<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Chen, Xiao</style></author><author><style face="normal" font="default" size="100%">Sanchis-Juan, Alba</style></author><author><style face="normal" font="default" size="100%">French, Courtney E</style></author><author><style face="normal" font="default" size="100%">Connell, Andrew J</style></author><author><style face="normal" font="default" size="100%">Delon, Isabelle</style></author><author><style face="normal" font="default" size="100%">Kingsbury, Zoya</style></author><author><style face="normal" font="default" size="100%">Chawla, Aditi</style></author><author><style face="normal" font="default" size="100%">Halpern, Aaron L</style></author><author><style face="normal" font="default" size="100%">Taft, Ryan J</style></author><author><style face="normal" font="default" size="100%">Bentley, David R</style></author><author><style face="normal" font="default" size="100%">Butchbach, Matthew E R</style></author><author><style face="normal" font="default" size="100%">Raymond, F Lucy</style></author><author><style face="normal" font="default" size="100%">Eberle, Michael A</style></author></authors><translated-authors><author><style face="normal" font="default" size="100%">NIHR BioResource</style></author></translated-authors></contributors><titles><title><style face="normal" font="default" size="100%">Spinal muscular atrophy diagnosis and carrier screening from genome sequencing data.</style></title><secondary-title><style face="normal" font="default" size="100%">Genet Med</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Genet Med</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Base Sequence</style></keyword><keyword><style  face="normal" font="default" size="100%">Child</style></keyword><keyword><style  face="normal" font="default" size="100%">Child, Preschool</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Muscular Atrophy, Spinal</style></keyword><keyword><style  face="normal" font="default" size="100%">Survival of Motor Neuron 1 Protein</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2020</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2020 05</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">22</style></volume><pages><style face="normal" font="default" size="100%">945-953</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;&lt;b&gt;PURPOSE: &lt;/b&gt;Spinal muscular atrophy (SMA), caused by loss of the SMN1 gene, is a leading cause of early childhood death. Due to the near identical sequences of SMN1 and SMN2, analysis of this region is challenging. Population-wide SMA screening to quantify the SMN1 copy number (CN) is recommended by the American College of Medical Genetics and Genomics.&lt;/p&gt;&lt;p&gt;&lt;b&gt;METHODS: &lt;/b&gt;We developed a method that accurately identifies the CN of SMN1 and SMN2 using genome sequencing (GS) data by analyzing read depth and eight informative reference genome differences between SMN1/2.&lt;/p&gt;&lt;p&gt;&lt;b&gt;RESULTS: &lt;/b&gt;We characterized SMN1/2 in 12,747 genomes, identified 1568 samples with SMN1 gains or losses and 6615 samples with SMN2 gains or losses, and calculated a pan-ethnic carrier frequency of 2%, consistent with previous studies. Additionally, 99.8% of our SMN1 and 99.7% of SMN2 CN calls agreed with orthogonal methods, with a recall of 100% for SMA and 97.8% for carriers, and a precision of 100% for both SMA and carriers.&lt;/p&gt;&lt;p&gt;&lt;b&gt;CONCLUSION: &lt;/b&gt;This SMN copy-number caller can be used to identify both carrier and affected status of SMA, enabling SMA testing to be offered as a comprehensive test in neonatal care and an accurate carrier screening tool in GS sequencing projects.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">5</style></issue><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/32066871?dopt=Abstract</style></custom1></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Luo, Ruibang</style></author><author><style face="normal" font="default" size="100%">Sedlazeck, Fritz J</style></author><author><style face="normal" font="default" size="100%">Lam, Tak-Wah</style></author><author><style face="normal" font="default" size="100%">Schatz, Michael C</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">A multi-task convolutional deep neural network for variant calling in single molecule sequencing.</style></title><secondary-title><style face="normal" font="default" size="100%">Nat Commun</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Nat Commun</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Base Sequence</style></keyword><keyword><style  face="normal" font="default" size="100%">Computational Biology</style></keyword><keyword><style  face="normal" font="default" size="100%">DNA Mutational Analysis</style></keyword><keyword><style  face="normal" font="default" size="100%">Genome, Human</style></keyword><keyword><style  face="normal" font="default" size="100%">Genome-Wide Association Study</style></keyword><keyword><style  face="normal" font="default" size="100%">Genomics</style></keyword><keyword><style  face="normal" font="default" size="100%">Genotype</style></keyword><keyword><style  face="normal" font="default" size="100%">Genotyping Techniques</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">INDEL Mutation</style></keyword><keyword><style  face="normal" font="default" size="100%">Nanopores</style></keyword><keyword><style  face="normal" font="default" size="100%">Neural