-#!/usr/bin/perl
+#!/usr/bin/env perl
use Getopt::Long;
use Pod::Usage;
-use File::Basename;
-use Switch;
+
+use FindBin;
+use lib $FindBin::RealBin;
+use rsem_perl_utils qw(runCommand collectResults showVersionInfo);
+
+use Env qw(@PATH);
+@PATH = ($FindBin::RealBin, "$FindBin::RealBin/sam", @PATH);
+
use strict;
#const
my $NSPC = 50;
my $NMB = 1024; # default
+my $SortMem = "1G"; # default as 1G per thread
my $status = 0;
my $genBamF = 1; # default is generating transcript bam file
my $genGenomeBamF = 0;
my $sampling = 0;
+my $calcPME = 0;
my $calcCI = 0;
-my $var_opt = 0; # temporarily, only for internal use
my $quiet = 0;
my $help = 0;
my $strand_specific = 0;
+my $bowtie2 = 0;
+my $bowtie2_path = "";
+my $bowtie2_mismatch_rate = 0.1;
+my $bowtie2_k = 200;
+my $bowtie2_sensitivity_level = "sensitive"; # must be one of "very_fast", "fast", "sensitive", "very_sensitive"
+
+my $seed = "NULL";
+
+my $version = 0;
+
my $mTime = 0;
my ($time_start, $time_end, $time_alignment, $time_rsem, $time_ci) = (0, 0, 0, 0, 0);
+my $mate1_list = "";
+my $mate2_list = "";
+my $inpF = "";
+
+my ($refName, $sampleName, $sampleToken, $temp_dir, $stat_dir, $imdName, $statName) = ();
+my $gap = 32;
+
+my $alleleS = 0;
+
GetOptions("keep-intermediate-files" => \$keep_intermediate_files,
+ "temporary-folder=s" => \$temp_dir,
"no-qualities" => \$no_qual,
"paired-end" => \$paired_end,
"strand-specific" => \$strand_specific,
"phred33-quals" => \$phred33,
"phred64-quals" => \$phred64, #solexa1.3-quals" => \$phred64,
"solexa-quals" => \$solexa,
+ "bowtie2" => \$bowtie2,
+ "bowtie2-path=s" => \$bowtie2_path,
+ "bowtie2-mismatch-rate=f" => \$bowtie2_mismatch_rate,
+ "bowtie2-k=i" => \$bowtie2_k,
+ "bowtie2-sensitivity-level=s" => \$bowtie2_sensitivity_level,
"forward-prob=f" => \$probF,
"fragment-length-min=i" => \$minL,
"fragment-length-max=i" => \$maxL,
"no-bam-output" => sub { $genBamF = 0; },
"output-genome-bam" => \$genGenomeBamF,
"sampling-for-bam" => \$sampling,
- "var" => \$var_opt,
+ "calc-pme" => \$calcPME,
+ "gibbs-burnin=i" => \$BURNIN,
+ "gibbs-number-of-samples=i" => \$NCV,
+ "gibbs-sampling-gap=i", \$SAMPLEGAP,
"calc-ci" => \$calcCI,
+ "ci-credibility-level=f" => \$CONFIDENCE,
"ci-memory=i" => \$NMB,
+ "ci-number-of-samples-per-count-vector=i" => \$NSPC,
+ "samtools-sort-mem=s" => \$SortMem,
+ "seed=i" => \$seed,
"time" => \$mTime,
+ "version" => \$version,
"q|quiet" => \$quiet,
"h|help" => \$help) or pod2usage(-exitval => 2, -verbose => 2);
pod2usage(-verbose => 2) if ($help == 1);
-
+&showVersionInfo($FindBin::RealBin) if ($version == 1);
#check parameters and options
if ($is_sam || $is_bam) {
pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (scalar(@ARGV) != 3);
pod2usage(-msg => "--sam and --bam cannot be active at the same time!", -exitval => 2, -verbose => 2) if ($is_sam == 1&& $is_bam == 1);
- pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m, --phred33-quals, --phred64-quals or --solexa-quals cannot be set if input is SAM/BAM format!", -exitval => 2, -verbose => 2) if ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200 || $phred33 || $phred64 || $solexa);
+ pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m, --phred33-quals, --phred64-quals, --solexa-quals, --bowtie2, --bowtie2-path, --bowtie2-mismatch-rate, --bowtie2-k and --bowtie2-sensitivity-level cannot be set if input is SAM/BAM format!", -exitval => 2, -verbose => 2) if ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200 || $phred33 || $phred64 || $solexa || $bowtie2 || $bowtie2_path ne "" || $bowtie2_mismatch_rate != 0.1 || $bowtie2_k != 200 || $bowtie2_sensitivity_level ne "sensitive");
}
else {
pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (!$paired_end && scalar(@ARGV) != 3 || $paired_end && scalar(@ARGV) != 4);
- pod2usage(-msg => "Only one of --phred33-quals --phred64-quals/--solexa1.3-quals --solexa-suqls can be active!", -exitval => 2, -verbose => 2) if ($phred33 + $phred64 + $solexa > 1);
- podwusage(-msg => "--sam , --bam or --sam-header-info cannot be set if use bowtie aligner to produce alignments!", -exitval => 2, -verbose => 2) if ($is_sam || $is_bam || $fn_list ne "");
+ pod2usage(-msg => "If --no-qualities is set, neither --phred33-quals, --phred64-quals or --solexa-quals can be active!", -exitval => 2, -verbose => 2) if ($no_qual && ($phred33 + $phred64 + $solexa > 0));
+ pod2usage(-msg => "Only one of --phred33-quals, --phred64-quals, and --solexa-quals can be active!", -exitval => 2, -verbose => 2) if ($phred33 + $phred64 + $solexa > 1);
+ pod2usage(-msg => "--sam , --bam or --sam-header-info cannot be set if use bowtie/bowtie2 aligner to produce alignments!", -exitval => 2, -verbose => 2) if ($is_sam || $is_bam || $fn_list ne "");
