7 use lib $FindBin::RealBin;
8 use rsem_perl_utils qw(runCommand collectResults showVersionInfo);
11 @PATH = ($FindBin::RealBin, "$FindBin::RealBin/sam", @PATH);
19 my $CONFIDENCE = 0.95;
22 my $NMB = 1024; # default
23 my $SortMem = "1G"; # default as 1G per thread
27 my $read_type = 1; # default, single end with qual
34 my $chunkMbs = 0; # 0 = use bowtie default
55 my $genBamF = 1; # default is generating transcript bam file
56 my $genGenomeBamF = 0;
60 my $var_opt = 0; # temporarily, only for internal use
66 my $keep_intermediate_files = 0;
68 my $strand_specific = 0;
71 my $bowtie2_path = "";
72 my $bowtie2_mismatch_rate = 0.1;
74 my $bowtie2_sensitivity_level = "sensitive"; # must be one of "very_fast", "fast", "sensitive", "very_sensitive"
81 my ($time_start, $time_end, $time_alignment, $time_rsem, $time_ci) = (0, 0, 0, 0, 0);
87 my ($refName, $sampleName, $sampleToken, $temp_dir, $stat_dir, $imdName, $statName) = ();
92 GetOptions("keep-intermediate-files" => \$keep_intermediate_files,
93 "temporary-folder=s" => \$temp_dir,
94 "no-qualities" => \$no_qual,
95 "paired-end" => \$paired_end,
96 "strand-specific" => \$strand_specific,
99 "sam-header-info=s" => \$fn_list,
100 "tag=s" => \$tagName,
101 "seed-length=i" => \$L,
102 "bowtie-path=s" => \$bowtie_path,
105 "bowtie-m=i" => \$maxHits,
106 "bowtie-chunkmbs=i" => \$chunkMbs,
107 "phred33-quals" => \$phred33,
108 "phred64-quals" => \$phred64, #solexa1.3-quals" => \$phred64,
109 "solexa-quals" => \$solexa,
110 "bowtie2" => \$bowtie2,
111 "bowtie2-path=s" => \$bowtie2_path,
112 "bowtie2-mismatch-rate=f" => \$bowtie2_mismatch_rate,
113 "bowtie2-k=i" => \$bowtie2_k,
114 "bowtie2-sensitivity-level=s" => \$bowtie2_sensitivity_level,
115 "forward-prob=f" => \$probF,
116 "fragment-length-min=i" => \$minL,
117 "fragment-length-max=i" => \$maxL,
118 "fragment-length-mean=f" => \$mean,
119 "fragment-length-sd=f" => \$sd,
120 "estimate-rspd" => \$estRSPD,
121 "num-rspd-bins=i" => \$B,
122 "p|num-threads=i" => \$nThreads,
123 "no-bam-output" => sub { $genBamF = 0; },
124 "output-genome-bam" => \$genGenomeBamF,
125 "sampling-for-bam" => \$sampling,
126 "calc-pme" => \$calcPME,
128 "calc-ci" => \$calcCI,
129 "ci-memory=i" => \$NMB,
130 "samtools-sort-mem=s" => \$SortMem,
133 "version" => \$version,
134 "q|quiet" => \$quiet,
135 "h|help" => \$help) or pod2usage(-exitval => 2, -verbose => 2);
137 pod2usage(-verbose => 2) if ($help == 1);
138 &showVersionInfo($FindBin::RealBin) if ($version == 1);
140 #check parameters and options
142 if ($is_sam || $is_bam) {
143 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (scalar(@ARGV) != 3);
144 pod2usage(-msg => "--sam and --bam cannot be active at the same time!", -exitval => 2, -verbose => 2) if ($is_sam == 1&& $is_bam == 1);
145 pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m, --phred33-quals, --phred64-quals, --solexa-quals, --bowtie2, --bowtie2-path, --bowtie2-mismatch-rate, --bowtie2-k and --bowtie2-sensitivity-level cannot be set if input is SAM/BAM format!", -exitval => 2, -verbose => 2) if ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200 || $phred33 || $phred64 || $solexa || $bowtie2 || $bowtie2_path ne "" || $bowtie2_mismatch_rate != 0.1 || $bowtie2_k != 200 || $bowtie2_sensitivity_level ne "sensitive");
148 pod2usage(-msg => "Invalid number of arguments!", -exitval => 2, -verbose => 2) if (!$paired_end && scalar(@ARGV) != 3 || $paired_end && scalar(@ARGV) != 4);
