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 "no-bam-output" => sub { $genBamF = 0; },
90 "output-genome-bam" => \$genGenomeBamF,
91 "sampling-for-bam" => \$sampling,
92 "calc-ci" => \$calcCI,
93 "ci-memory=i" => \$NMB,
96 "h|help" => \$help) or pod2usage(-exitval => 2, -verbose => 2);
98 pod2usage(-verbose => 2) if ($help == 1);
101 #check parameters and options
103 if ($is_sam || $is_bam) {
104 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (scalar(@ARGV) != 3);
105 pod2usage(-msg => "--sam and --bam cannot be active at the same time!", -exitval => 2, -verbose => 2) if ($is_sam == 1&& $is_bam == 1);
106 pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m, --phred33-quals, --phred64-quals or --solexa-quals cannot be set if input is SAM/BAM format!", -exitval => 2, -verbose => 2) if ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200 || $phred33 || $phred64 || $solexa);
109 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (!$paired_end && scalar(@ARGV) != 3 || $paired_end && scalar(@ARGV) != 4);
110 pod2usage(-msg => "Only one of --phred33-quals --phred64-quals/--solexa1.3-quals --solexa-suqls can be active!", -exitval => 2, -verbose => 2) if ($phred33 + $phred64 + $solexa > 1);
111 podwusage(-msg => "--sam , --bam or --sam-header-info cannot be set if use bowtie aligner to produce alignments!", -exitval => 2, -verbose => 2) if ($is_sam || $is_bam || $fn_list ne "");
114 pod2usage(-msg => "Forward probability should be in [0, 1]!", -exitval => 2, -verbose => 2) if ($probF < 0 || $probF > 1);
115 pod2usage(-msg => "Min fragment length should be at least 1!", -exitval => 2, -verbose => 2) if ($minL < 1);
116 pod2usage(-msg => "Min fragment length should be smaller or equal to max fragment length!", -exitval => 2, -verbose => 2) if ($minL > $maxL);
117 pod2usage(-msg => "The memory allocated for calculating credibility intervals should be at least 1 MB!\n", -exitval => 2, -verbose => 2) if ($NMB < 1);
118 pod2usage(-msg => "Number of threads should be at least 1!\n", -exitval => 2, -verbose => 2) if ($nThreads < 1);
119 pod2usage(-msg => "Seed length should be at least 5!\n", -exitval => 2, -verbose => 2) if ($L < 5);
120 pod2usage(-msg => "--sampling-for-bam cannot be specified if --no-bam-output is specified!\n", -exitval => 2, -verbose => 2) if ($sampling && !$genBamF);
121 pod2usage(-msg => "--output-genome-bam cannot be specified if --no-bam-output is specified!\n", -exitval => 2, -verbose => 2) if ($genGenomeBamF && !$genBamF);
123 if ($L < 25) { print "Warning: the seed length set is less than 25! This is only allowed if the references are not added poly(A) tails.\n"; }
125 if ($strand_specific) { $probF = 1.0; }
131 my ($refName, $sampleName, $sampleToken, $temp_dir, $stat_dir, $imdName) = ();
135 if ($no_qual) { $read_type = 2; }
136 else { $read_type = 3; }
139 if ($no_qual) { $read_type = 0; }
140 else { $read_type = 1; }
143 if (scalar(@ARGV) == 3) {
144 if ($is_sam || $is_bam) { $inpF = $ARGV[0]; }
145 else {$mate1_list = $ARGV[0]; }
147 $sampleName = $ARGV[2];
150 $mate1_list = $ARGV[0];
151 $mate2_list = $ARGV[1];
153 $sampleName = $ARGV[3];
156 if ($genGenomeBamF) {
157 open(INPUT, "$refName.ti");
158 my $line = <INPUT>; chomp($line);
160 my ($M, $type) = split(/ /, $line);
161 pod2usage(-msg => "No genome information provided, so genome bam file cannot be generated!\n", -exitval => 2, -verbose => 2) if ($type != 0);
164 my $pos = rindex($sampleName, '/');
165 if ($pos < 0) { $sampleToken = $sampleName; }
166 else { $sampleToken = substr($sampleName, $pos + 1); }
168 $temp_dir = "$sampleName.temp";
169 $stat_dir = "$sampleName.stat";
171 if (!(-d $temp_dir) && !mkdir($temp_dir)) { print "Fail to create folder $temp_dir.\n"; exit(-1); }
