13 my $CONFIDENCE = 0.95;
16 my $NMB = 1024; # default
20 my $read_type = 1; # default, single end with qual
47 my $genBamF = 1; # default is generating transcript bam file
48 my $genGenomeBamF = 0;
56 my $keep_intermediate_files = 0;
58 my $strand_specific = 0;
61 my ($time_start, $time_end, $time_alignment, $time_rsem, $time_ci) = (0, 0, 0, 0, 0);
63 GetOptions("keep-intermediate-files" => \$keep_intermediate_files,
64 "no-qualities" => \$no_qual,
65 "paired-end" => \$paired_end,
66 "strand-specific" => \$strand_specific,
69 "sam-header-info=s" => \$fn_list,
71 "seed-length=i" => \$L,
72 "bowtie-path=s" => \$bowtie_path,
75 "bowtie-m=i" => \$maxHits,
76 "phred33-quals" => \$phred33,
77 "phred64-quals" => \$phred64, #solexa1.3-quals" => \$phred64,
78 "solexa-quals" => \$solexa,
79 "forward-prob=f" => \$probF,
80 "fragment-length-min=i" => \$minL,
81 "fragment-length-max=i" => \$maxL,
82 "fragment-length-mean=f" => \$mean,
83 "fragment-length-sd=f" => \$sd,
84 "estimate-rspd" => \$estRSPD,
85 "num-rspd-bins=i" => \$B,
86 "p|num-threads=i" => \$nThreads,
87 "output-genome-bam" => \$genGenomeBamF,
88 "sampling-for-bam" => \$sampling,
89 "calc-ci" => \$calcCI,
90 "ci-memory=i" => \$NMB,
93 "h|help" => \$help) or pod2usage(-exitval => 2, -verbose => 2);
95 pod2usage(-verbose => 2) if ($help == 1);
98 #check parameters and options
100 if ($is_sam || $is_bam) {
101 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (scalar(@ARGV) != 3);
102 pod2usage(-msg => "--sam and --bam cannot be active at the same time!", -exitval => 2, -verbose => 2) if ($is_sam == 1&& $is_bam == 1);
103 pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m, --phred33-quals, --phred64-quals or --solexa-quals cannot be set if input is SAM/BAM format!", -exitval => 2, -verbose => 2) if ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200 || $phred33 || $phred64 || $solexa);
106 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (!$paired_end && scalar(@ARGV) != 3 || $paired_end && scalar(@ARGV) != 4);
107 pod2usage(-msg => "Only one of --phred33-quals --phred64-quals/--solexa1.3-quals --solexa-suqls can be active!", -exitval => 2, -verbose => 2) if ($phred33 + $phred64 + $solexa > 1);
108 podwusage(-msg => "--sam , --bam or --sam-header-info cannot be set if use bowtie aligner to produce alignments!", -exitval => 2, -verbose => 2) if ($is_sam || $is_bam || $fn_list ne "");
111 pod2usage(-msg => "Forward probability should be in [0, 1]!", -exitval => 2, -verbose => 2) if ($probF < 0 || $probF > 1);
112 pod2usage(-msg => "Min fragment length should be at least 1!", -exitval => 2, -verbose => 2) if ($minL < 1);
113 pod2usage(-msg => "Min fragment length should be smaller or equal to max fragment length!", -exitval => 2, -verbose => 2) if ($minL > $maxL);
114 pod2usage(-msg => "The memory allocated for calculating credibility intervals should be at least 1 MB!\n", -exitval => 2, -verbose => 2) if ($NMB < 1);
115 pod2usage(-msg => "Number of threads should be at least 1!\n", -exitval => 2, -verbose => 2) if ($nThreads < 1);
116 pod2usage(-msg => "Seed length should be at least 5!\n", -exitval => 2, -verbose => 2) if ($L < 5);
117 pod2usage(-msg => "--sampling-for-bam cannot be specified if --out-bam is not specified!\n", -exitval => 2, -verbose => 2) if ($sampling && !$genBamF);
119 if ($L < 25) { print "Warning: the seed length set is less than 25! This is only allowed if the references are not added poly(A) tails.\n"; }
121 if ($strand_specific) { $probF = 1.0; }
127 my ($refName, $sampleName, $sampleToken, $temp_dir, $stat_dir, $imdName) = ();
131 if ($no_qual) { $read_type = 2; }
132 else { $read_type = 3; }
135 if ($no_qual) { $read_type = 0; }
136 else { $read_type = 1; }
139 if (scalar(@ARGV) == 3) {