+ pod2usage(-msg => "--bowtie2-path, --bowtie2-mismatch-rate, --bowtie2-k and --bowtie2-sensitivity-level cannot be set if bowtie aligner is used!", -exitval => 2, -verbose => 2) if (!$bowtie2 && ($bowtie2_path ne "" || $bowtie2_mismatch_rate != 0.1 || $bowtie2_k != 200 || $bowtie2_sensitivity_level ne "sensitive"));
+ pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m cannot be set if bowtie2 aligner is used!", -exitval => 2, -verbose => 2) if ($bowtie2 && ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200));
+ pod2usage(-msg => "Mismatch rate must be within [0, 1]!", -exitval => 2, -verbose => 2) if ($bowtie2 && ($bowtie2_mismatch_rate < 0.0 || $bowtie2_mismatch_rate > 1.0));
+ pod2usage(-msg => "Sensitivity level must be one of \"very_fast\", \"fast\", \"sensitive\", and \"very_sensitive\"!", -exitval => 2, -verbose => 2) if ($bowtie2 && (($bowtie2_sensitivity_level ne "very_fast") && ($bowtie2_sensitivity_level ne "fast") && ($bowtie2_sensitivity_level ne "sensitive") && ($bowtie2_sensitivity_level ne "very_sensitive")));
}
pod2usage(-msg => "Forward probability should be in [0, 1]!", -exitval => 2, -verbose => 2) if ($probF < 0 || $probF > 1);
pod2usage(-msg => "Seed length should be at least 5!\n", -exitval => 2, -verbose => 2) if ($L < 5);
pod2usage(-msg => "--sampling-for-bam cannot be specified if --no-bam-output is specified!\n", -exitval => 2, -verbose => 2) if ($sampling && !$genBamF);
pod2usage(-msg => "--output-genome-bam cannot be specified if --no-bam-output is specified!\n", -exitval => 2, -verbose => 2) if ($genGenomeBamF && !$genBamF);
+pod2usage(-msg => "The seed for random number generator must be a non-negative 32bit integer!\n", -exitval => 2, -verbose => 2) if (($seed ne "NULL") && ($seed < 0 || $seed > 0xffffffff));
+pod2usage(-msg => "The credibility level should be within (0, 1)!\n", -exitval => 2, -verbose => 2) if ($CONFIDENCE <= 0.0 || $CONFIDENCE >= 1.0);
if ($L < 25) { print "Warning: the seed length set is less than 25! This is only allowed if the references are not added poly(A) tails.\n"; }
if ($strand_specific) { $probF = 1.0; }
-my $mate1_list = "";
-my $mate2_list = "";
-my $inpF = "";
-
-my ($refName, $sampleName, $sampleToken, $temp_dir, $stat_dir, $imdName) = ();
-my $gap = 32;
-
if ($paired_end) {
if ($no_qual) { $read_type = 2; }
else { $read_type = 3; }
$sampleName = $ARGV[3];
}
+if (((-e "$refName.ta") && !(-e "$refName.gt")) || (!(-e "$refName.ta") && (-e "$refName.gt"))) {
+ print "Allele-specific expression related reference files are corrupted!\n";
+ exit(-1);
+}
+
+$alleleS = (-e "$refName.ta") && (-e "$refName.gt");
+
if ($genGenomeBamF) {
open(INPUT, "$refName.ti");
my $line = <INPUT>; chomp($line);
if ($pos < 0) { $sampleToken = $sampleName; }
else { $sampleToken = substr($sampleName, $pos + 1); }
-$temp_dir = "$sampleName.temp";
+if ($temp_dir eq "") { $temp_dir = "$sampleName.temp"; }
$stat_dir = "$sampleName.stat";
if (!(-d $temp_dir) && !mkdir($temp_dir)) { print "Fail to create folder $temp_dir.\n"; exit(-1); }
if (!(-d $stat_dir) && !mkdir($stat_dir)) { print "Fail to create folder $stat_dir.\n"; exit(-1); }
$imdName = "$temp_dir/$sampleToken";
+$statName = "$stat_dir/$sampleToken";
if (!$is_sam && !$is_bam && !$no_qual && ($phred33 + $phred64 + $solexa == 0)) { $phred33 = 1; }
my ($mate_minL, $mate_maxL) = (1, $maxL);
if ($bowtie_path ne "") { $bowtie_path .= "/"; }
+if ($bowtie2_path ne "") { $bowtie2_path .= "/"; }
-my ($fn, $dir, $suf) = fileparse($0);
my $command = "";
if (!$is_sam && !$is_bam) {
- $command = $bowtie_path."bowtie";
- if ($no_qual) { $command .= " -f"; }
- else { $command .= " -q"; }
-
- if ($phred33) { $command .= " --phred33-quals"; }
- elsif ($phred64) { $command .= " --phred64-quals"; }
- elsif ($solexa) { $command .= " --solexa-quals"; }
+ if (!$bowtie2) {
+ $command = $bowtie_path."bowtie";
+ if ($no_qual) { $command .= " -f"; }
+ else { $command .= " -q"; }
- $command .= " -n $C -e $E -l $L";
- if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL"; }
- if ($chunkMbs > 0) { $command .= " --chunkmbs $chunkMbs"; }
+ if ($phred33) { $command .= " --phred33-quals"; }
+ elsif ($phred64) { $command .= " --phred64-quals"; }
+ elsif ($solexa) { $command .= " --solexa-quals"; }
- if ($strand_specific || $probF == 1.0) { $command .= " --norc"; }
- elsif ($probF == 0.0) { $command .= " --nofw"; }
-
- $command .= " -p $nThreads -a -m $maxHits -S";
- if ($quiet) { $command .= " --quiet"; }
-
- $command .= " $refName";
- if ($read_type == 0 || $read_type == 1) {