149 pod2usage(-msg => "If --no-qualities is set, neither --phred33-quals, --phred64-quals or --solexa-quals can be active!", -exitval => 2, -verbose => 2) if ($no_qual && ($phred33 + $phred64 + $solexa > 0));
150 pod2usage(-msg => "Only one of --phred33-quals, --phred64-quals, and --solexa-quals can be active!", -exitval => 2, -verbose => 2) if ($phred33 + $phred64 + $solexa > 1);
151 pod2usage(-msg => "--sam , --bam or --sam-header-info cannot be set if use bowtie/bowtie2 aligner to produce alignments!", -exitval => 2, -verbose => 2) if ($is_sam || $is_bam || $fn_list ne "");
152 pod2usage(-msg => "--bowtie2-path, --bowtie2-mismatch-rate, --bowtie2-k and --bowtie2-sensitivity-level cannot be set if bowtie aligner is used!", -exitval => 2, -verbose => 2) if (!$bowtie2 && ($bowtie2_path ne "" || $bowtie2_mismatch_rate != 0.1 || $bowtie2_k != 200 || $bowtie2_sensitivity_level ne "sensitive"));
153 pod2usage(-msg => "--bowtie-path, --bowtie-n, --bowtie-e, --bowtie-m cannot be set if bowtie2 aligner is used!", -exitval => 2, -verbose => 2) if ($bowtie2 && ($bowtie_path ne "" || $C != 2 || $E != 99999999 || $maxHits != 200));
154 pod2usage(-msg => "Mismatch rate must be within [0, 1]!", -exitval => 2, -verbose => 2) if ($bowtie2 && ($bowtie2_mismatch_rate < 0.0 || $bowtie2_mismatch_rate > 1.0));
155 pod2usage(-msg => "Sensitivity level must be one of \"very_fast\", \"fast\", \"sensitive\", and \"very_sensitive\"!", -exitval => 2, -verbose => 2) if ($bowtie2 && (($bowtie2_sensitivity_level ne "very_fast") && ($bowtie2_sensitivity_level ne "fast") && ($bowtie2_sensitivity_level ne "sensitive") && ($bowtie2_sensitivity_level ne "very_sensitive")));
158 pod2usage(-msg => "Forward probability should be in [0, 1]!", -exitval => 2, -verbose => 2) if ($probF < 0 || $probF > 1);
159 pod2usage(-msg => "Min fragment length should be at least 1!", -exitval => 2, -verbose => 2) if ($minL < 1);
160 pod2usage(-msg => "Min fragment length should be smaller or equal to max fragment length!", -exitval => 2, -verbose => 2) if ($minL > $maxL);
161 pod2usage(-msg => "The memory allocated for calculating credibility intervals should be at least 1 MB!\n", -exitval => 2, -verbose => 2) if ($NMB < 1);
162 pod2usage(-msg => "Number of threads should be at least 1!\n", -exitval => 2, -verbose => 2) if ($nThreads < 1);
163 pod2usage(-msg => "Seed length should be at least 5!\n", -exitval => 2, -verbose => 2) if ($L < 5);
164 pod2usage(-msg => "--sampling-for-bam cannot be specified if --no-bam-output is specified!\n", -exitval => 2, -verbose => 2) if ($sampling && !$genBamF);
165 pod2usage(-msg => "--output-genome-bam cannot be specified if --no-bam-output is specified!\n", -exitval => 2, -verbose => 2) if ($genGenomeBamF && !$genBamF);
166 pod2usage(-msg => "The seed for random number generator must be a non-negative 32bit integer!\n", -exitval => 2, -verbose => 2) if (($seed ne "NULL") && ($seed < 0 || $seed > 0xffffffff));
168 if ($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"; }
170 if ($strand_specific) { $probF = 1.0; }
173 if ($no_qual) { $read_type = 2; }
174 else { $read_type = 3; }
177 if ($no_qual) { $read_type = 0; }
178 else { $read_type = 1; }
181 if (scalar(@ARGV) == 3) {
182 if ($is_sam || $is_bam) { $inpF = $ARGV[0]; }
183 else {$mate1_list = $ARGV[0]; }
185 $sampleName = $ARGV[2];
