9 use rsem_perl_utils qw(runCommand collectResults showVersionInfo);
15 my $CONFIDENCE = 0.95;
18 my $NMB = 1024; # default
19 my $SortMem = "1G"; # default as 1G per thread
23 my $read_type = 1; # default, single end with qual
30 my $chunkMbs = 0; # 0 = use bowtie default
51 my $genBamF = 1; # default is generating transcript bam file
52 my $genGenomeBamF = 0;
56 my $var_opt = 0; # temporarily, only for internal use
62 my $keep_intermediate_files = 0;
64 my $strand_specific = 0;
67 my $bowtie2_path = "";
68 my $bowtie2_mismatch_rate = 0.1;
70 my $bowtie2_sensitivity_level = "sensitive"; # must be one of "very_fast", "fast", "sensitive", "very_sensitive"
75 my ($time_start, $time_end, $time_alignment, $time_rsem, $time_ci) = (0, 0, 0, 0, 0);
81 my ($refName, $sampleName, $sampleToken, $temp_dir, $stat_dir, $imdName, $statName) = ();
86 GetOptions("keep-intermediate-files" => \$keep_intermediate_files,
87 "temporary-folder=s" => \$temp_dir,
88 "no-qualities" => \$no_qual,
89 "paired-end" => \$paired_end,
90 "strand-specific" => \$strand_specific,
93 "sam-header-info=s" => \$fn_list,
95 "seed-length=i" => \$L,
96 "bowtie-path=s" => \$bowtie_path,
99 "bowtie-m=i" => \$maxHits,
100 "bowtie-chunkmbs=i" => \$chunkMbs,
101 "phred33-quals" => \$phred33,
102 "phred64-quals" => \$phred64, #solexa1.3-quals" => \$phred64,
103 "solexa-quals" => \$solexa,
104 "bowtie2" => \$bowtie2,
105 "bowtie2-path=s" => \$bowtie2_path,
106 "bowtie2-mismatch-rate=f" => \$bowtie2_mismatch_rate,
107 "bowtie2-k=i" => \$bowtie2_k,
108 "bowtie2-sensitivity-level=s" => \$bowtie2_sensitivity_level,
109 "forward-prob=f" => \$probF,
110 "fragment-length-min=i" => \$minL,
111 "fragment-length-max=i" => \$maxL,
112 "fragment-length-mean=f" => \$mean,
113 "fragment-length-sd=f" => \$sd,
114 "estimate-rspd" => \$estRSPD,
115 "num-rspd-bins=i" => \$B,
116 "p|num-threads=i" => \$nThreads,
117 "no-bam-output" => sub { $genBamF = 0; },
118 "output-genome-bam" => \$genGenomeBamF,
119 "sampling-for-bam" => \$sampling,
120 "calc-pme" => \$calcPME,
122 "calc-ci" => \$calcCI,
123 "ci-memory=i" => \$NMB,
124 "samtools-sort-mem=s" => \$SortMem,
126 "version" => \$version,
127 "q|quiet" => \$quiet,
128 "h|help" => \$help) or pod2usage(-exitval => 2, -verbose => 2);
130 my $dir = "$FindBin::Bin/";
132 pod2usage(-verbose => 2) if ($help == 1);
133 &showVersionInfo($dir) if ($version == 1);
135 #check parameters and options
137 if ($is_sam || $is_bam) {
138 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (scalar(@ARGV) != 3);
139 pod2usage(-msg => "--sam and --bam cannot be active at the same time!", -exitval => 2, -verbose => 2) if ($is_sam == 1&& $is_bam == 1);
140 pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m, --phred33-quals, --phred64-quals, --solexa-quals, --bowtie2, --bowtie2-path, --bowtie2-mismatch-rate, --bowtie2-k and --bowtie2-sensitivity-level cannot be set if input is SAM/BAM format!", -exitval => 2, -verbose => 2) if ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200 || $phred33 || $phred64 || $solexa || $bowtie2 || $bowtie2_path ne "" || $bowtie2_mismatch_rate != 0.1 || $bowtie2_k != 200 || $bowtie2_sensitivity_level ne "sensitive");
143 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (!$paired_end && scalar(@ARGV) != 3 || $paired_end && scalar(@ARGV) != 4);
144 pod2usage(-msg => "If --no-qualities is set, neither --phred33-quals, --phred64-quals or --solexa-quals can be active!", -exitval => 2, -verbose => 2) if ($no_qual && ($phred33 + $phred64 + $solexa > 0));
145 pod2usage(-msg => "Only one of --phred33-quals, --phred64-quals, and --solexa-quals can be active!", -exitval => 2, -verbose => 2) if ($phred33 + $phred64 + $solexa > 1);
146 pod2usage(-msg => "--sam , --bam or --sam-header-info cannot be set if use bowtie/bowtie2 aligner to produce alignments!", -exitval => 2, -verbose => 2) if ($is_sam || $is_bam || $fn_list ne "");