- $command .= " $mate1_list";
+ $command .= " -n $C -e $E -l $L";
+ if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL"; }
+ if ($chunkMbs > 0) { $command .= " --chunkmbs $chunkMbs"; }
+
+ if ($strand_specific || $probF == 1.0) { $command .= " --norc"; }
+ elsif ($probF == 0.0) { $command .= " --nofw"; }
+
+ $command .= " -p $nThreads -a -m $maxHits -S";
+ if ($quiet) { $command .= " --quiet"; }
+
+ $command .= " $refName";
+ if ($read_type == 0 || $read_type == 1) {
+ $command .= " $mate1_list";
+ }
+ else {
+ $command .= " -1 $mate1_list -2 $mate2_list";
+ }
+
+ # pipe to samtools to generate a BAM file
+ $command .= " | samtools view -S -b -o $imdName.bam -";
}
else {
- $command .= " -1 $mate1_list -2 $mate2_list";
+ $command = $bowtie2_path."bowtie2";
+ if ($no_qual) { $command .= " -f"; }
+ else { $command .= " -q"; }
+
+ if ($phred33) { $command .= " --phred33"; }
+ elsif ($phred64) { $command .= " --phred64"; }
+ elsif ($solexa) { $command .= " --solexa-quals"; }
+
+ if ($bowtie2_sensitivity_level eq "very_fast") { $command .= " --very-fast"; }
+ elsif ($bowtie2_sensitivity_level eq "fast") { $command .= " --fast"; }
+ elsif ($bowtie2_sensitivity_level eq "sensitive") { $command .= " --sensitive"; }
+ else { $command .= " --very-sensitive"; }
+
+ $command .= " --dpad 0 --gbar 99999999 --mp 1,1 --np 1 --score-min L,0,-$bowtie2_mismatch_rate";
+
+ if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL --no-mixed --no-discordant"; }
+
+ if ($strand_specific || $probF == 1.0) { $command .= " --norc"; }
+ elsif ($probF == 0.0) { $command .= " --nofw"; }
+
+ $command .= " -p $nThreads -k $bowtie2_k";
+ if ($quiet) { $command .= " --quiet"; }
+
+ $command .= " -x $refName";
+ if ($read_type == 0 || $read_type == 1) {
+ $command .= " -U $mate1_list";
+ }
+ else {
+ $command .= " -1 $mate1_list -2 $mate2_list";
+ }
+
+ # pipe to samtools to generate a BAM file
+ $command .= " | samtools view -S -b -o $imdName.bam -";
}
- $command .= " | gzip > $sampleName.sam.gz";
-
if ($mTime) { $time_start = time(); }
&runCommand($command);
if ($mTime) { $time_end = time(); $time_alignment = $time_end - $time_start; }
- $inpF = "$sampleName.sam.gz";
- $is_sam = 1; # output of bowtie is a sam file
+ $inpF = "$imdName.bam";
+ $is_bam = 1; # alignments are outputed as a BAM file
}
if ($mTime) { $time_start = time(); }
-$command = $dir."rsem-parse-alignments $refName $sampleName $sampleToken";
+$command = "rsem-parse-alignments $refName $imdName $statName";
my $samInpType;
if ($is_sam) { $samInpType = "s"; }
&runCommand($command);
-$command = $dir."rsem-build-read-index $gap";
-switch($read_type) {
- case 0 { $command .= " 0 $quiet $imdName\_alignable.fa"; }
- case 1 { $command .= " 1 $quiet $imdName\_alignable.fq"; }
- case 2 { $command .= " 0 $quiet $imdName\_alignable_1.fa $imdName\_alignable_2.fa"; }
- case 3 { $command .= " 1 $quiet $imdName\_alignable_1.fq $imdName\_alignable_2.fq"; }
-}
+$command = "rsem-build-read-index $gap";
+if ($read_type == 0) { $command .= " 0 $quiet $imdName\_alignable.fa"; }
+elsif ($read_type == 1) { $command .= " 1 $quiet $imdName\_alignable.fq"; }
+elsif ($read_type == 2) { $command .= " 0 $quiet $imdName\_alignable_1.fa $imdName\_alignable_2.fa"; }
+elsif ($read_type == 3) { $command .= " 1 $quiet $imdName\_alignable_1.fq $imdName\_alignable_2.fq"; }
+else { print "Impossible! read_type is not in [1,2,3,4]!\n"; exit(-1); }
&runCommand($command);
my $doesOpen = open(OUTPUT, ">$imdName.mparams");
print OUTPUT "$L\n";
close(OUTPUT);
-$command = $dir."rsem-run-em $refName $read_type $sampleName $sampleToken -p $nThreads";
+my @seeds = ();
+if ($seed ne "NULL") {
+ srand($seed);
+ for (my $i = 0; $i < 3; $i++) {
+ push(@seeds, int(rand(1 << 32)));
+ }
+}
+
+$command = "rsem-run-em $refName $read_type $sampleName $imdName $statName -p $nThreads";
if ($genBamF) {
$command .= " -b $samInpType $inpF";
if ($fn_list ne "") { $command .= " 1 $fn_list"; }
else { $command .= " 0"; }
if ($sampling) { $command .= " --sampling"; }
+ if ($seed ne "NULL") { $command .= " --seed $seeds[0]"; }
}
-if ($calcCI || $var_opt) { $command .= " --gibbs-out"; }
+if ($calcPME || $calcCI) { $command .= " --gibbs-out"; }
if ($quiet) { $command .= " -q"; }
&runCommand($command);
+if ($alleleS) {
+ &collectResults("allele", "$imdName.allele_res", "$sampleName.alleles.results"); # allele level
+ &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
+ &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
+}
+else {
+ &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
+ &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
+}
+
if ($genBamF) {
