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;
55 my $var_opt = 0; # temporarily, only for internal use
61 my $keep_intermediate_files = 0;
63 my $strand_specific = 0;
66 my $bowtie2_path = "";
67 my $bowtie2_mismatch_rate = 0.1;
69 my $bowtie2_sensitivity_level = "sensitive"; # must be one of "very_fast", "fast", "sensitive", "very_sensitive"
74 my ($time_start, $time_end, $time_alignment, $time_rsem, $time_ci) = (0, 0, 0, 0, 0);
80 my ($refName, $sampleName, $sampleToken, $temp_dir, $stat_dir, $imdName, $statName) = ();
83 GetOptions("keep-intermediate-files" => \$keep_intermediate_files,
84 "temporary-folder=s" => \$temp_dir,
85 "no-qualities" => \$no_qual,
86 "paired-end" => \$paired_end,
87 "strand-specific" => \$strand_specific,
90 "sam-header-info=s" => \$fn_list,
92 "seed-length=i" => \$L,
93 "bowtie-path=s" => \$bowtie_path,
96 "bowtie-m=i" => \$maxHits,
97 "bowtie-chunkmbs=i" => \$chunkMbs,
98 "phred33-quals" => \$phred33,
99 "phred64-quals" => \$phred64, #solexa1.3-quals" => \$phred64,
100 "solexa-quals" => \$solexa,
101 "bowtie2" => \$bowtie2,
102 "bowtie2-path=s" => \$bowtie2_path,
103 "bowtie2-mismatch-rate=f" => \$bowtie2_mismatch_rate,
104 "bowtie2-k=i" => \$bowtie2_k,
105 "bowtie2-sensitivity-level=s" => \$bowtie2_sensitivity_level,
106 "forward-prob=f" => \$probF,
107 "fragment-length-min=i" => \$minL,
108 "fragment-length-max=i" => \$maxL,
109 "fragment-length-mean=f" => \$mean,
110 "fragment-length-sd=f" => \$sd,
111 "estimate-rspd" => \$estRSPD,
112 "num-rspd-bins=i" => \$B,
113 "p|num-threads=i" => \$nThreads,
114 "no-bam-output" => sub { $genBamF = 0; },
115 "output-genome-bam" => \$genGenomeBamF,
116 "sampling-for-bam" => \$sampling,
118 "calc-ci" => \$calcCI,
119 "ci-memory=i" => \$NMB,
120 "samtools-sort-mem=s" => \$SortMem,
122 "version" => \$version,
123 "q|quiet" => \$quiet,
124 "h|help" => \$help) or pod2usage(-exitval => 2, -verbose => 2);
126 my $dir = "$FindBin::Bin/";
128 pod2usage(-verbose => 2) if ($help == 1);
129 &showVersionInfo($dir) if ($version == 1);
131 #check parameters and options
133 if ($is_sam || $is_bam) {
134 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (scalar(@ARGV) != 3);
135 pod2usage(-msg => "--sam and --bam cannot be active at the same time!", -exitval => 2, -verbose => 2) if ($is_sam == 1&& $is_bam == 1);
136 pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m, --phred33-quals, --phred64-quals, --solexa-quals, --bowtie2, --bowtie2-path, --bowtie2-mismatch-rate, --bowtie2-k and --bowtie2-sensitivity-level cannot be set if input is SAM/BAM format!", -exitval => 2, -verbose => 2) if ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200 || $phred33 || $phred64 || $solexa || $bowtie2 || $bowtie2_path ne "" || $bowtie2_mismatch_rate != 0.1 || $bowtie2_k != 200 || $bowtie2_sensitivity_level ne "sensitive");
139 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (!$paired_end && scalar(@ARGV) != 3 || $paired_end && scalar(@ARGV) != 4);
140 pod2usage(-msg => "If --no-qualities is set, neither --phred33-quals, --phred64-quals or --solexa-quals can be active!", -exitval => 2, -verbose => 2) if ($no_qual && ($phred33 + $phred64 + $solexa > 0));
141 pod2usage(-msg => "Only one of --phred33-quals, --phred64-quals, and --solexa-quals can be active!", -exitval => 2, -verbose => 2) if ($phred33 + $phred64 + $solexa > 1);
142 pod2usage(-msg => "--sam , --bam or --sam-header-info cannot be set if use bowtie/bowtie2 aligner to produce alignments!", -exitval => 2, -verbose => 2) if ($is_sam || $is_bam || $fn_list ne "");
143 pod2usage(-msg => "--bowtie2-path, --bowtie2-mismatch-rate, --bowtie2-k and --bowtie2-sensitivity-level cannot be set if bowtie aligner is used!", -exitval => 2, -verbose => 2) if (!$bowtie2 && ($bowtie2_path ne "" || $bowtie2_mismatch_rate != 0.1 || $bowtie2_k != 200 || $bowtie2_sensitivity_level ne "sensitive"));
