From: Bo Li <bli@cs.wisc.edu>
Date: Sun, 9 Mar 2014 20:40:25 +0000 (-0500)
Subject: Fixed a typo in rsem-calculate-expression's document; Added multi-thread and memory... 
X-Git-Url: https://git.donarmstrong.com/?p=rsem.git;a=commitdiff_plain;h=f5dc7f9504136b08210ca8a5f3371060b4c04f60

Fixed a typo in rsem-calculate-expression's document; Added multi-thread and memory options to samtools sort thanks to Dr. Samuel Arvidsson
---

diff --git a/README.md b/README.md
index f6a88dc..b93678d 100644
--- a/README.md
+++ b/README.md
@@ -454,9 +454,9 @@ RSEM uses the [Boost C++](http://www.boost.org) and
 [EBSeq](http://www.biostat.wisc.edu/~ningleng/EBSeq_Package/) for
 differential expression analysis.
 
-We thank earonesty for contributing patches.
+We thank earonesty, Dr. Samuel Arvidsson for contributing patches.
 
-We thank Han Lin for suggesting possible fixes. 
+We thank Han Lin, j.miller for suggesting possible fixes. 
 
 ## <a name="license"></a> License
 
diff --git a/rsem-calculate-expression b/rsem-calculate-expression
index d724167..b523edd 100755
--- a/rsem-calculate-expression
+++ b/rsem-calculate-expression
@@ -16,6 +16,7 @@ my $CONFIDENCE = 0.95;
 my $NSPC = 50;
 
 my $NMB = 1024; # default
+my $SortMem = "1G"; # default as 1G per thread
 
 my $status = 0;
 
@@ -116,6 +117,7 @@ GetOptions("keep-intermediate-files" => \$keep_intermediate_files,
 	   "var" => \$var_opt,
 	   "calc-ci" => \$calcCI,
 	   "ci-memory=i" => \$NMB,
+	   "samtools-sort-mem=s" => \$SortMem,
 	   "time" => \$mTime,
 	   "version" => \$version,
 	   "q|quiet" => \$quiet,
@@ -336,7 +338,7 @@ if ($quiet) { $command .= " -q"; }
 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
 
 if ($genBamF) {
-    $command = $dir."sam/samtools sort $sampleName.transcript.bam $sampleName.transcript.sorted";
+    $command = $dir."sam/samtools sort -@ $nThreads -m $SortMem $sampleName.transcript.bam $sampleName.transcript.sorted";
     &runCommand($command);
     $command = $dir."sam/samtools index $sampleName.transcript.sorted.bam";
     &runCommand($command);
@@ -344,7 +346,7 @@ if ($genBamF) {
     if ($genGenomeBamF) {
 	$command = $dir."rsem-tbam2gbam $refName $sampleName.transcript.bam $sampleName.genome.bam";
 	&runCommand($command);
-	$command = $dir."sam/samtools sort $sampleName.genome.bam $sampleName.genome.sorted";
+	$command = $dir."sam/samtools sort -@ $nThreads -m $SortMem $sampleName.genome.bam $sampleName.genome.sorted";
 	&runCommand($command);
 	$command = $dir."sam/samtools index $sampleName.genome.sorted.bam";
 	&runCommand($command);
@@ -468,7 +470,7 @@ RSEM reads header information from input by default. If this option is on, heade
 
 =item B<-p/--num-threads> <int>
 
-Number of threads to use. Both Bowtie/Bowtie2 and expression estimation will use this many threads. (Default: 1)
+Number of threads to use. Both Bowtie/Bowtie2, expression estimation and 'samtools sort' will use this many threads. (Default: 1)
 
 =item B<--no-bam-output>
 
@@ -528,7 +530,7 @@ Input quality scores are solexa encoded (from GA Pipeline ver. < 1.3). (Default:
 
 =item B<--bowtie2>
 
-Use Bowtie 2 instead of Bowtie to align reads. Since currently RSEM does not handle indel, local and discordant alignments, the Bowtie2 parameters are set in a way to avoid those alignments. In particular, we use options '--very-sensitive --dpad 0 --gbar 99999999 --mp 1,1 --np 1 --score-min L,0,-rate'. "-rate", the last parameter of '--score-min' is the negative value of the mismatch rate provided by option '--bowtie2-mismatch-rate'. If reads are paired-end, we additionally use options '--no-mixed' and '--no-discordant'. (Default: off)
+Use Bowtie 2 instead of Bowtie to align reads. Since currently RSEM does not handle indel, local and discordant alignments, the Bowtie2 parameters are set in a way to avoid those alignments. In particular, we use options '--sensitive --dpad 0 --gbar 99999999 --mp 1,1 --np 1 --score-min L,0,-0.1' by default. "-0.1", the last parameter of '--score-min' is the negative value of the maximum mismatch rate allowed. This rate can be set by option '--bowtie2-mismatch-rate'. If reads are paired-end, we additionally use options '--no-mixed' and '--no-discordant'. (Default: off)
 
 =item B<--bowtie2-path> <path>
 
@@ -578,6 +580,10 @@ Number of bins in the RSPD. Only relevant when '--estimate-rspd' is specified.
 
 Maximum size (in memory, MB) of the auxiliary buffer used for computing credibility intervals (CI). Set it larger for a faster CI calculation. However, leaving 2 GB memory free for other usage is recommended. (Default: 1024)
 
+=item B<--samtools-sort-mem> <string>
+
+Set the maximum memory per thread that can be used by 'samtools sort'. <string> represents the memory and accepts suffices 'K/M/G'. RSEM will pass <string> to the '-m' option of 'samtools sort'.  Please note that the default used here is different from the default used by samtools. (Default: 1G)
+
 =item B<--keep-intermediate-files>
 
 Keep temporary files generated by RSEM.  RSEM creates a temporary directory, 'sample_name.temp', into which it puts all intermediate output files. If this directory already exists, RSEM overwrites all files generated by previous RSEM runs inside of it. By default, after RSEM finishes, the temporary directory is deleted.  Set this option to prevent the deletion of this directory and the intermediate files inside of it. (Default: off)