- $command = $dir."sam/samtools sort $sampleName.transcript.bam $sampleName.transcript.sorted";
+ $command = "samtools sort -@ $nThreads -m $SortMem $sampleName.transcript.bam $sampleName.transcript.sorted";
&runCommand($command);
- $command = $dir."sam/samtools index $sampleName.transcript.sorted.bam";
+ $command = "samtools index $sampleName.transcript.sorted.bam";
&runCommand($command);
if ($genGenomeBamF) {
- $command = $dir."rsem-tbam2gbam $refName $sampleName.transcript.bam $sampleName.genome.bam";
+ $command = "rsem-tbam2gbam $refName $sampleName.transcript.bam $sampleName.genome.bam";
&runCommand($command);
- $command = $dir."sam/samtools sort $sampleName.genome.bam $sampleName.genome.sorted";
+ $command = "samtools sort -@ $nThreads -m $SortMem $sampleName.genome.bam $sampleName.genome.sorted";
&runCommand($command);
- $command = $dir."sam/samtools index $sampleName.genome.sorted.bam";
+ $command = "samtools index $sampleName.genome.sorted.bam";
&runCommand($command);
}
}
-&collectResults("$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
-&collectResults("$imdName.gene_res", "$sampleName.genes.results"); # gene level
-
if ($mTime) { $time_end = time(); $time_rsem = $time_end - $time_start; }
if ($mTime) { $time_start = time(); }
-if ($calcCI || $var_opt) {
- $command = $dir."rsem-run-gibbs $refName $sampleName $sampleToken $BURNIN $NCV $SAMPLEGAP";
+if ($calcPME || $calcCI ) {
+ $command = "rsem-run-gibbs $refName $imdName $statName $BURNIN $NCV $SAMPLEGAP";
$command .= " -p $nThreads";
- if ($var_opt) { $command .= " --var"; }
+ if ($seed ne "NULL") { $command .= " --seed $seeds[1]"; }
if ($quiet) { $command .= " -q"; }
&runCommand($command);
}
-if ($calcCI) {
- system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak1");
- system("mv $sampleName.genes.results $imdName.genes.results.bak1");
- &collectResults("$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
- &collectResults("$imdName.gene_res", "$sampleName.genes.results"); # gene level
+if ($calcPME || $calcCI) {
+ if ($alleleS) {
+ system("mv $sampleName.alleles.results $imdName.alleles.results.bak1");
+ system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak1");
+ system("mv $sampleName.genes.results $imdName.genes.results.bak1");
+ &collectResults("allele", "$imdName.allele_res", "$sampleName.alleles.results"); # allele level
+ &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
+ &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
+ }
+ else {
+ system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak1");
+ system("mv $sampleName.genes.results $imdName.genes.results.bak1");
+ &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
+ &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
+ }
+}
- $command = $dir."rsem-calculate-credibility-intervals $refName $sampleName $sampleToken $CONFIDENCE $NCV $NSPC $NMB";
+if ($calcCI) {
+ $command = "rsem-calculate-credibility-intervals $refName $imdName $statName $CONFIDENCE $NCV $NSPC $NMB";
$command .= " -p $nThreads";
+ if ($seed ne "NULL") { $command .= " --seed $seeds[2]"; }
if ($quiet) { $command .= " -q"; }
&runCommand($command);
- system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak2");
- system("mv $sampleName.genes.results $imdName.genes.results.bak2");
- &collectResults("$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
- &collectResults("$imdName.gene_res", "$sampleName.genes.results"); # gene level
+ if ($alleleS) {
+ system("mv $sampleName.alleles.results $imdName.alleles.results.bak2");
+ system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak2");
+ system("mv $sampleName.genes.results $imdName.genes.results.bak2");
+ &collectResults("allele", "$imdName.allele_res", "$sampleName.alleles.results"); # allele level
+ &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
+ &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
+ }
+ else {
+ system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak2");
+ system("mv $sampleName.genes.results $imdName.genes.results.bak2");
+ &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
+ &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
+ }
}
if ($mTime) { $time_end = time(); $time_ci = $time_end - $time_start; }
print OUTPUT "Aligning reads: $time_alignment s.\n";
print OUTPUT "Estimating expression levels: $time_rsem s.\n";
print OUTPUT "Calculating credibility intervals: $time_ci s.\n";
- my $time_del = $time_end - $time_start;
+# my $time_del = $time_end - $time_start;
# print OUTPUT "Delete: $time_del s.\n";
close(OUTPUT);
}
-# command, {err_msg}
-sub runCommand {
- print $_[0]."\n";
- my $status = system($_[0]);
- if ($status != 0) {
