|
1
|
1 <tool id="rsem_calculate_expression" name="RSEM calculate expression" version="EBA2016-v1">
|
|
0
|
2 <description>RNA-Seq by Expectation-Maximization</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="1.2.28">rsem</requirement>
|
|
|
5 <requirement type="package" version="1.1.2">bowtie</requirement>
|
|
|
6 <requirement type="package" version="2.2.6">bowtie2</requirement>
|
|
|
7 </requirements>
|
|
|
8 <command>
|
|
|
9 rsem-calculate-expression
|
|
|
10 ## --tag string
|
|
|
11 #if $seedlength:
|
|
|
12 --seed-length $seedlength
|
|
|
13 #end if
|
|
|
14 --forward-prob $forward_prob
|
|
|
15 #if $rsem_options.fullparams == 'fullset':
|
|
|
16 ## Fragment info
|
|
|
17 #if $rsem_options.fragment_length_mean:
|
|
|
18 --fragment-length-mean $rsem_options.fragment_length_mean
|
|
|
19 #end if
|
|
|
20 #if $rsem_options.fragment_length_min:
|
|
|
21 --fragment-length-min $rsem_options.fragment_length_min
|
|
|
22 #end if
|
|
|
23 #if $rsem_options.fragment_length_sd:
|
|
|
24 --fragment-length-sd $rsem_options.fragment_length_sd
|
|
|
25 #end if
|
|
|
26 #if $rsem_options.fragment_length_max:
|
|
|
27 --fragment-length-max $rsem_options.fragment_length_max
|
|
|
28 #end if
|
|
|
29 ## RSPD
|
|
|
30 #if $rsem_options.rspd.estimate == 'yes':
|
|
|
31 --estimate-rspd
|
|
|
32 #if $rsem_options.rspd.num_rspd_bins:
|
|
|
33 --num-rspd-bins $rsem_options.rspd.num_rspd_bins
|
|
|
34 #end if
|
|
|
35 #end if
|
|
|
36 ## Calculate 95% credibility intervals and posterior mean estimates.
|
|
1
|
37 #if $rsem_options.ci == 'yes':
|
|
0
|
38 --calc-ci
|
|
1
|
39 --ci-memory 2048
|
|
0
|
40 #end if
|
|
|
41 #end if
|
|
1
|
42 ## Calculate PME
|
|
|
43 $rsem_options.pme
|
|
|
44 --num-threads \${GALAXY_SLOTS:-4}
|
|
|
45 #if str($input.usebowtie.bowtie) == "one":
|
|
|
46 #if $input.format != 'bam' and $input.usebowtie.bowtie_options.fullparams == 'fullset':
|
|
0
|
47 ## Bowtie params
|
|
1
|
48 #if $input.usebowtie.bowtie_options.bowtie_e:
|
|
|
49 --bowtie-e $input.usebowtie.bowtie_options.bowtie_e
|
|
0
|
50 #end if
|
|
1
|
51 #if $input.usebowtie.bowtie_options.bowtie_m:
|
|
|
52 --bowtie-m $input.usebowtie.bowtie_options.bowtie_m
|
|
|
53 #end if
|
|
|
54 #if $input.usebowtie.bowtie_options.bowtie_n:
|
|
|
55 --bowtie-n $input.usebowtie.bowtie_options.bowtie_n
|
|
0
|
56 #end if
|
|
1
|
57 #end if
|
|
|
58
|
|
|
59 #elif str($input.usebowtie.bowtie) == "two":
|
|
|
60 --bowtie2
|
|
0
|
61 #end if
|
|
1
|
62
|
|
0
|
63 ## Outputs
|
|
|
64 #if $rsem_outputs.result_bams == 'none':
|
|
|
65 --no-bam-output
|
|
|
66 #else
|
|
|
67 #if $rsem_outputs.result_bams == 'both':
|
|
|
68 --output-genome-bam
|
|
|
69 #end if
|
|
|
70 $rsem_outputs.sampling_for_bam
|
|
|
71 #end if
|
|
|
72 ## Input data
|
|
|
73 #if $input.format=="fastq"
|
|
|
74 $input.fastq_select
|
|
|
75 #if $input.fastq.matepair=="single":
|
|
|
76 $input.fastq.singlefastq
|
|
|
77 #elif $input.fastq.matepair=="paired":
|
|
|
78 --paired-end
|
|
|
79 $input.fastq.fastq1
|
|
|
80 $input.fastq.fastq2
|
|
|
81 #end if
|
|
|
82 #elif $input.format=="fasta"
|
|
|
83 --no-qualities
|
|
|
84 #if $input.fasta.matepair=="single":
|
|
|
85 $input.fasta.singlefasta
|
|
|
86 #elif $input.fasta.matepair=="paired":
|
|
|
87 --paired-end
|
|
|
88 $input.fasta.fasta1
|
|
|
89 $input.fasta.fasta2
|
|
|
90 #end if
|
|
|
91 #elif $input.format=="sam"
|
|
|
92 #if $input.matepair=="paired":
|
|
|
93 --paired-end
|
|
|
94 #end if
|
|
|
95 #if $input.rsem_sam._extension == 'sam':
|
|
|
96 --sam
|
|
|
97 #elif $input.rsem_sam._extension == 'bam':
|
|
|
98 --bam
|
|
|
99 #end if
|
|
|
100 $input.rsem_sam
|
|
|
101 #end if
|
|
|
102 ## RSEM reference
|
|
|
103 #if $reference.refSrc == 'history':
|
|
|
104 ${reference.rsem_ref.extra_files_path}/${reference.rsem_ref.metadata.reference_name}
|
|
|
105 #elif $reference.refSrc == 'cached':
|
|
|
106 ${reference.index.fields.path}
|
|
|
107 #end if
|
|
|
108 ## sample_name: use a hard coded name so we can pull out galaxy outputs
|
|
|
109 rsem_output
|
|
