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;
52 my $var_opt = 0; # temporarily, only for internal use
58 my $keep_intermediate_files = 0;
60 my $strand_specific = 0;
63 my ($time_start, $time_end, $time_alignment, $time_rsem, $time_ci) = (0, 0, 0, 0, 0);
69 my ($refName, $sampleName, $sampleToken, $temp_dir, $stat_dir, $imdName, $statName) = ();
72 GetOptions("keep-intermediate-files" => \$keep_intermediate_files,
73 "temporary-folder=s" => \$temp_dir,
74 "no-qualities" => \$no_qual,
75 "paired-end" => \$paired_end,
76 "strand-specific" => \$strand_specific,
79 "sam-header-info=s" => \$fn_list,
81 "seed-length=i" => \$L,
82 "bowtie-path=s" => \$bowtie_path,
85 "bowtie-m=i" => \$maxHits,
86 "bowtie-chunkmbs=i" => \$chunkMbs,
87 "phred33-quals" => \$phred33,
88 "phred64-quals" => \$phred64, #solexa1.3-quals" => \$phred64,
89 "solexa-quals" => \$solexa,
90 "forward-prob=f" => \$probF,
91 "fragment-length-min=i" => \$minL,
92 "fragment-length-max=i" => \$maxL,
93 "fragment-length-mean=f" => \$mean,
94 "fragment-length-sd=f" => \$sd,
95 "estimate-rspd" => \$estRSPD,
96 "num-rspd-bins=i" => \$B,
97 "p|num-threads=i" => \$nThreads,
98 "no-bam-output" => sub { $genBamF = 0; },
99 "output-genome-bam" => \$genGenomeBamF,
100 "sampling-for-bam" => \$sampling,
102 "calc-ci" => \$calcCI,
103 "ci-memory=i" => \$NMB,
105 "q|quiet" => \$quiet,
106 "h|help" => \$help) or pod2usage(-exitval => 2, -verbose => 2);
108 pod2usage(-verbose => 2) if ($help == 1);
111 #check parameters and options
113 if ($is_sam || $is_bam) {
114 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (scalar(@ARGV) != 3);
115 pod2usage(-msg => "--sam and --bam cannot be active at the same time!", -exitval => 2, -verbose => 2) if ($is_sam == 1&& $is_bam == 1);
116 pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m, --phred33-quals, --phred64-quals or --solexa-quals cannot be set if input is SAM/BAM format!", -exitval => 2, -verbose => 2) if ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200 || $phred33 || $phred64 || $solexa);
119 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (!$paired_end && scalar(@ARGV) != 3 || $paired_end && scalar(@ARGV) != 4);
120 pod2usage(-msg => "Only one of --phred33-quals --phred64-quals/--solexa1.3-quals --solexa-suqls can be active!", -exitval => 2, -verbose => 2) if ($phred33 + $phred64 + $solexa > 1);
121 podwusage(-msg => "--sam , --bam or --sam-header-info cannot be set if use bowtie aligner to produce alignments!", -exitval => 2, -verbose => 2) if ($is_sam || $is_bam || $fn_list ne "");
124 pod2usage(-msg => "Forward probability should be in [0, 1]!", -exitval => 2, -verbose => 2) if ($probF < 0 || $probF > 1);
125 pod2usage(-msg => "Min fragment length should be at least 1!", -exitval => 2, -verbose => 2) if ($minL < 1);
126 pod2usage(-msg => "Min fragment length should be smaller or equal to max fragment length!", -exitval => 2, -verbose => 2) if ($minL > $maxL);
127 pod2usage(-msg => "The memory allocated for calculating credibility intervals should be at least 1 MB!\n", -exitval => 2, -verbose => 2) if ($NMB < 1);
128 pod2usage(-msg => "Number of threads should be at least 1!\n", -exitval => 2, -verbose => 2) if ($nThreads < 1);
129 pod2usage(-msg => "Seed length should be at least 5!\n", -exitval => 2, -verbose => 2) if ($L < 5);
130 pod2usage(-msg => "--sampling-for-bam cannot be specified if --no-bam-output is specified!\n", -exitval => 2, -verbose => 2) if ($sampling && !$genBamF);
131 pod2usage(-msg => "--output-genome-bam cannot be specified if --no-bam-output is specified!\n", -exitval => 2, -verbose => 2) if ($genGenomeBamF && !$genBamF);
133 if ($L < 25) { print "Warning: the seed length set is less than 25! This is only allowed if the references are not added poly(A) tails.\n"; }
135 if ($strand_specific) { $probF = 1.0; }
138 if ($no_qual) { $read_type = 2; }
139 else { $read_type = 3; }
142 if ($no_qual) { $read_type = 0; }