144 pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m cannot be set if bowtie2 aligner is used!", -exitval => 2, -verbose => 2) if ($bowtie2 && ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200));
145 pod2usage(-msg => "Mismatch rate must be within [0, 1]!", -exitval => 2, -verbose => 2) if ($bowtie2 && ($bowtie2_mismatch_rate < 0.0 || $bowtie2_mismatch_rate > 1.0));
146 pod2usage(-msg => "Sensitivity level must be one of \"very_fast\", \"fast\", \"sensitive\", and \"very_sensitive\"!", -exitval => 2, -verbose => 2) if ($bowtie2 && (($bowtie2_sensitivity_level ne "very_fast") && ($bowtie2_sensitivity_level ne "fast") && ($bowtie2_sensitivity_level ne "sensitive") && ($bowtie2_sensitivity_level ne "very_sensitive")));
149 pod2usage(-msg => "Forward probability should be in [0, 1]!", -exitval => 2, -verbose => 2) if ($probF < 0 || $probF > 1);
150 pod2usage(-msg => "Min fragment length should be at least 1!", -exitval => 2, -verbose => 2) if ($minL < 1);
151 pod2usage(-msg => "Min fragment length should be smaller or equal to max fragment length!", -exitval => 2, -verbose => 2) if ($minL > $maxL);
152 pod2usage(-msg => "The memory allocated for calculating credibility intervals should be at least 1 MB!\n", -exitval => 2, -verbose => 2) if ($NMB < 1);
153 pod2usage(-msg => "Number of threads should be at least 1!\n", -exitval => 2, -verbose => 2) if ($nThreads < 1);
154 pod2usage(-msg => "Seed length should be at least 5!\n", -exitval => 2, -verbose => 2) if ($L < 5);
155 pod2usage(-msg => "--sampling-for-bam cannot be specified if --no-bam-output is specified!\n", -exitval => 2, -verbose => 2) if ($sampling && !$genBamF);
156 pod2usage(-msg => "--output-genome-bam cannot be specified if --no-bam-output is specified!\n", -exitval => 2, -verbose => 2) if ($genGenomeBamF && !$genBamF);
158 if ($L < 25) { print "Warning: the seed length set is less than 25! This is only allowed if the references are not added poly(A) tails.\n"; }
160 if ($strand_specific) { $probF = 1.0; }
163 if ($no_qual) { $read_type = 2; }
164 else { $read_type = 3; }
167 if ($no_qual) { $read_type = 0; }
168 else { $read_type = 1; }
171 if (scalar(@ARGV) == 3) {
172 if ($is_sam || $is_bam) { $inpF = $ARGV[0]; }
173 else {$mate1_list = $ARGV[0]; }
175 $sampleName = $ARGV[2];
178 $mate1_list = $ARGV[0];
179 $mate2_list = $ARGV[1];
181 $sampleName = $ARGV[3];
184 if ($genGenomeBamF) {
185 open(INPUT, "$refName.ti");
186 my $line = <INPUT>; chomp($line);
188 my ($M, $type) = split(/ /, $line);
189 pod2usage(-msg => "No genome information provided, so genome bam file cannot be generated!\n", -exitval => 2, -verbose => 2) if ($type != 0);
192 my $pos = rindex($sampleName, '/');
193 if ($pos < 0) { $sampleToken = $sampleName; }
194 else { $sampleToken = substr($sampleName, $pos + 1); }
196 if ($temp_dir eq "") { $temp_dir = "$sampleName.temp"; }
197 $stat_dir = "$sampleName.stat";
199 if (!(-d $temp_dir) && !mkdir($temp_dir)) { print "Fail to create folder $temp_dir.\n"; exit(-1); }
200 if (!(-d $stat_dir) && !mkdir($stat_dir)) { print "Fail to create folder $stat_dir.\n"; exit(-1); }
202 $imdName = "$temp_dir/$sampleToken";
203 $statName = "$stat_dir/$sampleToken";
205 if (!$is_sam && !$is_bam && !$no_qual && ($phred33 + $phred64 + $solexa == 0)) { $phred33 = 1; }
207 my ($mate_minL, $mate_maxL) = (1, $maxL);
209 if ($bowtie_path ne "") { $bowtie_path .= "/"; }
210 if ($bowtie2_path ne "") { $bowtie2_path .= "/"; }
214 if (!$is_sam && !$is_bam) {
216 $command = $bowtie_path."bowtie";
217 if ($no_qual) { $command .= " -f"; }
218 else { $command .= " -q"; }
220 if ($phred33) { $command .= " --phred33-quals"; }
221 elsif ($phred64) { $command .= " --phred64-quals"; }
222 elsif ($solexa) { $command .= " --solexa-quals"; }
224 $command .= " -n $C -e $E -l $L";
225 if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL"; }
226 if ($chunkMbs > 0) { $command .= " --chunkmbs $chunkMbs"; }
228 if ($strand_specific || $probF == 1.0) { $command .= " --norc"; }
229 elsif ($probF == 0.0) { $command .= " --nofw"; }