- my $errmsg;
- if (scalar(@_) > 1) { $errmsg = $_[1]; }
- else { $errmsg = "\"$command\" failed! Plase check if you provide correct parameters/options for the pipeline!"; }
- print $errmsg."\n";
- exit(-1);
- }
- print "\n";
-}
-
-# inpF, outF
-sub collectResults {
- my $local_status;
- my ($inpF, $outF);
- my (@results, @ids) = ();
- my $line;
- my $cnt;
-
- $inpF = $_[0];
- $outF = $_[1];
-
- $local_status = open(INPUT, $inpF);
- if ($local_status == 0) { print "Fail to open file $inpF!\n"; exit(-1); }
-
- $cnt = 0;
- @results = ();
-
- while ($line = <INPUT>) {
- ++$cnt;
- chomp($line);
- my @local_arr = split(/\t/, $line);
- if ($cnt == 4) { @ids = @local_arr; }
- else { push(@results, \@local_arr); }
- }
-
- push(@results, \@ids);
- close(INPUT);
-
- $local_status = open(OUTPUT, ">$outF");
- if ($local_status == 0) { print "Fail to create file $outF!\n"; exit(-1); }
-
- my $n = scalar(@results);
- my $m = scalar(@{$results[0]});
- for (my $i = 0; $i < $m; $i++) {
- my @out_arr = ();
- for (my $j = 0; $j < $n; $j++) { push(@out_arr, $results[$j][$i]); }
- $" = "\t";
- print OUTPUT "@out_arr\n";
- }
- close(OUTPUT);
-}
-
-
__END__
=head1 NAME
=head1 SYNOPSIS
-=over
-
- rsem-calculate-expression [options] upstream_read_file(s) reference_name sample_name
- rsem-calculate-expression [options] --paired-end upstream_read_file(s) downstream_read_file(s) reference_name sample_name
+ rsem-calculate-expression [options] upstream_read_file(s) reference_name sample_name
+ rsem-calculate-expression [options] --paired-end upstream_read_file(s) downstream_read_file(s) reference_name sample_name
rsem-calculate-expression [options] --sam/--bam [--paired-end] input reference_name sample_name
-=back
-
=head1 ARGUMENTS
=over
=back
-=head1 OPTIONS
+=head1 BASIC OPTIONS
=over
=item B<--strand-specific>
-The RNA-Seq protocol used to generate the reads is strand specific, i.e., all (upstream) reads are derived from the forward strand. This option is equivalent to --forward-prob=1.0. With this option set, if RSEM runs the Bowtie aligner, the '--norc' Bowtie option will be used, which disables alignment to the reverse strand of transcripts. (Default: off)
+The RNA-Seq protocol used to generate the reads is strand specific, i.e., all (upstream) reads are derived from the forward strand. This option is equivalent to --forward-prob=1.0. With this option set, if RSEM runs the Bowtie/Bowtie 2 aligner, the '--norc' Bowtie/Bowtie 2 option will be used, which disables alignment to the reverse strand of transcripts. (Default: off)
+
+=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 '--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<--sam>
Input file is in BAM format. (Default: off)
-=item B<--sam-header-info> <file>
-
-RSEM reads header information from input by default. If this option is on, header information is read from the specified file. For the format of the file, please see SAM official website. (Default: "")
-
=item B<-p/--num-threads> <int>
-Number of threads to use. Both Bowtie 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>
=item B<--sampling-for-bam>
-When RSEM generates a BAM file, instead of outputing all alignments a read has with their posterior probabilities, one alignment is sampled and outputed according to the posterior probabilities. If the sampling result is that the read comes from the "noise" transcript, nothing is outputed. (Default: off)
+When RSEM generates a BAM file, instead of outputing all alignments a read has with their posterior probabilities, one alignment is sampled according to the posterior probabilities. The sampling procedure includes the alignment to the "noise" transcript, which does not appear in the BAM file. Only the sampled alignment has a weight of 1. All other alignments have weight 0. If the "noise" transcript is sampled, all alignments appeared in the BAM file should have weight 0. (Default: off)
+
+=item B<--seed> <uint32>
+
+Set the seed for the random number generators used in calculating posterior mean estimates and credibility intervals. The seed must be a non-negative 32 bit interger. (Default: off)
+
+=item B<--calc-pme>
+
+Run RSEM's collapsed Gibbs sampler to calculate posterior mean estimates. (Default: off)
=item B<--calc-ci>
-Calculate 95% credibility intervals and posterior mean estimates. (Default: off)
+Calculate 95% credibility intervals and posterior mean estimates. The credibility level can be changed by setting '--ci-credibility-level'. (Default: off)
+
+=item B<-q/--quiet>
+
+Suppress the output of logging information. (Default: off)
+
+=item B<-h/--help>
+
+Show help information.
