@article {Shringarpure039347, author = {Suyash S. Shringarpure and Carlos D. Bustamante and Kenneth Lange and David H. Alexander}, title = {Efficient analysis of large datasets and sex bias with ADMIXTURE}, elocation-id = {039347}, year = {2016}, doi = {10.1101/039347}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Background: A number of large genomic datasets are being generated for studies of human ancestry and diseases. The ADMIXTURE program is commonly used to infer individual ancestry from genomic data.Results: We describe two improvements to the ADMIXTURE software. The first enables ADMIXTURE to infer ancestry for a new set of individuals using cluster allele frequencies from a reference set of individuals. Using data from the 1000 Genomes Project, we show that this allows ADMIXTURE to infer ancestry for 10,920 individuals in a few hours (a 5x speedup). This mode also allows ADMIXTURE to correctly estimate individual ancestry and allele frequencies from a set of related individuals. The second modification allows ADMIXTURE to correctly handle X-chromosome (and other haploid) data from both males and females. We demonstrate increased power to detect sex-biased admixture in African-American individuals from the 1000 Genomes project using this extension.Conclusions: These modifications make ADMIXTURE more efficient and versatile, allowing users to extract more information from large genomic datasets.}, URL = {https://www.biorxiv.org/content/early/2016/02/10/039347}, eprint = {https://www.biorxiv.org/content/early/2016/02/10/039347.full.pdf}, journal = {bioRxiv} }