172 if (!(-d $stat_dir) && !mkdir($stat_dir)) { print "Fail to create folder $stat_dir.\n"; exit(-1); }
174 $imdName = "$temp_dir/$sampleToken";
176 if (!$is_sam && !$is_bam && $phred33 + $phred64 + $solexa == 0) { $phred33 = 1; }
178 my ($mate_minL, $mate_maxL) = (1, $maxL);
180 if ($bowtie_path ne "") { $bowtie_path .= "/"; }
182 my ($fn, $dir, $suf) = fileparse($0);
185 if (!$is_sam && !$is_bam) {
186 $command = $bowtie_path."bowtie";
187 if ($read_type == 0 || $read_type == 2) { $command .= " -f"; }
188 else { $command .= " -q"; }
190 if ($phred33) { $command .= " --phred33-quals"; }
191 elsif ($phred64) { $command .= " --phred64-quals"; }
192 elsif ($solexa) { $command .= " --solexa-quals"; }
193 else { print "Oh, no!!!"; exit(2); }
195 $command .= " -n $C -e $E -l $L";
196 if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL"; }
197 if ($chunkMbs > 0) { $command .= " --chunkmbs $chunkMbs"; }
199 if ($strand_specific || $probF == 1.0) { $command .= " --norc"; }
200 elsif ($probF == 0.0) { $command .= " --nofw"; }
202 $command .= " -p $nThreads -a -m $maxHits -S";
203 if ($quiet) { $command .= " --quiet"; }
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 > $sampleName.sam.gz";
215 if ($mTime) { $time_start = time(); }
217 &runCommand($command);
219 if ($mTime) { $time_end = time(); $time_alignment = $time_end - $time_start; }
221 $inpF = "$sampleName.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 $NCV $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 $NCV $NSPC $NMB";
307 $command .= " -p $nThreads";
308 if ($quiet) { $command .= " -q"; }
309 &runCommand($command);
311 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak2");
312 system("mv $sampleName.genes.results $imdName.genes.results.bak2");
313 &collectResults("$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
314 &collectResults("$imdName.gene_res", "$sampleName.genes.results"); # gene level
317 if ($mTime) { $time_end = time(); $time_ci = $time_end - $time_start; }
319 if ($mTime) { $time_start = time(); }
321 if (!$keep_intermediate_files) {
322 &runCommand("rm -rf $temp_dir", "Fail to delete the temporary folder!");
325 if ($mTime) { $time_end = time(); }
328 open(OUTPUT, ">$sampleName.time");
329 print OUTPUT "Aligning reads: $time_alignment s.\n";
330 print OUTPUT "Estimating expression levels: $time_rsem s.\n";
331 print OUTPUT "Calculating credibility intervals: $time_ci s.\n";
332 my $time_del = $time_end - $time_start;
333 # print OUTPUT "Delete: $time_del s.\n";
340 my $status = system($_[0]);
343 if (scalar(@_) > 1) { $errmsg = $_[1]; }
344 else { $errmsg = "\"$command\" failed! Plase check if you provide correct parameters/options for the pipeline!"; }
355 my (@results, @ids) = ();
362 $local_status = open(INPUT, $inpF);
363 if ($local_status == 0) { print "Fail to open file $inpF!\n"; exit(-1); }
368 while ($line = <INPUT>) {
371 my @local_arr = split(/\t/, $line);
372 if ($cnt == 4) { @ids = @local_arr; }
373 else { push(@results, \@local_arr); }
376 push(@results, \@ids);
379 $local_status = open(OUTPUT, ">$outF");
380 if ($local_status == 0) { print "Fail to create file $outF!\n"; exit(-1); }
382 my $n = scalar(@results);
383 my $m = scalar(@{$results[0]});
384 for (my $i = 0; $i < $m; $i++) {
386 for (my $j = 0; $j < $n; $j++) { push(@out_arr, $results[$j][$i]); }
388 print OUTPUT "@out_arr\n";
398 rsem-calculate-expression
404 rsem-calculate-expression [options] upstream_read_file(s) reference_name sample_name
405 rsem-calculate-expression [options] --paired-end upstream_read_file(s) downstream_read_file(s) reference_name sample_name
406 rsem-calculate-expression [options] --sam/--bam [--paired-end] input reference_name sample_name
414 =item B<upstream_read_files(s)>
416 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.
