{"id":"W2951038513","doi":"10.1038/s41598-017-01005-x","title":"Novel metrics to measure coverage in whole exome sequencing datasets reveal local and global non-uniformity","year":2017,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of General Medical Sciences; National Human Genome Research Institute; Fudan University; National Institute of Mental Health; Canadian Institutes of Health Research; Huck Institutes of the Life Sciences; Brain and Behavior Research Foundation; Università degli Studi di Milano-Bicocca; Pennsylvania State University; National Institutes of Health; March of Dimes Foundation; Howard Hughes Medical Institute; National Alliance for Research on Schizophrenia and Depression","keywords":"Exome sequencing; Exome; Computer science; Sequence (biology); Data mining; Segmental duplication; Computational biology; Measure (data warehouse); Genome; Biology; Genetics; Gene; Mutation","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005401556,0.0006862172,0.0009626307,0.006926896,0.000510006,0.001701497,0.0006512481,0.0006758937,0.0007439943],"category_scores_gemma":[0.01988914,0.000222269,0.0006650133,0.005249224,0.0009293925,0.001468895,0.002163257,0.0007588548,0.0002058621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006439427,"about_ca_system_score_gemma":0.0004462443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001616902,"about_ca_topic_score_gemma":0.002224214,"domain_scores_codex":[0.9966317,0.0009236521,0.0004873546,0.0007934601,0.0009129522,0.0002509649],"domain_scores_gemma":[0.9818579,0.01102938,0.00342798,0.001558537,0.001650762,0.0004755546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008638002,0.0001353788,0.7594571,0.0006597021,0.001677479,0.0005076911,0.00098306,0.06057219,0.05678952,0.005558799,0.002759013,0.1100363],"study_design_scores_gemma":[0.00005107844,0.000470086,0.6090532,0.0001370691,0.0003864842,0.00123351,0.000862582,0.3341571,0.03055485,0.01747565,0.005465878,0.0001524919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8186888,0.001527773,0.1735122,0.000150174,0.00003797523,0.0001250988,0.003635827,0.0008501734,0.001472062],"genre_scores_gemma":[0.967432,0.0001832033,0.0284171,0.00006530494,0.00003659505,0.0001109479,0.003413691,0.00009989746,0.0002413058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006926896,"threshold_uncertainty_score":0.02856648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01969921130099575,"score_gpt":0.2683690865769058,"score_spread":0.24866987527591,"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."}}