Networks (Computer)</style></keyword><keyword><style  face="normal" font="default" size="100%">Polymorphism, Single Nucleotide</style></keyword><keyword><style  face="normal" font="default" size="100%">Sequence Analysis, DNA</style></keyword><keyword><style  face="normal" font="default" size="100%">Software</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2019</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2019 03 01</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">10</style></volume><pages><style face="normal" font="default" size="100%">998</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;The accurate identification of DNA sequence variants is an important, but challenging task in genomics. It is particularly difficult for single molecule sequencing, which has a per-nucleotide error rate of ~5-15%. Meeting this demand, we developed Clairvoyante, a multi-task five-layer convolutional neural network model for predicting variant type (SNP or indel), zygosity, alternative allele and indel length from aligned reads. For the well-characterized NA12878 human sample, Clairvoyante achieves 99.67, 95.78, 90.53% F1-score on 1KP common variants, and 98.65, 92.57, 87.26% F1-score for whole-genome analysis, using Illumina, PacBio, and Oxford Nanopore data, respectively. Training on a second human sample shows Clairvoyante is sample agnostic and finds variants in less than 2 h on a standard server. Furthermore, we present 3,135 variants that are missed using Illumina but supported independently by both PacBio and Oxford Nanopore reads. Clairvoyante is available open-source ( https://github.com/aquaskyline/Clairvoyante ), with modules to train, utilize and visualize the model.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">1</style></issue><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/30824707?dopt=Abstract</style></custom1></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Sanghvi, Rashesh V</style></author><author><style face="normal" font="default" size="100%">Buhay, Christian J</style></author><author><style face="normal" font="default" size="100%">Powell, Bradford C</style></author><author><style face="normal" font="default" size="100%">Tsai, Ellen A</style></author><author><style face="normal" font="default" size="100%">Dorschner, Michael O</style></author><author><style face="normal" font="default" size="100%">Hong, Celine S</style></author><author><style face="normal" font="default" size="100%">Lebo, Matthew S</style></author><author><style face="normal" font="default" size="100%">Sasson, Ariella</style></author><author><style face="normal" font="default" size="100%">Hanna, David S</style></author><author><style face="normal" font="default" size="100%">McGee, Sean</style></author><author><style face="normal" font="default" size="100%">Bowling, Kevin M</style></author><author><style face="normal" font="default" size="100%">Cooper, Gregory M</style></author><author><style face="normal" font="default" size="100%">Gray, David E</style></author><author><style face="normal" font="default" size="100%">Lonigro, Robert J</style></author><author><style face="normal" font="default" size="100%">Dunford, Andrew</style></author><author><style face="normal" font="default" size="100%">Brennan, Christine A</style></author><author><style face="normal" font="default" size="100%">Cibulskis, Carrie</style></author><author><style face="normal" font="default" size="100%">Walker, Kimberly</style></author><author><style face="normal" font="default" size="100%">Carneiro, Mauricio O</style></author><author><style face="normal" font="default" size="100%">Sailsbery, Joshua</style></author><author><style face="normal" font="default" size="100%">Hindorff, Lucia A</style></author><author><style face="normal" font="default" size="100%">Robinson, Dan R</style></author><author><style face="normal" font="default" size="100%">Santani, Avni</style></author><author><style face="normal" font="default" size="100%">Sarmady, Mahdi</style></author><author><style face="normal" font="default" size="100%">Rehm, Heidi L</style></author><author><style face="normal" font="default" size="100%">Biesecker, Leslie G</style></author><author><style face="normal" font="default" size="100%">Nickerson, Deborah A</style></author><author><style face="normal" font="default" size="100%">Hutter, Carolyn M</style></author><author><style face="normal" font="default" size="100%">Garraway, Levi</style></author><author><style face="normal" font="default" size="100%">Muzny, Donna M</style></author><author><style face="normal" font="default" size="100%">Wagle, Nikhil</style></author></authors><translated-authors><author><style face="normal" font="default" size="100%">NHGRI Clinical Sequencing Exploratory Research (CSER) Consortium</style></author></translated-authors></contributors><titles><title><style face="normal" font="default" size="100%">Characterizing reduced coverage regions through comparison of exome and genome sequencing data across 10 centers.</style></title><secondary-title><style face="normal" font="default" size="100%">Genet Med</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Genet. Med.