%0 Journal Article %1 Huang:2003aa %A Huang, Xiaoqiu %A Wang, Jianmin %A Aluru, Srinivas %A Yang, Shiaw-Pyng %A Hillier, LaDeana %D 2003 %J Genome Res %K Algorithms, Alignment, Animals, Biology, Computational Contig Genome, Humans Mapping, Mice, Sequence Software, %N 9 %P 2164--70 %R 10.1101/gr.1390403 %T PCAP: a whole-genome assembly program %V 13 %X We describe a whole-genome assembly program named PCAP for processing tens of millions of reads. The PCAP program has several features to address efficiency and accuracy issues in assembly. Multiple processors are used to perform most time-consuming computations in assembly. A more sensitive method is used to avoid missing overlaps caused by sequencing errors. Repetitive regions of reads are detected on the basis of many overlaps with other reads, instead of many shorter word matches with other reads. Contaminated end regions of reads are identified and removed. Generation of a consensus sequence for a contig is based on an alignment of reads in the contig, in which both base quality values and coverage information are used to determine every consensus base. The PCAP program was tested on a mouse whole-genome data set of 30 million reads and a human Chromosome 20 data set of 1.7 million reads. The program is freely available for academic use.

@article{Huang:2003aa, abstract = {We describe a whole-genome assembly program named PCAP for processing tens of millions of reads. The PCAP program has several features to address efficiency and accuracy issues in assembly. Multiple processors are used to perform most time-consuming computations in assembly. A more sensitive method is used to avoid missing overlaps caused by sequencing errors. Repetitive regions of reads are detected on the basis of many overlaps with other reads, instead of many shorter word matches with other reads. Contaminated end regions of reads are identified and removed. Generation of a consensus sequence for a contig is based on an alignment of reads in the contig, in which both base quality values and coverage information are used to determine every consensus base. The PCAP program was tested on a mouse whole-genome data set of 30 million reads and a human Chromosome 20 data set of 1.7 million reads. The program is freely available for academic use.}, added-at = {2007-09-17T20:19:41.000+0200}, affiliation = {Department of Computer Science Iowa State University, Ames, Iowa 50011-1040, USA. xqhuang@cs.iastate.edu}, author = {Huang, Xiaoqiu and Wang, Jianmin and Aluru, Srinivas and Yang, Shiaw-Pyng and Hillier, LaDeana}, biburl = {https://www.bibsonomy.org/bibtex/2e2924e542de58d497e99b128d8659faa/dzerbino}, doi = {10.1101/gr.1390403}, interhash = {f461b8681a355c4fcc7b150a61f27ff0}, intrahash = {e2924e542de58d497e99b128d8659faa}, issue = {9}, journal = {Genome Res}, keywords = {Algorithms, Alignment, Animals, Biology, Computational Contig Genome, Humans Mapping, Mice, Sequence Software,}, language = {English}, local-url = {file://localhost/Users/danielzerbino/Documents/Papers/2003/Huang/Genome%20Res%202003%20Huang.pdf}, month = Sep, number = 9, pages = {2164--70}, pii = {13/9/2164}, pmid = {12952883}, timestamp = {2007-09-17T20:19:43.000+0200}, title = {PCAP: a whole-genome assembly program}, uri = {papers://055852FE-1648-42FE-91D0-8CA474D2B905/Paper/p27}, volume = 13, year = 2003 }