147 pod2usage(-msg => "--bowtie2-path, --bowtie2-mismatch-rate, --bowtie2-k and --bowtie2-sensitivity-level cannot be set if bowtie aligner is used!", -exitval => 2, -verbose => 2) if (!$bowtie2 && ($bowtie2_path ne "" || $bowtie2_mismatch_rate != 0.1 || $bowtie2_k != 200 || $bowtie2_sensitivity_level ne "sensitive"));
148 pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m cannot be set if bowtie2 aligner is used!", -exitval => 2, -verbose => 2) if ($bowtie2 && ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200));
149 pod2usage(-msg => "Mismatch rate must be within [0, 1]!", -exitval => 2, -verbose => 2) if ($bowtie2 && ($bowtie2_mismatch_rate < 0.0 || $bowtie2_mismatch_rate > 1.0));
150 pod2usage(-msg => "Sensitivity level must be one of \"very_fast\", \"fast\", \"sensitive\", and \"very_sensitive\"!", -exitval => 2, -verbose => 2) if ($bowtie2 && (($bowtie2_sensitivity_level ne "very_fast") && ($bowtie2_sensitivity_level ne "fast") && ($bowtie2_sensitivity_level ne "sensitive") && ($bowtie2_sensitivity_level ne "very_sensitive")));
153 pod2usage(-msg => "Forward probability should be in [0, 1]!", -exitval => 2, -verbose => 2) if ($probF < 0 || $probF > 1);
154 pod2usage(-msg => "Min fragment length should be at least 1!", -exitval => 2, -verbose => 2) if ($minL < 1);
155 pod2usage(-msg => "Min fragment length should be smaller or equal to max fragment length!", -exitval => 2, -verbose => 2) if ($minL > $maxL);
156 pod2usage(-msg => "The memory allocated for calculating credibility intervals should be at least 1 MB!\n", -exitval => 2, -verbose => 2) if ($NMB < 1);
157 pod2usage(-msg => "Number of threads should be at least 1!\n", -exitval => 2, -verbose => 2) if ($nThreads < 1);
158 pod2usage(-msg => "Seed length should be at least 5!\n", -exitval => 2, -verbose => 2) if ($L < 5);
159 pod2usage(-msg => "--sampling-for-bam cannot be specified if --no-bam-output is specified!\n", -exitval => 2, -verbose => 2) if ($sampling && !$genBamF);
160 pod2usage(-msg => "--output-genome-bam cannot be specified if --no-bam-output is specified!\n", -exitval => 2, -verbose => 2) if ($genGenomeBamF && !$genBamF);
162 if ($L < 25) { print "Warning: the seed length set is less than 25! This is only allowed if the references are not added poly(A) tails.\n"; }
164 if ($strand_specific) { $probF = 1.0; }
167 if ($no_qual) { $read_type = 2; }
168 else { $read_type = 3; }
171 if ($no_qual) { $read_type = 0; }
172 else { $read_type = 1; }
175 if (scalar(@ARGV) == 3) {
176 if ($is_sam || $is_bam) { $inpF = $ARGV[0]; }
177 else {$mate1_list = $ARGV[0]; }
179 $sampleName = $ARGV[2];
182 $mate1_list = $ARGV[0];
183 $mate2_list = $ARGV[1];
185 $sampleName = $ARGV[3];
188 if (((-e "$refName.ta") && !(-e "$refName.gt")) || (!(-e "$refName.ta") && (-e "$refName.gt"))) {
189 print "Allele-specific expression related reference files are corrupted!\n";
193 $alleleS = (-e "$refName.ta") && (-e "$refName.gt");
195 if ($genGenomeBamF) {
196 open(INPUT, "$refName.ti");
197 my $line = <INPUT>; chomp($line);
199 my ($M, $type) = split(/ /, $line);
200 pod2usage(-msg => "No genome information provided, so genome bam file cannot be generated!\n", -exitval => 2, -verbose => 2) if ($type != 0);
203 my $pos = rindex($sampleName, '/');
204 if ($pos < 0) { $sampleToken = $sampleName; }
205 else { $sampleToken = substr($sampleName, $pos + 1); }
207 if ($temp_dir eq "") { $temp_dir = "$sampleName.temp"; }
208 $stat_dir = "$sampleName.stat";
210 if (!(-d $temp_dir) && !mkdir($temp_dir)) { print "Fail to create folder $temp_dir.\n"; exit(-1); }
211 if (!(-d $stat_dir) && !mkdir($stat_dir)) { print "Fail to create folder $stat_dir.\n"; exit(-1); }
213 $imdName = "$temp_dir/$sampleToken";
214 $statName = "$stat_dir/$sampleToken";
216 if (!$is_sam && !$is_bam && !$no_qual && ($phred33 + $phred64 + $solexa == 0)) { $phred33 = 1; }
218 my ($mate_minL, $mate_maxL) = (1, $maxL);
220 if ($bowtie_path ne "") { $bowtie_path .= "/"; }
221 if ($bowtie2_path ne "") { $bowtie2_path .= "/"; }
225 if (!$is_sam && !$is_bam) {
227 $command = $bowtie_path."bowtie";
228 if ($no_qual) { $command .= " -f"; }