231 $command .= " -p $nThreads -a -m $maxHits -S";
232 if ($quiet) { $command .= " --quiet"; }
234 $command .= " $refName";
235 if ($read_type == 0 || $read_type == 1) {
236 $command .= " $mate1_list";
239 $command .= " -1 $mate1_list -2 $mate2_list";
242 # pipe to samtools to generate a BAM file
243 $command .= " | $dir\sam/samtools view -S -b -o $imdName.bam -";
246 $command = $bowtie2_path."bowtie2";
247 if ($no_qual) { $command .= " -f"; }
248 else { $command .= " -q"; }
250 if ($phred33) { $command .= " --phred33"; }
251 elsif ($phred64) { $command .= " --phred64"; }
252 elsif ($solexa) { $command .= " --solexa-quals"; }
254 if ($bowtie2_sensitivity_level eq "very_fast") { $command .= " --very-fast"; }
255 elsif ($bowtie2_sensitivity_level eq "fast") { $command .= " --fast"; }
256 elsif ($bowtie2_sensitivity_level eq "sensitive") { $command .= " --sensitive"; }
257 else { $command .= " --very-sensitive"; }
259 $command .= " --dpad 0 --gbar 99999999 --mp 1,1 --np 1 --score-min L,0,-$bowtie2_mismatch_rate";
261 if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL --no-mixed --no-discordant"; }
263 if ($strand_specific || $probF == 1.0) { $command .= " --norc"; }
264 elsif ($probF == 0.0) { $command .= " --nofw"; }
266 $command .= " -p $nThreads -k $bowtie2_k";
267 if ($quiet) { $command .= " --quiet"; }
269 $command .= " -x $refName";
270 if ($read_type == 0 || $read_type == 1) {
271 $command .= " -U $mate1_list";
274 $command .= " -1 $mate1_list -2 $mate2_list";
277 # pipe to samtools to generate a BAM file
278 $command .= " | $dir\sam/samtools view -S -b -o $imdName.bam -";
281 if ($mTime) { $time_start = time(); }
283 &runCommand($command);
285 if ($mTime) { $time_end = time(); $time_alignment = $time_end - $time_start; }
287 $inpF = "$imdName.bam";
288 $is_bam = 1; # alignments are outputed as a BAM file
291 if ($mTime) { $time_start = time(); }
293 $command = $dir."rsem-parse-alignments $refName $imdName $statName";
296 if ($is_sam) { $samInpType = "s"; }
297 elsif ($is_bam) { $samInpType = "b"; }
299 $command .= " $samInpType $inpF -t $read_type";
300 if ($fn_list ne "") { $command .= " -l $fn_list"; }
301 if ($tagName ne "") { $command .= " -tag $tagName"; }
302 if ($quiet) { $command .= " -q"; }
304 &runCommand($command);
306 $command = $dir."rsem-build-read-index $gap";
307 if ($read_type == 0) { $command .= " 0 $quiet $imdName\_alignable.fa"; }
308 elsif ($read_type == 1) { $command .= " 1 $quiet $imdName\_alignable.fq"; }
309 elsif ($read_type == 2) { $command .= " 0 $quiet $imdName\_alignable_1.fa $imdName\_alignable_2.fa"; }
310 elsif ($read_type == 3) { $command .= " 1 $quiet $imdName\_alignable_1.fq $imdName\_alignable_2.fq"; }
311 else { print "Impossible! read_type is not in [1,2,3,4]!\n"; exit(-1); }
312 &runCommand($command);
314 my $doesOpen = open(OUTPUT, ">$imdName.mparams");
315 if ($doesOpen == 0) { print "Cannot generate $imdName.mparams!\n"; exit(-1); }
316 print OUTPUT "$minL $maxL\n";
317 print OUTPUT "$probF\n";
318 print OUTPUT "$estRSPD\n";
320 print OUTPUT "$mate_minL $mate_maxL\n";
321 print OUTPUT "$mean $sd\n";
325 $command = $dir."rsem-run-em $refName $read_type $sampleName $imdName $statName -p $nThreads";
327 $command .= " -b $samInpType $inpF";
328 if ($fn_list ne "") { $command .= " 1 $fn_list"; }
329 else { $command .= " 0"; }
330 if ($sampling) { $command .= " --sampling"; }
332 if ($calcCI || $var_opt) { $command .= " --gibbs-out"; }
333 if ($quiet) { $command .= " -q"; }
335 &runCommand($command);
337 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
338 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
341 $command = $dir."sam/samtools sort -@ $nThreads -m $SortMem $sampleName.transcript.bam $sampleName.transcript.sorted";
342 &runCommand($command);
343 $command = $dir."sam/samtools index $sampleName.transcript.sorted.bam";
344 &runCommand($command);
346 if ($genGenomeBamF) {
347 $command = $dir."rsem-tbam2gbam $refName $sampleName.transcript.bam $sampleName.genome.bam";
