@article {Bodea043166, author = {Corneliu A. Bodea and Benjamin M. Neale and Stephan Ripke and The International IBD Genetics Consortium and Mark J. Daly and Bernie Devlin and Kathryn Roeder}, title = {A method to exploit the structure of genetic ancestry space to enhance case-control studies}, elocation-id = {043166}, year = {2016}, doi = {10.1101/043166}, publisher = {Cold Spring Harbor Laboratory}, abstract = {One goal of human genetics is to understand the genetic basis of disease, a challenge for diseases of complex inheritance because risk alleles are few relative to the vast set of benign variants. Risk variants are often sought by association studies in which allele frequencies in cases are contrasted with those from population-based samples used as controls. In an ideal world we would know population-level allele frequencies, releasing researchers to focus on case subjects. We argue this ideal is possible, at least theoretically, and we outline a path to achieving it in reality. If such a resource were to exist, it would yield ample savings and would facilitate the effective use of data repositories by removing administrative and technical barriers. We call this concept the Universal Control Repository Network (UNICORN), a means to perform association analyses without necessitating direct access to individual-level control data. Our approach to UNICORN uses existing genetic resources and various statistical tools to analyze these data, including hierarchical clustering with spectral analysis of ancestry; and empirical Bayesian analysis along with Gaussian spatial processes to estimate ancestry-specific allele frequencies. We demonstrate our approach using tens of thousands of controls from studies of Crohn{\textquoteright}s disease, showing how it controls false positives, provides power similar to that achieved when all control data are directly accessible, and enhances power when control data are limiting or even imperfectly matched ancestrally. These results highlight how UNICORN can enable reliable, powerful and convenient genetic association analyses without access to the individual level data.}, URL = {https://www.biorxiv.org/content/early/2016/03/10/043166}, eprint = {https://www.biorxiv.org/content/early/2016/03/10/043166.full.pdf}, journal = {bioRxiv} }