{"id":"W3001208427","doi":"10.1083/jcb.201904090","title":"A reference library for assigning protein subcellular localizations by image-based machine learning","year":2020,"lang":"en","type":"article","venue":"The Journal of Cell Biology","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Sunnybrook Hospital","funders":"Canadian Institutes of Health Research; Canada Research Chairs","keywords":"Endoplasmic reticulum; Subcellular localization; Biology; Protein subcellular localization prediction; Organelle; Protein Sorting Signals; Cell biology; Fusion protein; Protein targeting; Mutant; Cell; Computational biology; Cytoplasm; Biochemistry; Membrane protein; Peptide sequence; Gene; Signal peptide; Recombinant DNA","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":[0.0003301097,0.0001219027,0.0001930723,0.00003797574,0.00009113725,0.00002162679,0.000366423,0.0001142609,0.00005427748],"category_scores_gemma":[0.0001965058,0.00008364362,0.0001193662,0.0001124496,0.0001021619,0.000009032899,0.00007728293,0.0002256448,0.000002730932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005540142,"about_ca_system_score_gemma":0.00009356088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000434939,"about_ca_topic_score_gemma":8.451159e-7,"domain_scores_codex":[0.9990166,0.0003032355,0.0003210101,0.0001393524,0.00006031119,0.000159502],"domain_scores_gemma":[0.9992228,0.00005496828,0.0003673303,0.0001463068,0.0001352576,0.00007332326],"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":[0.0001986894,0.00002987712,0.0001660868,0.00001791948,0.00003446609,0.000001619308,0.00001957607,0.0001219575,0.9937655,0.000009693518,0.005293746,0.0003408947],"study_design_scores_gemma":[0.0003479456,0.0009225648,0.000001546221,0.000007013767,0.00005617309,0.00000341882,0.00002266759,0.002527351,0.8662525,0.00007033205,0.1297005,0.00008800164],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.170773,0.003283092,0.8226759,0.001882979,0.00001262705,0.0003172829,0.00002307215,0.00003159264,0.001000395],"genre_scores_gemma":[0.9889205,0.0002653096,0.009069152,0.0009207763,0.000123805,0.000008349478,0.0002978809,0.00002835656,0.0003659369],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8181474,"threshold_uncertainty_score":0.3410888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01076829043483213,"score_gpt":0.2402807207006582,"score_spread":0.229512430265826,"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."}}