Automated De Novo Identification of Repeat Sequence Families in Sequenced Genomes Export

@article{bao:recon, abstract = {10.1101/gr.88502 Repetitive sequences make up a major part of eukaryotic genomes. We have developed an approach for the de novo identification and classification of repeat sequence families that is based on extensions to the usual approach of single linkage clustering of local pairwise alignments between genomic sequences. Our extensions use multiple alignment information to define the boundaries of individual copies of the repeats and to distinguish homologous but distinct repeat element families. When tested on the human genome, our approach was able to properly identify and group known transposable elements. The program,, should be useful for first-pass automatic classification of repeats in newly sequenced genomes. [The following individuals kindly provided reagents, samples, or unpublished information as indicated in the paper: R. Klein.]}, address = {Howard Hughes Medical Institute and Department of Genetics, Washington University School of Medicine, St. Louis, Missouri 63110, USA.}, author = {Bao, Zhirong and Eddy, Sean R.}, booktitle = {Genome Research}, citeulike-article-id = {454555}, citeulike-linkout-0 = {http://dx.doi.org/10.1101/gr.88502}, citeulike-linkout-1 = {http://genome.cshlp.org/content/12/8/1269.abstract}, citeulike-linkout-2 = {http://genome.cshlp.org/content/12/8/1269.full.pdf}, citeulike-linkout-3 = {http://www.genome.org/cgi/content/abstract/12/8/1269}, citeulike-linkout-4 = {http://view.ncbi.nlm.nih.gov/pubmed/12176934}, citeulike-linkout-5 = {http://www.hubmed.org/display.cgi?uids=12176934}, day = {1}, doi = {10.1101/gr.88502}, issn = {1088-9051}, journal = {Genome Research}, keywords = {assembly, repeat}, month = {August}, number = {8}, pages = {1269--1276}, posted-at = {2008-05-29 14:49:09}, priority = {2}, title = {Automated De Novo Identification of Repeat Sequence Families in Sequenced Genomes}, url = {http://dx.doi.org/10.1101/gr.88502}, volume = {12}, year = {2002} }

TY - JOUR ID - bao:recon L3 - citeulike-article-id:454555 N2 - 10.1101/gr.88502 Repetitive sequences make up a major part of eukaryotic genomes. We have developed an approach for the de novo identification and classification of repeat sequence families that is based on extensions to the usual approach of single linkage clustering of local pairwise alignments between genomic sequences. Our extensions use multiple alignment information to define the boundaries of individual copies of the repeats and to distinguish homologous but distinct repeat element families. When tested on the human genome, our approach was able to properly identify and group known transposable elements. The program,, should be useful for first-pass automatic classification of repeats in newly sequenced genomes. [The following individuals kindly provided reagents, samples, or unpublished information as indicated in the paper: R. Klein.] IS - 8 JF - Genome Research SN - 1088-9051 AD - Howard Hughes Medical Institute and Department of Genetics, Washington University School of Medicine, St. Louis, Missouri 63110, USA. EP - 1276 TI - Automated De Novo Identification of Repeat Sequence Families in Sequenced Genomes VL - 12 T2 - Genome Research SP - 1269 KW - assembly KW - repeat AU - Bao, Zhirong AU - Eddy, Sean PY - 2002/08/01/ UR - http://dx.doi.org/10.1101/gr.88502 ER -