%\VignetteIndexEntry{smlSet construction overview}
%\VignetteKeywords{Genetical genomics,SNP,expression}
%\VignettePackage{GGBase}


%
% NOTE -- ONLY EDIT THE .Rnw FILE!!!  The .tex file is
% likely to be overwritten.
%
\documentclass[12pt]{article}

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


\textwidth=6.2in
\textheight=8.5in
%\parskip=.3cm
\oddsidemargin=.1in
\evensidemargin=.1in
\headheight=-.3in

\newcommand{\scscst}{\scriptscriptstyle}
\newcommand{\scst}{\scriptstyle}


\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}}}

\textwidth=6.2in

\bibliographystyle{plainnat} 
 
\begin{document}
%\setkeys{Gin}{width=0.55\textwidth}

\title{how to make an smlSet from hapmap data}
\author{VJ Carey}
\maketitle

\begin{enumerate}
\item \textbf{Raw data acquisition:} Obtain the hapmap files from the bulk data download.
A typical filename is 
\begin{verbatim}
genotypes_chrY_YRI_r23_nr.b36_fwd.txt.gz
\end{verbatim}

\item use snpStats read.HapMap.data to obtain the associated SnpMatrix
and support data frame.  We do this for the 24 main chromosome files.
We save the SnpMatrix for chromosome n to C[nn].rda.
Be careful with the ordering of filenames -- should match desired ordering
of chromosomes.
%An example, after saving the reads to .rda files, is
<<dol,eval=FALSE,echo=FALSE>>=
load("C1.rda")
names(C1)
C1[[2]][1,]
@
%Note that the chromosome is 10, so there is no correspondence between
%rda filename and chromosome.  We will have to check the contents of
%the file to assign to a chromosome, but that is not too onerous.

%\item \textbf{Formatting of location data:} Pull the 'support' data together so that a SNP location resource can
%be made.
%
%The steps are
%\begin{enumerate}
%\item iterate over the saved reads and accumulate the location data frame.
%Assuming that the only .rda files in the current folder are
%read.HapMap.data results, the following will work, yielding a dataframe
%called supp.
%
%<<dor,keep.source=TRUE,eval=FALSE>>=
%supp = NULL; 
%for (i in 1:24) { 
%  cat(i)
%  load(ofi[i]); fn = gsub(".rda", "", ofi[i]); supp = rbind(supp, get(fn)$snp.supp) 
%  rm(fn)
%  gc()
%}
%@
%\item get the dataframe into order -- sort by chromosomes and position within
%chromosome:
%
%<<doo,eval=FALSE>>=
%cc = as.character(supp$Chrom)
%cc = gsub("chr", "", cc)
%cc[cc=="X"] = 23
%cc[cc=="Y"] = 24
%ncc = as.numeric(cc)
%oo = order(cc, supp$Posi)
%osupp = supp[oo,]
%save(osupp, file="osupp.rda")
%@
%
%\end{enumerate}
%
%\item serialize the location data to SQLite
%
%<<doarr,eval=FALSE>>=
%supp2SQLite(osupp, "hmyriAmbB36_23a" , "hmyriAmbB36_23a.sqlite")
%@
%
%Now, for example, we have
%\begin{verbatim}
%> myc = dbConnect(myd, "hmyriAmbB36_23a.sqlite")
%> dbGetQuery(myc, "select * from hmyriAmbB36_23a limit 5")
%      rsid alleles chrnum   loc
%1 10399749       Y      1 45162
%2  2949421       W      1 45413
%3  2691310       M      1 46844
%4  4030303       Y      1 72434
%5  4030300       K      1 72515
%\end{verbatim}
%
\item \textbf{Create a list of SnpMatrix of genotype data:}

<<domo,eval=FALSE>>=
ofi = dir(patt="C.*rda")
allsm = list()
cn = rep(NA,24)
for (i in 1:24) { 
  cat(i)
  load(ofi[i]); fn = gsub(".rda", "", ofi[i]); allsm[[i]] =  get(fn)[[1]]
  cn[i] = as.character(get(fn)[[2]][1,"Chromosome"])
  print(fn)
  rm(fn)
  gc()
}
@

Don't forget to give names 1:22, X, Y to the list elements.

\item Create an environment and assign the list created above to symbol \texttt{smList}
in that environment.  This environment is a valid value for the smlEnv slot of a
smlSet instance.

\item The chromInds slot gives numerical indices indicating which chromosomes are
included; see hmceuB36.2021 in GGtools for an example.


\item  remaining slots are as in ExpressionSet


\end{enumerate}

\end{document}