Needles in the Haystack: Identifying Individuals Present in Pooled Genomic Data Export

@article{citeulike:5887977, abstract = {Recent publications have described and applied a novel metric that quantifies the genetic distance of an individual with respect to two population samples, and have suggested that the metric makes it possible to infer the presence of an individual of known genotype in a sample for which only the marginal allele frequencies are known. However, the assumptions, limitations, and utility of this metric remained incompletely characterized. Here we present empirical tests of the method using publicly accessible genotypes, as well as analytical investigations of the method's strengths and limitations. The results reveal that the null distribution is sensitive to the underlying assumptions, making it difficult to accurately calibrate thresholds for classifying an individual as a member of the population samples. As a result, the false-positive rates obtained in practice are considerably higher than previously believed. However, despite the metric's inadequacies for identifying the presence of an individual in a sample, our results suggest potential avenues for future research on tuning this method to problems of ancestry inference or disease prediction. By revealing both the strengths and limitations of the proposed method, we hope to elucidate situations in which this distance metric may be used in an appropriate manner. We also discuss the implications of our findings in forensics applications and in the protection of GWAS participant privacy.}, author = {Braun, Rosemary and Rowe, William and Schaefer, Carl and Zhang, Jinghui and Buetow, Kenneth}, citeulike-article-id = {5887977}, citeulike-linkout-0 = {http://dx.doi.org/10.1371/journal.pgen.1000668}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/19798441}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=19798441}, day = {2}, doi = {10.1371/journal.pgen.1000668}, issn = {1553-7404}, journal = {PLoS Genet}, keywords = {gwa, pooling}, month = {October}, number = {10}, pages = {e1000668+}, posted-at = {2009-10-20 10:11:10}, priority = {2}, publisher = {Public Library of Science}, title = {Needles in the Haystack: Identifying Individuals Present in Pooled Genomic Data}, url = {http://dx.doi.org/10.1371/journal.pgen.1000668}, volume = {5}, year = {2009} }

TY - JOUR ID - citeulike:5887977 L3 - citeulike-article-id:5887977 N2 - Recent publications have described and applied a novel metric that quantifies the genetic distance of an individual with respect to two population samples, and have suggested that the metric makes it possible to infer the presence of an individual of known genotype in a sample for which only the marginal allele frequencies are known. However, the assumptions, limitations, and utility of this metric remained incompletely characterized. Here we present empirical tests of the method using publicly accessible genotypes, as well as analytical investigations of the method's strengths and limitations. The results reveal that the null distribution is sensitive to the underlying assumptions, making it difficult to accurately calibrate thresholds for classifying an individual as a member of the population samples. As a result, the false-positive rates obtained in practice are considerably higher than previously believed. However, despite the metric's inadequacies for identifying the presence of an individual in a sample, our results suggest potential avenues for future research on tuning this method to problems of ancestry inference or disease prediction. By revealing both the strengths and limitations of the proposed method, we hope to elucidate situations in which this distance metric may be used in an appropriate manner. We also discuss the implications of our findings in forensics applications and in the protection of GWAS participant privacy. IS - 10 JF - PLoS Genet SN - 1553-7404 TI - Needles in the Haystack: Identifying Individuals Present in Pooled Genomic Data PB - Public Library of Science VL - 5 SP - e1000668 KW - gwa KW - pooling AU - Braun, Rosemary AU - Rowe, William AU - Schaefer, Carl AU - Zhang, Jinghui AU - Buetow, Kenneth PY - 2009/10/02/ UR - http://dx.doi.org/10.1371/journal.pgen.1000668 ER -