13 my $CONFIDENCE = 0.95;
16 my $NMB = 1024; # default
20 my $read_type = 1; # default, single end with qual
27 my $chunkMbs = 0; # 0 = use bowtie default
48 my $genBamF = 1; # default is generating transcript bam file
49 my $genGenomeBamF = 0;
57 my $keep_intermediate_files = 0;
59 my $strand_specific = 0;
62 my ($time_start, $time_end, $time_alignment, $time_rsem, $time_ci) = (0, 0, 0, 0, 0);
64 GetOptions("keep-intermediate-files" => \$keep_intermediate_files,
65 "no-qualities" => \$no_qual,
66 "paired-end" => \$paired_end,
67 "strand-specific" => \$strand_specific,
70 "sam-header-info=s" => \$fn_list,
72 "seed-length=i" => \$L,
73 "bowtie-path=s" => \$bowtie_path,
76 "bowtie-m=i" => \$maxHits,
77 "bowtie-chunkmbs=i" => \$chunkMbs,
78 "phred33-quals" => \$phred33,
79 "phred64-quals" => \$phred64, #solexa1.3-quals" => \$phred64,
80 "solexa-quals" => \$solexa,
81 "forward-prob=f" => \$probF,
82 "fragment-length-min=i" => \$minL,
83 "fragment-length-max=i" => \$maxL,
84 "fragment-length-mean=f" => \$mean,
85 "fragment-length-sd=f" => \$sd,
86 "estimate-rspd" => \$estRSPD,
87 "num-rspd-bins=i" => \$B,
88 "p|num-threads=i" => \$nThreads,
89 "output-genome-bam" => \$genGenomeBamF,
90 "sampling-for-bam" => \$sampling,
91 "calc-ci" => \$calcCI,
92 "ci-memory=i" => \$NMB,
95 "h|help" => \$help) or pod2usage(-exitval => 2, -verbose => 2);
97 pod2usage(-verbose => 2) if ($help == 1);
100 #check parameters and options
102 if ($is_sam || $is_bam) {
103 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (scalar(@ARGV) != 3);
104 pod2usage(-msg => "--sam and --bam cannot be active at the same time!", -exitval => 2, -verbose => 2) if ($is_sam == 1&& $is_bam == 1);
105 pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m, --phred33-quals, --phred64-quals or --solexa-quals cannot be set if input is SAM/BAM format!", -exitval => 2, -verbose => 2) if ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200 || $phred33 || $phred64 || $solexa);
108 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (!$paired_end && scalar(@ARGV) != 3 || $paired_end && scalar(@ARGV) != 4);
109 pod2usage(-msg => "Only one of --phred33-quals --phred64-quals/--solexa1.3-quals --solexa-suqls can be active!", -exitval => 2, -verbose => 2) if ($phred33 + $phred64 + $solexa > 1);
110 podwusage(-msg => "--sam , --bam or --sam-header-info cannot be set if use bowtie aligner to produce alignments!", -exitval => 2, -verbose => 2) if ($is_sam || $is_bam || $fn_list ne "");
113 pod2usage(-msg => "Forward probability should be in [0, 1]!", -exitval => 2, -verbose => 2) if ($probF < 0 || $probF > 1);
114 pod2usage(-msg => "Min fragment length should be at least 1!", -exitval => 2, -verbose => 2) if ($minL < 1);
115 pod2usage(-msg => "Min fragment length should be smaller or equal to max fragment length!", -exitval => 2, -verbose => 2) if ($minL > $maxL);
116 pod2usage(-msg => "The memory allocated for calculating credibility intervals should be at least 1 MB!\n", -exitval => 2, -verbose => 2) if ($NMB < 1);
117 pod2usage(-msg => "Number of threads should be at least 1!\n", -exitval => 2, -verbose => 2) if ($nThreads < 1);
118 pod2usage(-msg => "Seed length should be at least 5!\n", -exitval => 2, -verbose => 2) if ($L < 5);
119 pod2usage(-msg => "--sampling-for-bam cannot be specified if --out-bam is not specified!\n", -exitval => 2, -verbose => 2) if ($sampling && !$genBamF);
121 if ($L < 25) { print "Warning: the seed length set is less than 25! This is only allowed if the references are not added poly(A) tails.\n"; }
123 if ($strand_specific) { $probF = 1.0; }
129 my ($refName, $sampleName, $sampleToken, $temp_dir, $stat_dir, $imdName) = ();
133 if ($no_qual) { $read_type = 2; }
134 else { $read_type = 3; }
137 if ($no_qual) { $read_type = 0; }
138 else { $read_type = 1; }
