One of the key advances in genome assembly that has led to a significant improvement in contig lengths has been utilization of paired reads (mate-pairs). While in most assemblers, mate-pair information is used in a post-processing step, the recently proposed Paired de Bruijn Graph (PDBG) approach incorporates the mate-pair information directly in the assembly graph structure. However, the PDBG approach faces difficulties when the variation in the insert sizes is high. To address this problem, we first transform mate-pairs into edge-pair histograms that allow one to better estimate the distance between edges in the assembly graph that represent regions linked by multiple mate-pairs. Further, we combine the ideas of mate-pair transformation and PDBGs to construct new data structures for genome assembly: pathsets and pathset graphs.
%0 Conference Paper
%1 DBLP:conf/recomb/PhamASTPA12
%A Pham, Son K.
%A Antipov, Dmitry
%A Sirotkin, Alexander
%A Tesler, Glenn
%A Pevzner, Pavel A.
%A Alekseyev, Max A.
%B RECOMB
%D 2012
%E Chor, Benny
%I Springer
%K bioinformatics sequencing
%P 200-212
%R 10.1007/978-3-642-29627-7_21
%T Pathset Graphs: A Novel Approach for Comprehensive Utilization
of Paired Reads in Genome Assembly
%V 7262
%X One of the key advances in genome assembly that has led to a significant improvement in contig lengths has been utilization of paired reads (mate-pairs). While in most assemblers, mate-pair information is used in a post-processing step, the recently proposed Paired de Bruijn Graph (PDBG) approach incorporates the mate-pair information directly in the assembly graph structure. However, the PDBG approach faces difficulties when the variation in the insert sizes is high. To address this problem, we first transform mate-pairs into edge-pair histograms that allow one to better estimate the distance between edges in the assembly graph that represent regions linked by multiple mate-pairs. Further, we combine the ideas of mate-pair transformation and PDBGs to construct new data structures for genome assembly: pathsets and pathset graphs.
%@ 978-3-642-29626-0
@inproceedings{DBLP:conf/recomb/PhamASTPA12,
abstract = {One of the key advances in genome assembly that has led to a significant improvement in contig lengths has been utilization of paired reads (mate-pairs). While in most assemblers, mate-pair information is used in a post-processing step, the recently proposed Paired de Bruijn Graph (PDBG) approach incorporates the mate-pair information directly in the assembly graph structure. However, the PDBG approach faces difficulties when the variation in the insert sizes is high. To address this problem, we first transform mate-pairs into edge-pair histograms that allow one to better estimate the distance between edges in the assembly graph that represent regions linked by multiple mate-pairs. Further, we combine the ideas of mate-pair transformation and PDBGs to construct new data structures for genome assembly: pathsets and pathset graphs.},
added-at = {2012-04-20T21:26:27.000+0200},
author = {Pham, Son K. and Antipov, Dmitry and Sirotkin, Alexander and Tesler, Glenn and Pevzner, Pavel A. and Alekseyev, Max A.},
bibsource = {DBLP, http://dblp.uni-trier.de},
biburl = {https://www.bibsonomy.org/bibtex/20d39f7564b92bf744f0935da06b6ce2f/ytyoun},
booktitle = {RECOMB},
crossref = {DBLP:conf/recomb/2012},
doi = {10.1007/978-3-642-29627-7_21},
editor = {Chor, Benny},
interhash = {f5dd2e12a1a16b26ca3781713a8446c2},
intrahash = {0d39f7564b92bf744f0935da06b6ce2f},
isbn = {978-3-642-29626-0},
keywords = {bioinformatics sequencing},
pages = {200-212},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
timestamp = {2016-06-14T13:40:36.000+0200},
title = {Pathset Graphs: A Novel Approach for Comprehensive Utilization
of Paired Reads in Genome Assembly},
volume = 7262,
year = 2012
}