{"id":"W2346607470","doi":"10.1101/051888","title":"Novel metrics to measure coverage in whole exome sequencing datasets reveal local and global non-uniformity","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Huck Institutes of the Life Sciences; Hungarian Scientific Research Fund; National Alliance for Research on Schizophrenia and Depression; Fudan University; Brain and Behavior Research Foundation; Università degli Studi di Milano-Bicocca; McGill University; Cancer Research Society; National Natural Science Foundation of China; Pennsylvania State University; National Institutes of Health; March of Dimes Foundation","keywords":"Exome sequencing; Exome; Computer science; Sequence (biology); Computational biology; Data mining; Measure (data warehouse); Segmental duplication; 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":[0.005806797,0.0007252099,0.0009956649,0.007242875,0.0005251161,0.001814389,0.0006946126,0.0007507298,0.0007067719],"category_scores_gemma":[0.02200528,0.0002373221,0.0006915765,0.005575284,0.00105139,0.001534772,0.002259236,0.0008709079,0.0002054666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007032721,"about_ca_system_score_gemma":0.0004698034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001671773,"about_ca_topic_score_gemma":0.002200802,"domain_scores_codex":[0.9964331,0.001020589,0.0004859166,0.0008531628,0.0009462831,0.0002609297],"domain_scores_gemma":[0.9798568,0.01232391,0.003711019,0.001800333,0.001766968,0.0005410495],"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":[0.0009601001,0.0001499771,0.7356449,0.0007087556,0.001788561,0.0005343222,0.001062958,0.07696379,0.05878909,0.007340291,0.003535698,0.1125214],"study_design_scores_gemma":[0.0000575293,0.000447902,0.5343464,0.0001424108,0.0003450442,0.00118442,0.0008164279,0.4022081,0.03240636,0.02208481,0.005798524,0.0001620472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7907981,0.001587479,0.200683,0.0001814782,0.00004216921,0.0001295372,0.00407025,0.000995717,0.001512335],"genre_scores_gemma":[0.9636493,0.0001862809,0.03184215,0.00007865211,0.00004338779,0.0001158094,0.003698979,0.0001227756,0.0002626271],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.007242875,"threshold_uncertainty_score":0.03070968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01346978981018909,"score_gpt":0.2266882533623023,"score_spread":0.2132184635521132,"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."}}