In shotgun sequencing projects, the genome or BAC length is not always known. We approach estimating genome length by first estimating the repeat structure of the genome or BAC, sometimes of interest in its own right, on the basis of a set of random reads from a genome project. Moreover, we can find the consensus for repeat families before assembly. Our methods are based on the l-tuple content of the reads.
%0 Journal Article
%1 li2003estimating
%A Li, X
%A Waterman, M S
%D 2003
%J Genome Res
%K repeats sequencing summary_statistics transposable_elements
%N 8
%P 1916-1922
%R 10.1101/gr.1251803
%T Estimating the repeat structure and length of DNA sequences using L-tuples
%U http://www.ncbi.nlm.nih.gov/pubmed/12902383
%V 13
%X In shotgun sequencing projects, the genome or BAC length is not always known. We approach estimating genome length by first estimating the repeat structure of the genome or BAC, sometimes of interest in its own right, on the basis of a set of random reads from a genome project. Moreover, we can find the consensus for repeat families before assembly. Our methods are based on the l-tuple content of the reads.
@article{li2003estimating,
abstract = {In shotgun sequencing projects, the genome or BAC length is not always known. We approach estimating genome length by first estimating the repeat structure of the genome or BAC, sometimes of interest in its own right, on the basis of a set of random reads from a genome project. Moreover, we can find the consensus for repeat families before assembly. Our methods are based on the l-tuple content of the reads.},
added-at = {2014-02-18T22:53:52.000+0100},
author = {Li, X and Waterman, M S},
biburl = {https://www.bibsonomy.org/bibtex/254e8bbbdf2be0122a740feff841940ae/peter.ralph},
doi = {10.1101/gr.1251803},
interhash = {837b015c9aaa8c06da375fbcb5fa41e3},
intrahash = {54e8bbbdf2be0122a740feff841940ae},
journal = {Genome Res},
keywords = {repeats sequencing summary_statistics transposable_elements},
month = aug,
number = 8,
pages = {1916-1922},
pmid = {12902383},
timestamp = {2014-02-18T22:53:52.000+0100},
title = {Estimating the repeat structure and length of {DNA} sequences using {L}-tuples},
url = {http://www.ncbi.nlm.nih.gov/pubmed/12902383},
volume = 13,
year = 2003
}