188 $mate1_list = $ARGV[0];
189 $mate2_list = $ARGV[1];
191 $sampleName = $ARGV[3];
194 if (((-e "$refName.ta") && !(-e "$refName.gt")) || (!(-e "$refName.ta") && (-e "$refName.gt"))) {
195 print "Allele-specific expression related reference files are corrupted!\n";
199 $alleleS = (-e "$refName.ta") && (-e "$refName.gt");
201 if ($genGenomeBamF) {
202 open(INPUT, "$refName.ti");
203 my $line = <INPUT>; chomp($line);
205 my ($M, $type) = split(/ /, $line);
206 pod2usage(-msg => "No genome information provided, so genome bam file cannot be generated!\n", -exitval => 2, -verbose => 2) if ($type != 0);
209 my $pos = rindex($sampleName, '/');
210 if ($pos < 0) { $sampleToken = $sampleName; }
211 else { $sampleToken = substr($sampleName, $pos + 1); }
213 if ($temp_dir eq "") { $temp_dir = "$sampleName.temp"; }
214 $stat_dir = "$sampleName.stat";
216 if (!(-d $temp_dir) && !mkdir($temp_dir)) { print "Fail to create folder $temp_dir.\n"; exit(-1); }
217 if (!(-d $stat_dir) && !mkdir($stat_dir)) { print "Fail to create folder $stat_dir.\n"; exit(-1); }
219 $imdName = "$temp_dir/$sampleToken";
220 $statName = "$stat_dir/$sampleToken";
222 if (!$is_sam && !$is_bam && !$no_qual && ($phred33 + $phred64 + $solexa == 0)) { $phred33 = 1; }
224 my ($mate_minL, $mate_maxL) = (1, $maxL);
226 if ($bowtie_path ne "") { $bowtie_path .= "/"; }
227 if ($bowtie2_path ne "") { $bowtie2_path .= "/"; }
231 if (!$is_sam && !$is_bam) {
233 $command = $bowtie_path."bowtie";
234 if ($no_qual) { $command .= " -f"; }
235 else { $command .= " -q"; }
237 if ($phred33) { $command .= " --phred33-quals"; }
238 elsif ($phred64) { $command .= " --phred64-quals"; }
239 elsif ($solexa) { $command .= " --solexa-quals"; }
241 $command .= " -n $C -e $E -l $L";
242 if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL"; }
243 if ($chunkMbs > 0) { $command .= " --chunkmbs $chunkMbs"; }
245 if ($strand_specific || $probF == 1.0) { $command .= " --norc"; }
246 elsif ($probF == 0.0) { $command .= " --nofw"; }
248 $command .= " -p $nThreads -a -m $maxHits -S";
249 if ($quiet) { $command .= " --quiet"; }
251 $command .= " $refName";
252 if ($read_type == 0 || $read_type == 1) {
253 $command .= " $mate1_list";
256 $command .= " -1 $mate1_list -2 $mate2_list";
259 # pipe to samtools to generate a BAM file
260 $command .= " | samtools view -S -b -o $imdName.bam -";
263 $command = $bowtie2_path."bowtie2";
264 if ($no_qual) { $command .= " -f"; }
265 else { $command .= " -q"; }
267 if ($phred33) { $command .= " --phred33"; }
268 elsif ($phred64) { $command .= " --phred64"; }
269 elsif ($solexa) { $command .= " --solexa-quals"; }
271 if ($bowtie2_sensitivity_level eq "very_fast") { $command .= " --very-fast"; }
272 elsif ($bowtie2_sensitivity_level eq "fast") { $command .= " --fast"; }
273 elsif ($bowtie2_sensitivity_level eq "sensitive") { $command .= " --sensitive"; }
274 else { $command .= " --very-sensitive"; }
276 $command .= " --dpad 0 --gbar 99999999 --mp 1,1 --np 1 --score-min L,0,-$bowtie2_mismatch_rate";
278 if ($read_type == 2 || $read_type == 3) { $command .= " -I $minL -X $maxL --no-mixed --no-discordant"; }
280 if ($strand_specific || $probF == 1.0) { $command .= " --norc"; }
281 elsif ($probF == 0.0) { $command .= " --nofw"; }
283 $command .= " -p $nThreads -k $bowtie2_k";
284 if ($quiet) { $command .= " --quiet"; }
286 $command .= " -x $refName";
