{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008733896,0.0001283585,0.0001423286,0.0000624875,0.00037286,0.0003650723,0.0002367042,0.00009191858,0.000002651032],"category_scores_gemma":[0.0003940189,0.0001206856,0.00004752336,0.0001369765,0.0001714561,0.00001708193,0.0004299002,0.00005378271,0.000004574053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006687611,"about_ca_system_score_gemma":0.0002792359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002503064,"about_ca_topic_score_gemma":0.0005570367,"domain_scores_codex":[0.9985234,0.00001181047,0.0002559106,0.0006956186,0.0002406927,0.0002726369],"domain_scores_gemma":[0.9983842,0.000002828006,0.0001685661,0.001136017,0.0000926299,0.0002157786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00007189833,0.0001709475,0.0767966,0.0000692437,0.0000417294,0.001449498,0.00008094473,0.0009441277,0.8805254,0.00003010593,0.0300259,0.009793603],"study_design_scores_gemma":[0.002097656,0.0003259845,0.5847408,0.0002277551,0.0001006543,0.003156437,0.0004269885,0.0007197243,0.1368879,0.002510536,0.2670787,0.001726851],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935587,0.0001968499,0.003787624,0.0001079593,0.001227146,0.0002182757,0.0003933859,0.000004260673,0.0005057706],"genre_scores_gemma":[0.9984306,0.00000534238,0.0005455023,0.00008066536,0.00004893638,0.000006708976,0.0005444632,0.000007622637,0.0003302197],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7436374,"threshold_uncertainty_score":0.4921415,"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."}}