A robust framework for detecting structural variations in a genome Export

@article{citeulike:2960147, abstract = {Motivation: Recently, structural genomic variants have come to the forefront as a significant source of variation in the human population, but the identification of these variants in a large genome remains a challenge. The complete sequencing of a human individual is prohibitive at current costs, while current polymorphism detection technologies, such as SNP arrays, are not able to identify many of the large scale events. One of the most promising methods to detect such variants is the computational mapping of clone-end sequences to a reference genome. Results: Here, we present a probabilistic framework for the identification of structural variants using clone-end sequencing. Unlike previous methods, our approach does not rely on an a priori determined mapping of all reads to the reference. Instead, we build a framework for finding the most probable assignment of sequenced clones to potential structural variants based on the other clones. We compare our predictions with the structural variants identified in three previous studies. While there is a statistically significant correlation between the predictions, we also find a significant number of previously uncharacterized structural variants. Furthermore, we identify a number of putative cross-chromosomal events, primarily located proximally to the centromeres of the chromosomes. Availability: Our dataset, results and source code are available at http://compbio.cs.toronto.edu/structvar/ Contact:seunghak@cs.toronto.edu,echeran@cs.toronto.edu,brudno@cs.toronto.edu 10.1093/bioinformatics/btn176}, author = {Lee, Seunghak and Cheran, Elango and Brudno, Michael}, booktitle = {Bioinformatics}, citeulike-article-id = {2960147}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btn176}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/content/24/13/i59.abstract}, citeulike-linkout-2 = {http://bioinformatics.oxfordjournals.org/content/24/13/i59.full.pdf}, citeulike-linkout-3 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/24/13/i59}, citeulike-linkout-4 = {http://view.ncbi.nlm.nih.gov/pubmed/18586745}, citeulike-linkout-5 = {http://www.hubmed.org/display.cgi?uids=18586745}, day = {1}, doi = {10.1093/bioinformatics/btn176}, journal = {Bioinformatics}, keywords = {functional-genome, genome-structure, genome-variation, informatics, reviews, systems-biology}, month = {July}, number = {13}, pages = {i59--67}, posted-at = {2009-01-16 16:46:13}, priority = {2}, title = {A robust framework for detecting structural variations in a genome}, url = {http://dx.doi.org/10.1093/bioinformatics/btn176}, volume = {24}, year = {2008} }

TY - JOUR ID - citeulike:2960147 L3 - citeulike-article-id:2960147 N2 - Motivation: Recently, structural genomic variants have come to the forefront as a significant source of variation in the human population, but the identification of these variants in a large genome remains a challenge. The complete sequencing of a human individual is prohibitive at current costs, while current polymorphism detection technologies, such as SNP arrays, are not able to identify many of the large scale events. One of the most promising methods to detect such variants is the computational mapping of clone-end sequences to a reference genome. Results: Here, we present a probabilistic framework for the identification of structural variants using clone-end sequencing. Unlike previous methods, our approach does not rely on an a priori determined mapping of all reads to the reference. Instead, we build a framework for finding the most probable assignment of sequenced clones to potential structural variants based on the other clones. We compare our predictions with the structural variants identified in three previous studies. While there is a statistically significant correlation between the predictions, we also find a significant number of previously uncharacterized structural variants. Furthermore, we identify a number of putative cross-chromosomal events, primarily located proximally to the centromeres of the chromosomes. Availability: Our dataset, results and source code are available at http://compbio.cs.toronto.edu/structvar/ Contact:seunghak@cs.toronto.edu,echeran@cs.toronto.edu,brudno@cs.toronto.edu 10.1093/bioinformatics/btn176 IS - 13 JF - Bioinformatics EP - 67 TI - A robust framework for detecting structural variations in a genome VL - 24 T2 - Bioinformatics SP - i59 KW - functional-genome KW - genome-structure KW - genome-variation KW - informatics KW - reviews KW - systems-biology AU - Lee, Seunghak AU - Cheran, Elango AU - Brudno, Michael PY - 2008/07/01/ UR - http://dx.doi.org/10.1093/bioinformatics/btn176 ER -