Mercurial > repos > jjohnson > rsem
annotate rsem_calculate_expression.xml @ 5:14267d364365 default tip
Update for dataset files_path - use model from BB pull request 532
author | Jim Johnson <jj@umn.edu> |
---|---|
date | Thu, 04 Feb 2016 06:50:26 -0600 |
parents | 30a8343fb0e7 |
children |
rev | line source |
---|---|
0 | 1 <tool id="rsem_calculate_expression" name="RSEM calculate expression" version="1.1.17"> |
2 <description>RNA-Seq by Expectation-Maximization</description> | |
3 <requirements> | |
4 <requirement type="package" version="1.1.17">rsem</requirement> | |
5 <requirement type="package" version="1.0.0">bowtie</requirement> | |
6 </requirements> | |
7 <command> | |
8 rsem-calculate-expression | |
9 ## --tag string | |
10 #if $seedlength: | |
11 --seed-length $seedlength | |
12 #end if | |
13 --forward-prob $forward_prob | |
14 #if $rsem_options.fullparams == 'fullset': | |
15 ## Fragment info | |
16 #if $rsem_options.fragment_length_mean: | |
17 --fragment-length-mean $rsem_options.fragment_length_mean | |
18 #end if | |
19 #if $rsem_options.fragment_length_min: | |
20 --fragment-length-min $rsem_options.fragment_length_min | |
21 #end if | |
22 #if $rsem_options.fragment_length_sd: | |
23 --fragment-length-sd $rsem_options.fragment_length_sd | |
24 #end if | |
25 #if $rsem_options.fragment_length_max: | |
26 --fragment-length-max $rsem_options.fragment_length_max | |
27 #end if | |
28 ## RSPD | |
29 #if $rsem_options.rspd.estimate == 'yes': | |
30 --estimate-rspd | |
31 #if $rsem_options.rspd.num_rspd_bins: | |
32 --num-rspd-bins $rsem_options.rspd.num_rspd_bins | |
33 #end if | |
34 #end if | |
35 ## Calculate 95% credibility intervals and posterior mean estimates. | |
36 #if $rsem_options.useci.ci == 'yes': | |
37 --calc-ci | |
38 #if $rsem_options.useci.cimem: | |
39 --ci-memory $rsem_options.useci.cimem | |
40 #end if | |
41 #end if | |
42 #end if | |
43 ## --num-threads $GALAXY_SLOTS | |
44 #if $input.format != 'bam' and $input.bowtie_options.fullparams == 'fullset': | |
45 ## Bowtie params | |
46 #if $bowtie_options.bowtie_e: | |
47 --bowtie-e $bowtie_options.bowtie_e | |
48 #end if | |
49 #if $bowtie_options.bowtie_m: | |
50 --bowtie-m $bowtie_options.bowtie_m | |
51 #end if | |
52 #if $bowtie_options.bowtie_n: | |
53 --bowtie-n $bowtie_options.bowtie_n | |
54 #end if | |
55 #end if | |
56 ## Outputs | |
57 #if $rsem_outputs.result_bams == 'none': | |
58 --no-bam-output | |
59 #else | |
60 #if $rsem_outputs.result_bams == 'both': | |
61 --output-genome-bam | |
62 #end if | |
63 $rsem_outputs.sampling_for_bam | |
64 #end if | |
65 ## Input data | |
66 #if $input.format=="fastq" | |
67 $input.fastq_select | |
68 #if $input.fastq.matepair=="single": | |
69 $input.fastq.singlefastq | |
70 #elif $input.fastq.matepair=="paired": | |
71 --paired-end | |
72 $input.fastq.fastq1 | |
73 $input.fastq.fastq2 | |
74 #end if | |
75 #elif $input.format=="fasta" | |
76 --no-qualities | |
77 #if $input.fasta.matepair=="single": | |
78 $input.fasta.singlefasta | |
79 #elif $input.fasta.matepair=="paired": | |
80 --paired-end | |
81 $input.fasta.fasta1 | |
82 $input.fasta.fasta2 | |
83 #end if | |
84 #elif $input.format=="sam" | |
85 #if $input.matepair=="paired": | |
86 --paired-end | |
87 #end if | |
88 #if $input.rsem_sam._extension == 'sam': | |
89 --sam | |
90 #elif $input.rsem_sam._extension == 'bam': | |
91 --bam | |
92 #end if | |
93 $input.rsem_sam | |
94 #end if | |
95 ## RSEM reference | |
96 #if $reference.refSrc == 'history': | |
5
14267d364365
Update for dataset files_path - use model from BB pull request 532
Jim Johnson <jj@umn.edu>
parents:
4
diff
changeset
|
97 ${reference.rsem_ref.extra_files_path}/${reference.rsem_ref.metadata.reference_name} |
0 | 98 #elif $reference.refSrc == 'cached': |
99 ${reference.index.fields.path} | |
100 #end if | |
101 ## sample_name: use a hard coded name so we can pull out galaxy outputs | |
102 rsem_output | |
103 ## direct output into logfile | |
104 > $log | |
105 </command> | |
106 <macros> | |
107 <macro name="rsem_options"> | |
108 <param name="seedlength" type="integer" value="25" optional="true" label="Seed length used by the read aligner" help="Providing the correct value for this parameter is important for RSEM's accuracy if the data are single-end reads. RSEM uses this value for Bowtie's seed length parameter. The minimum value is 25. (Default:25)"> | |
