% Created 2013-12-02 Mon 23:12
\documentclass{article}
<<style, eval=TRUE, echo=FALSE, results="asis">>=
BiocStyle::latex()
@
\usepackage[utf8]{inputenc}
\usepackage[T1]{fontenc}
\usepackage{fixltx2e}
\usepackage{graphicx}
\usepackage{longtable}
\usepackage{float}
\usepackage{wrapfig}
\usepackage{rotating}
\usepackage[normalem]{ulem}
\usepackage{amsmath}
\usepackage{textcomp}
\usepackage{marvosym}
\usepackage{wasysym}
\usepackage{amssymb}
\usepackage{hyperref}
\tolerance=1000
\author{Julian Gehring, EMBL Heidelberg}
\date{\today}
\title{COSMIC 67}
\hypersetup{
  pdfkeywords={},
  pdfsubject={},
  pdfcreator={Emacs 24.1.1 (Org mode 8.2.3c)}}
\begin{document}

\maketitle
\tableofcontents

%\VignetteEngine{knitr::knitr}
%\VignetteIndexEntry{COSMIC.67 - PDF}
%\VignettePackage{COSMIC.67}

<<echo=FALSE, results='hide'>>=
set.seed(1)
options(width=65)
library(knitr)
opts_chunk$set(background = "#FFFFFF", comment = NA, fig.path = "")
@ %def


\section{Introduction}
\label{sec-1}

The \Biocpkg{COSMIC.67} package provides the curated mutations published
with the COSMIC release version 67 (2013-10-24).  Both variants found in coding
and non-coding regions are included and offered as a single object of class
'CollapsedVCF' and a bgzipped and tabix-index 'VCF' file.

Additionally, the package contains the Cancer Gene Census, a list of genes
causally linked to cancer.

\section{Accessing and Using the Data}
\label{sec-2}

<<load_packages,results='hide'>>=
library(VariantAnnotation)
library(GenomicRanges)
@ %def

<<load_data>>=
data(package = "COSMIC.67")
data(cosmic_67, package = "COSMIC.67")
@ %def

<<overlap_with_tp53>>=
tp53_range = GRanges("17", IRanges(7565097, 7590856))
vcf_path = system.file("vcf", "cosmic_67.vcf.gz", package = "COSMIC.67")
cosmic_tp53 = readVcf(vcf_path, genome = "GRCh37", ScanVcfParam(which = tp53_range))
cosmic_tp53
@ %def

<<CGC>>=
data(cgc_67, package = "COSMIC.67")
head(cgc_67)
@ %def

For details on the collection and curation of the original data,
please see the webpage of the COSMIC project:
\url{http://cancer.sanger.ac.uk/cancergenome/projects/cosmic/}.
\section{Data Provenance}
\label{sec-3}

\subsection{COSMIC Mutations}
\label{sec-3-1}

The following steps are performed for importing and processing of the
VCF data:

\begin{enumerate}
\item Downloading of the VCF files 'CosmicCodingMuts\_v67\_20131024.vcf.gz'
and 'CosmicNonCodingVariants\_v67\_20131024.vcf.gz' from
'ftp://ngs.sanger.ac.uk/production/cosmic/' to 'inst/raw/'.

\item Importing of both files to R using 'readVcf'.

\item Sorting of the seqlevels and adding 'seqinfo' data for the toplevel
chromosomes of 'GRCh37'.

\item Merging of both objects, sorting according to genomic position.

\item Converting the object to class \texttt{VariantAnnotation::VRanges}.

\item Converting the 'character' columns to 'factors'.

\item Saving the merged object to 'data/cosmic\_v67\_vcf.rda'.

\item Exporting the merged object as a bgzipped and tabix-indexed 'VCF'
to 'inst/vcf/cosmic\_v67.vcf.gz'.
\end{enumerate}

\subsection{Cancer Gene Census}
\label{sec-3-2}

The following steps are performed for importing and processing of the
Cancer Gene Census data:

\begin{enumerate}
\item Downloading of the 'cancer\_gene\_census.tsv' file from
   \url{ftp://ftp.sanger.ac.uk/pub/CGP/cosmic/data_export} to 'inst/raw'.

\item Import of the files as a data frame.

\item Annotation of the 'HGNC' and 'ENSEMBLID' identifiers, using the
'ENTREZ gene ID' as query with the 'org.Hs.eg.db' object.

\item Saving the object to 'data/cgc\_67.rda'.
\end{enumerate}
\section{Data Source}
\label{sec-4}

The mutation data was obtained from the Sanger Institute Catalogue Of
Somatic Mutations In Cancer web site, \url{http://www.sanger.ac.uk/cosmic}

\href{http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2409828/}{Bamford et al (2004):\\
The COSMIC (Catalogue of Somatic Mutations in Cancer) database and website.\\
Br J Cancer, 91,355-358.}

For details on the usage and redistribution of the data, please see
\url{ftp://ftp.sanger.ac.uk/pub/CGP/cosmic/GUIDELINES_ON_THE_USE_OF_THIS_DATA.txt}.

\section{References}
\label{sec-5}

\begin{itemize}
\item \url{http://cancer.sanger.ac.uk/cancergenome/projects/cosmic/}

\item \url{http://nar.oxfordjournalls.org/content/39/suppl_1/D945.long}

\item \url{ftp://ftp.sanger.ac.uk/pub/CGP/cosmic/GUIDELINES_ON_THE_USE_OF_THIS_DATA.txt}
\end{itemize}

\section{Session Info}
\label{sec-6}

<<echo=FALSE>>=
sessionInfo()
@ %def
% Emacs 24.1.1 (Org mode 8.2.3c)
\end{document}