%0 Journal Article %1 bhatia2013estimating %A Bhatia, G %A Patterson, N %A Sankararaman, S %A Price, A L %D 2013 %J Genome Res %K F_ST population_genetics review %N 9 %P 1514-1521 %R 10.1101/gr.154831.113 %T Estimating and interpreting FST: the impact of rare variants %U https://www.ncbi.nlm.nih.gov/pubmed/23861382 %V 23 %X In a pair of seminal papers, Sewall Wright and Gustave Mal\é\cot introduced FST as a measure of structure in natural populations. In the decades that followed, a number of papers provided differing definitions, estimation methods, and interpretations beyond Wright's. While this diversity in methods has enabled many studies in genetics, it has also introduced confusion regarding how to estimate FST from available data. Considering this confusion, wide variation in published estimates of FST for pairs of HapMap populations is a cause for concern. These estimates changed-in some cases more than twofold-when comparing estimates from genotyping arrays to those from sequence data. Indeed, changes in FST from sequencing data might be expected due to population genetic factors affecting rare variants. While rare variants do influence the result, we show that this is largely through differences in estimation methods. Correcting for this yields estimates of FST that are much more concordant between sequence and genotype data. These differences relate to three specific issues: (1) estimating FST for a single SNP, (2) combining estimates of FST across multiple SNPs, and (3) selecting the set of SNPs used in the computation. Changes in each of these aspects of estimation may result in FST estimates that are highly divergent from one another. Here, we clarify these issues and propose solutions.

@article{bhatia2013estimating, abstract = {In a pair of seminal papers, Sewall Wright and Gustave Mal\{\'e\}cot introduced FST as a measure of structure in natural populations. In the decades that followed, a number of papers provided differing definitions, estimation methods, and interpretations beyond Wright's. While this diversity in methods has enabled many studies in genetics, it has also introduced confusion regarding how to estimate FST from available data. Considering this confusion, wide variation in published estimates of FST for pairs of HapMap populations is a cause for concern. These estimates changed-in some cases more than twofold-when comparing estimates from genotyping arrays to those from sequence data. Indeed, changes in FST from sequencing data might be expected due to population genetic factors affecting rare variants. While rare variants do influence the result, we show that this is largely through differences in estimation methods. Correcting for this yields estimates of FST that are much more concordant between sequence and genotype data. These differences relate to three specific issues: (1) estimating FST for a single SNP, (2) combining estimates of FST across multiple SNPs, and (3) selecting the set of SNPs used in the computation. Changes in each of these aspects of estimation may result in FST estimates that are highly divergent from one another. Here, we clarify these issues and propose solutions. }, added-at = {2019-05-16T01:58:47.000+0200}, author = {Bhatia, G and Patterson, N and Sankararaman, S and Price, A L}, biburl = {https://www.bibsonomy.org/bibtex/255907278efce0f1c7440fe32e0e17068/peter.ralph}, doi = {10.1101/gr.154831.113}, interhash = {d7dddd5faab82555fda75b9a7a6e72a2}, intrahash = {55907278efce0f1c7440fe32e0e17068}, journal = {Genome Res}, keywords = {F_ST population_genetics review}, month = sep, number = 9, pages = {1514-1521}, pmid = {23861382}, timestamp = {2019-05-16T01:58:47.000+0200}, title = {Estimating and interpreting {FST}: the impact of rare variants}, url = {https://www.ncbi.nlm.nih.gov/pubmed/23861382}, volume = 23, year = 2013 }