140 if ($is_sam || $is_bam) { $inpF = $ARGV[0]; }
141 else {$mate1_list = $ARGV[0]; }
143 $sampleName = $ARGV[2];
146 $mate1_list = $ARGV[0];
147 $mate2_list = $ARGV[1];
149 $sampleName = $ARGV[3];
152 if ($genGenomeBamF) {
153 open(INPUT, "$refName.ti");
154 my $line = <INPUT>; chomp($line);
156 my ($M, $type) = split(/ /, $line);
157 pod2usage(-msg => "No genome information provided, so genome bam file cannot be generated!\n", -exitval => 2, -verbose => 2) if ($type != 0);
160 my $pos = rindex($sampleName, '/');
161 if ($pos < 0) { $sampleToken = $sampleName; }
162 else { $sampleToken = substr($sampleName, $pos + 1); }
164 $temp_dir = "$sampleName.temp";
165 $stat_dir = "$sampleName.stat";
167 if (!(-d $temp_dir) && !mkdir($temp_dir)) { print "Fail to create folder $temp_dir.\n"; exit(-1); }
168 if (!(-d $stat_dir) && !mkdir($stat_dir)) { print "Fail to create folder $stat_dir.\n"; exit(-1); }
170 $imdName = "$temp_dir/$sampleToken";
172 if (!$is_sam && !$is_bam && $phred33 + $phred64 + $solexa == 0) { $phred33 = 1; }
174 my ($mate_minL, $mate_maxL) = (1, $maxL);
176 if ($bowtie_path ne "") { $bowtie_path .= "/"; }
178 my ($fn, $dir, $suf) = fileparse($0);
181 if (!$is_sam && !$is_bam) {
182 $command = $bowtie_path."bowtie";
183 if ($read_type == 0 || $read_type == 2) { $command .= " -f"; }
184 else { $command .= " -q"; }
186 if ($phred33) { $command .= " --phred33-quals"; }
187 elsif ($phred64) { $command .= " --phred64-quals"; }
188 elsif ($solexa) { $command .= " --solexa-quals"; }
189 else { print "Oh, no!!!"; exit(2); }
191 $command .= " -n $C -e $E -l $L";
193 if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL"; }
195 if ($strand_specific || $probF == 1.0) { $command .= " --norc"; }
196 elsif ($probF == 0.0) { $command .= " --nofw"; }
198 $command .= " -p $nThreads -a -m $maxHits -S";
199 if ($quiet) { $command .= " --quiet"; }
201 $command .= " $refName";
202 if ($read_type == 0 || $read_type == 1) {
203 $command .= " $mate1_list";
206 $command .= " -1 $mate1_list -2 $mate2_list";
209 $command .= " | gzip > $imdName.sam.gz";
211 if ($mTime) { $time_start = time(); }
213 &runCommand($command);
215 if ($mTime) { $time_end = time(); $time_alignment = $time_end - $time_start; }
217 $inpF = "$imdName.sam.gz";
218 $is_sam = 1; # output of bowtie is a sam file
221 if ($mTime) { $time_start = time(); }
223 $command = $dir."rsem-parse-alignments $refName $sampleName $sampleToken";
226 if ($is_sam) { $samInpType = "s"; }
227 elsif ($is_bam) { $samInpType = "b"; }
229 $command .= " $samInpType $inpF -t $read_type";
230 if ($fn_list ne "") { $command .= " -l $fn_list"; }
231 if ($tagName ne "") { $command .= " -tag $tagName"; }
232 if ($quiet) { $command .= " -q"; }
234 &runCommand($command);
236 $command = $dir."rsem-build-read-index $gap";
238 case 0 { $command .= " 0 $quiet $imdName\_alignable.fa"; }
239 case 1 { $command .= " 1 $quiet $imdName\_alignable.fq"; }
240 case 2 { $command .= " 0 $quiet $imdName\_alignable_1.fa $imdName\_alignable_2.fa"; }
241 case 3 { $command .= " 1 $quiet $imdName\_alignable_1.fq $imdName\_alignable_2.fq"; }
243 &runCommand($command);
245 my $doesOpen = open(OUTPUT, ">$imdName.mparams");
246 if ($doesOpen == 0) { print "Cannot generate $imdName.mparams!\n"; exit(-1); }
247 print OUTPUT "$minL $maxL\n";
248 print OUTPUT "$probF\n";
249 print OUTPUT "$estRSPD\n";
251 print OUTPUT "$mate_minL $mate_maxL\n";
252 print OUTPUT "$mean $sd\n";
256 $command = $dir."rsem-run-em $refName $read_type $sampleName $sampleToken -p $nThreads";
258 $command .= " -b $samInpType $inpF";
259 if ($fn_list ne "") { $command .= " 1 $fn_list"; }
260 else { $command .= " 0"; }
261 if ($sampling) { $command .= " --sampling"; }