109 </param> | |
110 <param name="forward_prob" type="select" label="Is the library strand specific?"> | |
111 <option value="0.5" selected="true">No</option> | |
112 <option value="1">Yes, the reads (or first reads from paired-end libraries) are only in the forward orientation</option> | |
113 <option value="0">Yes, the reads (or first reads from paired-end libraries) are only in the reverse orientation</option> | |
114 </param> | |
115 <conditional name="rsem_options"> | |
116 <param name="fullparams" type="select" label="Additional RSEM options"> | |
117 <option value="default">Use RSEM Defaults</option> | |
118 <option value="fullset">Set Additional RSEM Options</option> | |
119 </param> | |
120 <when value="default"/> | |
121 <when value="fullset"> | |
122 <param name="fragment_length_min" type="integer" value="1" optional="true" label="Minimum read/insert length." help=" This is also the value for the bowtie -I option"> | |
123 <validator type="in_range" message="0 or greater" min="0" /> | |
124 </param> | |
125 <param name="fragment_length_max" type="integer" value="1000" optional="true" label="Maximum read/insert length." help=" This is also the value for the bowtie -X option"> | |
126 <validator type="in_range" message="0 or greater" min="0" max="1000000"/> | |
127 </param> | |
128 <param name="fragment_length_mean" type="float" value="" optional="true" label="Fragment length mean (single-end data only)" help="The mean of the fragment length distribution, which is assumed to be a Gaussian. (Default: -1, which disables use of the fragment length distribution)"> | |
129 </param> | |
130 <param name="fragment_length_sd" type="float" value="" optional="true" label="The standard deviation of the fragment length distribution (single-end data only)" help="Default 0, which assumes that all fragments are of the same length, given by the rounded value of fragment length mean. "> | |
131 </param> | |
132 <conditional name="rspd"> | |
133 <param name="estimate" type="select" lanel="Read Start Position Distribution (RSPD)" | |
134 help="Set this option if you want to estimate the read start position distribution (RSPD) from data. Otherwise, RSEM will use a uniform RSPD."> | |
135 <option value="no" selected="true">Use a uniform RSPD</option> | |
136 <option value="yes">Estimate and correct for a non-uniform RSPD</option> | |
137 </param> | |
138 <when value="no"/> | |
139 <when value="yes"> | |
140 <param name="num_rspd_bins" type="integer" value="20" optional="true" label="Number of bins in the RSPD." help="Use of the default setting of 20 is recommended."> | |
141 <validator type="in_range" message="" min="0" max="100"/> | |
142 </param> | |
143 </when> | |
144 </conditional> | |
145 <conditional name="useci"> | |
146 <param name="ci" type="select" label="Calculate 95% Credibility Intervals"> | |
147 <option value="no" selected="true">no</option> | |
148 <option value="yes">yes</option> | |
149 </param> | |
150 <when value="no"/> | |
151 <when value="yes"> | |
152 <param name="cimem" size="4" type="text" value="1024" label="Amount of memory in (MB) for computing CI" /> | |
153 </when> | |
154 </conditional> | |
155 </when> | |
156 </conditional> | |
157 </macro> | |
158 <macro name="bowtie_options"> | |
159 <conditional name="bowtie_options"> | |
160 <param name="fullparams" type="select" label="bowtie settings"> | |
161 <option value="default">use bowtie defaults</option> | |
162 <option value="fullset">set bowtie options</option> | |
163 </param> | |
164 <when value="default"/> | |
165 <when value="fullset"> | |
166 <param name="bowtie_n" type="integer" value="2" optional="true" label="Bowtie mismatches" help="Bowtie parameter max # of mismatches in the seed. (Range: 0-3, Default: 2) "> | |
167 <validator type="in_range" message="max # of mismatches in the seed between 0 and 3" min="0" max="3"/> | |
168 </param> | |
169 <param name="bowtie_e" type="integer" value="99999999" label="Maximum sum of quality scores at mismatched positions in read alignments. This is also the value for the Bowtie -e option"> | |
