-#!/usr/bin/perl
+#!/usr/bin/env perl
use Getopt::Long;
use Pod::Usage;
-use FindBin;
-use lib $FindBin::Bin;
-use strict;
+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 $BURNIN = 200;
my $NCV = 1000;
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 $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;
"output-genome-bam" => \$genGenomeBamF,
"sampling-for-bam" => \$sampling,
"calc-pme" => \$calcPME,
- "var" => \$var_opt,
+ "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);
-my $dir = "$FindBin::Bin/";
-
pod2usage(-verbose => 2) if ($help == 1);
-&showVersionInfo($dir) if ($version == 1);
+&showVersionInfo($FindBin::RealBin) if ($version == 1);
#check parameters and options
pod2usage(-msg => "Seed length should be at least 5!\n", -exitval => 2, -verbose => 2) if ($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"; }
}
# pipe to samtools to generate a BAM file
- $command .= " | $dir\sam/samtools view -S -b -o $imdName.bam -";
+ $command .= " | samtools view -S -b -o $imdName.bam -";
}
else {
$command = $bowtie2_path."bowtie2";
}
# pipe to samtools to generate a BAM file
- $command .= " | $dir\sam/samtools view -S -b -o $imdName.bam -";
+ $command .= " | samtools view -S -b -o $imdName.bam -";
}
if ($mTime) { $time_start = time(); }
if ($mTime) { $time_start = time(); }
-$command = $dir."rsem-parse-alignments $refName $imdName $statName";
+$command = "rsem-parse-alignments $refName $imdName $statName";
my $samInpType;
if ($is_sam) { $samInpType = "s"; }
&runCommand($command);
-$command = $dir."rsem-build-read-index $gap";
+$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 $imdName\_alignable_2.fa"; }
print OUTPUT "$L\n";
close(OUTPUT);
-$command = $dir."rsem-run-em $refName $read_type $sampleName $imdName $statName -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 $seeds[0]"; }
}
-if ($calcPME || $var_opt || $calcCI) { $command .= " --gibbs-out"; }
+if ($calcPME || $calcCI) { $command .= " --gibbs-out"; }
if ($quiet) { $command .= " -q"; }
&runCommand($command);
}
if ($genBamF) {
- $command = $dir."sam/samtools sort -@ $nThreads -m $SortMem $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 -@ $nThreads -m $SortMem $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);
}
}
if ($mTime) { $time_start = time(); }
-if ($calcPME || $var_opt || $calcCI ) {
- $command = $dir."rsem-run-gibbs $refName $imdName $statName $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) {
- $command = $dir."rsem-calculate-credibility-intervals $refName $imdName $statName $CONFIDENCE $NCV $NSPC $NMB";
+ $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);
=back
-=head1 OPTIONS
+=head1 BASIC OPTIONS
=over
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 SAM format. (Default: off)
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/Bowtie2, expression estimation and 'samtools sort' will use this many threads. (Default: 1)
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>
Input quality scores are solexa encoded (from GA Pipeline ver. < 1.3). (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<--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)
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<--ci-number-of-samples-per-count-vector> <int>
+
+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<--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)
Output time consumed by each step of RSEM to 'sample_name.time'. (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 DESCRIPTION
contains column names separated by the tab character. The format of
each line in the rest of this file is:
-transcript_id gene_id length effective_length expected_count TPM FPKM IsoPct [pme_expected_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]
+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
optional. They will not be presented if neither '--calc-pme' nor
gene has only one isoform or the gene information is not provided,
this field will be set to 100.
-'pme_expected_count', 'pme_TPM', 'pme_FPKM' are posterior mean
-estimates calculated by RSEM's Gibbs sampler. 'IsoPct_from_pme_TPM' is
-the isoform percentage calculated from 'pme_TPM' values.
+'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.
'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%
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 [pme_expected_count pme_TPM pme_FPKM TPM_ci_lower_bound TPM_ci_upper_bound FPKM_ci_lower_bound FPKM_ci_upper_bound]
+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
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 [pme_expected_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]
+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
projects / rsem.git / blobdiff