+
+=item B<--version>
+
+Show version information.
+
+=back
+
+=head1 ADVANCED OPTIONS
+
+=over
+
+=item B<--sam-header-info> <file>
+
+RSEM reads header information from input by default. If this option is on, header information is read from the specified file. For the format of the file, please see SAM official website. (Default: "")
=item B<--seed-length> <int>
=item B<--bowtie-path> <path>
-The path to the bowtie executables. (Default: the path to the bowtie executables is assumed to be in the user's PATH environment variable)
+The path to the Bowtie executables. (Default: the path to the Bowtie executables is assumed to be in the user's PATH environment variable)
=item B<--bowtie-n> <int>
=item B<--bowtie-chunkmbs> <int>
-(Bowtie parameter) memory allocated for best first alignment calculation (Default: 0 - use bowtie's default)
+(Bowtie parameter) memory allocated for best first alignment calculation (Default: 0 - use Bowtie's default)
=item B<--phred33-quals>
Input quality scores are solexa encoded (from GA Pipeline ver. < 1.3). (Default: off)
+=item B<--bowtie2-path> <path>
+
+(Bowtie 2 parameter) The path to the Bowtie 2 executables. (Default: the path to the Bowtie 2 executables is assumed to be in the user's PATH environment variable)
+
+=item B<--bowtie2-mismatch-rate> <double>
+
+(Bowtie 2 parameter) The maximum mismatch rate allowed. (Default: 0.1)
+
+=item B<--bowtie2-k> <int>
+
+(Bowtie 2 parameter) Find up to <int> alignments per read. (Default: 200)
+
+=item B<--bowtie2-sensitivity-level> <string>
+
+(Bowtie 2 parameter) Set Bowtie 2's preset options in --end-to-end mode. This option controls how hard Bowtie 2 tries to find alignments. <string> must be one of "very_fast", "fast", "sensitive" and "very_sensitive". The four candidates correspond to Bowtie 2's "--very-fast", "--fast", "--sensitive" and "--very-sensitive" options. (Default: "sensitive" - use Bowtie 2's default)
+
=item B<--forward-prob> <double>
Probability of generating a read from the forward strand of a transcript. Set to 1 for a strand-specific protocol where all (upstream) reads are derived from the forward strand, 0 for a strand-specific protocol where all (upstream) read are derived from the reverse strand, or 0.5 for a non-strand-specific protocol. (Default: 0.5)
=item B<--fragment-length-min> <int>
-Minimum read/insert length allowed. This is also the value for the bowtie -I option. (Default: 1)
+Minimum read/insert length allowed. This is also the value for the Bowtie/Bowtie2 -I option. (Default: 1)
=item B<--fragment-length-max> <int>
-Maximum read/insert length allowed. This is also the value for the bowtie -X option. (Default: 1000)
+Maximum read/insert length allowed. This is also the value for the Bowtie/Bowtie 2 -X option. (Default: 1000)
=item B<--fragment-length-mean> <double>
Number of bins in the RSPD. Only relevant when '--estimate-rspd' is specified. Use of the default setting is recommended. (Default: 20)
+=item B<--gibbs-burnin> <int>
+
+The number of burn-in rounds for RSEM's Gibbs sampler. Each round passes over the entire data set once. If RSEM can use multiple threads, multiple Gibbs samplers will start at the same time and all samplers share the same burn-in number. (Default: 200)
+
+=item B<--gibbs-number-of-samples> <int>
+
+The total number of count vectors RSEM will collect from its Gibbs samplers. (Default: 1000)
+
+=item B<--gibbs-sampling-gap> <int>
+
+The number of rounds between two succinct count vectors RSEM collects. If the count vector after round N is collected, the count vector after round N + <int> will also be collected. (Default: 1)
+
+=item B<--ci-credibility-level> <double>
+
+The credibility level for credibility intervals. (Default: 0.95)
+
=item B<--ci-memory> <int>
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<--keep-intermediate-files>
+=item B<--ci-number-of-samples-per-count-vector> <int>
-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)
+The number of read generating probability vectors sampled per sampled count vector. The crebility intervals are calculated by first sampling P(C | D) and then sampling P(Theta | C) for each sampled count vector. This option controls how many Theta vectors are sampled per sampled count vector. (Default: 50)
-=item B<--time>
+=item B<--samtools-sort-mem> <string>
-Output time consumed by each step of RSEM to 'sample_name.time'. (Default: off)
+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<-q/--quiet>
+=item B<--keep-intermediate-files>
-Suppress the output of logging information. (Default: off)
+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)
-=item B<-h/--help>
+=item B<--temporary-folder> <string>
-Show help information.
