Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences. Export

@article{citeulike:777430, abstract = {MOTIVATION: In 2001 and 2002, we published two papers (Bioinformatics, 17, 282-283, Bioinformatics, 18, 77-82) describing an ultrafast protein sequence clustering program called cd-hit. This program can efficiently cluster a huge protein database with millions of sequences. However, the applications of the underlying algorithm are not limited to only protein sequences clustering, here we present several new programs using the same algorithm including cd-hit-2d, cd-hit-est and cd-hit-est-2d. Cd-hit-2d compares two protein datasets and reports similar matches between them; cd-hit-est clusters a DNA/RNA sequence database and cd-hit-est-2d compares two nucleotide datasets. All these programs can handle huge datasets with millions of sequences and can be hundreds of times faster than methods based on the popular sequence comparison and database search tools, such as BLAST.}, address = {Burnham Institute for Medical Research La Jolla, CA 92037, USA. liwz@sdsc.edu}, author = {Li, W. and Godzik, A.}, citeulike-article-id = {777430}, citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/16731699}, citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=16731699}, day = {1}, issn = {1367-4803}, journal = {Bioinformatics}, keywords = {clustering, nucleotide, protein}, month = {July}, number = {13}, pages = {1658--1659}, posted-at = {2009-11-02 09:46:49}, priority = {2}, title = {Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/16731699}, volume = {22}, year = {2006} }

TY - JOUR ID - citeulike:777430 L3 - citeulike-article-id:777430 N2 - MOTIVATION: In 2001 and 2002, we published two papers (Bioinformatics, 17, 282-283, Bioinformatics, 18, 77-82) describing an ultrafast protein sequence clustering program called cd-hit. This program can efficiently cluster a huge protein database with millions of sequences. However, the applications of the underlying algorithm are not limited to only protein sequences clustering, here we present several new programs using the same algorithm including cd-hit-2d, cd-hit-est and cd-hit-est-2d. Cd-hit-2d compares two protein datasets and reports similar matches between them; cd-hit-est clusters a DNA/RNA sequence database and cd-hit-est-2d compares two nucleotide datasets. All these programs can handle huge datasets with millions of sequences and can be hundreds of times faster than methods based on the popular sequence comparison and database search tools, such as BLAST. IS - 13 JF - Bioinformatics SN - 1367-4803 AD - Burnham Institute for Medical Research La Jolla, CA 92037, USA. liwz@sdsc.edu EP - 1659 TI - Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences. VL - 22 SP - 1658 KW - clustering KW - nucleotide KW - protein AU - Li, W AU - Godzik, A PY - 2006/07/01/ UR - http://view.ncbi.nlm.nih.gov/pubmed/16731699 ER -