141 if (scalar(@ARGV) == 3) {
142 if ($is_sam || $is_bam) { $inpF = $ARGV[0]; }
143 else {$mate1_list = $ARGV[0]; }
145 $sampleName = $ARGV[2];
148 $mate1_list = $ARGV[0];
149 $mate2_list = $ARGV[1];
151 $sampleName = $ARGV[3];
154 if ($genGenomeBamF) {
155 open(INPUT, "$refName.ti");
156 my $line = <INPUT>; chomp($line);
158 my ($M, $type) = split(/ /, $line);
159 pod2usage(-msg => "No genome information provided, so genome bam file cannot be generated!\n", -exitval => 2, -verbose => 2) if ($type != 0);
162 my $pos = rindex($sampleName, '/');
163 if ($pos < 0) { $sampleToken = $sampleName; }
164 else { $sampleToken = substr($sampleName, $pos + 1); }
166 $temp_dir = "$sampleName.temp";
167 $stat_dir = "$sampleName.stat";
169 if (!(-d $temp_dir) && !mkdir($temp_dir)) { print "Fail to create folder $temp_dir.\n"; exit(-1); }
170 if (!(-d $stat_dir) && !mkdir($stat_dir)) { print "Fail to create folder $stat_dir.\n"; exit(-1); }
172 $imdName = "$temp_dir/$sampleToken";
174 if (!$is_sam && !$is_bam && $phred33 + $phred64 + $solexa == 0) { $phred33 = 1; }
176 my ($mate_minL, $mate_maxL) = (1, $maxL);
178 if ($bowtie_path ne "") { $bowtie_path .= "/"; }
180 my ($fn, $dir, $suf) = fileparse($0);
183 if (!$is_sam && !$is_bam) {
184 $command = $bowtie_path."bowtie";
185 if ($read_type == 0 || $read_type == 2) { $command .= " -f"; }
186 else { $command .= " -q"; }
188 if ($phred33) { $command .= " --phred33-quals"; }
189 elsif ($phred64) { $command .= " --phred64-quals"; }
190 elsif ($solexa) { $command .= " --solexa-quals"; }
191 else { print "Oh, no!!!"; exit(2); }
193 $command .= " -n $C -e $E -l $L";
195 if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL"; }
197 if ($strand_specific || $probF == 1.0) { $command .= " --norc"; }
198 elsif ($probF == 0.0) { $command .= " --nofw"; }
200 $command .= " -p $nThreads -a -m $maxHits -S";
201 if ($quiet) { $command .= " --quiet"; }
203 $command .= " --chunkmbs $chunkMbs" if $chunkMbs > 0;
205 $command .= " $refName";
206 if ($read_type == 0 || $read_type == 1) {
207 $command .= " $mate1_list";
210 $command .= " -1 $mate1_list -2 $mate2_list";
213 $command .= " | gzip > $imdName.sam.gz";
215 if ($mTime) { $time_start = time(); }
217 &runCommand($command);
219 if ($mTime) { $time_end = time(); $time_alignment = $time_end - $time_start; }
221 $inpF = "$imdName.sam.gz";
222 $is_sam = 1; # output of bowtie is a sam file
225 if ($mTime) { $time_start = time(); }
227 $command = $dir."rsem-parse-alignments $refName $sampleName $sampleToken";
230 if ($is_sam) { $samInpType = "s"; }
231 elsif ($is_bam) { $samInpType = "b"; }
233 $command .= " $samInpType $inpF -t $read_type";
234 if ($fn_list ne "") { $command .= " -l $fn_list"; }
235 if ($tagName ne "") { $command .= " -tag $tagName"; }
236 if ($quiet) { $command .= " -q"; }
238 &runCommand($command);
240 $command = $dir."rsem-build-read-index $gap";
242 case 0 { $command .= " 0 $quiet $imdName\_alignable.fa"; }
243 case 1 { $command .= " 1 $quiet $imdName\_alignable.fq"; }
244 case 2 { $command .= " 0 $quiet $imdName\_alignable_1.fa $imdName\_alignable_2.fa"; }
245 case 3 { $command .= " 1 $quiet $imdName\_alignable_1.fq $imdName\_alignable_2.fq"; }
247 &runCommand($command);
249 my $doesOpen = open(OUTPUT, ">$imdName.mparams");
250 if ($doesOpen == 0) { print "Cannot generate $imdName.mparams!\n"; exit(-1); }
251 print OUTPUT "$minL $maxL\n";
252 print OUTPUT "$probF\n";
253 print OUTPUT "$estRSPD\n";
255 print OUTPUT "$mate_minL $mate_maxL\n";
256 print OUTPUT "$mean $sd\n";
260 $command = $dir."rsem-run-em $refName $read_type $sampleName $sampleToken -p $nThreads";
262 $command .= " -b $samInpType $inpF";
263 if ($fn_list ne "") { $command .= " 1 $fn_list"; }
264 else { $command .= " 0"; }
265 if ($sampling) { $command .= " --sampling"; }