287 if ($read_type == 0 || $read_type == 1) {
288 $command .= " -U $mate1_list";
291 $command .= " -1 $mate1_list -2 $mate2_list";
294 # pipe to samtools to generate a BAM file
295 $command .= " | samtools view -S -b -o $imdName.bam -";
298 if ($mTime) { $time_start = time(); }
300 &runCommand($command);
302 if ($mTime) { $time_end = time(); $time_alignment = $time_end - $time_start; }
304 $inpF = "$imdName.bam";
305 $is_bam = 1; # alignments are outputed as a BAM file
308 if ($mTime) { $time_start = time(); }
310 $command = "rsem-parse-alignments $refName $imdName $statName";
313 if ($is_sam) { $samInpType = "s"; }
314 elsif ($is_bam) { $samInpType = "b"; }
316 $command .= " $samInpType $inpF -t $read_type";
317 if ($fn_list ne "") { $command .= " -l $fn_list"; }
318 if ($tagName ne "") { $command .= " -tag $tagName"; }
319 if ($quiet) { $command .= " -q"; }
321 &runCommand($command);
323 $command = "rsem-build-read-index $gap";
324 if ($read_type == 0) { $command .= " 0 $quiet $imdName\_alignable.fa"; }
325 elsif ($read_type == 1) { $command .= " 1 $quiet $imdName\_alignable.fq"; }
326 elsif ($read_type == 2) { $command .= " 0 $quiet $imdName\_alignable_1.fa $imdName\_alignable_2.fa"; }
327 elsif ($read_type == 3) { $command .= " 1 $quiet $imdName\_alignable_1.fq $imdName\_alignable_2.fq"; }
328 else { print "Impossible! read_type is not in [1,2,3,4]!\n"; exit(-1); }
329 &runCommand($command);
331 my $doesOpen = open(OUTPUT, ">$imdName.mparams");
332 if ($doesOpen == 0) { print "Cannot generate $imdName.mparams!\n"; exit(-1); }
333 print OUTPUT "$minL $maxL\n";
334 print OUTPUT "$probF\n";
335 print OUTPUT "$estRSPD\n";
337 print OUTPUT "$mate_minL $mate_maxL\n";
338 print OUTPUT "$mean $sd\n";
343 if ($seed ne "NULL") {
345 for (my $i = 0; $i < 3; $i++) {
346 push(@seeds, int(rand(1 << 32)));
350 $command = "rsem-run-em $refName $read_type $sampleName $imdName $statName -p $nThreads";
352 $command .= " -b $samInpType $inpF";
353 if ($fn_list ne "") { $command .= " 1 $fn_list"; }
354 else { $command .= " 0"; }
355 if ($sampling) { $command .= " --sampling"; }
356 if ($seed ne "NULL") { $command .= " --seed $seeds[0]"; }
358 if ($calcPME || $var_opt || $calcCI) { $command .= " --gibbs-out"; }
359 if ($quiet) { $command .= " -q"; }
361 &runCommand($command);
364 &collectResults("allele", "$imdName.allele_res", "$sampleName.alleles.results"); # allele level
365 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
366 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
369 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
370 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
374 $command = "samtools sort -@ $nThreads -m $SortMem $sampleName.transcript.bam $sampleName.transcript.sorted";
375 &runCommand($command);
376 $command = "samtools index $sampleName.transcript.sorted.bam";
377 &runCommand($command);
379 if ($genGenomeBamF) {
380 $command = "rsem-tbam2gbam $refName $sampleName.transcript.bam $sampleName.genome.bam";
381 &runCommand($command);
382 $command = "samtools sort -@ $nThreads -m $SortMem $sampleName.genome.bam $sampleName.genome.sorted";
383 &runCommand($command);
384 $command = "samtools index $sampleName.genome.sorted.bam";
385 &runCommand($command);
389 if ($mTime) { $time_end = time(); $time_rsem = $time_end - $time_start; }
391 if ($mTime) { $time_start = time(); }
393 if ($calcPME || $var_opt || $calcCI ) {