143 else { $read_type = 1; }
146 if (scalar(@ARGV) == 3) {
147 if ($is_sam || $is_bam) { $inpF = $ARGV[0]; }
148 else {$mate1_list = $ARGV[0]; }
150 $sampleName = $ARGV[2];
153 $mate1_list = $ARGV[0];
154 $mate2_list = $ARGV[1];
156 $sampleName = $ARGV[3];
159 if ($genGenomeBamF) {
160 open(INPUT, "$refName.ti");
161 my $line = <INPUT>; chomp($line);
163 my ($M, $type) = split(/ /, $line);
164 pod2usage(-msg => "No genome information provided, so genome bam file cannot be generated!\n", -exitval => 2, -verbose => 2) if ($type != 0);
167 my $pos = rindex($sampleName, '/');
168 if ($pos < 0) { $sampleToken = $sampleName; }
169 else { $sampleToken = substr($sampleName, $pos + 1); }
171 if ($temp_dir eq "") { $temp_dir = "$sampleName.temp"; }
172 $stat_dir = "$sampleName.stat";
174 if (!(-d $temp_dir) && !mkdir($temp_dir)) { print "Fail to create folder $temp_dir.\n"; exit(-1); }
175 if (!(-d $stat_dir) && !mkdir($stat_dir)) { print "Fail to create folder $stat_dir.\n"; exit(-1); }
177 $imdName = "$temp_dir/$sampleToken";
178 $statName = "$stat_dir/$sampleToken";
180 if (!$is_sam && !$is_bam && !$no_qual && ($phred33 + $phred64 + $solexa == 0)) { $phred33 = 1; }
182 my ($mate_minL, $mate_maxL) = (1, $maxL);
184 if ($bowtie_path ne "") { $bowtie_path .= "/"; }
186 my ($fn, $dir, $suf) = fileparse($0);
189 if (!$is_sam && !$is_bam) {
190 $command = $bowtie_path."bowtie";
191 if ($no_qual) { $command .= " -f"; }
192 else { $command .= " -q"; }
194 if ($phred33) { $command .= " --phred33-quals"; }
195 elsif ($phred64) { $command .= " --phred64-quals"; }
196 elsif ($solexa) { $command .= " --solexa-quals"; }
198 $command .= " -n $C -e $E -l $L";
199 if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL"; }
200 if ($chunkMbs > 0) { $command .= " --chunkmbs $chunkMbs"; }
202 if ($strand_specific || $probF == 1.0) { $command .= " --norc"; }
203 elsif ($probF == 0.0) { $command .= " --nofw"; }
205 $command .= " -p $nThreads -a -m $maxHits -S";
206 if ($quiet) { $command .= " --quiet"; }
208 $command .= " $refName";
209 if ($read_type == 0 || $read_type == 1) {
210 $command .= " $mate1_list";
213 $command .= " -1 $mate1_list -2 $mate2_list";
216 # pipe to samtools to generate a BAM file
217 $command .= " | $dir\sam/samtools view -S -b -o $imdName.bam -";
219 if ($mTime) { $time_start = time(); }
221 &runCommand($command);
223 if ($mTime) { $time_end = time(); $time_alignment = $time_end - $time_start; }
225 $inpF = "$imdName.bam";
226 $is_bam = 1; # alignments are outputed as a BAM file
229 if ($mTime) { $time_start = time(); }
231 $command = $dir."rsem-parse-alignments $refName $imdName $statName";
234 if ($is_sam) { $samInpType = "s"; }
235 elsif ($is_bam) { $samInpType = "b"; }
237 $command .= " $samInpType $inpF -t $read_type";
238 if ($fn_list ne "") { $command .= " -l $fn_list"; }
239 if ($tagName ne "") { $command .= " -tag $tagName"; }
240 if ($quiet) { $command .= " -q"; }
242 &runCommand($command);
244 $command = $dir."rsem-build-read-index $gap";
246 case 0 { $command .= " 0 $quiet $imdName\_alignable.fa"; }
247 case 1 { $command .= " 1 $quiet $imdName\_alignable.fq"; }
248 case 2 { $command .= " 0 $quiet $imdName\_alignable_1.fa $imdName\_alignable_2.fa"; }
249 case 3 { $command .= " 1 $quiet $imdName\_alignable_1.fq $imdName\_alignable_2.fq"; }
251 &runCommand($command);
253 my $doesOpen = open(OUTPUT, ">$imdName.mparams");
254 if ($doesOpen == 0) { print "Cannot generate $imdName.mparams!\n"; exit(-1); }
255 print OUTPUT "$minL $maxL\n";
256 print OUTPUT "$probF\n";
257 print OUTPUT "$estRSPD\n";
259 print OUTPUT "$mate_minL $mate_maxL\n";
260 print OUTPUT "$mean $sd\n";
264 $command = $dir."rsem-run-em $refName $read_type $sampleName $imdName $statName -p $nThreads";
266 $command .= " -b $samInpType $inpF";
267 if ($fn_list ne "") { $command .= " 1 $fn_list"; }
268 else { $command .= " 0"; }
269 if ($sampling) { $command .= " --sampling"; }