348 &runCommand($command);
349 $command = $dir."sam/samtools sort -@ $nThreads -m $SortMem $sampleName.genome.bam $sampleName.genome.sorted";
350 &runCommand($command);
351 $command = $dir."sam/samtools index $sampleName.genome.sorted.bam";
352 &runCommand($command);
356 if ($mTime) { $time_end = time(); $time_rsem = $time_end - $time_start; }
358 if ($mTime) { $time_start = time(); }
360 if ($calcCI || $var_opt) {
361 $command = $dir."rsem-run-gibbs $refName $imdName $statName $BURNIN $NCV $SAMPLEGAP";
362 $command .= " -p $nThreads";
363 if ($var_opt) { $command .= " --var"; }
364 if ($quiet) { $command .= " -q"; }
365 &runCommand($command);
369 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak1");
370 system("mv $sampleName.genes.results $imdName.genes.results.bak1");
371 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
372 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
374 $command = $dir."rsem-calculate-credibility-intervals $refName $imdName $statName $CONFIDENCE $NCV $NSPC $NMB";
375 $command .= " -p $nThreads";
376 if ($quiet) { $command .= " -q"; }
377 &runCommand($command);
379 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak2");
380 system("mv $sampleName.genes.results $imdName.genes.results.bak2");
381 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
382 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
385 if ($mTime) { $time_end = time(); $time_ci = $time_end - $time_start; }
387 if ($mTime) { $time_start = time(); }
389 if (!$keep_intermediate_files) {
390 &runCommand("rm -rf $temp_dir", "Fail to delete the temporary folder!");
393 if ($mTime) { $time_end = time(); }
396 open(OUTPUT, ">$sampleName.time");
397 print OUTPUT "Aligning reads: $time_alignment s.\n";
398 print OUTPUT "Estimating expression levels: $time_rsem s.\n";
399 print OUTPUT "Calculating credibility intervals: $time_ci s.\n";
400 my $time_del = $time_end - $time_start;
401 # print OUTPUT "Delete: $time_del s.\n";
409 rsem-calculate-expression
413 rsem-calculate-expression [options] upstream_read_file(s) reference_name sample_name
414 rsem-calculate-expression [options] --paired-end upstream_read_file(s) downstream_read_file(s) reference_name sample_name
415 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/Bowtie 2 aligner, the '--norc' Bowtie/Bowtie 2 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/Bowtie2, expression estimation and 'samtools sort' 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)
533 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)
535 =item B<--bowtie2-path> <path>
537 (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)
539 =item B<--bowtie2-mismatch-rate> <double>
541 (Bowtie 2 parameter) The maximum mismatch rate allowed. (Default: 0.1)
543 =item B<--bowtie2-k> <int>
545 (Bowtie 2 parameter) Find up to <int> alignments per read. (Default: 200)
547 =item B<--bowtie2-sensitivity-level> <string>
549 (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)
551 =item B<--forward-prob> <double>
553 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)
555 =item B<--fragment-length-min> <int>
557 Minimum read/insert length allowed. This is also the value for the Bowtie/Bowtie2 -I option. (Default: 1)
559 =item B<--fragment-length-max> <int>
561 Maximum read/insert length allowed. This is also the value for the Bowtie/Bowtie 2 -X option. (Default: 1000)
563 =item B<--fragment-length-mean> <double>
565 (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)
567 =item B<--fragment-length-sd> <double>
569 (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>)
571 =item B<--estimate-rspd>
573 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)
575 =item B<--num-rspd-bins> <int>
577 Number of bins in the RSPD. Only relevant when '--estimate-rspd' is specified. Use of the default setting is recommended. (Default: 20)
579 =item B<--ci-memory> <int>
581 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)
