@article{She01012009,
author = {She, Rong and Chu, Jeffrey S.-C. and Wang, Ke and Pei, Jian and Chen, Nansheng}, 
title = {genBlastA: Enabling BLAST to identify homologous gene sequences},
volume = {19}, 
number = {1}, 
pages = {143-149}, 
year = {2009}, 
doi = {10.1101/gr.082081.108}, 
abstract ={BLAST is an extensively used local similarity search tool for identifying homologous sequences. When a gene sequence (either protein sequence or nucleotide sequence) is used as a query to search for homologous sequences in a genome, the search results, represented as a list of high-scoring pairs (HSPs), are fragments of candidate genes rather than full-length candidate genes. Relevant HSPs (“signals”), which represent candidate genes in the target genome sequences, are buried within a report that contains also hundreds to thousands of random HSPs (“noises”). Consequently, BLAST results are often overwhelming and confusing even to experienced users. For effective use of BLAST, a program is needed for extracting relevant HSPs that represent candidate homologous genes from the entire HSP report. To achieve this goal, we have designed a graph-based algorithm, genBlastA, which automatically filters HSPs into well-defined groups, each representing a candidate gene in the target genome. The novelty of genBlastA is an edge length metric that reflects a set of biologically motivated requirements so that each shortest path corresponds to an HSP group representing a homologous gene. We have demonstrated that this novel algorithm is both efficient and accurate for identifying homologous sequences, and that it outperforms existing approaches with similar functionalities.}, 
URL = {http://genome.cshlp.org/content/19/1/143.abstract}, 
eprint = {http://genome.cshlp.org/content/19/1/143.full.pdf+html}, 
journal = {Genome Research} 
}