394 $command = "rsem-run-gibbs $refName $imdName $statName $BURNIN $NCV $SAMPLEGAP";
395 $command .= " -p $nThreads";
396 if ($var_opt) { $command .= " --var"; }
397 if ($seed ne "NULL") { $command .= " --seed $seeds[1]"; }
398 if ($quiet) { $command .= " -q"; }
399 &runCommand($command);
402 if ($calcPME || $calcCI) {
404 system("mv $sampleName.alleles.results $imdName.alleles.results.bak1");
405 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak1");
406 system("mv $sampleName.genes.results $imdName.genes.results.bak1");
407 &collectResults("allele", "$imdName.allele_res", "$sampleName.alleles.results"); # allele level
408 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
409 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
412 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak1");
413 system("mv $sampleName.genes.results $imdName.genes.results.bak1");
414 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
415 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
420 $command = "rsem-calculate-credibility-intervals $refName $imdName $statName $CONFIDENCE $NCV $NSPC $NMB";
421 $command .= " -p $nThreads";
422 if ($seed ne "NULL") { $command .= " --seed $seeds[2]"; }
423 if ($quiet) { $command .= " -q"; }
424 &runCommand($command);
427 system("mv $sampleName.alleles.results $imdName.alleles.results.bak2");
428 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak2");
429 system("mv $sampleName.genes.results $imdName.genes.results.bak2");
430 &collectResults("allele", "$imdName.allele_res", "$sampleName.alleles.results"); # allele level
431 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
432 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
435 system("mv $sampleName.isoforms.results $imdName.isoforms.results.bak2");
436 system("mv $sampleName.genes.results $imdName.genes.results.bak2");
437 &collectResults("isoform", "$imdName.iso_res", "$sampleName.isoforms.results"); # isoform level
438 &collectResults("gene", "$imdName.gene_res", "$sampleName.genes.results"); # gene level
442 if ($mTime) { $time_end = time(); $time_ci = $time_end - $time_start; }
444 if ($mTime) { $time_start = time(); }
446 if (!$keep_intermediate_files) {
447 &runCommand("rm -rf $temp_dir", "Fail to delete the temporary folder!");
450 if ($mTime) { $time_end = time(); }
453 open(OUTPUT, ">$sampleName.time");
454 print OUTPUT "Aligning reads: $time_alignment s.\n";
455 print OUTPUT "Estimating expression levels: $time_rsem s.\n";
456 print OUTPUT "Calculating credibility intervals: $time_ci s.\n";
457 # my $time_del = $time_end - $time_start;
458 # print OUTPUT "Delete: $time_del s.\n";
466 rsem-calculate-expression
470 rsem-calculate-expression [options] upstream_read_file(s) reference_name sample_name
471 rsem-calculate-expression [options] --paired-end upstream_read_file(s) downstream_read_file(s) reference_name sample_name
472 rsem-calculate-expression [options] --sam/--bam [--paired-end] input reference_name sample_name
478 =item B<upstream_read_files(s)>
480 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.
482 =item B<downstream_read_file(s)>
484 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.
488 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.
490 =item B<reference_name>
492 The name of the reference used. The user must have run 'rsem-prepare-reference' with this reference_name before running this program.