583 =item B<--samtools-sort-mem> <string>
585 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)
587 =item B<--keep-intermediate-files>
589 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)
591 =item B<--temporary-folder> <string>
593 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)
597 Output time consumed by each step of RSEM to 'sample_name.time'. (Default: off)
601 Suppress the output of logging information. (Default: off)
605 Show help information.
609 Show version information.
615 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.
617 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:
619 convert-sam-for-rsem /ref/mouse_125 input.sam -o input_for_rsem.sam
621 For details, please refer to 'convert-sam-for-rsem's documentation page.
623 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 '*'.
625 The user must run 'rsem-prepare-reference' with the appropriate reference before using this program.
627 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.
629 Please note that some of the default values for the Bowtie parameters are not the same as those defined for Bowtie itself.
631 The temporary directory and all intermediate files will be removed when RSEM finishes unless '--keep-intermediate-files' is specified.
633 With the '--calc-ci' option, 95% credibility intervals and posterior mean estimates will be calculated in addition to maximum likelihood estimates.
639 =item B<sample_name.isoforms.results>
641 File containing isoform level expression estimates. The first line
642 contains column names separated by the tab character. The format of
643 each line in the rest of this file is:
645 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]
647 Fields are separated by the tab character. Fields within "[]" are only
648 presented if '--calc-ci' is set.
650 'transcript_id' is the transcript name of this transcript. 'gene_id'
651 is the gene name of the gene which this transcript belongs to (denote
652 this gene as its parent gene). If no gene information is provided,
653 'gene_id' and 'transcript_id' are the same.
655 'length' is this transcript's sequence length (poly(A) tail is not
656 counted). 'effective_length' counts only the positions that can
657 generate a valid fragment. If no poly(A) tail is added,
658 'effective_length' is equal to transcript length - mean fragment
659 length + 1. If one transcript's effective length is less than 1, this
660 transcript's both effective length and abundance estimates are set to
663 'expected_count' is the sum of the posterior probability of each read
664 comes from this transcript over all reads. Because 1) each read
665 aligning to this transcript has a probability of being generated from
666 background noise; 2) RSEM may filter some alignable low quality reads,
667 the sum of expected counts for all transcript are generally less than
668 the total number of reads aligned.
670 'TPM' stands for Transcripts Per Million. It is a relative measure of
671 transcript abundance. The sum of all transcripts' TPM is 1
672 million. 'FPKM' stands for Fragments Per Kilobase of transcript per
673 Million mapped reads. It is another relative measure of transcript
674 abundance. If we define l_bar be the mean transcript length in a
675 sample, which can be calculated as
677 l_bar = \sum_i TPM_i / 10^6 * effective_length_i (i goes through every transcript),
679 the following equation is hold:
681 FPKM_i = 10^3 / l_bar * TPM_i.
683 We can see that the sum of FPKM is not a constant across samples.
685 'IsoPct' stands for isoform percentage. It is the percentage of this
686 transcript's abandunce over its parent gene's abandunce. If its parent
687 gene has only one isoform or the gene information is not provided,
688 this field will be set to 100.
690 'pme_expected_count', 'pme_TPM', 'pme_FPKM' are posterior mean
691 estimates calculated by RSEM's Gibbs sampler. 'IsoPct_from_pme_TPM' is
692 the isoform percentage calculated from 'pme_TPM' values.