267 if ($calcCI) { $command .= " --gibbs-out"; }
268 if ($quiet) { $command .= " -q"; }
270 &runCommand($command);
273 $command = $dir."sam/samtools sort $sampleName.transcript.bam $sampleName.transcript.sorted";
274 &runCommand($command);
275 $command = $dir."sam/samtools index $sampleName.transcript.sorted.bam";
276 &runCommand($command);
278 if ($genGenomeBamF) {
279 $command = $dir."rsem-tbam2gbam $refName $sampleName.transcript.bam $sampleName.genome.bam";
280 &runCommand($command);
281 $command = $dir."sam/samtools sort $sampleName.genome.bam $sampleName.genome.sorted";
282 &runCommand($command);
283 $command = $dir."sam/samtools index $sampleName.genome.sorted.bam";
284 &runCommand($command);
288 &collectResults("$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
289 &collectResults("$imdName.gene_res", "$sampleName.genes.results"); # gene level
291 if ($mTime) { $time_end = time(); $time_rsem = $time_end - $time_start; }
293 if ($mTime) { $time_start = time(); }
296 $command = $dir."rsem-run-gibbs $refName $sampleName $sampleToken $BURNIN $CHAINLEN $SAMPLEGAP";
297 # $command .= " -p $nThreads";
298 if ($quiet) { $command .= " -q"; }
299 &runCommand($command);
301 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak1");
302 system("mv $sampleName.genes.results $imdName.genes.results.bak1");
303 &collectResults("$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
304 &collectResults("$imdName.gene_res", "$sampleName.genes.results"); # gene level
306 $command = $dir."rsem-calculate-credibility-intervals $refName $sampleName $sampleToken $CONFIDENCE $NSPC $NMB";
307 if ($quiet) { $command .= " -q"; }
308 &runCommand($command);
310 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak2");
311 system("mv $sampleName.genes.results $imdName.genes.results.bak2");
312 &collectResults("$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
313 &collectResults("$imdName.gene_res", "$sampleName.genes.results"); # gene level
316 if ($mTime) { $time_end = time(); $time_ci = $time_end - $time_start; }
318 if ($mTime) { $time_start = time(); }
320 if (!$keep_intermediate_files) {
321 &runCommand("rm -rf $temp_dir", "Fail to delete the temporary folder!");
324 if ($mTime) { $time_end = time(); }
327 open(OUTPUT, ">$sampleName.time");
328 print OUTPUT "Alignment: $time_alignment s.\n";
329 print OUTPUT "RSEM: $time_rsem s.\n";
330 print OUTPUT "CI: $time_ci s.\n";
331 my $time_del = $time_end - $time_start;
332 print OUTPUT "Delete: $time_del s.\n";
339 my $status = system($_[0]);
342 if (scalar(@_) > 1) { $errmsg = $_[1]; }
343 else { $errmsg = "\"$command\" failed! Plase check if you provide correct parameters/options for the pipeline!"; }
354 my (@results, @ids) = ();
361 $local_status = open(INPUT, $inpF);
362 if ($local_status == 0) { print "Fail to open file $inpF!\n"; exit(-1); }
367 while ($line = <INPUT>) {
370 my @local_arr = split(/\t/, $line);
371 if ($cnt == 4) { @ids = @local_arr; }
372 else { push(@results, \@local_arr); }
375 push(@results, \@ids);
378 $local_status = open(OUTPUT, ">$outF");
379 if ($local_status == 0) { print "Fail to create file $outF!\n"; exit(-1); }
381 my $n = scalar(@results);
382 my $m = scalar(@{$results[0]});
383 for (my $i = 0; $i < $m; $i++) {
385 for (my $j = 0; $j < $n; $j++) { push(@out_arr, $results[$j][$i]); }
387 print OUTPUT "@out_arr\n";
397 rsem-calculate-expression
403 rsem-calculate-expression [options] upstream_read_file(s) reference_name sample_name
404 rsem-calculate-expression [options] --paired-end upstream_read_file(s) downstream_read_file(s) reference_name sample_name
405 rsem-calculate-expression [options] --sam/--bam [--paired-end] input reference_name sample_name
413 =item B<upstream_read_files(s)>
415 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.
