{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006517324,0.000449193,0.0003940948,0.0001612386,0.0003175103,0.0002663876,0.0009677855,0.0005512325,0.000006275551],"category_scores_gemma":[0.0001991566,0.0003847444,0.0004034715,0.0005522998,0.0001349628,0.000003085114,0.001037037,0.0003789075,0.0000533319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007392529,"about_ca_system_score_gemma":0.0003999934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006114725,"about_ca_topic_score_gemma":0.0001110703,"domain_scores_codex":[0.9977764,0.00007718035,0.0005125999,0.0008550045,0.0002573324,0.0005214858],"domain_scores_gemma":[0.9971242,0.0000362816,0.0003722492,0.001918193,0.0003832344,0.0001658719],"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":[0.00003974028,0.00008540115,0.01354346,0.0001567854,0.002847996,0.00002266973,0.000006789941,0.007372538,0.9726561,0.0006560888,0.00260725,0.000005162473],"study_design_scores_gemma":[0.001306892,0.0002675208,0.2631111,0.0002156756,0.003716563,5.29898e-8,0.00004622581,0.05532266,0.5423754,0.00007149771,0.1292967,0.004269728],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9897632,0.001321565,0.006380052,0.0003903114,0.001150748,0.0003887789,0.0004403564,0.0001464902,0.00001847711],"genre_scores_gemma":[0.9939478,0.002604481,0.002289932,0.0001154665,0.0006590866,0.0001257638,0.000007166676,0.0001291266,0.0001211816],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4302807,"threshold_uncertainty_score":0.9998605,"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."}}