694 'TPM_ci_lower_bound', 'TPM_ci_upper_bound', 'FPKM_ci_lower_bound' and
695 'FPKM_ci_upper_bound' are lower(l) and upper(u) bounds of 95%
696 credibility intervals for TPM and FPKM values. The bounds are
697 inclusive (i.e. [l, u]).
699 =item B<sample_name.genes.results>
701 File containing gene level expression estimates. The first line
702 contains column names separated by the tab character. The format of
703 each line in the rest of this file is:
705 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]
707 Fields are separated by the tab character. Fields within "[]" are only
708 presented if '--calc-ci' is set.
710 'transcript_id(s)' is a comma-separated list of transcript_ids
711 belonging to this gene. If no gene information is provided, 'gene_id'
712 and 'transcript_id(s)' are identical (the 'transcript_id').
714 A gene's 'length' and 'effective_length' are
715 defined as the weighted average of its transcripts' lengths and
716 effective lengths (weighted by 'IsoPct'). A gene's abundance estimates
717 are just the sum of its transcripts' abundance estimates.
719 =item B<sample_name.transcript.bam, sample_name.transcript.sorted.bam and sample_name.transcript.sorted.bam.bai>
721 Only generated when --no-bam-output is not specified.
723 'sample_name.transcript.bam' is a BAM-formatted file of read
724 alignments in transcript coordinates. The MAPQ field of each alignment
725 is set to min(100, floor(-10 * log10(1.0 - w) + 0.5)), where w is the
726 posterior probability of that alignment being the true mapping of a
727 read. In addition, RSEM pads a new tag ZW:f:value, where value is a
728 single precision floating number representing the posterior
729 probability. Because this file contains all alignment lines produced
730 by bowtie or user-specified aligners, it can also be used as a
731 replacement of the aligner generated BAM/SAM file. For paired-end
732 reads, if one mate has alignments but the other does not, this file
733 marks the alignable mate as "unmappable" (flag bit 0x4) and appends an
734 optional field "Z0:A:!".
736 'sample_name.transcript.sorted.bam' and
737 'sample_name.transcript.sorted.bam.bai' are the sorted BAM file and
738 indices generated by samtools (included in RSEM package).
740 =item B<sample_name.genome.bam, sample_name.genome.sorted.bam and sample_name.genome.sorted.bam.bai>
742 Only generated when --no-bam-output is not specified and --output-genome-bam is specified.
744 'sample_name.genome.bam' is a BAM-formatted file of read alignments in
745 genomic coordinates. Alignments of reads that have identical genomic
746 coordinates (i.e., alignments to different isoforms that share the
747 same genomic region) are collapsed into one alignment. The MAPQ field
748 of each alignment is set to min(100, floor(-10 * log10(1.0 - w) +
749 0.5)), where w is the posterior probability of that alignment being
750 the true mapping of a read. In addition, RSEM pads a new tag
751 ZW:f:value, where value is a single precision floating number
752 representing the posterior probability. If an alignment is spliced, a
753 XS:A:value tag is also added, where value is either '+' or '-'
754 indicating the strand of the transcript it aligns to.
756 'sample_name.genome.sorted.bam' and 'sample_name.genome.sorted.bam.bai' are the
757 sorted BAM file and indices generated by samtools (included in RSEM package).
759 =item B<sample_name.time>
761 Only generated when --time is specified.
763 It contains time (in seconds) consumed by aligning reads, estimating expression levels and calculating credibility intervals.
765 =item B<sample_name.stat>
767 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.
773 Assume the path to the bowtie executables is in the user's PATH environment variable. Reference files are under '/ref' with name 'mouse_125'.
775 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:
777 rsem-calculate-expression --phred64-quals \
779 --output-genome-bam \
784 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:
786 rsem-calculate-expression -p 8 \
791 mmliver_paired_end_quals
793 3) '/data/mmliver.fa', single-end reads without quality scores. We want to use 8 threads:
795 rsem-calculate-expression -p 8 \
799 mmliver_single_without_quals
801 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:
803 rsem-calculate-expression --bowtie-path /sw/bowtie \
805 --fragment-length-mean 150.0 \
806 --fragment-length-sd 35.0 \
808 --output-genome-bam \
815 5) '/data/mmliver_paired_end_quals.bam', paired-end reads with quality scores. We want to use 8 threads:
817 rsem-calculate-expression --paired-end \
820 /data/mmliver_paired_end_quals.bam \
822 mmliver_paired_end_quals