%0 Journal Article %1 Chaisson:2004aa %A Chaisson, Mark %A Pevzner, Pavel %A Tang, Haixu %D 2004 %J Bioinformatics %K Algorithms, Alignment, Analysis, Base Contig DNA, Data, Expression Feasibility Gene Mapping, Molecular Profiling, Sequence Studies, %N 13 %P 2067--74 %R 10.1093/bioinformatics/bth205 %T Fragment assembly with short reads %V 20 %X MOTIVATION: Current DNA sequencing technology produces reads of about 500-750 bp, with typical coverage under 10x. New sequencing technologies are emerging that produce shorter reads (length 80-200 bp) but allow one to generate significantly higher coverage (30x and higher) at low cost. Modern assembly programs and error correction routines have been tuned to work well with current read technology but were not designed for assembly of short reads. RESULTS: We analyze the limitations of assembling reads generated by these new technologies and present a routine for base-calling in reads prior to their assembly. We demonstrate that while it is feasible to assemble such short reads, the resulting contigs will require significant (if not prohibitive) finishing efforts. AVAILABILITY: Available from the web at http://www.cse.ucsd.edu/groups/bioinformatics/software.html

@article{Chaisson:2004aa, abstract = {MOTIVATION: Current DNA sequencing technology produces reads of about 500-750 bp, with typical coverage under 10x. New sequencing technologies are emerging that produce shorter reads (length 80-200 bp) but allow one to generate significantly higher coverage (30x and higher) at low cost. Modern assembly programs and error correction routines have been tuned to work well with current read technology but were not designed for assembly of short reads. RESULTS: We analyze the limitations of assembling reads generated by these new technologies and present a routine for base-calling in reads prior to their assembly. We demonstrate that while it is feasible to assemble such short reads, the resulting contigs will require significant (if not prohibitive) finishing efforts. AVAILABILITY: Available from the web at http://www.cse.ucsd.edu/groups/bioinformatics/software.html}, added-at = {2007-09-17T20:19:41.000+0200}, affiliation = {Bioinformatics Program, University of California San Diego, La Jolla, CA 92093, USA. mchaisso@bioinf.ucsd.edu}, author = {Chaisson, Mark and Pevzner, Pavel and Tang, Haixu}, biburl = {https://www.bibsonomy.org/bibtex/2187f0308ae9e5fa2f47476b9ab180a20/dzerbino}, doi = {10.1093/bioinformatics/bth205}, interhash = {fe2d0450683c59fc5fa83a3294e626d6}, intrahash = {187f0308ae9e5fa2f47476b9ab180a20}, issue = {13}, journal = {Bioinformatics}, keywords = {Algorithms, Alignment, Analysis, Base Contig DNA, Data, Expression Feasibility Gene Mapping, Molecular Profiling, Sequence Studies,}, language = {English}, local-url = {file://localhost/Users/danielzerbino/Documents/Papers/2004/Chaisson/Bioinformatics%202004%20Chaisson.pdf}, month = Sep, number = 13, pages = {2067--74}, pii = {bth205}, pmid = {15059830}, timestamp = {2007-09-17T20:19:43.000+0200}, title = {Fragment assembly with short reads}, uri = {papers://055852FE-1648-42FE-91D0-8CA474D2B905/Paper/p25}, volume = 20, year = 2004 }