496 The name of the sample analyzed. All output files are prefixed by this name (e.g., sample_name.genes.results)
504 =item B<--paired-end>
506 Input reads are paired-end reads. (Default: off)
508 =item B<--no-qualities>
510 Input reads do not contain quality scores. (Default: off)
512 =item B<--strand-specific>
514 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)
518 Input file is in SAM format. (Default: off)
522 Input file is in BAM format. (Default: off)
524 =item B<--sam-header-info> <file>
526 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: "")
528 =item B<-p/--num-threads> <int>
530 Number of threads to use. Both Bowtie/Bowtie2, expression estimation and 'samtools sort' will use this many threads. (Default: 1)
532 =item B<--no-bam-output>
534 Do not output any BAM file. (Default: off)
536 =item B<--output-genome-bam>
538 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)
540 =item B<--sampling-for-bam>
542 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)
544 =item B<--seed> <uint32>
546 Set the seed for the random number generators used in calculating posterior mean estimates and credibility intervals. The seed must be a non-negative 32 bit interger. (Default: off)
550 Run RSEM's collapsed Gibbs sampler to calculate posterior mean estimates. (Default: off)
554 Calculate 95% credibility intervals and posterior mean estimates. (Default: off)
556 =item B<--seed-length> <int>
558 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)
560 =item B<--tag> <string>
562 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: "")
564 =item B<--bowtie-path> <path>
566 The path to the Bowtie executables. (Default: the path to the Bowtie executables is assumed to be in the user's PATH environment variable)
568 =item B<--bowtie-n> <int>
570 (Bowtie parameter) max # of mismatches in the seed. (Range: 0-3, Default: 2)
572 =item B<--bowtie-e> <int>
574 (Bowtie parameter) max sum of mismatch quality scores across the alignment. (Default: 99999999)
576 =item B<--bowtie-m> <int>
578 (Bowtie parameter) suppress all alignments for a read if > <int> valid alignments exist. (Default: 200)
580 =item B<--bowtie-chunkmbs> <int>
582 (Bowtie parameter) memory allocated for best first alignment calculation (Default: 0 - use Bowtie's default)
584 =item B<--phred33-quals>
586 Input quality scores are encoded as Phred+33. (Default: on)
588 =item B<--phred64-quals>
590 Input quality scores are encoded as Phred+64 (default for GA Pipeline ver. >= 1.3). (Default: off)
592 =item B<--solexa-quals>
594 Input quality scores are solexa encoded (from GA Pipeline ver. < 1.3). (Default: off)
598 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)
600 =item B<--bowtie2-path> <path>
602 (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)
604 =item B<--bowtie2-mismatch-rate> <double>
606 (Bowtie 2 parameter) The maximum mismatch rate allowed. (Default: 0.1)
608 =item B<--bowtie2-k> <int>
610 (Bowtie 2 parameter) Find up to <int> alignments per read. (Default: 200)
612 =item B<--bowtie2-sensitivity-level> <string>
614 (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)
616 =item B<--forward-prob> <double>
618 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)
620 =item B<--fragment-length-min> <int>
622 Minimum read/insert length allowed. This is also the value for the Bowtie/Bowtie2 -I option. (Default: 1)
624 =item B<--fragment-length-max> <int>
626 Maximum read/insert length allowed. This is also the value for the Bowtie/Bowtie 2 -X option. (Default: 1000)
628 =item B<--fragment-length-mean> <double>
630 (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)
632 =item B<--fragment-length-sd> <double>
634 (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>)
636 =item B<--estimate-rspd>
638 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)
640 =item B<--num-rspd-bins> <int>
642 Number of bins in the RSPD. Only relevant when '--estimate-rspd' is specified. Use of the default setting is recommended. (Default: 20)
644 =item B<--ci-memory> <int>
646 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)
648 =item B<--samtools-sort-mem> <string>
650 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)
652 =item B<--keep-intermediate-files>
654 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)
656 =item B<--temporary-folder> <string>
658 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)
662 Output time consumed by each step of RSEM to 'sample_name.time'. (Default: off)
666 Suppress the output of logging information. (Default: off)
670 Show help information.
674 Show version information.
680 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.
682 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:
684 convert-sam-for-rsem /ref/mouse_125 input.sam -o input_for_rsem.sam
686 For details, please refer to 'convert-sam-for-rsem's documentation page.
688 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 '*'.
690 The user must run 'rsem-prepare-reference' with the appropriate reference before using this program.
692 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.
694 Please note that some of the default values for the Bowtie parameters are not the same as those defined for Bowtie itself.