229 else { $command .= " -q"; }
231 if ($phred33) { $command .= " --phred33-quals"; }
232 elsif ($phred64) { $command .= " --phred64-quals"; }
233 elsif ($solexa) { $command .= " --solexa-quals"; }
235 $command .= " -n $C -e $E -l $L";
236 if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL"; }
237 if ($chunkMbs > 0) { $command .= " --chunkmbs $chunkMbs"; }
239 if ($strand_specific || $probF == 1.0) { $command .= " --norc"; }
240 elsif ($probF == 0.0) { $command .= " --nofw"; }
242 $command .= " -p $nThreads -a -m $maxHits -S";
243 if ($quiet) { $command .= " --quiet"; }
245 $command .= " $refName";
246 if ($read_type == 0 || $read_type == 1) {
247 $command .= " $mate1_list";
250 $command .= " -1 $mate1_list -2 $mate2_list";
253 # pipe to samtools to generate a BAM file
254 $command .= " | $dir\sam/samtools view -S -b -o $imdName.bam -";
257 $command = $bowtie2_path."bowtie2";
258 if ($no_qual) { $command .= " -f"; }
259 else { $command .= " -q"; }
261 if ($phred33) { $command .= " --phred33"; }
262 elsif ($phred64) { $command .= " --phred64"; }
263 elsif ($solexa) { $command .= " --solexa-quals"; }
265 if ($bowtie2_sensitivity_level eq "very_fast") { $command .= " --very-fast"; }
266 elsif ($bowtie2_sensitivity_level eq "fast") { $command .= " --fast"; }
267 elsif ($bowtie2_sensitivity_level eq "sensitive") { $command .= " --sensitive"; }
268 else { $command .= " --very-sensitive"; }
270 $command .= " --dpad 0 --gbar 99999999 --mp 1,1 --np 1 --score-min L,0,-$bowtie2_mismatch_rate";
272 if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL --no-mixed --no-discordant"; }
274 if ($strand_specific || $probF == 1.0) { $command .= " --norc"; }
275 elsif ($probF == 0.0) { $command .= " --nofw"; }
277 $command .= " -p $nThreads -k $bowtie2_k";
278 if ($quiet) { $command .= " --quiet"; }
280 $command .= " -x $refName";
281 if ($read_type == 0 || $read_type == 1) {
282 $command .= " -U $mate1_list";
285 $command .= " -1 $mate1_list -2 $mate2_list";
288 # pipe to samtools to generate a BAM file
289 $command .= " | $dir\sam/samtools view -S -b -o $imdName.bam -";
292 if ($mTime) { $time_start = time(); }
294 &runCommand($command);
296 if ($mTime) { $time_end = time(); $time_alignment = $time_end - $time_start; }
298 $inpF = "$imdName.bam";
299 $is_bam = 1; # alignments are outputed as a BAM file
302 if ($mTime) { $time_start = time(); }
304 $command = $dir."rsem-parse-alignments $refName $imdName $statName";
307 if ($is_sam) { $samInpType = "s"; }
308 elsif ($is_bam) { $samInpType = "b"; }
310 $command .= " $samInpType $inpF -t $read_type";
311 if ($fn_list ne "") { $command .= " -l $fn_list"; }
312 if ($tagName ne "") { $command .= " -tag $tagName"; }
313 if ($quiet) { $command .= " -q"; }
315 &runCommand($command);
317 $command = $dir."rsem-build-read-index $gap";
318 if ($read_type == 0) { $command .= " 0 $quiet $imdName\_alignable.fa"; }
319 elsif ($read_type == 1) { $command .= " 1 $quiet $imdName\_alignable.fq"; }
320 elsif ($read_type == 2) { $command .= " 0 $quiet $imdName\_alignable_1.fa $imdName\_alignable_2.fa"; }
321 elsif ($read_type == 3) { $command .= " 1 $quiet $imdName\_alignable_1.fq $imdName\_alignable_2.fq"; }
322 else { print "Impossible! read_type is not in [1,2,3,4]!\n"; exit(-1); }
323 &runCommand($command);
325 my $doesOpen = open(OUTPUT, ">$imdName.mparams");
326 if ($doesOpen == 0) { print "Cannot generate $imdName.mparams!\n"; exit(-1); }
327 print OUTPUT "$minL $maxL\n";
328 print OUTPUT "$probF\n";
329 print OUTPUT "$estRSPD\n";
331 print OUTPUT "$mate_minL $mate_maxL\n";
332 print OUTPUT "$mean $sd\n";
336 $command = $dir."rsem-run-em $refName $read_type $sampleName $imdName $statName -p $nThreads";
338 $command .= " -b $samInpType $inpF";
339 if ($fn_list ne "") { $command .= " 1 $fn_list"; }
340 else { $command .= " 0"; }
341 if ($sampling) { $command .= " --sampling"; }
343 if ($calcPME || $var_opt || $calcCI) { $command .= " --gibbs-out"; }
344 if ($quiet) { $command .= " -q"; }