+Set where to put the temporary files generated by RSEM. If the folder specified does not exist, RSEM will try to create it. (Default: sample_name.temp)
+
+=item B<--time>
+
+Output time consumed by each step of RSEM to 'sample_name.time'. (Default: off)
=back
=over
-=item B<sample_name.genes.results>
+=item B<sample_name.isoforms.results>
-File containing gene level expression estimates. The format of each
-line in this file is:
+File containing isoform level expression estimates. The first line
+contains column names separated by the tab character. The format of
+each line in the rest of this file is:
-gene_id expected_counts tau_value [pmc_value tau_pme_value tau_ci_lower_bound tau_ci_upper_bound] transcript_id_list
+transcript_id gene_id length effective_length expected_count TPM FPKM IsoPct [posterior_mean_count posterior_standard_deviation_of_count pme_TPM pme_FPKM IsoPct_from_pme_TPM TPM_ci_lower_bound TPM_ci_upper_bound FPKM_ci_lower_bound FPKM_ci_upper_bound]
-Fields are separated by the tab character. Fields within "[]" are only
-presented if '--calc-ci' is set. pme stands for posterior mean
-estimation. pmc stands for posterior mean counts. ci_lower_bound(l)
-means the lower bound of the credibility intervals, ci_upper_bound(u)
-means the upper bound of the credibility intervals. So the credibility
-interval is [l, u]. 'transcript_id_list' is a space-separated list of
-transcript_ids belonging to the gene. If no gene information is
-provided, this file has the same content as
-'sample_name.isoforms.results'.
+Fields are separated by the tab character. Fields within "[]" are
+optional. They will not be presented if neither '--calc-pme' nor
+'--calc-ci' is set.
-=item B<sample_name.isoforms.results>
+'transcript_id' is the transcript name of this transcript. 'gene_id'
+is the gene name of the gene which this transcript belongs to (denote
+this gene as its parent gene). If no gene information is provided,
+'gene_id' and 'transcript_id' are the same.
+
+'length' is this transcript's sequence length (poly(A) tail is not
+counted). 'effective_length' counts only the positions that can
+generate a valid fragment. If no poly(A) tail is added,
+'effective_length' is equal to transcript length - mean fragment
+length + 1. If one transcript's effective length is less than 1, this
+transcript's both effective length and abundance estimates are set to
+0.
+
+'expected_count' is the sum of the posterior probability of each read
+comes from this transcript over all reads. Because 1) each read
+aligning to this transcript has a probability of being generated from
+background noise; 2) RSEM may filter some alignable low quality reads,
+the sum of expected counts for all transcript are generally less than
+the total number of reads aligned.
+
+'TPM' stands for Transcripts Per Million. It is a relative measure of
+transcript abundance. The sum of all transcripts' TPM is 1
+million. 'FPKM' stands for Fragments Per Kilobase of transcript per
+Million mapped reads. It is another relative measure of transcript
+abundance. If we define l_bar be the mean transcript length in a
+sample, which can be calculated as
+
+l_bar = \sum_i TPM_i / 10^6 * effective_length_i (i goes through every transcript),
+
+the following equation is hold:
+
+FPKM_i = 10^3 / l_bar * TPM_i.
+
+We can see that the sum of FPKM is not a constant across samples.
-File containing isoform level expression values. The format of each
-line in this file is:
+'IsoPct' stands for isoform percentage. It is the percentage of this
+transcript's abandunce over its parent gene's abandunce. If its parent
+gene has only one isoform or the gene information is not provided,
+this field will be set to 100.
-transcript_id expected_counts tau_value [pmc_value tau_pme_value tau_ci_lower_bound tau_ci_upper_bound] gene_id
+'posterior_mean_count', 'pme_TPM', 'pme_FPKM' are posterior mean
+estimates calculated by RSEM's Gibbs
+sampler. 'posterior_standard_deviation_of_count' is the posterior
+standard deviation of counts. 'IsoPct_from_pme_TPM' is the isoform
+percentage calculated from 'pme_TPM' values.
-Fields are separated by the tab character. 'gene_id' is the gene_id of
-the gene which this transcript belongs to. If no gene information is
-provided, 'gene_id' and 'transcript_id' are the same.
+'TPM_ci_lower_bound', 'TPM_ci_upper_bound', 'FPKM_ci_lower_bound' and
+'FPKM_ci_upper_bound' are lower(l) and upper(u) bounds of 95%
+credibility intervals for TPM and FPKM values. The bounds are
+inclusive (i.e. [l, u]).
