A genealogical interpretation of principal components analysis. Export

@article{citeulike:5952306, abstract = {Principal components analysis, PCA, is a statistical method commonly used in population genetics to identify structure in the distribution of genetic variation across geographical location and ethnic background. However, while the method is often used to inform about historical demographic processes, little is known about the relationship between fundamental demographic parameters and the projection of samples onto the primary axes. Here I show that for SNP data the projection of samples onto the principal components can be obtained directly from considering the average coalescent times between pairs of haploid genomes. The result provides a framework for interpreting PCA projections in terms of underlying processes, including migration, geographical isolation, and admixture. I also demonstrate a link between PCA and Wright's f(st) and show that SNP ascertainment has a largely simple and predictable effect on the projection of samples. Using examples from human genetics, I discuss the application of these results to empirical data and the implications for inference.}, author = {McVean, Gil}, citeulike-article-id = {5952306}, citeulike-linkout-0 = {http://dx.doi.org/10.1371/journal.pgen.1000686}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/19834557}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=19834557}, day = {16}, doi = {10.1371/journal.pgen.1000686}, issn = {1553-7404}, journal = {PLoS genetics}, keywords = {stats}, month = {October}, number = {10}, pages = {e1000686+}, posted-at = {2009-11-02 17:30:25}, priority = {2}, publisher = {Public Library of Science}, title = {A genealogical interpretation of principal components analysis.}, url = {http://dx.doi.org/10.1371/journal.pgen.1000686}, volume = {5}, year = {2009} }

TY - JOUR ID - citeulike:5952306 L3 - citeulike-article-id:5952306 N2 - Principal components analysis, PCA, is a statistical method commonly used in population genetics to identify structure in the distribution of genetic variation across geographical location and ethnic background. However, while the method is often used to inform about historical demographic processes, little is known about the relationship between fundamental demographic parameters and the projection of samples onto the primary axes. Here I show that for SNP data the projection of samples onto the principal components can be obtained directly from considering the average coalescent times between pairs of haploid genomes. The result provides a framework for interpreting PCA projections in terms of underlying processes, including migration, geographical isolation, and admixture. I also demonstrate a link between PCA and Wright's f(st) and show that SNP ascertainment has a largely simple and predictable effect on the projection of samples. Using examples from human genetics, I discuss the application of these results to empirical data and the implications for inference. IS - 10 JF - PLoS genetics SN - 1553-7404 TI - A genealogical interpretation of principal components analysis. PB - Public Library of Science VL - 5 SP - e1000686 KW - stats AU - McVean, Gil PY - 2009/10/16/ UR - http://dx.doi.org/10.1371/journal.pgen.1000686 ER -