170 </param> | |
171 <param name="bowtie_m" type="integer" value="200" label="Discard alignments for reads with number of alignments greater than"> | |
172 </param> | |
173 </when> | |
174 </conditional> | |
175 </macro> | |
176 <macro name="sampling_for_bam"> | |
177 <param name="sampling_for_bam" type="boolean" truevalue="--sampling-for-bam" falsevalue="" checked="false" label="Use sampling for BAM"> | |
178 <help> 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) | |
179 </help> | |
180 </param> | |
181 </macro> | |
182 </macros> | |
183 | |
184 <inputs> | |
185 <param name="sample" type="text" value="rsem_sample" label="Sample name" /> | |
186 <conditional name="reference"> | |
187 <param name="refSrc" type="select" label="RSEM Reference Source"> | |
188 <option value="cached">Locally cached</option> | |
189 <option value="history">From your history</option> | |
190 </param> | |
191 <when value="cached"> | |
192 <param name="index" type="select" label="Select RSEM reference" help="Select from a list of pre-indexed references. If you don't see anything consult the wrapper's documentation on how to create or download a reference"> | |
193 <options from_data_table="rsem_indexes"> | |
194 <filter type="sort_by" column="2" /> | |
195 <validator type="no_options" message="No indexes are available" /> | |
196 </options> | |
197 </param> | |
198 </when> | |
199 <when value="history"> | |
200 <param name="rsem_ref" type="data" format="rsem_ref" label="RSEM reference" /> | |
201 </when> | |
202 </conditional> | |
203 <conditional name="input"> | |
204 <param name="format" type="select" label="RSEM Input file type"> | |
205 <option value="fastq">FASTQ</option> | |
206 <option value="fasta">FASTA</option> | |
207 <option value="sam">SAM/BAM</option> | |
208 </param> | |
209 <when value="fastq"> | |
210 <param name="fastq_select" size="15" type="select" label="FASTQ type" > | |
211 <option value="--phred33-quals" selected="true">phred33 qualities (default for sanger)</option> | |
212 <option value="--solexa-quals">solexa qualities</option> | |
213 <option value="--phred64-quals">phred64 qualities</option> | |
214 </param> | |
215 <conditional name="fastq"> | |
216 <param name="matepair" type="select" label="Library type"> | |
217 <option value="single">Single End Reads</option> | |
218 <option value="paired">Paired End Reads</option> | |
219 </param> | |
220 <when value="single"> | |
221 <param name="singlefastq" type="data" format="fastq" label="FASTQ file" /> | |
222 </when> | |
223 <when value="paired"> | |
224 <param name="fastq1" type="data" format="fastq" label="Read 1 fastq file" /> | |
225 <param name="fastq2" type="data" format="fastq" label="Read 2 fastq file" /> | |
226 </when> | |
227 </conditional> | |
228 <expand macro="bowtie_options"/> | |
229 </when> | |
230 <when value="fasta"> | |
231 <conditional name="fasta"> | |
232 <param name="matepair" type="select" label="Library Type"> | |
233 <option value="single">Single End Reads</option> | |
234 <option value="paired">Paired End Reads</option> | |
235 </param> | |
236 <when value="single"> | |
237 <param name="singlefasta" type="data" format="fasta" label="fasta file" /> | |
238 </when> | |
239 <when value="paired"> | |
240 <param name="fasta1" type="data" format="fasta" label="Read 1 fasta file" /> | |
241 <param name="fasta2" type="data" format="fasta" label="Read 2 fasta file" /> | |
242 </when> | |
243 </conditional> | |
244 <expand macro="bowtie_options"/> | |
245 </when> | |
246 <when value="sam"> | |
247 <!-- convert-sam-for-rsem /ref/mouse_125 input.sam -o input_for_rsem.sam --> | |
248 <param name="matepair" type="select" label="Library Type"> | |
249 <option value="single">Single End Reads</option> | |
250 <option value="paired">Paired End Reads</option> | |
251 </param> | |
252 <param name="rsem_sam" type="data" format="rsem_sam" label="RSEM formatted SAM file" /> | |
253 </when> | |
254 </conditional> | |
255 <expand macro="rsem_options"/> | |
256 <conditional name="rsem_outputs"> | |
257 <param name="result_bams" type="select" label="Create bam results files" | |
258 help="In addition to the transcript-coordinate-based BAM file output, also output a BAM file with the read alignments in genomic coordinates" > | |