418 =item B<downstream_read_file(s)>
420 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.
424 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.
426 =item B<reference_name>
428 The name of the reference used. The user must have run 'rsem-prepare-reference' with this reference_name before running this program.
432 The name of the sample analyzed. All output files are prefixed by this name (e.g., sample_name.genes.results)
440 =item B<--paired-end>
442 Input reads are paired-end reads. (Default: off)
444 =item B<--no-qualities>
446 Input reads do not contain quality scores. (Default: off)
448 =item B<--strand-specific>
450 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)
454 Input file is in SAM format. (Default: off)
458 Input file is in BAM format. (Default: off)
460 =item B<--sam-header-info> <file>
462 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: "")
464 =item B<-p/--num-threads> <int>
466 Number of threads to use. Both Bowtie and expression estimation will use this many threads. (Default: 1)
468 =item B<--no-bam-output>
470 Do not output any BAM file. (Default: off)
472 =item B<--output-genome-bam>
474 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)
476 =item B<--sampling-for-bam>
478 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)
482 Calculate 95% credibility intervals and posterior mean estimates. (Default: off)
484 =item B<--seed-length> <int>
486 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)
488 =item B<--tag> <string>
490 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: "")
492 =item B<--bowtie-path> <path>
494 The path to the bowtie executables. (Default: the path to the bowtie executables is assumed to be in the user's PATH environment variable)
496 =item B<--bowtie-n> <int>
498 (Bowtie parameter) max # of mismatches in the seed. (Range: 0-3, Default: 2)
500 =item B<--bowtie-e> <int>
502 (Bowtie parameter) max sum of mismatch quality scores across the alignment. (Default: 99999999)
504 =item B<--bowtie-m> <int>
506 (Bowtie parameter) suppress all alignments for a read if > <int> valid alignments exist. (Default: 200)
508 =item B<--bowtie-chunkmbs> <int>
510 (Bowtie parameter) memory allocated for best first alignment calculation (Default: 0 - use bowtie's default)
512 =item B<--phred33-quals>
514 Input quality scores are encoded as Phred+33. (Default: on)
516 =item B<--phred64-quals>
518 Input quality scores are encoded as Phred+64 (default for GA Pipeline ver. >= 1.3). (Default: off)
520 =item B<--solexa-quals>
522 Input quality scores are solexa encoded (from GA Pipeline ver. < 1.3). (Default: off)
524 =item B<--forward-prob> <double>
526 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)
528 =item B<--fragment-length-min> <int>
530 Minimum read/insert length allowed. This is also the value for the bowtie -I option. (Default: 1)
532 =item B<--fragment-length-max> <int>
534 Maximum read/insert length allowed. This is also the value for the bowtie -X option. (Default: 1000)
536 =item B<--fragment-length-mean> <double>
538 (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)
540 =item B<--fragment-length-sd> <double>
542 (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>)
544 =item B<--estimate-rspd>
546 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)
548 =item B<--num-rspd-bins> <int>
550 Number of bins in the RSPD. Only relevant when '--estimate-rspd' is specified. Use of the default setting is recommended. (Default: 20)
552 =item B<--ci-memory> <int>
554 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)
556 =item B<--keep-intermediate-files>
558 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)
562 Output time consumed by each step of RSEM to 'sample_name.time'. (Default: off)
566 Suppress the output of logging information. (Default: off)
570 Show help information.
576 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.
578 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:
580 convert-sam-for-rsem /ref/mouse_125 input.sam -o input_for_rsem.sam
582 For details, please refer to 'convert-sam-for-rsem's documentation page.
584 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 '*'.
586 The user must run 'rsem-prepare-reference' with the appropriate reference before using this program.
588 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.
590 Please note that some of the default values for the Bowtie parameters are not the same as those defined for Bowtie itself.
592 The temporary directory and all intermediate files will be removed when RSEM finishes unless '--keep-intermediate-files' is specified.
594 With the '--calc-ci' option, 95% credibility intervals and posterior mean estimates will be calculated in addition to maximum likelihood estimates.
