%0 Journal Article %1 galinsky2015principal %A Galinsky, Kevin J %A Bhatia, Gaurav %A Loh, Po-Ru %A Georgiev, Stoyan %A Mukherjee, Sayan %A Patterson, Nick J %A Price, Alkes L %D 2015 %I Cold Spring Harbor Labs Journals %J bioRxiv %K Krylov_methods PCA linear_algebra methods scans_for_selection software %R 10.1101/018143 %T Fast principal components analysis reveals independent evolution of ADH1B gene in Europe and East Asia %U http://biorxiv.org/content/early/2015/04/22/018143 %X Principal components analysis (PCA) is a widely used tool for inferring population structure and correcting confounding in genetic data. We introduce a new algorithm, FastPCA, that leverages recent advances in random matrix theory to accurately approximate top PCs while reducing time and memory cost from quadratic to linear in the number of individuals, a computational improvement of many orders of magnitude. We apply FastPCA to a cohort of 54,734 European Americans, identifying 5 distinct subpopulations spanning the top 4 PCs. Using a new test for natural selection based on population differentiation along these PCs, we replicate previously known selected loci and identify three new signals of selection, including selection in Europeans at the ADH1B gene. The coding variant rs1229984 has previously been associated to alcoholism and shown to be under selection in East Asians; we show that it is a rare example of independent evolution on two continents.

@article{galinsky2015principal, abstract = {Principal components analysis (PCA) is a widely used tool for inferring population structure and correcting confounding in genetic data. We introduce a new algorithm, FastPCA, that leverages recent advances in random matrix theory to accurately approximate top PCs while reducing time and memory cost from quadratic to linear in the number of individuals, a computational improvement of many orders of magnitude. We apply FastPCA to a cohort of 54,734 European Americans, identifying 5 distinct subpopulations spanning the top 4 PCs. Using a new test for natural selection based on population differentiation along these PCs, we replicate previously known selected loci and identify three new signals of selection, including selection in Europeans at the ADH1B gene. The coding variant rs1229984 has previously been associated to alcoholism and shown to be under selection in East Asians; we show that it is a rare example of independent evolution on two continents.}, added-at = {2015-05-01T06:42:50.000+0200}, author = {Galinsky, Kevin J and Bhatia, Gaurav and Loh, Po-Ru and Georgiev, Stoyan and Mukherjee, Sayan and Patterson, Nick J and Price, Alkes L}, biburl = {https://www.bibsonomy.org/bibtex/2400bcc099f5dc47d648709eae32fb968/peter.ralph}, doi = {10.1101/018143}, interhash = {503baf8c59ec281a0fb41c51f14d2d7a}, intrahash = {400bcc099f5dc47d648709eae32fb968}, journal = {bioRxiv}, keywords = {Krylov_methods PCA linear_algebra methods scans_for_selection software}, publisher = {Cold Spring Harbor Labs Journals}, timestamp = {2015-05-01T06:46:45.000+0200}, title = {Fast principal components analysis reveals independent evolution of {ADH1B} gene in {Europe} and {East} {Asia}}, url = {http://biorxiv.org/content/early/2015/04/22/018143}, year = 2015 }