259 <option value="none">No BAM results files</option> | |
260 <option value="default" selected="true">Transcript BAM results file</option> | |
261 <option value="both">Transcript and genome BAM results files</option> | |
262 </param> | |
263 <when value="none"/> | |
264 <when value="default"> | |
265 <expand macro="sampling_for_bam"/> | |
266 </when> | |
267 <when value="both"> | |
268 <expand macro="sampling_for_bam"/> | |
269 </when> | |
270 </conditional> | |
271 </inputs> | |
272 <stdio> | |
273 <exit_code range="1:" level="fatal" description="Error Running RSEM" /> | |
274 </stdio> | |
275 <outputs> | |
276 <data format="tabular" name="gene_abundances" label="${sample}.gene_abundances" from_work_dir="rsem_output.genes.results"/> | |
277 <data format="tabular" name="isoform_abundances" label="${sample}.isoform_abundances" from_work_dir="rsem_output.isoforms.results"/> | |
278 <data format="bam" name="transcript_bam" label="${sample}.transcript.bam" from_work_dir="rsem_output.transcript.bam" > | |
279 <filter>rsem_outputs['result_bams'] != "none"</filter> | |
280 </data> | |
281 <data format="bam" name="transcript_sorted_bam" label="${sample}.transcript.bam" from_work_dir="rsem_output.transcript.sorted.bam" > | |
282 <filter>rsem_outputs['result_bams'] != "none"</filter> | |
283 </data> | |
284 <data format="bam" name="genome_bam" label="${sample}.genome.bam" from_work_dir="rsem_output.genome.bam"> | |
285 <filter>rsem_outputs['result_bams'] == "both"</filter> | |
286 </data> | |
287 <data format="bam" name="genome_sorted_bam" label="${sample}.genome.sorted.bam" from_work_dir="rsem_output.genome.sorted.bam"> | |
288 <filter>rsem_outputs['result_bams'] == "both"</filter> | |
289 </data> | |
290 <data format="txt" name="log" label="${sample}.rsem_log"/> | |
291 </outputs> | |
292 <tests> | |
293 <test> | |
294 <param name="sample" value="rsem_sample"/> | |
295 <param name="refSrc" value="history"/> | |
2
5949673f9e3e
rename test data RSEM_ref_reference.rsem_ref
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
296 <param name="rsem_ref" value="RSEM_ref_reference.rsem_ref" ftype="rsem_ref"/> |
0 | 297 <param name="format" value="fastq"/> |
298 <param name="matepair" value="single"/> | |
299 <param name="singlefastq" value="test.fastq" ftype="fastqsanger"/> | |
300 <param name="result_bams" value="none"/> | |
301 <output name="gene_abundances"> | |
302 <assert_contents> | |
303 <has_text text="ENST00000423562,ENST00000438504,ENST00000488147,ENST00000538476,ENST00000541675" /> | |
304 </assert_contents> | |
305 </output> | |
306 <output name="isoform_abundances"> | |
307 <assert_contents> | |
308 <has_text text="ENST00000332831" /> | |
309 </assert_contents> | |
310 </output> | |
311 <output name="log"> | |
312 <assert_contents> | |
313 <has_text text="Expression Results are written" /> | |
314 </assert_contents> | |
315 </output> | |
316 </test> | |
317 </tests> | |
318 <help> | |
319 | |
320 | |
321 RSEM HOME PAGE - http://deweylab.biostat.wisc.edu/rsem/ | |
322 | |
323 NAME | |
324 rsem-calculate-expression | |
325 | |
326 SYNOPSIS | |
327 rsem-calculate-expression [options] upstream_read_file(s) reference_name sample_name | |
328 rsem-calculate-expression [options] --paired-end upstream_read_file/s downstream_read_file/s reference_name sample_name | |
329 rsem-calculate-expression [options] --sam/--bam [--paired-end] input reference_name sample_name | |
330 | |
331 ARGUMENTS | |
332 upstream_read_files/s | |
333 Comma-separated list of files containing single-end reads or | |
334 upstream reads for paired-end data. By default, these files are | |
335 assumed to be in FASTQ format. If the --no-qualities option is | |
336 specified, then FASTA format is expected. | |
337 | |
338 downstream_read_file/s | |
339 Comma-separated list of files containing downstream reads which are | |
340 paired with the upstream reads. By default, these files are assumed | |
341 to be in FASTQ format. If the --no-qualities option is specified, | |
342 then FASTA format is expected. | |
343 | |
344 input | |
345 SAM/BAM formatted input file. If "-" is specified for the filename, | |
