% 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”.
@ARTICLE{Hieke:128777,
author = {S. Hieke and A. Benner$^*$ and R. F. Schlenk and M.
Schumacher and L. Bullinger and H. Binder},
title = {{I}dentifying {P}rognostic {SNP}s in {C}linical {C}ohorts:
{C}omplementing {U}nivariate {A}nalyses by {R}esampling and
{M}ultivariable {M}odeling.},
journal = {PLoS one},
volume = {11},
number = {5},
issn = {1932-6203},
address = {Lawrence, Kan.},
publisher = {PLoS},
reportid = {DKFZ-2017-04792},
pages = {e0155226 -},
year = {2016},
abstract = {Clinical cohorts with time-to-event endpoints are
increasingly characterized by measurements of a number of
single nucleotide polymorphisms that is by a magnitude
larger than the number of measurements typically considered
at the gene level. At the same time, the size of clinical
cohorts often is still limited, calling for novel analysis
strategies for identifying potentially prognostic SNPs that
can help to better characterize disease processes. We
propose such a strategy, drawing on univariate testing ideas
from epidemiological case-controls studies on the one hand,
and multivariable regression techniques as developed for
gene expression data on the other hand. In particular, we
focus on stable selection of a small set of SNPs and
corresponding genes for subsequent validation. For
univariate analysis, a permutation-based approach is
proposed to test at the gene level. We use regularized
multivariable regression models for considering all SNPs
simultaneously and selecting a small set of potentially
important prognostic SNPs. Stability is judged according to
resampling inclusion frequencies for both the univariate and
the multivariable approach. The overall strategy is
illustrated with data from a cohort of acute myeloid
leukemia patients and explored in a simulation study. The
multivariable approach is seen to automatically focus on a
smaller set of SNPs compared to the univariate approach,
roughly in line with blocks of correlated SNPs. This more
targeted extraction of SNPs results in more stable selection
at the SNP as well as at the gene level. Thus, the
multivariable regression approach with resampling provides a
perspective in the proposed analysis strategy for SNP data
in clinical cohorts highlighting what can be added by
regularized regression techniques compared to univariate
analyses.},
cin = {C060},
ddc = {500},
cid = {I:(DE-He78)C060-20160331},
pnm = {313 - Cancer risk factors and prevention (POF3-313)},
pid = {G:(DE-HGF)POF3-313},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:27159447},
pmc = {pmc:PMC4861340},
doi = {10.1371/journal.pone.0155226},
url = {https://inrepo02.dkfz.de/record/128777},
}