A general approach to single-nucleotide polymorphism discovery.

@article{citeulike:1106952, abstract = {Single-nucleotide polymorphisms (SNPs) are the most abundant form of human genetic variation and a resource for mapping complex genetic traits. The large volume of data produced by high-throughput sequencing projects is a rich and largely untapped source of SNPs (refs 2, 3, 4, 5). We present here a unified approach to the discovery of variations in genetic sequence data of arbitrary DNA sources. We propose to use the rapidly emerging genomic sequence as a template on which to layer often unmapped, fragmentary sequence data and to use base quality values to discern true allelic variations from sequencing errors. By taking advantage of the genomic sequence we are able to use simpler yet more accurate methods for sequence organization: fragment clustering, paralogue identification and multiple alignment. We analyse these sequences with a novel, Bayesian inference engine, POLYBAYES, to calculate the probability that a given site is polymorphic. Rigorous treatment of base quality permits completely automated evaluation of the full length of all sequences, without limitations on alignment depth. We demonstrate this approach by accurate SNP predictions in human ESTs aligned to finished and working-draft quality genomic sequences, a data set representative of the typical challenges of sequence-based SNP discovery.}, address = {Washington University Department of Genetics and Genome Sequencing Center, St. Louis, Missouri, USA. gmarth@watson.wustl.edu}, author = {Marth, G. T. and Korf, I. and Yandell, M. D. and Yeh, R. T. and Gu, Z. and Zakeri, H. and Stitziel, N. O. and Hillier, L. and Kwok, P. Y. and Gish, W. R. }, citeulike-article-id = {1106952}, doi = {10.1038/70570}, issn = {1061-4036}, journal = {Nat Genet}, keywords = {qual}, month = {December}, number = {4}, pages = {452--456}, posted-at = {2008-03-21 15:37:44}, priority = {2}, title = {A general approach to single-nucleotide polymorphism discovery.}, url = {http://dx.doi.org/10.1038/70570}, volume = {23}, year = {1999} }

TY - JOUR ID - citeulike:1106952 L3 - citeulike-article-id:1106952 TI - A general approach to single-nucleotide polymorphism discovery. JF - Nat Genet VL - 23 IS - 4 SP - 452 EP - 456 AD - Washington University Department of Genetics and Genome Sequencing Center, St. Louis, Missouri, USA. gmarth@watson.wustl.edu SN - 1061-4036 N2 - Single-nucleotide polymorphisms (SNPs) are the most abundant form of human genetic variation and a resource for mapping complex genetic traits. The large volume of data produced by high-throughput sequencing projects is a rich and largely untapped source of SNPs (refs 2, 3, 4, 5). We present here a unified approach to the discovery of variations in genetic sequence data of arbitrary DNA sources. We propose to use the rapidly emerging genomic sequence as a template on which to layer often unmapped, fragmentary sequence data and to use base quality values to discern true allelic variations from sequencing errors. By taking advantage of the genomic sequence we are able to use simpler yet more accurate methods for sequence organization: fragment clustering, paralogue identification and multiple alignment. We analyse these sequences with a novel, Bayesian inference engine, POLYBAYES, to calculate the probability that a given site is polymorphic. Rigorous treatment of base quality permits completely automated evaluation of the full length of all sequences, without limitations on alignment depth. We demonstrate this approach by accurate SNP predictions in human ESTs aligned to finished and working-draft quality genomic sequences, a data set representative of the typical challenges of sequence-based SNP discovery. KW - qual AU - Marth, GT AU - Korf, I AU - Yandell, MD AU - Yeh, RT AU - Gu, Z AU - Zakeri, H AU - Stitziel, NO AU - Hillier, L AU - Kwok, PY AU - Gish, WR PY - 1999/12// UR - http://dx.doi.org/10.1038/70570 ER -