346 SAM/BAM input is instead assumed to come from standard input. RSEM | |
347 requires all alignments of the same read group together. For | |
348 paired-end reads, RSEM also requires the two mates of any alignment | |
349 be adjacent. See Description section for how to make input file obey | |
350 RSEM's requirements. | |
351 | |
352 reference_name | |
353 The name of the reference used. The user must have run | |
354 'rsem-prepare-reference' with this reference_name before running | |
355 this program. | |
356 | |
357 sample_name | |
358 The name of the sample analyzed. All output files are prefixed by | |
359 this name (e.g., sample_name.genes.results) | |
360 | |
361 OPTIONS | |
362 | |
363 --paired-end | |
364 Input reads are paired-end reads. (Default: off) | |
365 | |
366 --no-qualities | |
367 Input reads do not contain quality scores. (Default: off) | |
368 | |
369 --strand-specific | |
370 The RNA-Seq protocol used to generate the reads is strand specific, | |
371 i.e., all (upstream) reads are derived from the forward strand. This | |
372 option is equivalent to --forward-prob=1.0. With this option set, if | |
373 RSEM runs the Bowtie aligner, the '--norc' Bowtie option will be | |
374 used, which disables alignment to the reverse strand of transcripts. | |
375 (Default: off) | |
376 | |
377 --sam | |
378 Input file is in SAM format. (Default: off) | |
379 | |
380 --bam | |
381 Input file is in BAM format. (Default: off) | |
382 | |
383 --sam-header-info [file] | |
384 RSEM reads header information from input by default. If this option | |
385 is on, header information is read from the specified file. For the | |
386 format of the file, please see SAM official website. (Default: "") | |
387 | |
388 -p/--num-threads [int] | |
389 Number of threads to use. Both Bowtie and expression estimation will | |
390 use this many threads. (Default: 1) | |
391 | |
392 --no-bam-output | |
393 Do not output any BAM file. (Default: off) | |
394 | |
395 --output-genome-bam | |
396 Generate a BAM file, 'sample_name.genome.bam', with alignments | |
397 mapped to genomic coordinates and annotated with their posterior | |
398 probabilities. In addition, RSEM will call samtools (included in | |
399 RSEM package) to sort and index the bam file. | |
400 'sample_name.genome.sorted.bam' and | |
401 'sample_name.genome.sorted.bam.bai' will be generated. (Default: | |
402 off) | |
403 | |
404 --sampling-for-bam | |
405 When RSEM generates a BAM file, instead of outputing all alignments | |
406 a read has with their posterior probabilities, one alignment is | |
407 sampled and outputed according to the posterior probabilities. If | |
408 the sampling result is that the read comes from the "noise" | |
409 transcript, nothing is outputed. (Default: off) | |
410 | |
411 --calc-ci | |
412 Calculate 95% credibility intervals and posterior mean estimates. | |
413 (Default: off) | |
414 | |
415 --seed-length [int] | |
416 Seed length used by the read aligner. Providing the correct value is | |
417 important for RSEM. If RSEM runs Bowtie, it uses this value for | |
418 Bowtie's seed length parameter. Any read with its or at least one of | |
419 its mates' (for paired-end reads) length less than this value will | |
420 be ignored. If the references are not added poly(A) tails, the | |
421 minimum allowed value is 5, otherwise, the minimum allowed value is | |
422 25. Note that this script will only check if the value less or equal than | |
423 5 and give a warning message if the value less than 25 but greter or equal than | |
424 5. (Default: 25) | |
425 | |
426 --tag [string] | |
427 The name of the optional field used in the SAM input for identifying | |
428 a read with too many valid alignments. The field should have the | |
429 format [tagName]:i:[value], where a [value] bigger than 0 indicates | |
430 a read with too many alignments. (Default: "") | |
431 | |
432 --bowtie-path [path] | |
433 The path to the bowtie executables. (Default: the path to the bowtie | |
434 executables is assumed to be in the user's PATH environment | |
435 variable) | |
436 | |
437 --bowtie-n [int] | |
438 (Bowtie parameter) max # of mismatches in the seed. (Range: 0-3, | |
439 Default: 2) | |
440 | |
441 --bowtie-e [int] | |
