Deleterious SNP prediction: be mindful of your training data! Export

@article{citeulike:1218509, abstract = {Motivation: To predict which of the vast number of human single nucleotide polymorphisms (SNPs) are deleterious to gene function or likely to be disease associated is an important problem, and many methods have been reported in the literature. All methods require data sets of mutations classified as deleterious' or neutral' for training and/or validation. While different workers have used different data sets there has been no study of which is best. Here, the three most commonly used data sets are analysed. We examine their contents and relate this to classifiers, with the aims of revealing the strengths and pitfalls of each data set, and recommending a best approach for future studies. Results: The data sets examined are shown to be substantially different in content, particularly with regard to amino acid substitutions, reflecting the different ways in which they are derived. This leads to differences in classifiers and reveals some serious pitfalls of some data sets, making them less than ideal for non-synonymous SNP prediction. Availability: Software is available on request from the authors. Contact: d.r.westhead@leeds.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online. 10.1093/bioinformatics/btl649}, author = {Care, Matthew A. and Needham, Chris J. and Bulpitt, Andrew J. and Westhead, David R.}, citeulike-article-id = {1218509}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btl649}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/23/6/664}, citeulike-linkout-2 = {http://www.ingentaconnect.com/content/oup/cabios/2007/00000023/00000006/art00664}, citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/17234639}, citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=17234639}, day = {15}, doi = {10.1093/bioinformatics/btl649}, issn = {1367-4803}, journal = {Bioinformatics}, keywords = {bioinformatics, snp}, month = {March}, number = {6}, pages = {664--672}, posted-at = {2007-04-12 10:45:50}, priority = {2}, publisher = {Oxford University Press}, title = {Deleterious SNP prediction: be mindful of your training data!}, url = {http://dx.doi.org/10.1093/bioinformatics/btl649}, volume = {23}, year = {2007} }

TY - JOUR ID - citeulike:1218509 L3 - citeulike-article-id:1218509 N2 - Motivation: To predict which of the vast number of human single nucleotide polymorphisms (SNPs) are deleterious to gene function or likely to be disease associated is an important problem, and many methods have been reported in the literature. All methods require data sets of mutations classified as deleterious' or neutral' for training and/or validation. While different workers have used different data sets there has been no study of which is best. Here, the three most commonly used data sets are analysed. We examine their contents and relate this to classifiers, with the aims of revealing the strengths and pitfalls of each data set, and recommending a best approach for future studies. Results: The data sets examined are shown to be substantially different in content, particularly with regard to amino acid substitutions, reflecting the different ways in which they are derived. This leads to differences in classifiers and reveals some serious pitfalls of some data sets, making them less than ideal for non-synonymous SNP prediction. Availability: Software is available on request from the authors. Contact: d.r.westhead@leeds.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online. 10.1093/bioinformatics/btl649 IS - 6 JF - Bioinformatics SN - 1367-4803 EP - 672 TI - Deleterious SNP prediction: be mindful of your training data! PB - Oxford University Press VL - 23 SP - 664 KW - bioinformatics KW - snp AU - Care, Matthew AU - Needham, Chris AU - Bulpitt, Andrew AU - Westhead, David PY - 2007/03/15/ UR - http://dx.doi.org/10.1093/bioinformatics/btl649 ER -