346 &runCommand($command);
349 &collectResults("allele", "$imdName.allele_res", "$sampleName.alleles.results"); # allele level
350 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
351 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
354 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
355 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
359 $command = $dir."sam/samtools sort -@ $nThreads -m $SortMem $sampleName.transcript.bam $sampleName.transcript.sorted";
360 &runCommand($command);
361 $command = $dir."sam/samtools index $sampleName.transcript.sorted.bam";
362 &runCommand($command);
364 if ($genGenomeBamF) {
365 $command = $dir."rsem-tbam2gbam $refName $sampleName.transcript.bam $sampleName.genome.bam";
366 &runCommand($command);
367 $command = $dir."sam/samtools sort -@ $nThreads -m $SortMem $sampleName.genome.bam $sampleName.genome.sorted";
368 &runCommand($command);
369 $command = $dir."sam/samtools index $sampleName.genome.sorted.bam";
370 &runCommand($command);
374 if ($mTime) { $time_end = time(); $time_rsem = $time_end - $time_start; }
376 if ($mTime) { $time_start = time(); }
378 if ($calcPME || $var_opt || $calcCI ) {
379 $command = $dir."rsem-run-gibbs $refName $imdName $statName $BURNIN $NCV $SAMPLEGAP";
380 $command .= " -p $nThreads";
381 if ($var_opt) { $command .= " --var"; }
382 if ($quiet) { $command .= " -q"; }
383 &runCommand($command);
386 if ($calcPME || $calcCI) {
388 system("mv $sampleName.alleles.results $imdName.alleles.results.bak1");
389 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak1");
390 system("mv $sampleName.genes.results $imdName.genes.results.bak1");
391 &collectResults("allele", "$imdName.allele_res", "$sampleName.alleles.results"); # allele level
392 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
393 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
396 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak1");
397 system("mv $sampleName.genes.results $imdName.genes.results.bak1");
398 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
399 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
404 $command = $dir."rsem-calculate-credibility-intervals $refName $imdName $statName $CONFIDENCE $NCV $NSPC $NMB";
405 $command .= " -p $nThreads";
406 if ($quiet) { $command .= " -q"; }
407 &runCommand($command);
410 system("mv $sampleName.alleles.results $imdName.alleles.results.bak2");
411 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak2");
412 system("mv $sampleName.genes.results $imdName.genes.results.bak2");
413 &collectResults("allele", "$imdName.allele_res", "$sampleName.alleles.results"); # allele level
414 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
415 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
418 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak2");
419 system("mv $sampleName.genes.results $imdName.genes.results.bak2");
420 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
421 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
425 if ($mTime) { $time_end = time(); $time_ci = $time_end - $time_start; }
427 if ($mTime) { $time_start = time(); }
429 if (!$keep_intermediate_files) {
430 &runCommand("rm -rf $temp_dir", "Fail to delete the temporary folder!");
433 if ($mTime) { $time_end = time(); }
436 open(OUTPUT, ">$sampleName.time");
437 print OUTPUT "Aligning reads: $time_alignment s.\n";
438 print OUTPUT "Estimating expression levels: $time_rsem s.\n";
439 print OUTPUT "Calculating credibility intervals: $time_ci s.\n";
440 # my $time_del = $time_end - $time_start;
441 # print OUTPUT "Delete: $time_del s.\n";
449 rsem-calculate-expression
453 rsem-calculate-expression [options] upstream_read_file(s) reference_name sample_name
454 rsem-calculate-expression [options] --paired-end upstream_read_file(s) downstream_read_file(s) reference_name sample_name
455 rsem-calculate-expression [options] --sam/--bam [--paired-end] input reference_name sample_name
461 =item B<upstream_read_files(s)>