442 (Bowtie parameter) max sum of mismatch quality scores across the | |
443 alignment. (Default: 99999999) | |
444 | |
445 --bowtie-m [int] | |
446 (Bowtie parameter) suppress all alignments for a read if greater then [int] | |
447 valid alignments exist. (Default: 200) | |
448 | |
449 --bowtie-chunkmbs [int] | |
450 (Bowtie parameter) memory allocated for best first alignment | |
451 calculation (Default: 0 - use bowtie's default) | |
452 | |
453 --phred33-quals | |
454 Input quality scores are encoded as Phred+33. (Default: on) | |
455 | |
456 --phred64-quals | |
457 Input quality scores are encoded as Phred+64 (default for GA | |
458 Pipeline ver. less than 1.3). (Default: off) | |
459 | |
460 --solexa-quals | |
461 Input quality scores are solexa encoded (from GA Pipeline ver. less | |
462 than 1.3). (Default: off) | |
463 | |
464 --forward-prob [double] | |
465 Probability of generating a read from the forward strand of a | |
466 transcript. Set to 1 for a strand-specific protocol where all | |
467 (upstream) reads are derived from the forward strand, 0 for a | |
468 strand-specific protocol where all (upstream) read are derived from | |
469 the reverse strand, or 0.5 for a non-strand-specific protocol. | |
470 (Default: 0.5) | |
471 | |
472 --fragment-length-min [int] | |
473 Minimum read/insert length allowed. This is also the value for the | |
474 bowtie -I option. (Default: 1) | |
475 | |
476 --fragment-length-max [int] | |
477 Maximum read/insert length allowed. This is also the value for the | |
478 bowtie -X option. (Default: 1000) | |
479 | |
480 --fragment-length-mean [double] | |
481 (single-end data only) The mean of the fragment length distribution, | |
482 which is assumed to be a Gaussian. (Default: -1, which disables use | |
483 of the fragment length distribution) | |
484 | |
485 --fragment-length-sd [double] | |
486 (single-end data only) The standard deviation of the fragment length | |
487 distribution, which is assumed to be a Gaussian. (Default: 0, which | |
488 assumes that all fragments are of the same length, given by the | |
489 rounded value of --fragment-length-mean) | |
490 | |
491 --estimate-rspd | |
492 Set this option if you want to estimate the read start position | |
493 distribution (RSPD) from data. Otherwise, RSEM will use a uniform | |
494 RSPD. (Default: off) | |
495 | |
496 --num-rspd-bins [int] | |
497 Number of bins in the RSPD. Only relevant when '--estimate-rspd' is | |
498 specified. Use of the default setting is recommended. (Default: 20) | |
499 | |
500 --ci-memory [int] | |
501 Maximum size (in memory, MB) of the auxiliary buffer used for | |
502 computing credibility intervals (CI). Set it larger for a faster CI | |
503 calculation. However, leaving 2 GB memory free for other usage is | |
504 recommended. (Default: 1024) | |
505 | |
506 --keep-intermediate-files | |
507 Keep temporary files generated by RSEM. RSEM creates a temporary | |
508 directory, 'sample_name.temp', into which it puts all intermediate | |
509 output files. If this directory already exists, RSEM overwrites all | |
510 files generated by previous RSEM runs inside of it. By default, | |
511 after RSEM finishes, the temporary directory is deleted. Set this | |
512 option to prevent the deletion of this directory and the | |
513 intermediate files inside of it. (Default: off) | |
514 | |
515 --time | |
516 Output time consumed by each step of RSEM to 'sample_name.time'. | |
517 (Default: off) | |
518 | |
519 -q/--quiet | |
520 Suppress the output of logging information. (Default: off) | |
521 | |
522 -h/--help | |
523 Show help information. | |
524 | |
525 DESCRIPTION | |
526 In its default mode, this program aligns input reads against a reference | |
527 transcriptome with Bowtie and calculates expression values using the | |
528 alignments. RSEM assumes the data are single-end reads with quality | |
529 scores, unless the '--paired-end' or '--no-qualities' options are | |
530 specified. Users may use an alternative aligner by specifying one of the | |
531 --sam and --bam options, and providing an alignment file in the | |
532 specified format. However, users should make sure that they align | |
533 against the indices generated by 'rsem-prepare-reference' and the | |