263 if ($calcCI) { $command .= " --gibbs-out"; }
264 if ($quiet) { $command .= " -q"; }
266 &runCommand($command);
269 $command = $dir."sam/samtools sort $sampleName.transcript.bam $sampleName.transcript.sorted";
270 &runCommand($command);
271 $command = $dir."sam/samtools index $sampleName.transcript.sorted.bam";
272 &runCommand($command);
274 if ($genGenomeBamF) {
275 $command = $dir."rsem-tbam2gbam $refName $sampleName.transcript.bam $sampleName.genome.bam";
276 &runCommand($command);
277 $command = $dir."sam/samtools sort $sampleName.genome.bam $sampleName.genome.sorted";
278 &runCommand($command);
279 $command = $dir."sam/samtools index $sampleName.genome.sorted.bam";
280 &runCommand($command);
284 &collectResults("$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
285 &collectResults("$imdName.gene_res", "$sampleName.genes.results"); # gene level
287 if ($mTime) { $time_end = time(); $time_rsem = $time_end - $time_start; }
289 if ($mTime) { $time_start = time(); }
292 $command = $dir."rsem-run-gibbs $refName $sampleName $sampleToken $BURNIN $CHAINLEN $SAMPLEGAP";
293 # $command .= " -p $nThreads";
294 if ($quiet) { $command .= " -q"; }
295 &runCommand($command);
297 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak1");
298 system("mv $sampleName.genes.results $imdName.genes.results.bak1");
299 &collectResults("$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
300 &collectResults("$imdName.gene_res", "$sampleName.genes.results"); # gene level
302 $command = $dir."rsem-calculate-credibility-intervals $refName $sampleName $sampleToken $CONFIDENCE $NSPC $NMB";
303 if ($quiet) { $command .= " -q"; }
304 &runCommand($command);
306 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak2");
307 system("mv $sampleName.genes.results $imdName.genes.results.bak2");
308 &collectResults("$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
309 &collectResults("$imdName.gene_res", "$sampleName.genes.results"); # gene level
312 if ($mTime) { $time_end = time(); $time_ci = $time_end - $time_start; }
314 if ($mTime) { $time_start = time(); }
316 if (!$keep_intermediate_files) {
317 &runCommand("rm -rf $temp_dir", "Fail to delete the temporary folder!");
320 if ($mTime) { $time_end = time(); }
323 open(OUTPUT, ">$sampleName.time");
324 print OUTPUT "Alignment: $time_alignment s.\n";
325 print OUTPUT "RSEM: $time_rsem s.\n";
326 print OUTPUT "CI: $time_ci s.\n";
327 my $time_del = $time_end - $time_start;
328 print OUTPUT "Delete: $time_del s.\n";
335 my $status = system($_[0]);
338 if (scalar(@_) > 1) { $errmsg = $_[1]; }
339 else { $errmsg = "\"$command\" failed! Plase check if you provide correct parameters/options for the pipeline!"; }
350 my (@results, @ids) = ();
357 $local_status = open(INPUT, $inpF);
358 if ($local_status == 0) { print "Fail to open file $inpF!\n"; exit(-1); }
363 while ($line = <INPUT>) {
366 my @local_arr = split(/\t/, $line);
367 if ($cnt == 4) { @ids = @local_arr; }
368 else { push(@results, \@local_arr); }
371 push(@results, \@ids);
374 $local_status = open(OUTPUT, ">$outF");
375 if ($local_status == 0) { print "Fail to create file $outF!\n"; exit(-1); }
377 my $n = scalar(@results);
378 my $m = scalar(@{$results[0]});
379 for (my $i = 0; $i < $m; $i++) {
381 for (my $j = 0; $j < $n; $j++) { push(@out_arr, $results[$j][$i]); }
383 print OUTPUT "@out_arr\n";
393 rsem-calculate-expression
399 rsem-calculate-expression [options] upstream_read_file(s) reference_name sample_name
400 rsem-calculate-expression [options] --paired-end upstream_read_file(s) downstream_read_file(s) reference_name sample_name
401 rsem-calculate-expression [options] --sam/--bam [--paired-end] input reference_name sample_name
409 =item B<upstream_read_files(s)>