463 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.
465 =item B<downstream_read_file(s)>
467 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.
471 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.
473 =item B<reference_name>
475 The name of the reference used. The user must have run 'rsem-prepare-reference' with this reference_name before running this program.
479 The name of the sample analyzed. All output files are prefixed by this name (e.g., sample_name.genes.results)
487 =item B<--paired-end>
489 Input reads are paired-end reads. (Default: off)
491 =item B<--no-qualities>
493 Input reads do not contain quality scores. (Default: off)
495 =item B<--strand-specific>
497 The RNA-Seq protocol used to generate the reads is strand specific, i.e., all (upstream) reads are derived from the forward strand. This option is equivalent to --forward-prob=1.0. With this option set, if RSEM runs the Bowtie/Bowtie 2 aligner, the '--norc' Bowtie/Bowtie 2 option will be used, which disables alignment to the reverse strand of transcripts. (Default: off)
501 Input file is in SAM format. (Default: off)
505 Input file is in BAM format. (Default: off)
507 =item B<--sam-header-info> <file>
509 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: "")
511 =item B<-p/--num-threads> <int>
513 Number of threads to use. Both Bowtie/Bowtie2, expression estimation and 'samtools sort' will use this many threads. (Default: 1)
515 =item B<--no-bam-output>
517 Do not output any BAM file. (Default: off)
519 =item B<--output-genome-bam>
521 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)
523 =item B<--sampling-for-bam>
525 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)
529 Run RSEM's collapsed Gibbs sampler to calculate posterior mean estimates. (Default: off)
533 Calculate 95% credibility intervals and posterior mean estimates. (Default: off)
535 =item B<--seed-length> <int>
537 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)
539 =item B<--tag> <string>
541 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: "")
543 =item B<--bowtie-path> <path>
545 The path to the Bowtie executables. (Default: the path to the Bowtie executables is assumed to be in the user's PATH environment variable)
547 =item B<--bowtie-n> <int>
549 (Bowtie parameter) max # of mismatches in the seed. (Range: 0-3, Default: 2)
551 =item B<--bowtie-e> <int>
553 (Bowtie parameter) max sum of mismatch quality scores across the alignment. (Default: 99999999)
555 =item B<--bowtie-m> <int>
557 (Bowtie parameter) suppress all alignments for a read if > <int> valid alignments exist. (Default: 200)
559 =item B<--bowtie-chunkmbs> <int>
561 (Bowtie parameter) memory allocated for best first alignment calculation (Default: 0 - use Bowtie's default)
563 =item B<--phred33-quals>
565 Input quality scores are encoded as Phred+33. (Default: on)
567 =item B<--phred64-quals>
569 Input quality scores are encoded as Phred+64 (default for GA Pipeline ver. >= 1.3). (Default: off)
571 =item B<--solexa-quals>
573 Input quality scores are solexa encoded (from GA Pipeline ver. < 1.3). (Default: off)
577 Use Bowtie 2 instead of Bowtie to align reads. Since currently RSEM does not handle indel, local and discordant alignments, the Bowtie2 parameters are set in a way to avoid those alignments. In particular, we use options '--sensitive --dpad 0 --gbar 99999999 --mp 1,1 --np 1 --score-min L,0,-0.1' by default. "-0.1", the last parameter of '--score-min' is the negative value of the maximum mismatch rate allowed. This rate can be set by option '--bowtie2-mismatch-rate'. If reads are paired-end, we additionally use options '--no-mixed' and '--no-discordant'. (Default: off)
579 =item B<--bowtie2-path> <path>
581 (Bowtie 2 parameter) The path to the Bowtie 2 executables. (Default: the path to the Bowtie 2 executables is assumed to be in the user's PATH environment variable)
583 =item B<--bowtie2-mismatch-rate> <double>
585 (Bowtie 2 parameter) The maximum mismatch rate allowed. (Default: 0.1)