+
+=item B<sample_name.genes.results>
+
+File containing gene level expression estimates. The first line
+contains column names separated by the tab character. The format of
+each line in the rest of this file is:
+
+gene_id transcript_id(s) length effective_length expected_count TPM FPKM [posterior_mean_count posterior_standard_deviation_of_count pme_TPM pme_FPKM TPM_ci_lower_bound TPM_ci_upper_bound FPKM_ci_lower_bound FPKM_ci_upper_bound]
+
+Fields are separated by the tab character. Fields within "[]" are
+optional. They will not be presented if neither '--calc-pme' nor
+'--calc-ci' is set.
+
+'transcript_id(s)' is a comma-separated list of transcript_ids
+belonging to this gene. If no gene information is provided, 'gene_id'
+and 'transcript_id(s)' are identical (the 'transcript_id').
+
+A gene's 'length' and 'effective_length' are
+defined as the weighted average of its transcripts' lengths and
+effective lengths (weighted by 'IsoPct'). A gene's abundance estimates
+are just the sum of its transcripts' abundance estimates.
+
+=item B<sample_name.alleles.results>
+
+Only generated when the RSEM references are built with allele-specific
+transcripts.
+
+This file contains allele level expression estimates for
+allele-specific expression calculation. The first line
+contains column names separated by the tab character. The format of
+each line in the rest of this file is:
+
+allele_id transcript_id gene_id length effective_length expected_count TPM FPKM AlleleIsoPct AlleleGenePct [posterior_mean_count posterior_standard_deviation_of_count pme_TPM pme_FPKM AlleleIsoPct_from_pme_TPM AlleleGenePct_from_pme_TPM TPM_ci_lower_bound TPM_ci_upper_bound FPKM_ci_lower_bound FPKM_ci_upper_bound]
+
+Fields are separated by the tab character. Fields within "[]" are
+optional. They will not be presented if neither '--calc-pme' nor
+'--calc-ci' is set.
+
+'allele_id' is the allele-specific name of this allele-specific transcript.
+
+'AlleleIsoPct' stands for allele-specific percentage on isoform
+level. It is the percentage of this allele-specific transcript's
+abundance over its parent transcript's abundance. If its parent
+transcript has only one allele variant form, this field will be set to
+100.
+
+'AlleleGenePct' stands for allele-specific percentage on gene
+level. It is the percentage of this allele-specific transcript's
+abundance over its parent gene's abundance.
+
+'AlleleIsoPct_from_pme_TPM' and 'AlleleGenePct_from_pme_TPM' have
+similar meanings. They are calculated based on posterior mean
+estimates.
+
+Please note that if this file is present, the fields 'length' and
+'effective_length' in 'sample_name.isoforms.results' should be
+interpreted similarly as the corresponding definitions in
+'sample_name.genes.results'.
=item B<sample_name.transcript.bam, sample_name.transcript.sorted.bam and sample_name.transcript.sorted.bam.bai>
posterior probability of that alignment being the true mapping of a
read. In addition, RSEM pads a new tag ZW:f:value, where value is a
single precision floating number representing the posterior
-probability.
+probability. Because this file contains all alignment lines produced
+by bowtie or user-specified aligners, it can also be used as a
+replacement of the aligner generated BAM/SAM file. For paired-end
+reads, if one mate has alignments but the other does not, this file
+marks the alignable mate as "unmappable" (flag bit 0x4) and appends an
+optional field "Z0:A:!".
'sample_name.transcript.sorted.bam' and
'sample_name.transcript.sorted.bam.bai' are the sorted BAM file and
'sample_name.genome.sorted.bam' and 'sample_name.genome.sorted.bam.bai' are the
sorted BAM file and indices generated by samtools (included in RSEM package).
-=item B<sample_name.sam.gz>
-
-Only generated when the input files are raw reads instead of SAM/BAM format files
-
-It is the gzipped SAM output produced by bowtie aligner.
-
=item B<sample_name.time>
Only generated when --time is specified.
/ref/mouse_125 \
mmliver_single_without_quals
-4) Data are the same as 1). We want to take a fragment length distribution into consideration. We set the fragment length mean to 150 and the standard deviation to 35. In addition to a BAM file, we also want to generate credibility intervals. We allow RSEM to use 1GB of memory for CI calculation:
+4) Data are the same as 1). This time we assume the bowtie executables are under '/sw/bowtie'. We want to take a fragment length distribution into consideration. We set the fragment length mean to 150 and the standard deviation to 35. In addition to a BAM file, we also want to generate credibility intervals. We allow RSEM to use 1GB of memory for CI calculation:
rsem-calculate-expression --bowtie-path /sw/bowtie \
--phred64-quals \
/ref/mouse_125 \
mmliver_single_quals
-5) '/data/mmliver_paired_end_quals.bam', paired-end reads with quality scores. We want to use 8 threads:
+5) '/data/mmliver_paired_end_quals.bam', paired-end reads with quality scores. We want to use 8 threads:
rsem-calculate-expression --paired-end \
--bam \
projects / rsem.git / blobdiff