{"id":"W2501117253","doi":"10.1186/s12859-016-1097-3","title":"Evaluating the necessity of PCR duplicate removal from next-generation sequencing data and a comparison of approaches","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":178,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; Servier; Brigham Young University; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Transversion; Computational biology; Reference genome; Biology; DNA sequencing; Concordance; Genetics; Exome; Population; Data mining; Computer science; Bioinformatics; Exome sequencing; Gene; Mutation; Medicine","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":[0.0004260937,0.00008850403,0.0001543835,0.00001294369,0.00007030027,0.00001383685,0.0002582722,0.00005924161,0.000001416285],"category_scores_gemma":[0.0001641679,0.00005118764,0.00002631792,0.00003446421,0.0001277506,0.000004417881,0.000388001,0.00002673988,6.200606e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005607859,"about_ca_system_score_gemma":0.00006788268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003484488,"about_ca_topic_score_gemma":0.00008682989,"domain_scores_codex":[0.9992499,0.00004136324,0.0003723945,0.0001336432,0.0001086158,0.00009410609],"domain_scores_gemma":[0.9990092,0.00006109033,0.0003006612,0.0005532337,0.00005433089,0.00002146706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002718505,0.00001331367,0.01355285,0.00005146454,0.00005542499,1.86794e-8,0.0006853486,0.0002291906,0.9443132,0.00005712328,0.0001096054,0.04090528],"study_design_scores_gemma":[0.0006299813,0.0002476798,0.008155677,0.00004290307,0.00009466381,0.000004722788,0.001770003,0.6646588,0.3235516,0.000190258,0.0004769706,0.0001767829],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9640781,0.00126907,0.03413239,0.00005994014,0.00004024877,0.0001386622,0.0001419955,0.000001389524,0.0001381886],"genre_scores_gemma":[0.915427,0.0001230579,0.08426057,0.00001763895,0.00007085047,0.000003249385,0.00008054919,0.000005009175,0.00001202328],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6644296,"threshold_uncertainty_score":0.2087371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3861978566480501,"score_gpt":0.3493385526642588,"score_spread":0.03685930398379128,"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."}}