271 if ($calcCI || $var_opt) { $command .= " --gibbs-out"; }
272 if ($quiet) { $command .= " -q"; }
274 &runCommand($command);
276 &collectResults("$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
277 &collectResults("$imdName.gene_res", "$sampleName.genes.results"); # gene level
280 $command = $dir."sam/samtools sort $sampleName.transcript.bam $sampleName.transcript.sorted";
281 &runCommand($command);
282 $command = $dir."sam/samtools index $sampleName.transcript.sorted.bam";
283 &runCommand($command);
285 if ($genGenomeBamF) {
286 $command = $dir."rsem-tbam2gbam $refName $sampleName.transcript.bam $sampleName.genome.bam";
287 &runCommand($command);
288 $command = $dir."sam/samtools sort $sampleName.genome.bam $sampleName.genome.sorted";
289 &runCommand($command);
290 $command = $dir."sam/samtools index $sampleName.genome.sorted.bam";
291 &runCommand($command);
295 if ($mTime) { $time_end = time(); $time_rsem = $time_end - $time_start; }
297 if ($mTime) { $time_start = time(); }
299 if ($calcCI || $var_opt) {
300 $command = $dir."rsem-run-gibbs $refName $imdName $statName $BURNIN $NCV $SAMPLEGAP";
301 $command .= " -p $nThreads";
302 if ($var_opt) { $command .= " --var"; }
303 if ($quiet) { $command .= " -q"; }
304 &runCommand($command);
308 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak1");
309 system("mv $sampleName.genes.results $imdName.genes.results.bak1");
310 &collectResults("$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
311 &collectResults("$imdName.gene_res", "$sampleName.genes.results"); # gene level
313 $command = $dir."rsem-calculate-credibility-intervals $refName $imdName $statName $CONFIDENCE $NCV $NSPC $NMB";
314 $command .= " -p $nThreads";
315 if ($quiet) { $command .= " -q"; }
316 &runCommand($command);
318 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak2");
319 system("mv $sampleName.genes.results $imdName.genes.results.bak2");
320 &collectResults("$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
321 &collectResults("$imdName.gene_res", "$sampleName.genes.results"); # gene level
324 if ($mTime) { $time_end = time(); $time_ci = $time_end - $time_start; }
326 if ($mTime) { $time_start = time(); }
328 if (!$keep_intermediate_files) {
329 &runCommand("rm -rf $temp_dir", "Fail to delete the temporary folder!");
332 if ($mTime) { $time_end = time(); }
335 open(OUTPUT, ">$sampleName.time");
336 print OUTPUT "Aligning reads: $time_alignment s.\n";
337 print OUTPUT "Estimating expression levels: $time_rsem s.\n";
338 print OUTPUT "Calculating credibility intervals: $time_ci s.\n";
339 my $time_del = $time_end - $time_start;
340 # print OUTPUT "Delete: $time_del s.\n";
347 my $status = system($_[0]);
350 if (scalar(@_) > 1) { $errmsg .= $_[1]."\n"; }
351 $errmsg .= "\"$_[0]\" failed! Plase check if you provide correct parameters/options for the pipeline!\n";
362 my (@results, @ids) = ();
369 $local_status = open(INPUT, $inpF);
370 if ($local_status == 0) { print "Fail to open file $inpF!\n"; exit(-1); }
375 while ($line = <INPUT>) {
378 my @local_arr = split(/\t/, $line);
379 if ($cnt == 4) { @ids = @local_arr; }
380 else { push(@results, \@local_arr); }
383 push(@results, \@ids);
386 $local_status = open(OUTPUT, ">$outF");
387 if ($local_status == 0) { print "Fail to create file $outF!\n"; exit(-1); }
389 my $n = scalar(@results);
390 my $m = scalar(@{$results[0]});
391 for (my $i = 0; $i < $m; $i++) {
393 for (my $j = 0; $j < $n; $j++) { push(@out_arr, $results[$j][$i]); }
395 print OUTPUT "@out_arr\n";
405 rsem-calculate-expression
411 rsem-calculate-expression [options] upstream_read_file(s) reference_name sample_name
412 rsem-calculate-expression [options] --paired-end upstream_read_file(s) downstream_read_file(s) reference_name sample_name
413 rsem-calculate-expression [options] --sam/--bam [--paired-end] input reference_name sample_name
421 =item B<upstream_read_files(s)>
423 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.
