Large-scale analysis of gene clustering in bacteria Export

@article{citeulike:2858042, abstract = {An important strategy to study operons and their evolution is to investigate clustering of related genes across multiple bacterial genomes. Although existing algorithms are available that can identify gene clusters across two or more genomes, very few algorithms are efficient enough to study gene clusters across hundreds of genomes. We observe that a querying strategy can be used to analyze gene clusters across a large number of genomes and develop an efficient algorithm to identify all related clusters on a genome from a given query cluster. We use this algorithm to study gene clustering in 400 bacterial genomes by starting from a well-characterized list of operons in Escherichia coli K12 and perform comparative analysis of operon occurrences, gene orientations, and rearrangements both within and across clusters. We show that important biological insights can be obtained by comparing results across these categories. A software program implementing the algorithm (GCQuery) and supplementary data containing detailed results are available at http://faculty.cs.tamu.edu/shsze/gcquery. 10.1101/gr.072322.107}, author = {Yang, Qingwu and Sze, Sing-Hoi}, citeulike-article-id = {2858042}, citeulike-linkout-0 = {http://dx.doi.org/10.1101/gr.072322.107}, citeulike-linkout-1 = {http://www.genome.org/cgi/content/abstract/18/6/949}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/18390694}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=18390694}, day = {1}, doi = {10.1101/gr.072322.107}, journal = {Genome Res.}, keywords = {operon}, month = {June}, number = {6}, pages = {949--956}, posted-at = {2009-03-12 07:35:04}, priority = {2}, title = {Large-scale analysis of gene clustering in bacteria}, url = {http://dx.doi.org/10.1101/gr.072322.107}, volume = {18}, year = {2008} }

TY - JOUR ID - citeulike:2858042 L3 - citeulike-article-id:2858042 N2 - An important strategy to study operons and their evolution is to investigate clustering of related genes across multiple bacterial genomes. Although existing algorithms are available that can identify gene clusters across two or more genomes, very few algorithms are efficient enough to study gene clusters across hundreds of genomes. We observe that a querying strategy can be used to analyze gene clusters across a large number of genomes and develop an efficient algorithm to identify all related clusters on a genome from a given query cluster. We use this algorithm to study gene clustering in 400 bacterial genomes by starting from a well-characterized list of operons in Escherichia coli K12 and perform comparative analysis of operon occurrences, gene orientations, and rearrangements both within and across clusters. We show that important biological insights can be obtained by comparing results across these categories. A software program implementing the algorithm (GCQuery) and supplementary data containing detailed results are available at http://faculty.cs.tamu.edu/shsze/gcquery. 10.1101/gr.072322.107 IS - 6 JF - Genome Res. EP - 956 TI - Large-scale analysis of gene clustering in bacteria VL - 18 SP - 949 KW - operon AU - Yang, Qingwu AU - Sze, Sing-Hoi PY - 2008/06/01/ UR - http://dx.doi.org/10.1101/gr.072322.107 ER -