%\VignetteIndexEntry{oligoClasses Vignette}
%\VignetteKeywords{infractructure}
%\VignettePackage{oligoClasses}
\documentclass{article}
\usepackage{amsmath}
\usepackage{graphicx}
\usepackage{natbib}
\usepackage{color}
\usepackage[margin=1in]{geometry}

\newcommand{\scscst}{\scriptscriptstyle}
\newcommand{\scst}{\scriptstyle}
\newcommand{\Rpackage}[1]{\textit{#1}}
\newcommand{\Rfunction}[1]{\texttt{#1}}
\newcommand{\Robject}[1]{\texttt{#1}}
\newcommand{\R}{\textsf{R}}
\newcommand{\crlmm}{\Rpackage{crlmm}}
\newcommand{\oligo}{\Rpackage{oligo}}

\begin{document}
\title{Infrastructure classes for high-throughput SNP data}
\author{Robert Scharpf and Benilton Carvalho}
\maketitle


<<setup, echo=FALSE>>=
options(width=75)
library(oligoClasses)
@ 

This document describes some of the infrastructure classes used for
high-throughput genomic data.  For the classes used to organize SNP
data, we provide examples for initialization and illustrate some of the
accessors.  We should add a diagram showing the relationships of these
classes here.

[ Insert diagram of classes here ]

\section{Feature-level classes}

\section{Locus-level classes}

The examples below are completely simulated and are not meant to convey
any biological plausibility.

\subsection{SnpSet}

\subsubsection{Initialization}

<<initialize_snpset>>=
	theCalls <- matrix(sample(1:3, 20, rep=TRUE), nc=2)
	p <- matrix(runif(20), nc=2)
	theConfs <- round(-1000*log2(1-p))
	obj <- new("SnpSet", call=theCalls, callProbability=theConfs)
@ 

\subsubsection{Accessors}
<<accessors_snpset>>=
calls(obj)
confs(obj)
@ 

\subsubsection{Annotating}
<<annotation_snpset>>=
if(require("genomewidesnp6Crlmm")){
	ids <- c("SNP_A-2131660", "SNP_A-1967418", "SNP_A-1969580", "SNP_A-4263484",
		 "SNP_A-1978185", "SNP_A-4264431", "SNP_A-1980898", "SNP_A-1983139",
		 "SNP_A-4265735", "SNP_A-1995832")
	rownames(theCalls) <- rownames(p) <- rownames(theConfs) <- ids
	obj <- new("SnpSet", call=theCalls, callProbability=theConfs,
		   annotation="genomewidesnp6")
	featureData(obj) <- addFeatureAnnotation(obj)
	fvarLabels(obj)
	isSnp(obj)
	position(obj)
	chromosome(obj)
}
@ 

\subsection{CopyNumberSet}

\subsubsection{Initialization}

\subsubsection{Accessors}

\subsubsection{Annotating}

\subsection{CNSet}

\subsubsection{Initialization}

<<example_cnSet>>=
theCalls <- matrix(2, nc=2, nrow=10)
A <- matrix(sample(1:1000, 20), 10,2)
B <- matrix(sample(1:1000, 20), 10,2)
CA <- matrix(rnorm(20, 1), nrow=10)
CB <- matrix(rnorm(20, 1), nrow=10)
p <- matrix(runif(20), nc=2)
theConfs <- round(-1000*log2(1-p))
obj <- new("CNSet",
	   alleleA=A,
	   alleleB=B,
	   call=theCalls,
	   callProbability=theConfs,
	   CA=CA,
	   CB=CB)
@ 

\subsubsection{Accessors}

<<cnset_accessors>>=
calls(obj)
confs(obj)
A(obj)
B(obj)
CA(obj)
CB(obj)
@ 

\subsubsection{Annotating}
Annotating with chromosome and physical position:

%% BC: this is broken!
<<annotation_cnset, eval=FALSE>>=
if(require("genomewidesnp6Crlmm")){
	ids <- c("SNP_A-2131660", "SNP_A-1967418", "SNP_A-1969580", "SNP_A-4263484",
		 "SNP_A-1978185", "SNP_A-4264431", "SNP_A-1980898", "SNP_A-1983139",
		 "SNP_A-4265735", "SNP_A-1995832")
	rownames(theCalls) <- rownames(p) <- rownames(theConfs) <- ids
	rownames(A) <- rownames(B) <- rownames(CA) <- rownames(CB) <- ids
	obj2 <- new("CNSet",
		    alleleA=A,
		    alleleB=B,
		    call=theCalls,
		    callProbability=theConfs,
		    CA=CA,
		    CB=CB, annotation="genomewidesnp6")
	fvarLabels(obj2)
	## additional accessors
	isSnp(obj2)
	chromosome(obj2)
	position(obj2)
}
@


\section{Session Information}

The version number of R and packages loaded for generating the vignette
were:

<<echo=FALSE, results=tex>>=
toLatex(sessionInfo())
@  


\end{document}