425 =item B<downstream_read_file(s)>
427 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.
431 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.
433 =item B<reference_name>
435 The name of the reference used. The user must have run 'rsem-prepare-reference' with this reference_name before running this program.
439 The name of the sample analyzed. All output files are prefixed by this name (e.g., sample_name.genes.results)
447 =item B<--paired-end>
449 Input reads are paired-end reads. (Default: off)
451 =item B<--no-qualities>
453 Input reads do not contain quality scores. (Default: off)
455 =item B<--strand-specific>
457 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)
461 Input file is in SAM format. (Default: off)
465 Input file is in BAM format. (Default: off)
467 =item B<--sam-header-info> <file>
469 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: "")
471 =item B<-p/--num-threads> <int>
473 Number of threads to use. Both Bowtie and expression estimation will use this many threads. (Default: 1)
475 =item B<--no-bam-output>
477 Do not output any BAM file. (Default: off)
479 =item B<--output-genome-bam>
481 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)
483 =item B<--sampling-for-bam>
485 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)
489 Calculate 95% credibility intervals and posterior mean estimates. (Default: off)
491 =item B<--seed-length> <int>
493 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)
495 =item B<--tag> <string>
497 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: "")
499 =item B<--bowtie-path> <path>
501 The path to the bowtie executables. (Default: the path to the bowtie executables is assumed to be in the user's PATH environment variable)
503 =item B<--bowtie-n> <int>
505 (Bowtie parameter) max # of mismatches in the seed. (Range: 0-3, Default: 2)
507 =item B<--bowtie-e> <int>
509 (Bowtie parameter) max sum of mismatch quality scores across the alignment. (Default: 99999999)
511 =item B<--bowtie-m> <int>
513 (Bowtie parameter) suppress all alignments for a read if > <int> valid alignments exist. (Default: 200)
515 =item B<--bowtie-chunkmbs> <int>
517 (Bowtie parameter) memory allocated for best first alignment calculation (Default: 0 - use bowtie's default)
519 =item B<--phred33-quals>
521 Input quality scores are encoded as Phred+33. (Default: on)
523 =item B<--phred64-quals>
525 Input quality scores are encoded as Phred+64 (default for GA Pipeline ver. >= 1.3). (Default: off)
527 =item B<--solexa-quals>
529 Input quality scores are solexa encoded (from GA Pipeline ver. < 1.3). (Default: off)
531 =item B<--forward-prob> <double>
533 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)
535 =item B<--fragment-length-min> <int>
537 Minimum read/insert length allowed. This is also the value for the bowtie -I option. (Default: 1)
539 =item B<--fragment-length-max> <int>
541 Maximum read/insert length allowed. This is also the value for the bowtie -X option. (Default: 1000)
543 =item B<--fragment-length-mean> <double>
545 (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)
547 =item B<--fragment-length-sd> <double>
549 (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>)
551 =item B<--estimate-rspd>
553 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)
555 =item B<--num-rspd-bins> <int>
557 Number of bins in the RSPD. Only relevant when '--estimate-rspd' is specified. Use of the default setting is recommended. (Default: 20)
559 =item B<--ci-memory> <int>
561 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)
563 =item B<--keep-intermediate-files>
565 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)
567 =item B<--temporary-folder> <string>
569 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)
573 Output time consumed by each step of RSEM to 'sample_name.time'. (Default: off)
577 Suppress the output of logging information. (Default: off)
581 Show help information.
587 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.
589 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:
591 convert-sam-for-rsem /ref/mouse_125 input.sam -o input_for_rsem.sam
593 For details, please refer to 'convert-sam-for-rsem's documentation page.
595 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 '*'.
597 The user must run 'rsem-prepare-reference' with the appropriate reference before using this program.
599 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.
601 Please note that some of the default values for the Bowtie parameters are not the same as those defined for Bowtie itself.
603 The temporary directory and all intermediate files will be removed when RSEM finishes unless '--keep-intermediate-files' is specified.
605 With the '--calc-ci' option, 95% credibility intervals and posterior mean estimates will be calculated in addition to maximum likelihood estimates.