</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Base Sequence</style></keyword><keyword><style  face="normal" font="default" size="100%">Chromosome Mapping</style></keyword><keyword><style  face="normal" font="default" size="100%">Exome</style></keyword><keyword><style  face="normal" font="default" size="100%">Genome, Human</style></keyword><keyword><style  face="normal" font="default" size="100%">High-Throughput Nucleotide Sequencing</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Sequence Analysis, DNA</style></keyword><keyword><style  face="normal" font="default" size="100%">Software</style></keyword><keyword><style  face="normal" font="default" size="100%">Whole Exome Sequencing</style></keyword><keyword><style  face="normal" font="default" size="100%">Whole Genome Sequencing</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2018</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2018 08</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">20</style></volume><pages><style face="normal" font="default" size="100%">855-866</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;&lt;b&gt;PURPOSE: &lt;/b&gt;As massively parallel sequencing is increasingly being used for clinical decision making, it has become critical to understand parameters that affect sequencing quality and to establish methods for measuring and reporting clinical sequencing standards. In this report, we propose a definition for reduced coverage regions and describe a set of standards for variant calling in clinical sequencing applications.&lt;/p&gt;&lt;p&gt;&lt;b&gt;METHODS: &lt;/b&gt;To enable sequencing centers to assess the regions of poor sequencing quality in their own data, we optimized and used a tool (ExCID) to identify reduced coverage loci within genes or regions of particular interest. We used this framework to examine sequencing data from 500 patients generated in 10 projects at sequencing centers in the National Human Genome Research Institute/National Cancer Institute Clinical Sequencing Exploratory Research Consortium.&lt;/p&gt;&lt;p&gt;&lt;b&gt;RESULTS: &lt;/b&gt;This approach identified reduced coverage regions in clinically relevant genes, including known clinically relevant loci that were uniquely missed at individual centers, in multiple centers, and in all centers.&lt;/p&gt;&lt;p&gt;&lt;b&gt;CONCLUSION: &lt;/b&gt;This report provides a process road map for clinical sequencing centers looking to perform similar analyses on their data.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">8</style></issue><custom1><style face="normal" font="default" size="100%">http://www.ncbi.nlm.nih.gov/pubmed/29144510?dopt=Abstract</style></custom1></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Huang, Yi-Fei</style></author><author><style face="normal" font="default" size="100%">Gulko, Brad</style></author><author><style face="normal" font="default" size="100%">Siepel, Adam</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Fast, scalable prediction of deleterious noncoding variants from functional and population genomic data.</style></title><secondary-title><style face="normal" font="default" size="100%">Nat Genet</style></secondary-title><alt-title><style face="normal" font="default" size="100%">Nat Genet</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Animals</style></keyword><keyword><style  face="normal" font="default" size="100%">Base Sequence</style></keyword><keyword><style  face="normal" font="default" size="100%">Computational Biology</style></keyword><keyword><style  face="normal" font="default" size="100%">Evolution, Molecular</style></keyword><keyword><style  face="normal" font="default" size="100%">Genetic Variation</style></keyword><keyword><style  face="normal" font="default" size="100%">Genome</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Mammals</style></keyword><keyword><style  face="normal" font="default" size="100%">Metagenomics</style></keyword><keyword><style  face="normal" font="default" size="100%">Phenotype</style></keyword><keyword><style  face="normal" font="default" size="100%">Primates</style></keyword><keyword><style  face="normal" font="default" size="100%">Vertebrates</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2017</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2017 Apr</style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">49</style></volume><pages><style face="normal" font="default" size="100%">618-624</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Many genetic variants that influence phenotypes of interest are located outside of protein-coding genes, yet existing methods for identifying such variants have poor predictive power. Here we introduce a new computational method, called LINSIGHT, that substantially improves the prediction of noncoding nucleotide sites at which mutations are likely to have deleterious fitness consequences, and which, therefore, are likely to be phenotypically important. LINSIGHT combines a generalized linear model for functional genomic data with a probabilistic model of molecular evolution. The method is fast and highly scalable, enabling it to exploit the 'big data' available in modern genomics. We show that LINSIGHT outperforms the best available methods in identifying human noncoding variants associated with inherited diseases. In addition, we apply LINSIGHT to an atlas of human enhancers and show that the fitness consequences at enhancers depend on cell type, tissue specificity, and constraints at associated promoters.&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">4</style></issue><custom1><style face="normal" font="default" size="100%">https://www.ncbi.nlm.nih.gov/pubmed/28288115?dopt=Abstract</style></custom1></record></records></xml>