Hello, world! for GATK.
git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@101 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
parent
7bc45b68aa
commit
41fec1565c
Binary file not shown.
|
|
@ -0,0 +1,93 @@
|
|||
\documentclass[11pt,fullpage]{article}
|
||||
\usepackage[urlcolor=blue,colorlinks=true]{hyperref}
|
||||
|
||||
\oddsidemargin 0.0in
|
||||
\textwidth 6.5in
|
||||
|
||||
\begin{document}
|
||||
|
||||
\title{Getting Started with the Genome Analysis Toolkit (GATK)}
|
||||
\author{Matt Hanna}
|
||||
\date{16 Mar 2009}
|
||||
\maketitle
|
||||
|
||||
\section{Build Prerequisites}
|
||||
GATK requires JDK 1.6 and Ant 1.7.1 to compile.
|
||||
|
||||
\section{Getting and Building the Source}
|
||||
GATK is located in the Sting svn repository, and
|
||||
compiles using a build.xml in the root directory.
|
||||
|
||||
Download and build the source as follows:
|
||||
\begin{verbatim}
|
||||
svn co https://svnrepos/Sting/trunk Sting
|
||||
cd Sting
|
||||
ant
|
||||
\end{verbatim}
|
||||
|
||||
\section{Getting Started}
|
||||
The core concept behind GATK is the walker, a class that implements the
|
||||
three core operations, filtering, mapping, and reducing.
|
||||
|
||||
\begin{description}
|
||||
\item [filter] reduces the size of the dataset by applying a predicate.
|
||||
\item [map] Applies a function to each individual element in a dataset,
|
||||
effectively 'mapping' it to a new element.
|
||||
\item [reduce] Inductively combines the elements of a list. The base
|
||||
case is supplied by the reduceInit() function, and the inductive step
|
||||
is performed by the reduce() function.
|
||||
\end{description}
|
||||
Users of the GATK will provide a walker to run their analyses. The engine
|
||||
will produce a result by first filtering the dataset, running a map operation,
|
||||
and finally reducing the map operation to a single result.
|
||||
|
||||
\section{Example}
|
||||
This walker will print output for each read it sees, eventually computing the
|
||||
total number of reads by mapping every read to 1 and summing all the 1s to
|
||||
realize the total number of reads.
|
||||
|
||||
\begin{verbatim}
|
||||
import net.sf.samtools.SAMRecord;
|
||||
|
||||
import org.broadinstitute.sting.gatk.LocusContext;
|
||||
import org.broadinstitute.sting.gatk.walkers.BasicReadWalker;
|
||||
|
||||
/**
|
||||
* Define a class extending from BasicReadWalker with types
|
||||
* <MapType,ReduceType>.
|
||||
*/
|
||||
public class HelloWalker extends BasicReadWalker<Integer,Long> {
|
||||
private Long currentRead = 0L;
|
||||
|
||||
// Maps each read to the value 1.
|
||||
public Integer map(LocusContext context, SAMRecord read) {
|
||||
System.out.printf("Hello read %d%n", ++currentRead );
|
||||
return 1;
|
||||
}
|
||||
|
||||
// Provides an initial value for the reduce function.
|
||||
public Long reduceInit() { return 0L; }
|
||||
|
||||
// Defines how to compute the reduction given a value in the list.
|
||||
public Long reduce(Integer value, Long sum) {
|
||||
return sum + value;
|
||||
}
|
||||
}
|
||||
\end{verbatim}
|
||||
To compile the walker:
|
||||
\begin{verbatim}
|
||||
setenv CLASSPATH $STING_HOME/dist/GenomeAnalysisTK.jar:$STING_HOME/dist/sam-1.0.jar
|
||||
javac HelloWalker.java
|
||||
\end{verbatim}
|
||||
To run the walker:
|
||||
\begin{verbatim}
|
||||
mkdir $STING_HOME/dist/walkers
|
||||
cp HelloWalker.java $STING_HOME/dist/walkers
|
||||
java -Xmx4096m -jar dist/GenomeAnalysisTK.jar \
|
||||
INPUT_FILE=/broad/1KG/legacy_data/trio/na12878.bam \
|
||||
ANALYSIS_NAME=Hello L=chr1:10000000-10000100
|
||||
\end{verbatim}
|
||||
This command will run the walker across a subsection of chromosome 1, operating on
|
||||
reads which align to that subsection.
|
||||
|
||||
\end{document}
|
||||
Loading…
Reference in New Issue