411 Comma-separated list of files containing single-end reads or upstream reads for paired-end data. By default, these files are assumed to be in FASTQ format. If the --no-qualities option is specified, then FASTA format is expected.
413 =item B<downstream_read_file(s)>
415 Comma-separated list of files containing downstream reads which are paired with the upstream reads. By default, these files are assumed to be in FASTQ format. If the --no-qualities option is specified, then FASTA format is expected.
419 SAM/BAM formatted input file. If "-" is specified for the filename, SAM/BAM input is instead assumed to come from standard input. RSEM requires all alignments of the same read group together. For paired-end reads, RSEM also requires the two mates of any alignment be adjacent. See Description section for how to make input file obey RSEM's requirements.
421 =item B<reference_name>
423 The name of the reference used. The user must have run 'rsem-prepare-reference' with this reference_name before running this program.
427 The name of the sample analyzed. All output files are prefixed by this name (e.g., sample_name.genes.results)
435 =item B<--paired-end>
437 Input reads are paired-end reads. (Default: off)
439 =item B<--no-qualities>
441 Input reads do not contain quality scores. (Default: off)
443 =item B<--strand-specific>
445 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)
449 Input file is in SAM format. (Default: off)
453 Input file is in BAM format. (Default: off)
455 =item B<--sam-header-info> <file>
457 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: "")
459 =item B<-p/--num-threads> <int>
461 Number of threads to use. Both Bowtie and expression estimation will use this many threads. (Default: 1)
463 =item B<--output-genome-bam>
465 Generate a BAM file, 'sample_name.genome.bam', with alignments mapped to genomic coordinates and annotated with their posterior probabilities. In addition, RSEM will call samtools (included in RSEM package) to sort and index the bam file. 'sample_name.genome.sorted.bam' and 'sample_name.genome.sorted.bam.bai' will be generated. (Default: off)
467 =item B<--sampling-for-bam>
469 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)
473 Calculate 95% credibility intervals and posterior mean estimates. (Default: off)
475 =item B<--seed-length> <int>
477 Seed length used by the read aligner. Providing the correct value is important for RSEM. If RSEM runs Bowtie, it uses this value for Bowtie's seed length parameter. Any read with its or at least one of its mates' (for paired-end reads) length less than this value will be ignored. If the references are not added poly(A) tails, the minimum allowed value is 5, otherwise, the minimum allowed value is 25. Note that this script will only check if the value >= 5 and give a warning message if the value < 25 but >= 5. (Default: 25)
479 =item B<--tag> <string>
481 The name of the optional field used in the SAM input for identifying a read with too many valid alignments. The field should have the format <tagName>:i:<value>, where a <value> bigger than 0 indicates a read with too many alignments. (Default: "")
483 =item B<--bowtie-path> <path>
485 The path to the bowtie executables. (Default: the path to the bowtie executables is assumed to be in the user's PATH environment variable)
487 =item B<--bowtie-n> <int>
489 (Bowtie parameter) max # of mismatches in the seed. (Range: 0-3, Default: 2)
491 =item B<--bowtie-e> <int>
493 (Bowtie parameter) max sum of mismatch quality scores across the alignment. (Default: 99999999)
495 =item B<--bowtie-m> <int>
497 (Bowtie parameter) suppress all alignments for a read if > <int> valid alignments exist. (Default: 200)
499 =item B<--phred33-quals>