534 alignment file satisfies the requirements mentioned in ARGUMENTS | |
535 section. | |
536 | |
537 One simple way to make the alignment file satisfying RSEM's requirements | |
538 (assuming the aligner used put mates in a paired-end read adjacent) is | |
539 to use 'convert-sam-for-rsem' script. This script only accept SAM format | |
540 files as input. If a BAM format file is obtained, please use samtools to | |
541 convert it to a SAM file first. For example, if '/ref/mouse_125' is the | |
542 'reference_name' and the SAM file is named 'input.sam', you can run the | |
543 following command: | |
544 | |
545 convert-sam-for-rsem /ref/mouse_125 input.sam -o input_for_rsem.sam | |
546 | |
547 For details, please refer to 'convert-sam-for-rsem's documentation page. | |
548 | |
549 The SAM/BAM format RSEM uses is v1.4. However, it is compatible with old | |
550 SAM/BAM format. However, RSEM cannot recognize 0x100 in the FLAG field. | |
551 In addition, RSEM requires SEQ and QUAL are not '*'. | |
552 | |
553 The user must run 'rsem-prepare-reference' with the appropriate | |
554 reference before using this program. | |
555 | |
556 For single-end data, it is strongly recommended that the user provide | |
557 the fragment length distribution parameters (--fragment-length-mean and | |
558 --fragment-length-sd). For paired-end data, RSEM will automatically | |
559 learn a fragment length distribution from the data. | |
560 | |
561 Please note that some of the default values for the Bowtie parameters | |
562 are not the same as those defined for Bowtie itself. | |
563 | |
564 The temporary directory and all intermediate files will be removed when | |
565 RSEM finishes unless '--keep-intermediate-files' is specified. | |
566 | |
567 With the '--calc-ci' option, 95% credibility intervals and posterior | |
568 mean estimates will be calculated in addition to maximum likelihood | |
569 estimates. | |
570 | |
571 OUTPUT | |
572 sample_name.genes.results | |
573 File containing gene level expression estimates. The format of each | |
574 line in this file is: | |
575 | |
576 gene_id expected_counts tau_value [pmc_value tau_pme_value | |
577 tau_ci_lower_bound tau_ci_upper_bound] transcript_id_list | |
578 | |
579 Fields are separated by the tab character. Fields within "[]" are | |
580 only presented if '--calc-ci' is set. pme stands for posterior mean | |
581 estimation. pmc stands for posterior mean counts. ci_lower_bound(l) | |
582 means the lower bound of the credibility intervals, | |
583 ci_upper_bound(u) means the upper bound of the credibility | |
584 intervals. So the credibility interval is [l, u]. | |
585 'transcript_id_list' is a space-separated list of transcript_ids | |
586 belonging to the gene. If no gene information is provided, this file | |
587 has the same content as 'sample_name.isoforms.results'. | |
588 | |
589 sample_name.isoforms.results | |
590 File containing isoform level expression values. The format of each | |
591 line in this file is: | |
592 | |
593 transcript_id expected_counts tau_value [pmc_value tau_pme_value | |
594 tau_ci_lower_bound tau_ci_upper_bound] gene_id | |
595 | |
596 Fields are separated by the tab character. 'gene_id' is the gene_id | |
597 of the gene which this transcript belongs to. If no gene information | |
598 is provided, 'gene_id' and 'transcript_id' are the same. | |
599 | |
600 sample_name.transcript.bam, sample_name.transcript.sorted.bam and | |
601 sample_name.transcript.sorted.bam.bai | |
602 Only generated when --no-bam-output is not specified. | |
603 | |
604 'sample_name.transcript.bam' is a BAM-formatted file of read | |
605 alignments in transcript coordinates. The MAPQ field of each | |
606 alignment is set to min(100, floor(-10 * log10(1.0 - w) + 0.5)), | |
607 where w is the posterior probability of that alignment being the | |
608 true mapping of a read. In addition, RSEM pads a new tag ZW:f:value, | |
609 where value is a single precision floating number representing the | |
610 posterior probability. | |
611 | |
612 'sample_name.transcript.sorted.bam' and | |
613 'sample_name.transcript.sorted.bam.bai' are the sorted BAM file and | |
