% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{Prokopenko:145644,
author = {Prokopenko, D. and Hecker, J. and Silverman, E. and Pagano,
M. and Noethen, M. and Lange, Christoph and Loehlein Fie,
H.},
title = {{A}36: {U}tilizing the {J}accard {I}ndex to {R}eveal
{P}opulation{S}tratification in {S}equencing {D}ata: {A}
{S}imulation{S}tudy and an {A}pplication to the 1000
{G}enomes{P}roject},
journal = {Human heredity},
volume = {79},
number = {1},
issn = {0001-5652},
reportid = {DZNE-2020-00974},
pages = {44},
year = {2015},
abstract = {Population stratification is one of the major sources of
confounding in genetic association studies, potentially
causing falsepositive and false-negative results. The
effectiveness of existingadjustment approaches which are
mostly built on the estimationof the genetic
variance/covariance matrix is unclear for rare variants,
since those variants are genetically much ‘younger’
andmight represent a different pattern of population
structure.Here, we present a novel approach for the
identification of population substructure in high
density-genotyping data/next generation sequencing data. The
approach exploits the co-appearances of rare genetic
variants in individuals. The method can beapplied to all
available genetic loci, does not require linkage
disequilibrium (LD) pruning, and is computationally fast.
Usingsequencing data from the 1000 Genomes Project, the
features of the approach are illustrated and compared to
existing methodology (i.e. EIGENSTRAT). We find that our
approach works particularly well for genetic loci with very
small minor allele frequencies. The results suggest that the
inclusion of rare-variantdata/sequencing data in our
approach provides a much higherresolution-picture of
population-substructure than it can be obtained with
existing methodology. Furthermore, we performedextensive
simulation studies based on the minor allele frequencies of
the European populations. We find scenarios where ourmethod
was able to control the type 1 error more precisely
andshowed higher power.},
month = {Apr},
date = {2015-04-16},
organization = {43rd European Mathematical Genetics
Meeting 2015, Brest (France), 16 Apr
2015 - 17 Apr 2015},
cin = {U T4 Researchers - Bonn},
ddc = {610},
cid = {I:(DE-2719)7000008},
pnm = {345 - Population Studies and Genetics (POF3-345)},
pid = {G:(DE-HGF)POF3-345},
typ = {PUB:(DE-HGF)1 / PUB:(DE-HGF)16},
url = {https://pub.dzne.de/record/145644},
}