501 Input quality scores are encoded as Phred+33. (Default: on)
503 =item B<--phred64-quals>
505 Input quality scores are encoded as Phred+64 (default for GA Pipeline ver. >= 1.3). (Default: off)
507 =item B<--solexa-quals>
509 Input quality scores are solexa encoded (from GA Pipeline ver. < 1.3). (Default: off)
511 =item B<--forward-prob> <double>
513 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)
515 =item B<--fragment-length-min> <int>
517 Minimum read/insert length allowed. This is also the value for the bowtie -I option. (Default: 1)
519 =item B<--fragment-length-max> <int>
521 Maximum read/insert length allowed. This is also the value for the bowtie -X option. (Default: 1000)
523 =item B<--fragment-length-mean> <double>
525 (single-end data only) The mean of the fragment length distribution, which is assumed to be a Gaussian. (Default: -1, which disables use of the fragment length distribution)
527 =item B<--fragment-length-sd> <double>
529 (single-end data only) The standard deviation of the fragment length distribution, which is assumed to be a Gaussian. (Default: 0, which assumes that all fragments are of the same length, given by the rounded value of B<--fragment-length-mean>)
531 =item B<--estimate-rspd>
533 Set this option if you want to estimate the read start position distribution (RSPD) from data. Otherwise, RSEM will use a uniform RSPD. (Default: off)
535 =item B<--num-rspd-bins> <int>
537 Number of bins in the RSPD. Only relevant when '--estimate-rspd' is specified. Use of the default setting is recommended. (Default: 20)
539 =item B<--ci-memory> <int>
541 Amount of memory (in MB) RSEM is allowed to use for computing credibility intervals. (Default: 1024)
543 =item B<--keep-intermediate-files>
545 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)
549 Suppress the output of logging information. (Default: off)
553 Show help information.
559 In its default mode, this program aligns input reads against a reference transcriptome with Bowtie and calculates expression values using the alignments. RSEM assumes the data are single-end reads with quality scores, unless the '--paired-end' or '--no-qualities' options are specified. Users may use an alternative aligner by specifying one of the --sam and --bam options, and providing an alignment file in the specified format. However, users should make sure that they align against the indices generated by 'rsem-prepare-reference' and the alignment file satisfies the requirements mentioned in ARGUMENTS section.
561 One simple way to make the alignment file (e.g. input.sam) satisfying RSEM's requirements (assuming the aligner used put mates in a paired-end read adjacent) is to use the following command:
563 sort -k 1,1 -s input.sam > input.sorted.sam
565 The SAM/BAM format RSEM uses is v1.4. However, it is compatible with old SAM/BAM format. However, RSEM cannot recognize 0x100 in the FLAG field. In addition, RSEM requires SEQ and QUAL not be '*'.
567 The user must run 'rsem-prepare-reference' with the appropriate reference before using this program.
569 For single-end data, it is strongly recommended that the user provide the fragment length distribution parameters (--fragment-length-mean and --fragment-length-sd). For paired-end data, RSEM will automatically learn a fragment length distribution from the data.
571 Please note that some of the default values for the Bowtie parameters are not the same as those defined for Bowtie itself.
573 The temporary directory and all intermediate files will be removed when RSEM finishes unless '--keep-intermediate-files' is specified.
575 With the "--calc-ci" option, 95% credibility intervals and posterior mean estimates will be calculated in addition to maximum likelihood estimates.
