% 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”.
@PHDTHESIS{Allhoff:660061,
author = {Allhoff, Manuel},
othercontributors = {Berlage, Thomas and Zenke, Martin and Jarke, Matthias},
title = {{S}olving the differential peak calling problem in
{C}h{IP}-seq data},
school = {RWTH Aachen University},
type = {Dissertation},
address = {Aachen},
reportid = {RWTH-2016-05102},
pages = {1 Online-Ressource (xiii, 126 Seiten) : Illustrationen,
Diagramme},
year = {2016},
note = {Veröffentlicht auf dem Publikationsserver der RWTH Aachen
University; Dissertation, RWTH Aachen University, 2016},
abstract = {Gene expression is the process of selectively reading
genetic information and it describes a life-essential
mechanism in all known living organisms. Key players in the
regulation of gene expression are proteins that interact
with DNA. DNA-protein interaction sites are nowadays
analyzed in a genome wide manner with chromatin
immunoprecipitation followed by sequencing (ChIP-seq). With
ChIP-seq it becomes possible to assign a discrete value to
each genomic location. The value corresponds to the strength
of the protein binding event. Peaks, that is, regions with a
signal higher than expected by chance, correspond to the
protein-DNA interaction sites. Detecting such peaks is the
fundamental computational challenge in the ChIP-seq
analysis. As in every complex wet lab protocol, ChIP-seq
contains a wide range of potential biases. To reduce the
effect of unwanted biases, ChIP-seq experiments are often
replicated, which helps to distinguish between biological
and random events and to verify the reliability of all
experimental steps. Complex ChIP-seq based studies emphasize
the demand of methods to compare replicated ChIP-seq signals
which are associated with distinct biological conditions.
These studies investigate the differential peak calling
problem which is subject of current biological and medical
research. Solving this problem leads to a deeper
understanding of gene expression regulation. Several
computational challenges arise when detecting differential
peaks (DPs). First, the shape of ChIP-seq peaks depends on
the underlying protein of interest. For ChIP-seq data of
histone modifications, the DNA-protein interactions occur in
mid-size to large domains. Here, domains can span several
hundreds of base pairs and may have intricate patterns of
gains and losses of ChIP-seq signals within the same domain.
In contrast, ChIP-seq from transcription factors mostly
happens in small isolated peaks. Second, artefacts, which
arise due to the complexity of the ChIP-seq protocol,
produce signals with distinct signal-to-noise ratios, even
when they are produced in the same lab and follow the same
protocols. Furthermore, different sequencing depths between
samples aggravate the comparison of their ChIP-seq signal.
Hence, a robust normalization method for the ChIP-seq
signals is required. Finally, clinical samples, where
patients have a distinct genetic background, introduce
further variation to the distinct ChIP-seq signals.
Moreover, replicated ChIP-seq experiments introduce further
complexity which has to be reflected by the use of
sophisticated statistical models. Current differential peak
calling methods fail to cover all listed challenges. They
apply heuristic signal segmentation strategies, such as
window-based approaches, to identify DPs. There are only a
few attempts to normalize ChIP-seq data. Furthermore, most
methods do not support replicates. Hence, there is a clear
need for computational methods that address all challenges.
In this thesis, we propose ODIN and THOR, algorithms to
determine changes of protein-DNA complexes for distinct
cellular conditions in ChIP-seq experiments without and with
replicates. We apply a statistical model (hidden Markov
model) to call DPs and to handle replicates. We also
introduce a novel normalization strategy which is based on
control regions. These features lead to comprehensive
algorithms that accurately call DPs in ChIP-seq signals.
Moreover, the evaluation of differential peak calling
algorithms is an open problem. The research community lacks
both a direct metric to rate the algorithms and data sets
with a genome wide map of DNA-protein interaction sites
which can serve as gold standards. We propose two
alternative approaches for the evaluation. First, we present
indirect metrics to quantify DPs by taking advantage of gene
expression data and second, we use simulation to customize
artificial gold standards.},
cin = {080003 / 122620 / 120000},
ddc = {004},
cid = {$I:(DE-82)080003_20140620$ / $I:(DE-82)122620_20140620$ /
$I:(DE-82)120000_20140620$},
typ = {PUB:(DE-HGF)11},
urn = {urn:nbn:de:hbz:82-rwth-2016-051022},
url = {https://publications.rwth-aachen.de/record/660061},
}
guest ::