611 =item B<sample_name.genes.results>
613 File containing gene level expression estimates. The format of each
614 line in this file is:
616 gene_id expected_counts tau_value [pmc_value tau_pme_value tau_ci_lower_bound tau_ci_upper_bound] transcript_id_list
618 Fields are separated by the tab character. Fields within "[]" are only
619 presented if '--calc-ci' is set. pme stands for posterior mean
620 estimation. pmc stands for posterior mean counts. ci_lower_bound(l)
621 means the lower bound of the credibility intervals, ci_upper_bound(u)
622 means the upper bound of the credibility intervals. So the credibility
623 interval is [l, u]. 'transcript_id_list' is a space-separated list of
624 transcript_ids belonging to the gene. If no gene information is
625 provided, this file has the same content as
626 'sample_name.isoforms.results'.
628 =item B<sample_name.isoforms.results>
630 File containing isoform level expression values. The format of each
631 line in this file is:
633 transcript_id expected_counts tau_value [pmc_value tau_pme_value tau_ci_lower_bound tau_ci_upper_bound] gene_id
635 Fields are separated by the tab character. 'gene_id' is the gene_id of
636 the gene which this transcript belongs to. If no gene information is
637 provided, 'gene_id' and 'transcript_id' are the same.
639 =item B<sample_name.transcript.bam, sample_name.transcript.sorted.bam and sample_name.transcript.sorted.bam.bai>
641 Only generated when --no-bam-output is not specified.
643 'sample_name.transcript.bam' is a BAM-formatted file of read
644 alignments in transcript coordinates. The MAPQ field of each alignment
645 is set to min(100, floor(-10 * log10(1.0 - w) + 0.5)), where w is the
646 posterior probability of that alignment being the true mapping of a
647 read. In addition, RSEM pads a new tag ZW:f:value, where value is a
648 single precision floating number representing the posterior
649 probability. Because this file contains all alignment lines produced
650 by bowtie or user-specified aligners, it can also be used as a
651 replacement of the aligner generated BAM/SAM file. For paired-end
652 reads, if one mate has alignments but the other does not, this file
653 marks the alignable mate as "unmappable" (flag bit 0x4) and appends an
654 optional field "Z0:A:!".
656 'sample_name.transcript.sorted.bam' and
657 'sample_name.transcript.sorted.bam.bai' are the sorted BAM file and
658 indices generated by samtools (included in RSEM package).
660 =item B<sample_name.genome.bam, sample_name.genome.sorted.bam and sample_name.genome.sorted.bam.bai>
662 Only generated when --no-bam-output is not specified and --output-genome-bam is specified.
664 'sample_name.genome.bam' is a BAM-formatted file of read alignments in
665 genomic coordinates. Alignments of reads that have identical genomic
666 coordinates (i.e., alignments to different isoforms that share the
667 same genomic region) are collapsed into one alignment. The MAPQ field
668 of each alignment is set to min(100, floor(-10 * log10(1.0 - w) +
669 0.5)), where w is the posterior probability of that alignment being
670 the true mapping of a read. In addition, RSEM pads a new tag
671 ZW:f:value, where value is a single precision floating number
672 representing the posterior probability. If an alignment is spliced, a
673 XS:A:value tag is also added, where value is either '+' or '-'
674 indicating the strand of the transcript it aligns to.
676 'sample_name.genome.sorted.bam' and 'sample_name.genome.sorted.bam.bai' are the
677 sorted BAM file and indices generated by samtools (included in RSEM package).
679 =item B<sample_name.time>
681 Only generated when --time is specified.
683 It contains time (in seconds) consumed by aligning reads, estimating expression levels and calculating credibility intervals.
685 =item B<sample_name.stat>
687 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.
693 Assume the path to the bowtie executables is in the user's PATH environment variable. Reference files are under '/ref' with name 'mouse_125'.
695 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:
697 rsem-calculate-expression --phred64-quals \
699 --output-genome-bam \
704 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:
706 rsem-calculate-expression -p 8 \
711 mmliver_paired_end_quals
713 3) '/data/mmliver.fa', single-end reads without quality scores. We want to use 8 threads:
715 rsem-calculate-expression -p 8 \
719 mmliver_single_without_quals
721 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:
723 rsem-calculate-expression --bowtie-path /sw/bowtie \
725 --fragment-length-mean 150.0 \
726 --fragment-length-sd 35.0 \
728 --output-genome-bam \
735 5) '/data/mmliver_paired_end_quals.bam', paired-end reads with quality scores. We want to use 8 threads:
737 rsem-calculate-expression --paired-end \
740 /data/mmliver_paired_end_quals.bam \
742 mmliver_paired_end_quals