587 =item B<--bowtie2-k> <int>
589 (Bowtie 2 parameter) Find up to <int> alignments per read. (Default: 200)
591 =item B<--bowtie2-sensitivity-level> <string>
593 (Bowtie 2 parameter) Set Bowtie 2's preset options in --end-to-end mode. This option controls how hard Bowtie 2 tries to find alignments. <string> must be one of "very_fast", "fast", "sensitive" and "very_sensitive". The four candidates correspond to Bowtie 2's "--very-fast", "--fast", "--sensitive" and "--very-sensitive" options. (Default: "sensitive" - use Bowtie 2's default)
595 =item B<--forward-prob> <double>
597 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)
599 =item B<--fragment-length-min> <int>
601 Minimum read/insert length allowed. This is also the value for the Bowtie/Bowtie2 -I option. (Default: 1)
603 =item B<--fragment-length-max> <int>
605 Maximum read/insert length allowed. This is also the value for the Bowtie/Bowtie 2 -X option. (Default: 1000)
607 =item B<--fragment-length-mean> <double>
609 (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)
611 =item B<--fragment-length-sd> <double>
613 (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>)
615 =item B<--estimate-rspd>
617 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)
619 =item B<--num-rspd-bins> <int>
621 Number of bins in the RSPD. Only relevant when '--estimate-rspd' is specified. Use of the default setting is recommended. (Default: 20)
623 =item B<--ci-memory> <int>
625 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)
627 =item B<--samtools-sort-mem> <string>
629 Set the maximum memory per thread that can be used by 'samtools sort'. <string> represents the memory and accepts suffices 'K/M/G'. RSEM will pass <string> to the '-m' option of 'samtools sort'. Please note that the default used here is different from the default used by samtools. (Default: 1G)
631 =item B<--keep-intermediate-files>
633 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)
635 =item B<--temporary-folder> <string>
637 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)
641 Output time consumed by each step of RSEM to 'sample_name.time'. (Default: off)
645 Suppress the output of logging information. (Default: off)
649 Show help information.
653 Show version information.
659 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.
661 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:
663 convert-sam-for-rsem /ref/mouse_125 input.sam -o input_for_rsem.sam
665 For details, please refer to 'convert-sam-for-rsem's documentation page.
667 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 '*'.
669 The user must run 'rsem-prepare-reference' with the appropriate reference before using this program.
671 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.
673 Please note that some of the default values for the Bowtie parameters are not the same as those defined for Bowtie itself.
675 The temporary directory and all intermediate files will be removed when RSEM finishes unless '--keep-intermediate-files' is specified.
677 With the '--calc-ci' option, 95% credibility intervals and posterior mean estimates will be calculated in addition to maximum likelihood estimates.
683 =item B<sample_name.isoforms.results>
685 File containing isoform level expression estimates. The first line
686 contains column names separated by the tab character. The format of
687 each line in the rest of this file is:
689 transcript_id gene_id length effective_length expected_count TPM FPKM IsoPct [pme_expected_count pme_TPM pme_FPKM IsoPct_from_pme_TPM TPM_ci_lower_bound TPM_ci_upper_bound FPKM_ci_lower_bound FPKM_ci_upper_bound]
691 Fields are separated by the tab character. Fields within "[]" are
692 optional. They will not be presented if neither '--calc-pme' nor
695 'transcript_id' is the transcript name of this transcript. 'gene_id'
696 is the gene name of the gene which this transcript belongs to (denote
697 this gene as its parent gene). If no gene information is provided,
698 'gene_id' and 'transcript_id' are the same.
