@article{Zerbino01052008, author = {Zerbino, Daniel R. and Birney, Ewan}, title = {Velvet: Algorithms for de novo short read assembly using de Bruijn graphs}, year = {2008}, doi = {10.1101/gr.074492.107}, abstract ={We have developed a new set of algorithms, collectively called “Velvet,” to manipulate de Bruijn graphs for genomic sequence assembly. A de Bruijn graph is a compact representation based on short words (k-mers) that is ideal for high coverage, very short read (25–50 bp) data sets. Applying Velvet to very short reads and paired-ends information only, one can produce contigs of significant length, up to 50-kb N50 length in simulations of prokaryotic data and 3-kb N50 on simulated mammalian BACs. When applied to real Solexa data sets without read pairs, Velvet generated contigs of ∼8 kb in a prokaryote and 2 kb in a mammalian BAC, in close agreement with our simulated results without read-pair information. Velvet represents a new approach to assembly that can leverage very short reads in combination with read pairs to produce useful assemblies.}, URL = {http://genome.cshlp.org/content/early/2008/04/07/gr.074492.107.abstract}, eprint = {http://genome.cshlp.org/content/early/2008/04/07/gr.074492.107.full.pdf+html}, journal = {Genome Research} }