainty_score":0.4491881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009820439929410696,"score_gpt":0.2489673547677503,"score_spread":0.2391469148383396,"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."}}