700 'length' is this transcript's sequence length (poly(A) tail is not
701 counted). 'effective_length' counts only the positions that can
702 generate a valid fragment. If no poly(A) tail is added,
703 'effective_length' is equal to transcript length - mean fragment
704 length + 1. If one transcript's effective length is less than 1, this
705 transcript's both effective length and abundance estimates are set to
708 'expected_count' is the sum of the posterior probability of each read
709 comes from this transcript over all reads. Because 1) each read
710 aligning to this transcript has a probability of being generated from
711 background noise; 2) RSEM may filter some alignable low quality reads,
712 the sum of expected counts for all transcript are generally less than
713 the total number of reads aligned.
715 'TPM' stands for Transcripts Per Million. It is a relative measure of
716 transcript abundance. The sum of all transcripts' TPM is 1
717 million. 'FPKM' stands for Fragments Per Kilobase of transcript per
718 Million mapped reads. It is another relative measure of transcript
719 abundance. If we define l_bar be the mean transcript length in a
720 sample, which can be calculated as
722 l_bar = \sum_i TPM_i / 10^6 * effective_length_i (i goes through every transcript),
724 the following equation is hold:
726 FPKM_i = 10^3 / l_bar * TPM_i.
728 We can see that the sum of FPKM is not a constant across samples.
730 'IsoPct' stands for isoform percentage. It is the percentage of this
731 transcript's abandunce over its parent gene's abandunce. If its parent
732 gene has only one isoform or the gene information is not provided,
733 this field will be set to 100.
735 'pme_expected_count', 'pme_TPM', 'pme_FPKM' are posterior mean
736 estimates calculated by RSEM's Gibbs sampler. 'IsoPct_from_pme_TPM' is
737 the isoform percentage calculated from 'pme_TPM' values.
739 'TPM_ci_lower_bound', 'TPM_ci_upper_bound', 'FPKM_ci_lower_bound' and
740 'FPKM_ci_upper_bound' are lower(l) and upper(u) bounds of 95%
741 credibility intervals for TPM and FPKM values. The bounds are
742 inclusive (i.e. [l, u]).
744 =item B<sample_name.genes.results>
746 File containing gene level expression estimates. The first line
747 contains column names separated by the tab character. The format of
748 each line in the rest of this file is:
750 gene_id transcript_id(s) length effective_length expected_count TPM FPKM [pme_expected_count pme_TPM pme_FPKM TPM_ci_lower_bound TPM_ci_upper_bound FPKM_ci_lower_bound FPKM_ci_upper_bound]
752 Fields are separated by the tab character. Fields within "[]" are
753 optional. They will not be presented if neither '--calc-pme' nor
756 'transcript_id(s)' is a comma-separated list of transcript_ids
757 belonging to this gene. If no gene information is provided, 'gene_id'
758 and 'transcript_id(s)' are identical (the 'transcript_id').
760 A gene's 'length' and 'effective_length' are
761 defined as the weighted average of its transcripts' lengths and
762 effective lengths (weighted by 'IsoPct'). A gene's abundance estimates
763 are just the sum of its transcripts' abundance estimates.
765 =item B<sample_name.alleles.results>
767 Only generated when the RSEM references are built with allele-specific
770 This file contains allele level expression estimates for
771 allele-specific expression calculation. The first line
772 contains column names separated by the tab character. The format of
773 each line in the rest of this file is:
775 allele_id transcript_id gene_id length effective_length expected_count TPM FPKM AlleleIsoPct AlleleGenePct [pme_expected_count pme_TPM pme_FPKM AlleleIsoPct_from_pme_TPM AlleleGenePct_from_pme_TPM TPM_ci_lower_bound TPM_ci_upper_bound FPKM_ci_lower_bound FPKM_ci_upper_bound]
777 Fields are separated by the tab character. Fields within "[]" are
778 optional. They will not be presented if neither '--calc-pme' nor
781 'allele_id' is the allele-specific name of this allele-specific transcript.