417 =item B<downstream_read_file(s)>
419 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.
423 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.
425 =item B<reference_name>
427 The name of the reference used. The user must have run 'rsem-prepare-reference' with this reference_name before running this program.
431 The name of the sample analyzed. All output files are prefixed by this name (e.g., sample_name.genes.results)
439 =item B<--paired-end>
441 Input reads are paired-end reads. (Default: off)
443 =item B<--no-qualities>
445 Input reads do not contain quality scores. (Default: off)
447 =item B<--strand-specific>
449 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)
453 Input file is in SAM format. (Default: off)
457 Input file is in BAM format. (Default: off)
459 =item B<--sam-header-info> <file>
461 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: "")
463 =item B<-p/--num-threads> <int>
465 Number of threads to use. Both Bowtie and expression estimation will use this many threads. (Default: 1)
467 =item B<--output-genome-bam>
469 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)
471 =item B<--sampling-for-bam>
473 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)
477 Calculate 95% credibility intervals and posterior mean estimates. (Default: off)
479 =item B<--seed-length> <int>
481 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)
483 =item B<--tag> <string>
485 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: "")
487 =item B<--bowtie-path> <path>
489 The path to the bowtie executables. (Default: the path to the bowtie executables is assumed to be in the user's PATH environment variable)
491 =item B<--bowtie-n> <int>
493 (Bowtie parameter) max # of mismatches in the seed. (Range: 0-3, Default: 2)
495 =item B<--bowtie-e> <int>
497 (Bowtie parameter) max sum of mismatch quality scores across the alignment. (Default: 99999999)
499 =item B<--bowtie-m> <int>
501 (Bowtie parameter) suppress all alignments for a read if > <int> valid alignments exist. (Default: 200)
503 =item B<--bowtie-chunkmbs> <int>
505 (Bowtie parameter) memory allocated for best first alignment calculation (Default: 0 - use bowtie's default)
507 =item B<--phred33-quals>
509 Input quality scores are encoded as Phred+33. (Default: on)
511 =item B<--phred64-quals>
513 Input quality scores are encoded as Phred+64 (default for GA Pipeline ver. >= 1.3). (Default: off)
515 =item B<--solexa-quals>
517 Input quality scores are solexa encoded (from GA Pipeline ver. < 1.3). (Default: off)
519 =item B<--forward-prob> <double>
521 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)
523 =item B<--fragment-length-min> <int>
525 Minimum read/insert length allowed. This is also the value for the bowtie -I option. (Default: 1)
527 =item B<--fragment-length-max> <int>
529 Maximum read/insert length allowed. This is also the value for the bowtie -X option. (Default: 1000)
531 =item B<--fragment-length-mean> <double>
533 (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)
535 =item B<--fragment-length-sd> <double>
537 (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>)
539 =item B<--estimate-rspd>
541 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)
543 =item B<--num-rspd-bins> <int>
545 Number of bins in the RSPD. Only relevant when '--estimate-rspd' is specified. Use of the default setting is recommended. (Default: 20)
547 =item B<--ci-memory> <int>
549 Amount of memory (in MB) RSEM is allowed to use for computing credibility intervals. (Default: 1024)
551 =item B<--keep-intermediate-files>
553 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)
557 Suppress the output of logging information. (Default: off)
561 Show help information.
567 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.
569 One simple way to make the alignment file satisfying RSEM's requirements (assuming the aligner used put mates in a paired-end read adjacent) is to use 'convert-sam-for-rsem' script. This script only accept SAM format files as input. If a BAM format file is obtained, please use samtools to convert it to a SAM file first. For example, if '/ref/mouse_125' is the 'reference_name' and the SAM file is named 'input.sam', you can run the following command:
571 convert-sam-for-rsem /ref/mouse_125 input.sam -o input_for_rsem.sam
573 For details, please refer to 'convert-sam-for-rsem's documentation page.
575 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 are not '*'.
577 The user must run 'rsem-prepare-reference' with the appropriate reference before using this program.
579 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.
