Please cite the paper below for the ChIPpeakAnno package.
Lihua J Zhu, Claude Gazin, Nathan D Lawson, Herve Pages, Simon M Lin, David S Lapointe and Michael R Green, ChIPpeakAnno: a Bioconductor package to annotate ChIP-seq and ChIP-chip data. BMC Bioinformatics. 2010, 11:237
Zhu LJ. Integrative analysis of ChIP-chip and ChIP-seq dataset. Methods Mol Biol. 2013;1067:105-24.
Corresponding BibTeX entries:
@Article{,
title = {ChIPpeakAnno: a Bioconductor package to annotate ChIP-seq
and ChIP-chip data},
author = {Lihua Zhu and Claude Gazin and Nathan Lawson and Hervé
Pagès and Simon Lin and David Lapointe and Michael Green},
journal = {BMC Bioinformatics},
volume = {11},
year = {2010},
number = {1},
pages = {237},
url = {http://www.biomedcentral.com/1471-2105/11/237},
doi = {10.1186/1471-2105-11-237},
pubmedid = {20459804},
issn = {1471-2105},
abstract = {BACKGROUND:Chromatin immunoprecipitation (ChIP)
followed by high-throughput sequencing (ChIP-seq) or ChIP
followed by genome tiling array analysis (ChIP-chip) have become
standard technologies for genome-wide identification of
DNA-binding protein target sites. A number of algorithms have
been developed in parallel that allow identification of binding
sites from ChIP-seq or ChIP-chip datasets and subsequent
visualization in the University of California Santa Cruz (UCSC)
Genome Browser as custom annotation tracks. However, summarizing
these tracks can be a daunting task, particularly if there are a
large number of binding sites or the binding sites are
distributed widely across the genome.RESULTS:We have developed
ChIPpeakAnno as a Bioconductor package within the statistical
programming environment R to facilitate batch annotation of
enriched peaks identified from ChIP-seq, ChIP-chip, cap analysis
of gene expression (CAGE) or any experiments resulting in a large
number of enriched genomic regions. The binding sites annotated
with ChIPpeakAnno can be viewed easily as a table, a pie chart or
plotted in histogram form, i.e., the distribution of distances to
the nearest genes for each set of peaks. In addition, we have
implemented functionalities for determining the significance of
overlap between replicates or binding sites among transcription
factors within a complex, and for drawing Venn diagrams to
visualize the extent of the overlap between replicates.
Furthermore, the package includes functionalities to retrieve
sequences flanking putative binding sites for PCR amplification,
cloning, or motif discovery, and to identify Gene Ontology (GO)
terms associated with adjacent genes.CONCLUSIONS:ChIPpeakAnno
enables batch annotation of the binding sites identified from
ChIP-seq, ChIP-chip, CAGE or any technology that results in a
large number of enriched genomic regions within the statistical
programming environment R. Allowing users to pass their own
annotation data such as a different Chromatin immunoprecipitation
(ChIP) preparation and a dataset from literature, or existing
annotation packages, such as GenomicFeatures and BSgenome,
provides flexibility. Tight integration to the biomaRt package
enables up-to-date annotation retrieval from the BioMart
database.},
}
@InBook{,
booktitle = {Tilling Arrays},
title = {Integrative analysis of ChIP-chip and ChIP-seq dataset},
author = {Lihua Zhu},
chapter = {4},
editor = {Tin-Lap Lee and Alfred Chun Shui Luk},
publisher = {Humana Press},
journal = {Methods in Molecular Biology},
volume = {1067},
year = {2013},
pages = {-19},
url =
{http://link.springer.com/protocol/10.1007%2F978-1-62703-607-8_8},
doi = {10.1007/978-1-62703-607-8_8},
pubmedid = {23975789},
issn = {1064-3745},
abstract = {Epigenetic regulation and interactions between
transcription factors and regulatory genomic regions play crucial
roles in controlling transcriptional regulatory networks that
drive development, environmental responses, and disease.
Chromatin immunoprecipitation (ChIP) followed by high-throughput
sequencing (ChIP-seq) and ChIP followed by genomic tiling
microarray hybridization (ChIP-chip) are the two of the most
widely used technologies for genome-wide identification of DNA
protein interactions and histone modification in vivo. Many
algorithms and tools have been developed and evaluated that allow
identification of transcription factor binding sites from
ChIP-seq or ChIP-chip datasets. However, binding site
identification is only the first step; the ultimate goal is to
discover the regulatory network of the transcription factor (TF).
Here, we present a common workflow for downstream analysis of
ChIP-chip and ChIP-seq with an emphasis on annotating binding
sites and integration with gene expression data to identify
direct and indirect targets of the TF. These tools will help with
the overall goal of unraveling transcriptional regulatory
networks using datasets publicly available in GEO.},
}