581 =item B<sample_name.genes.results>
583 File containing gene level expression estimates. The format of each
584 line in this file is:
586 gene_id expected_counts tau_value [pmc_value tau_pme_value tau_ci_lower_bound tau_ci_upper_bound] transcript_id_list
588 Fields are separated by the tab character. Fields within "[]" are only
589 presented if '--calc-ci' is set. pme stands for posterior mean
590 estimation. pmc stands for posterior mean counts. ci_lower_bound(l)
591 means the lower bound of the credibility intervals, ci_upper_bound(u)
592 means the upper bound of the credibility intervals. So the credibility
593 interval is [l, u]. 'transcript_id_list' is a space-separated list of
594 transcript_ids belonging to the gene. If no gene information is
595 provided, this file has the same content as
596 'sample_name.isoforms.results'.
598 =item B<sample_name.isoforms.results>
600 File containing isoform level expression values. The format of each
601 line in this file is:
603 transcript_id expected_counts tau_value [pmc_value tau_pme_value tau_ci_lower_bound tau_ci_upper_bound] gene_id
605 Fields are separated by the tab character. 'gene_id' is the gene_id of
606 the gene which this transcript belongs to. If no gene information is
607 provided, 'gene_id' and 'transcript_id' are the same.
609 =item B<sample_name.transcript.bam, sample_name.transcript.sorted.bam and sample_name.transcript.sorted.bam.bai>
611 'sample_name.transcript.bam' is a BAM-formatted file of read
612 alignments in transcript coordinates. The MAPQ field of each alignment
613 is set to min(100, floor(-10 * log10(1.0 - w) + 0.5)), where w is the
614 posterior probability of that alignment being the true mapping of a
615 read. In addition, RSEM pads a new tag ZW:f:value, where value is a
616 single precision floating number representing the posterior
619 'sample_name.transcript.sorted.bam' and
620 'sample_name.transcript.sorted.bam.bai' are the sorted BAM file and
621 indices generated by samtools (included in RSEM package).
623 =item B<sample_name.genome.bam, sample_name.genome.sorted.bam and sample_name.genome.sorted.bam.bai>
625 Only generated when --output-genome-bam is specified.
627 'sample_name.genome.bam' is a BAM-formatted file of read alignments in
628 genomic coordinates. Alignments of reads that have identical genomic
629 coordinates (i.e., alignments to different isoforms that share the
630 same genomic region) are collapsed into one alignment. The MAPQ field
631 of each alignment is set to min(100, floor(-10 * log10(1.0 - w) +
632 0.5)), where w is the posterior probability of that alignment being
633 the true mapping of a read. In addition, RSEM pads a new tag
634 ZW:f:value, where value is a single precision floating number
635 representing the posterior probability. If an alignment is spliced, a
636 XS:A:value tag is also added, where value is either '+' or '-'
637 indicating the strand of the transcript it aligns to.
639 'sample_name.genome.sorted.bam' and 'sample_name.genome.sorted.bam.bai' are the
640 sorted BAM file and indices generated by samtools (included in RSEM package).
642 =item B<sample_name.stat>
644 This is a folder instead of a file. All model related statistics are stored in this folder. Use 'rsem-plot-model' can generate plots using this folder.
650 Assume the path to the bowtie executables is in the user's PATH environment variable. Reference files are under '/ref' with name 'mm9'.
652 1) '/data/mmliver.fq', single-end reads with quality scores. Quality scores are encoded as for 'GA pipeline version >= 1.3'. We want to use 8 threads and generate a genome BAM file:
654 rsem-calculate-expression --phred64-quals \
656 --output-genome-bam \
661 2) '/data/mmliver_1.fq' and '/data/mmliver_2.fq', paired-end reads with quality scores. Quality scores are in SANGER format. We want to use 8 threads and do not generate a genome BAM file:
663 rsem-calculate-expression -p 8 \
668 mmliver_paired_end_quals
670 3) '/data/mmliver.fa', single-end reads without quality scores. We want to use 8 threads:
672 rsem-calculate-expression -p 8 \
676 mmliver_single_without_quals
678 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:
680 rsem-calculate-expression --bowtie-path /sw/bowtie \
682 --fragment-length-mean 150.0 \
683 --fragment-length-sd 35.0 \
685 --output-genome-bam \
692 5) '/data/mmliver_paired_end_quals.bam', paired-end reads with quality scores. We want to use 8 threads:
694 rsem-calculate-expression --paired-end \
697 /data/mmliver_paired_end_quals.bam \
699 mmliver_paired_end_quals