783 'AlleleIsoPct' stands for allele-specific percentage on isoform
784 level. It is the percentage of this allele-specific transcript's
785 abundance over its parent transcript's abundance. If its parent
786 transcript has only one allele variant form, this field will be set to
789 'AlleleGenePct' stands for allele-specific percentage on gene
790 level. It is the percentage of this allele-specific transcript's
791 abundance over its parent gene's abundance.
793 'AlleleIsoPct_from_pme_TPM' and 'AlleleGenePct_from_pme_TPM' have
794 similar meanings. They are calculated based on posterior mean
797 Please note that if this file is present, the fields 'length' and
798 'effective_length' in 'sample_name.isoforms.results' should be
799 interpreted similarly as the corresponding definitions in
800 'sample_name.genes.results'.
802 =item B<sample_name.transcript.bam, sample_name.transcript.sorted.bam and sample_name.transcript.sorted.bam.bai>
804 Only generated when --no-bam-output is not specified.
806 'sample_name.transcript.bam' is a BAM-formatted file of read
807 alignments in transcript coordinates. The MAPQ field of each alignment
808 is set to min(100, floor(-10 * log10(1.0 - w) + 0.5)), where w is the
809 posterior probability of that alignment being the true mapping of a
810 read. In addition, RSEM pads a new tag ZW:f:value, where value is a
811 single precision floating number representing the posterior
812 probability. Because this file contains all alignment lines produced
813 by bowtie or user-specified aligners, it can also be used as a
814 replacement of the aligner generated BAM/SAM file. For paired-end
815 reads, if one mate has alignments but the other does not, this file
816 marks the alignable mate as "unmappable" (flag bit 0x4) and appends an
817 optional field "Z0:A:!".
819 'sample_name.transcript.sorted.bam' and
820 'sample_name.transcript.sorted.bam.bai' are the sorted BAM file and
821 indices generated by samtools (included in RSEM package).
823 =item B<sample_name.genome.bam, sample_name.genome.sorted.bam and sample_name.genome.sorted.bam.bai>
825 Only generated when --no-bam-output is not specified and --output-genome-bam is specified.
827 'sample_name.genome.bam' is a BAM-formatted file of read alignments in
828 genomic coordinates. Alignments of reads that have identical genomic
829 coordinates (i.e., alignments to different isoforms that share the
830 same genomic region) are collapsed into one alignment. The MAPQ field
831 of each alignment is set to min(100, floor(-10 * log10(1.0 - w) +
832 0.5)), where w is the posterior probability of that alignment being
833 the true mapping of a read. In addition, RSEM pads a new tag
834 ZW:f:value, where value is a single precision floating number
835 representing the posterior probability. If an alignment is spliced, a
836 XS:A:value tag is also added, where value is either '+' or '-'
837 indicating the strand of the transcript it aligns to.
839 'sample_name.genome.sorted.bam' and 'sample_name.genome.sorted.bam.bai' are the
840 sorted BAM file and indices generated by samtools (included in RSEM package).
842 =item B<sample_name.time>
844 Only generated when --time is specified.
846 It contains time (in seconds) consumed by aligning reads, estimating expression levels and calculating credibility intervals.
848 =item B<sample_name.stat>
850 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.
856 Assume the path to the bowtie executables is in the user's PATH environment variable. Reference files are under '/ref' with name 'mouse_125'.
858 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:
860 rsem-calculate-expression --phred64-quals \
862 --output-genome-bam \
867 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:
869 rsem-calculate-expression -p 8 \
874 mmliver_paired_end_quals
876 3) '/data/mmliver.fa', single-end reads without quality scores. We want to use 8 threads:
878 rsem-calculate-expression -p 8 \
882 mmliver_single_without_quals
884 4) Data are the same as 1). This time we assume the bowtie executables are under '/sw/bowtie'. 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:
886 rsem-calculate-expression --bowtie-path /sw/bowtie \
888 --fragment-length-mean 150.0 \
889 --fragment-length-sd 35.0 \
891 --output-genome-bam \
898 5) '/data/mmliver_paired_end_quals.bam', paired-end reads with quality scores. We want to use 8 threads:
900 rsem-calculate-expression --paired-end \
903 /data/mmliver_paired_end_quals.bam \
905 mmliver_paired_end_quals