581 Please note that some of the default values for the Bowtie parameters are not the same as those defined for Bowtie itself.
583 The temporary directory and all intermediate files will be removed when RSEM finishes unless '--keep-intermediate-files' is specified.
585 With the '--calc-ci' option, 95% credibility intervals and posterior mean estimates will be calculated in addition to maximum likelihood estimates.
591 =item B<sample_name.genes.results>
593 File containing gene level expression estimates. The format of each
594 line in this file is:
596 gene_id expected_counts tau_value [pmc_value tau_pme_value tau_ci_lower_bound tau_ci_upper_bound] transcript_id_list
598 Fields are separated by the tab character. Fields within "[]" are only
599 presented if '--calc-ci' is set. pme stands for posterior mean
600 estimation. pmc stands for posterior mean counts. ci_lower_bound(l)
601 means the lower bound of the credibility intervals, ci_upper_bound(u)
602 means the upper bound of the credibility intervals. So the credibility
603 interval is [l, u]. 'transcript_id_list' is a space-separated list of
604 transcript_ids belonging to the gene. If no gene information is
605 provided, this file has the same content as
606 'sample_name.isoforms.results'.
608 =item B<sample_name.isoforms.results>
610 File containing isoform level expression values. The format of each
611 line in this file is:
613 transcript_id expected_counts tau_value [pmc_value tau_pme_value tau_ci_lower_bound tau_ci_upper_bound] gene_id
615 Fields are separated by the tab character. 'gene_id' is the gene_id of
616 the gene which this transcript belongs to. If no gene information is
617 provided, 'gene_id' and 'transcript_id' are the same.
619 =item B<sample_name.transcript.bam, sample_name.transcript.sorted.bam and sample_name.transcript.sorted.bam.bai>
621 'sample_name.transcript.bam' is a BAM-formatted file of read
622 alignments in transcript coordinates. The MAPQ field of each alignment
623 is set to min(100, floor(-10 * log10(1.0 - w) + 0.5)), where w is the
624 posterior probability of that alignment being the true mapping of a
625 read. In addition, RSEM pads a new tag ZW:f:value, where value is a
626 single precision floating number representing the posterior
629 'sample_name.transcript.sorted.bam' and
630 'sample_name.transcript.sorted.bam.bai' are the sorted BAM file and
631 indices generated by samtools (included in RSEM package).
633 =item B<sample_name.genome.bam, sample_name.genome.sorted.bam and sample_name.genome.sorted.bam.bai>
635 Only generated when --output-genome-bam is specified.
637 'sample_name.genome.bam' is a BAM-formatted file of read alignments in
638 genomic coordinates. Alignments of reads that have identical genomic
639 coordinates (i.e., alignments to different isoforms that share the
640 same genomic region) are collapsed into one alignment. The MAPQ field
641 of each alignment is set to min(100, floor(-10 * log10(1.0 - w) +
642 0.5)), where w is the posterior probability of that alignment being
643 the true mapping of a read. In addition, RSEM pads a new tag
644 ZW:f:value, where value is a single precision floating number
645 representing the posterior probability. If an alignment is spliced, a
646 XS:A:value tag is also added, where value is either '+' or '-'
647 indicating the strand of the transcript it aligns to.
649 'sample_name.genome.sorted.bam' and 'sample_name.genome.sorted.bam.bai' are the
650 sorted BAM file and indices generated by samtools (included in RSEM package).
652 =item B<sample_name.stat>
654 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.
660 Assume the path to the bowtie executables is in the user's PATH environment variable. Reference files are under '/ref' with name 'mouse_125'.
662 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:
664 rsem-calculate-expression --phred64-quals \
666 --output-genome-bam \
671 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:
673 rsem-calculate-expression -p 8 \
678 mmliver_paired_end_quals
680 3) '/data/mmliver.fa', single-end reads without quality scores. We want to use 8 threads:
682 rsem-calculate-expression -p 8 \
686 mmliver_single_without_quals
688 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:
690 rsem-calculate-expression --bowtie-path /sw/bowtie \
692 --fragment-length-mean 150.0 \
693 --fragment-length-sd 35.0 \
695 --output-genome-bam \
702 5) '/data/mmliver_paired_end_quals.bam', paired-end reads with quality scores. We want to use 8 threads:
704 rsem-calculate-expression --paired-end \
707 /data/mmliver_paired_end_quals.bam \
709 mmliver_paired_end_quals