696 The temporary directory and all intermediate files will be removed when RSEM finishes unless '--keep-intermediate-files' is specified.
698 With the '--calc-ci' option, 95% credibility intervals and posterior mean estimates will be calculated in addition to maximum likelihood estimates.
704 =item B<sample_name.isoforms.results>
706 File containing isoform level expression estimates. The first line
707 contains column names separated by the tab character. The format of
708 each line in the rest of this file is:
710 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]
712 Fields are separated by the tab character. Fields within "[]" are
713 optional. They will not be presented if neither '--calc-pme' nor
716 'transcript_id' is the transcript name of this transcript. 'gene_id'
717 is the gene name of the gene which this transcript belongs to (denote
718 this gene as its parent gene). If no gene information is provided,
719 'gene_id' and 'transcript_id' are the same.
721 'length' is this transcript's sequence length (poly(A) tail is not
722 counted). 'effective_length' counts only the positions that can
723 generate a valid fragment. If no poly(A) tail is added,
724 'effective_length' is equal to transcript length - mean fragment
725 length + 1. If one transcript's effective length is less than 1, this
726 transcript's both effective length and abundance estimates are set to
729 'expected_count' is the sum of the posterior probability of each read
730 comes from this transcript over all reads. Because 1) each read
731 aligning to this transcript has a probability of being generated from
732 background noise; 2) RSEM may filter some alignable low quality reads,
733 the sum of expected counts for all transcript are generally less than
734 the total number of reads aligned.
736 'TPM' stands for Transcripts Per Million. It is a relative measure of
737 transcript abundance. The sum of all transcripts' TPM is 1
738 million. 'FPKM' stands for Fragments Per Kilobase of transcript per
739 Million mapped reads. It is another relative measure of transcript
740 abundance. If we define l_bar be the mean transcript length in a
741 sample, which can be calculated as
743 l_bar = \sum_i TPM_i / 10^6 * effective_length_i (i goes through every transcript),
745 the following equation is hold:
747 FPKM_i = 10^3 / l_bar * TPM_i.
749 We can see that the sum of FPKM is not a constant across samples.
751 'IsoPct' stands for isoform percentage. It is the percentage of this
752 transcript's abandunce over its parent gene's abandunce. If its parent
753 gene has only one isoform or the gene information is not provided,
754 this field will be set to 100.
756 'pme_expected_count', 'pme_TPM', 'pme_FPKM' are posterior mean
757 estimates calculated by RSEM's Gibbs sampler. 'IsoPct_from_pme_TPM' is
758 the isoform percentage calculated from 'pme_TPM' values.
760 'TPM_ci_lower_bound', 'TPM_ci_upper_bound', 'FPKM_ci_lower_bound' and
761 'FPKM_ci_upper_bound' are lower(l) and upper(u) bounds of 95%
762 credibility intervals for TPM and FPKM values. The bounds are
763 inclusive (i.e. [l, u]).
765 =item B<sample_name.genes.results>
767 File containing gene level expression estimates. The first line
768 contains column names separated by the tab character. The format of
769 each line in the rest of this file is:
771 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]
773 Fields are separated by the tab character. Fields within "[]" are
774 optional. They will not be presented if neither '--calc-pme' nor
777 'transcript_id(s)' is a comma-separated list of transcript_ids
778 belonging to this gene. If no gene information is provided, 'gene_id'
779 and 'transcript_id(s)' are identical (the 'transcript_id').
781 A gene's 'length' and 'effective_length' are
782 defined as the weighted average of its transcripts' lengths and
783 effective lengths (weighted by 'IsoPct'). A gene's abundance estimates
784 are just the sum of its transcripts' abundance estimates.
786 =item B<sample_name.alleles.results>
788 Only generated when the RSEM references are built with allele-specific
791 This file contains allele level expression estimates for
792 allele-specific expression calculation. The first line
793 contains column names separated by the tab character. The format of
794 each line in the rest of this file is:
796 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]
798 Fields are separated by the tab character. Fields within "[]" are
799 optional. They will not be presented if neither '--calc-pme' nor
802 'allele_id' is the allele-specific name of this allele-specific transcript.
