%
% NOTE -- ONLY EDIT THE .Rnw FILE!!!  The .tex file is
% likely to be overwritten.
%
\documentclass[landscape]{article}

\usepackage{amsmath,pstricks}
\usepackage[authoryear,round]{natbib}
\usepackage{hyperref}
\usepackage{sectsty}
\usepackage{landscape}
\usepackage{graphics}

\textwidth=10.9in
\textheight=6.5in
%\parskip=.3cm
\oddsidemargin=.0in
\evensidemargin=.0in
\headheight=-.3in


\newcommand{\scscst}{\scriptscriptstyle}
\newcommand{\scst}{\scriptstyle}
\newcommand{\dimfo}{\fontsize{14}{16}\selectfont}
\newcommand{\expfo}{\fontsize{18}{22}\selectfont}


\newcommand{\Rfunction}[1]{{\texttt{#1}}}
\newcommand{\Robject}[1]{{\texttt{#1}}}
\newcommand{\Rpackage}[1]{{\textit{#1}}}
\newcommand{\Rmethod}[1]{{\texttt{#1}}}
\newcommand{\Rfunarg}[1]{{\texttt{#1}}}
\newcommand{\Rclass}[1]{{\textit{#1}}}

\newcommand\bi{\begin{itemize}}
\newcommand\ei{\end{itemize}}

\textwidth=8.2in

\bibliographystyle{plainnat} 

\renewcommand{\familydefault}{\sfdefault}

\usepackage[T1]{fontenc}

\newcommand\cp{{\clearpage}}
\newcommand\sts[1]{\Huge \textbf{#1}}
\newcommand\stsh[1]{\huge \textbf{#1}}
\newcommand\stsL[1]{\Large \textbf{#1}}
\newcommand\stsl[1]{\large \textbf{#1}}

\begin{document}

\fontsize{18}{22}
\selectfont
\allsectionsfont{\sffamily}
\sectionfont{\fontfamily{phv}\fontsize{18}{22}\selectfont}
\subsectionfont{\fontfamily{phv}\fontsize{18}{22}\selectfont}
\subsubsectionfont{\fontfamily{phv}\fontsize{18}{22}\selectfont}


%\setkeys{Gin}{width=0.85\textwidth}

{
\Huge
\begin{center}
\textbf{Pathway annotation case study \\ intro insert, March 2008 bioconductor course
\\ \copyright 2008, VJ Carey Ph D}
\end{center}
\begin{itemize}
\item "Gene sets" are popular tools for analysis
\item rapid survey of a large family of gene sets is
facilitated by programming
\item conversion of moderately conventional annotation for
genes/gene sets to operators on Bioconductor data structures
is illustrated
\ei
}

\clearpage

{\sts{Is my gene in any pathways?}
\bi
\item case of TBX21
\item KEGG -- nothing
\item NCBI -- nothing
\item What about the Broad GSEA-related gene sets?
\item Bioconductor package GSEABase helps navigate these
\ei
}

\clearpage

{\stsL{broadsets.rda}
<<dd>>=
library(GSEABase)
if (!exists("broadsets")) load("broadsets.rda")
broadsets
class(broadsets)
getClass(class(broadsets))
@
}

\clearpage

{\stsL{information on a set}
<<dd2>>=
broadsets[[1]]
details(broadsets[[1]])
@
}

\clearpage

{\stsL{GeneSetCollection operations}
\bi
\item a GeneSetCollection instance is an R list of
GeneSets
\item iteration over list elements is relatively
easy in R
\item need to know how to operate usefully on
a GeneSet
\item poked at one above with `details' method
\item another method of interest: geneIds
<<dog>>=
geneIds(broadsets[[1]])
allids = lapply(broadsets, geneIds)
tbxchk = sapply(allids, function(x) any(x == "TBX21"))
sum(tbxchk)
hastbx = which(tbxchk)
sapply(broadsets[hastbx], setName)
@
\ei
}

\clearpage

{\stsL{More info}
\bi
\item we have identified 12 'gene sets' that include TBX21
\item what are they?  we can see that one is just a cytoband
\ei
<<lkm>>=
broadsets[["V$LYF1_01"]]
@
}

\clearpage

{\stsL{More info}
<<lkddd>>=
details(broadsets[["V$LYF1_01"]])
longDescription(broadsets[["V$LYF1_01"]])
@
\bi
\item
This longDescription result is not very useful ... it is
a long string of HTML.  If we write it to a file, we can run
a browser.  Use writeLines
\ei
}

\clearpage

\setkeys{Gin}{width=1.15\textwidth}
\includegraphics{lyf1}

\clearpage

\includegraphics{lyf1b}

\clearpage

{\sts{Upshots}
\bi
\item A collection of over 3000 sets of genes is
bound to a single R variable name (broadsets)
\item Each set is self-documenting and includes a list of
HUGO identifiers (as given by Broad)
\item  methods \verb+geneIds+, \verb+details+, \verb+longDescription+
provide uniform information on each set
\item programming expertise useful
\bi
\item general string matching (\texttt{x == 'TBX21'}) or pattern
matching (grep, caseconversion etc) available directly to constituents

\item shortcuts \verb+broadsets[["V$LYF1_01"]]+
\ei
\item exploit sets and their structures for thorough statistical analysis
\ei
}

\clearpage

{\stsL{Application -- note number of features retained}
<<dodiii>>=
library(Biobase)
library(ALL)
data(ALL)
keep = broadsets[["V$LYF1_01"]]
geneIdType(keep) = AnnotationIdentifier(annotation(ALL))
ALL[ geneIds(keep), ]
@
}

\end{document}