614 indices generated by samtools (included in RSEM package). | |
615 | |
616 sample_name.genome.bam, sample_name.genome.sorted.bam and | |
617 sample_name.genome.sorted.bam.bai | |
618 Only generated when --no-bam-output is not specified and | |
619 --output-genome-bam is specified. | |
620 | |
621 'sample_name.genome.bam' is a BAM-formatted file of read alignments | |
622 in genomic coordinates. Alignments of reads that have identical | |
623 genomic coordinates (i.e., alignments to different isoforms that | |
624 share the same genomic region) are collapsed into one alignment. The | |
625 MAPQ field of each alignment is set to min(100, floor(-10 * | |
626 log10(1.0 - w) + 0.5)), where w is the posterior probability of that | |
627 alignment being the true mapping of a read. In addition, RSEM pads a | |
628 new tag ZW:f:value, where value is a single precision floating | |
629 number representing the posterior probability. If an alignment is | |
630 spliced, a XS:A:value tag is also added, where value is either '+' | |
631 or '-' indicating the strand of the transcript it aligns to. | |
632 | |
633 'sample_name.genome.sorted.bam' and | |
634 'sample_name.genome.sorted.bam.bai' are the sorted BAM file and | |
635 indices generated by samtools (included in RSEM package). | |
636 | |
637 sample_name.sam.gz | |
638 Only generated when the input files are raw reads instead of SAM/BAM | |
639 format files | |
640 | |
641 It is the gzipped SAM output produced by bowtie aligner. | |
642 | |
643 sample_name.time | |
644 Only generated when --time is specified. | |
645 | |
646 It contains time (in seconds) consumed by aligning reads, estimating | |
647 expression levels and calculating credibility intervals. | |
648 | |
649 sample_name.stat | |
650 This is a folder instead of a file. All model related statistics are | |
651 stored in this folder. Use 'rsem-plot-model' can generate plots | |
652 using this folder. | |
653 | |
654 EXAMPLES | |
655 Assume the path to the bowtie executables is in the user's PATH | |
656 environment variable. Reference files are under '/ref' with name | |
657 'mouse_125'. | |
658 | |
659 1) '/data/mmliver.fq', single-end reads with quality scores. Quality | |
660 scores are encoded as for 'GA pipeline version >= 1.3'. We want to use 8 | |
661 threads and generate a genome BAM file: | |
662 | |
663 rsem-calculate-expression --phred64-quals \ | |
664 -p 8 \ | |
665 --output-genome-bam \ | |
666 /data/mmliver.fq \ | |
667 /ref/mouse_125 \ | |
668 mmliver_single_quals | |
669 | |
670 2) '/data/mmliver_1.fq' and '/data/mmliver_2.fq', paired-end reads with | |
671 quality scores. Quality scores are in SANGER format. We want to use 8 | |
672 threads and do not generate a genome BAM file: | |
673 | |
674 rsem-calculate-expression -p 8 \ | |
675 --paired-end \ | |
676 /data/mmliver_1.fq \ | |
677 /data/mmliver_2.fq \ | |
678 /ref/mouse_125 \ | |
679 mmliver_paired_end_quals | |
680 | |
681 3) '/data/mmliver.fa', single-end reads without quality scores. We want | |
682 to use 8 threads: | |
683 | |
684 rsem-calculate-expression -p 8 \ | |
685 --no-qualities \ | |
686 /data/mmliver.fa \ | |
687 /ref/mouse_125 \ | |
688 mmliver_single_without_quals | |
689 | |
690 4) Data are the same as 1). We want to take a fragment length | |
691 distribution into consideration. We set the fragment length mean to 150 | |
692 and the standard deviation to 35. In addition to a BAM file, we also | |
693 want to generate credibility intervals. We allow RSEM to use 1GB of | |
694 memory for CI calculation: | |
695 | |
696 rsem-calculate-expression --bowtie-path /sw/bowtie \ | |
697 --phred64-quals \ | |
698 --fragment-length-mean 150.0 \ | |
699 --fragment-length-sd 35.0 \ | |
700 -p 8 \ | |
701 --output-genome-bam \ | |
702 --calc-ci \ | |
703 --ci-memory 1024 \ | |
704 /data/mmliver.fq \ | |
705 /ref/mouse_125 \ | |
706 mmliver_single_quals | |
707 | |
708 5) '/data/mmliver_paired_end_quals.bam', paired-end reads with quality | |
709 scores. We want to use 8 threads: | |
710 | |
711 rsem-calculate-expression --paired-end \ | |
712 --bam \ | |
713 -p 8 \ | |
714 /data/mmliver_paired_end_quals.bam \ | |
715 /ref/mouse_125 \ | |
716 mmliver_paired_end_quals | |
717 </help> | |
718 </tool> |