804 'AlleleIsoPct' stands for allele-specific percentage on isoform
805 level. It is the percentage of this allele-specific transcript's
806 abundance over its parent transcript's abundance. If its parent
807 transcript has only one allele variant form, this field will be set to
810 'AlleleGenePct' stands for allele-specific percentage on gene
811 level. It is the percentage of this allele-specific transcript's
812 abundance over its parent gene's abundance.
814 'AlleleIsoPct_from_pme_TPM' and 'AlleleGenePct_from_pme_TPM' have
815 similar meanings. They are calculated based on posterior mean
818 Please note that if this file is present, the fields 'length' and
819 'effective_length' in 'sample_name.isoforms.results' should be
820 interpreted similarly as the corresponding definitions in
821 'sample_name.genes.results'.
823 =item B<sample_name.transcript.bam, sample_name.transcript.sorted.bam and sample_name.transcript.sorted.bam.bai>
825 Only generated when --no-bam-output is not specified.
827 'sample_name.transcript.bam' is a BAM-formatted file of read
828 alignments in transcript coordinates. The MAPQ field of each alignment
829 is set to min(100, floor(-10 * log10(1.0 - w) + 0.5)), where w is the
830 posterior probability of that alignment being the true mapping of a
831 read. In addition, RSEM pads a new tag ZW:f:value, where value is a
832 single precision floating number representing the posterior
833 probability. Because this file contains all alignment lines produced
834 by bowtie or user-specified aligners, it can also be used as a
835 replacement of the aligner generated BAM/SAM file. For paired-end
836 reads, if one mate has alignments but the other does not, this file
837 marks the alignable mate as "unmappable" (flag bit 0x4) and appends an
838 optional field "Z0:A:!".
840 'sample_name.transcript.sorted.bam' and
841 'sample_name.transcript.sorted.bam.bai' are the sorted BAM file and
842 indices generated by samtools (included in RSEM package).
844 =item B<sample_name.genome.bam, sample_name.genome.sorted.bam and sample_name.genome.sorted.bam.bai>
846 Only generated when --no-bam-output is not specified and --output-genome-bam is specified.
848 'sample_name.genome.bam' is a BAM-formatted file of read alignments in
849 genomic coordinates. Alignments of reads that have identical genomic
850 coordinates (i.e., alignments to different isoforms that share the
851 same genomic region) are collapsed into one alignment. The MAPQ field
852 of each alignment is set to min(100, floor(-10 * log10(1.0 - w) +
853 0.5)), where w is the posterior probability of that alignment being
854 the true mapping of a read. In addition, RSEM pads a new tag
855 ZW:f:value, where value is a single precision floating number
856 representing the posterior probability. If an alignment is spliced, a
857 XS:A:value tag is also added, where value is either '+' or '-'
858 indicating the strand of the transcript it aligns to.
860 'sample_name.genome.sorted.bam' and 'sample_name.genome.sorted.bam.bai' are the
861 sorted BAM file and indices generated by samtools (included in RSEM package).
863 =item B<sample_name.time>
865 Only generated when --time is specified.
867 It contains time (in seconds) consumed by aligning reads, estimating expression levels and calculating credibility intervals.
869 =item B<sample_name.stat>
871 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.
877 Assume the path to the bowtie executables is in the user's PATH environment variable. Reference files are under '/ref' with name 'mouse_125'.
879 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:
881 rsem-calculate-expression --phred64-quals \
883 --output-genome-bam \
888 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:
890 rsem-calculate-expression -p 8 \
895 mmliver_paired_end_quals
897 3) '/data/mmliver.fa', single-end reads without quality scores. We want to use 8 threads:
899 rsem-calculate-expression -p 8 \
903 mmliver_single_without_quals
905 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:
907 rsem-calculate-expression --bowtie-path /sw/bowtie \
909 --fragment-length-mean 150.0 \
910 --fragment-length-sd 35.0 \
912 --output-genome-bam \
919 5) '/data/mmliver_paired_end_quals.bam', paired-end reads with quality scores. We want to use 8 threads:
921 rsem-calculate-expression --paired-end \
924 /data/mmliver_paired_end_quals.bam \
926 mmliver_paired_end_quals