{"id":"W4362660267","doi":"10.1101/2023.04.04.535623","title":"The ENCODE Uniform Analysis Pipelines","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"ENCODE; Pipeline transport; Computer science; Computational biology; Biology; Genetics; Engineering; Gene; Mechanical engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.007650137,0.003273566,0.001945198,0.006350477,0.00234265,0.006347827,0.004859633,0.001748239,0.05389627],"category_scores_gemma":[0.0232033,0.002536993,0.00392683,0.006167451,0.001198938,0.003290489,0.006213644,0.003822085,0.08084188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003456866,"about_ca_system_score_gemma":0.008975096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01445877,"about_ca_topic_score_gemma":0.01155643,"domain_scores_codex":[0.9924887,0.001238488,0.001189888,0.002286338,0.002077682,0.0007188426],"domain_scores_gemma":[0.988804,0.002578238,0.0007718889,0.003885275,0.003343168,0.0006173939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001450695,0.0001008868,0.003233266,0.002021768,0.0003274384,0.0006599656,0.0006902714,0.004518922,0.01317148,0.02888545,0.8545215,0.09041853],"study_design_scores_gemma":[0.00021124,0.00007587653,0.001920174,0.0003732853,0.000152687,0.0004300244,0.0001652774,0.007559766,0.02540493,0.02429065,0.9392101,0.0002060018],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.002756613,0.0009921431,0.2082684,0.001386077,0.000797475,0.0008598099,0.390496,0.3691545,0.02528911],"genre_scores_gemma":[0.01543132,0.0009897389,0.1662502,0.001437379,0.0001515345,0.001879497,0.7217414,0.07788111,0.01423785],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.05389627,"threshold_uncertainty_score":0.180301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01054884254317662,"score_gpt":0.2204822338529736,"score_spread":0.209933391309797,"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."}}