600 =item B<sample_name.genes.results>
602 File containing gene level expression estimates. The format of each
603 line in this file is:
605 gene_id expected_counts tau_value [pmc_value tau_pme_value tau_ci_lower_bound tau_ci_upper_bound] transcript_id_list
607 Fields are separated by the tab character. Fields within "[]" are only
608 presented if '--calc-ci' is set. pme stands for posterior mean
609 estimation. pmc stands for posterior mean counts. ci_lower_bound(l)
610 means the lower bound of the credibility intervals, ci_upper_bound(u)
611 means the upper bound of the credibility intervals. So the credibility
612 interval is [l, u]. 'transcript_id_list' is a space-separated list of
613 transcript_ids belonging to the gene. If no gene information is
614 provided, this file has the same content as
615 'sample_name.isoforms.results'.
617 =item B<sample_name.isoforms.results>
619 File containing isoform level expression values. The format of each
620 line in this file is:
622 transcript_id expected_counts tau_value [pmc_value tau_pme_value tau_ci_lower_bound tau_ci_upper_bound] gene_id
624 Fields are separated by the tab character. 'gene_id' is the gene_id of
625 the gene which this transcript belongs to. If no gene information is
626 provided, 'gene_id' and 'transcript_id' are the same.
628 =item B<sample_name.transcript.bam, sample_name.transcript.sorted.bam and sample_name.transcript.sorted.bam.bai>
630 Only generated when --no-bam-output is not specified.
632 'sample_name.transcript.bam' is a BAM-formatted file of read
633 alignments in transcript coordinates. The MAPQ field of each alignment
634 is set to min(100, floor(-10 * log10(1.0 - w) + 0.5)), where w is the
635 posterior probability of that alignment being the true mapping of a
636 read. In addition, RSEM pads a new tag ZW:f:value, where value is a
637 single precision floating number representing the posterior
640 'sample_name.transcript.sorted.bam' and
641 'sample_name.transcript.sorted.bam.bai' are the sorted BAM file and
642 indices generated by samtools (included in RSEM package).
644 =item B<sample_name.genome.bam, sample_name.genome.sorted.bam and sample_name.genome.sorted.bam.bai>
646 Only generated when --no-bam-output is not specified and --output-genome-bam is specified.
648 'sample_name.genome.bam' is a BAM-formatted file of read alignments in
649 genomic coordinates. Alignments of reads that have identical genomic
650 coordinates (i.e., alignments to different isoforms that share the
651 same genomic region) are collapsed into one alignment. The MAPQ field
652 of each alignment is set to min(100, floor(-10 * log10(1.0 - w) +
653 0.5)), where w is the posterior probability of that alignment being
654 the true mapping of a read. In addition, RSEM pads a new tag
655 ZW:f:value, where value is a single precision floating number
656 representing the posterior probability. If an alignment is spliced, a
657 XS:A:value tag is also added, where value is either '+' or '-'
658 indicating the strand of the transcript it aligns to.
660 'sample_name.genome.sorted.bam' and 'sample_name.genome.sorted.bam.bai' are the
661 sorted BAM file and indices generated by samtools (included in RSEM package).
663 =item B<sample_name.sam.gz>
665 Only generated when the input files are raw reads instead of SAM/BAM format files
667 It is the gzipped SAM output produced by bowtie aligner.
669 =item B<sample_name.time>
671 Only generated when --time is specified.
673 It contains time (in seconds) consumed by aligning reads, estimating expression levels and calculating credibility intervals.
675 =item B<sample_name.stat>
677 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.
683 Assume the path to the bowtie executables is in the user's PATH environment variable. Reference files are under '/ref' with name 'mouse_125'.
685 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:
687 rsem-calculate-expression --phred64-quals \
689 --output-genome-bam \
694 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:
696 rsem-calculate-expression -p 8 \
701 mmliver_paired_end_quals
703 3) '/data/mmliver.fa', single-end reads without quality scores. We want to use 8 threads:
705 rsem-calculate-expression -p 8 \
709 mmliver_single_without_quals
711 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:
713 rsem-calculate-expression --bowtie-path /sw/bowtie \
715 --fragment-length-mean 150.0 \
716 --fragment-length-sd 35.0 \
718 --output-genome-bam \
725 5) '/data/mmliver_paired_end_quals.bam', paired-end reads with quality scores. We want to use 8 threads:
727 rsem-calculate-expression --paired-end \
730 /data/mmliver_paired_end_quals.bam \
732 mmliver_paired_end_quals