|
110 ## direct output into logfile
|
|
|
111 > $log
|
|
|
112 </command>
|
|
|
113 <macros>
|
|
|
114 <macro name="rsem_options">
|
|
|
115 <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)">
|
|
|
116 </param>
|
|
|
117 <param name="forward_prob" type="select" label="Is the library strand specific?">
|
|
|
118 <option value="0.5" selected="true">No</option>
|
|
|
119 <option value="1">Yes, the reads (or first reads from paired-end libraries) are only in the forward orientation</option>
|
|
|
120 <option value="0">Yes, the reads (or first reads from paired-end libraries) are only in the reverse orientation</option>
|
|
|
121 </param>
|
|
|
122 <conditional name="rsem_options">
|
|
|
123 <param name="fullparams" type="select" label="Additional RSEM options">
|
|
|
124 <option value="default">Use RSEM Defaults</option>
|
|
|
125 <option value="fullset">Set Additional RSEM Options</option>
|
|
|
126 </param>
|
|
|
127 <when value="default"/>
|
|
|
128 <when value="fullset">
|
|
|
129 <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">
|
|
|
130 <validator type="in_range" message="0 or greater" min="0" />
|
|
|
131 </param>
|
|
|
132 <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">
|
|
|
133 <validator type="in_range" message="0 or greater" min="0" max="1000000"/>
|
|
|
134 </param>
|
|
|
135 <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)">
|
|
|
136 </param>
|
|
|
137 <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. ">
|
|
|
138 </param>
|
|
|
139 <conditional name="rspd">
|
|
|
140 <param name="estimate" type="select" lanel="Read Start Position Distribution (RSPD)"
|
|
|
141 help="Set this option if you want to estimate the read start position distribution (RSPD) from data. Otherwise, RSEM will use a uniform RSPD.">
|
|
|
142 <option value="no" selected="true">Use a uniform RSPD</option>
|
|
|
143 <option value="yes">Estimate and correct for a non-uniform RSPD</option>
|
|
|
144 </param>
|
|
|
145 <when value="no"/>
|
|
|
146 <when value="yes">
|
|
|
147 <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.">
|
|
|
148 <validator type="in_range" message="" min="0" max="100"/>
|
|
|
149 </param>
|
|
|
150 </when>
|
|
|
151 </conditional>
|
|
|
152 <param name="ci" type="select" label="Calculate 95% Credibility Intervals">
|
|
|
153 <option value="no" selected="true">no</option>
|
|
|
154 <option value="yes">yes</option>
|
|
|
155 </param>
|
|
1
|
156
|
|
|
157 <param name="pme" type="boolean" truevalue="--calc-pme" falsevalue="" label="Calculate posterior mean estimates ? (collapsed Gibbs sampler)" />
|
|
0
|
158 </when>
|
|
|
159 </conditional>
|
|
|
160 </macro>
|
|
|
161 <macro name="bowtie_options">
|
|
1
|
162 <conditional name="usebowtie">
|
|
|
163 <param name="bowtie" type="select" label="Use bowtie 1 or 2 ?">
|
|
|
164 <option value="one" selected="true">Bowtie 1</option>
|
|
|
165 <option value="two">Bowtie 2</option>
|
|
|
166 </param>
|
|
|
167 <when value="one">
|
|
|
168 <conditional name="bowtie_options">
|
|
0
|
169 <param name="fullparams" type="select" label="bowtie settings">
|
|
|
170 <option value="default">use bowtie defaults</option>
|
|
|
171 <option value="fullset">set bowtie options</option>
|
|
|
172 </param>
|
|
|
173 <when value="default"/>
|
|
|
174 <when value="fullset">
|
|
|
175 <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) ">
|
|
|
176 <validator type="in_range" message="max # of mismatches in the seed between 0 and 3" min="0" max="3"/>
|
|
|
177 </param>
|
|
|
178 <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">
|
|
|
179 </param>
|
|
|
180 <param name="bowtie_m" type="integer" value="200" label="Discard alignments for reads with number of alignments greater than">
|
|
|
181 </param>
|
|
|
182 </when>
|
|
|
183 </conditional>
|
|
1
|
184 </when>
|
|
|
185 <when value="two" />
|
|
|
186 </conditional>
|
|
0
|
187 </macro>
|
|
|
188 <macro name="sampling_for_bam">
|
|
|
189 <param name="sampling_for_bam" type="boolean" truevalue="--sampling-for-bam" falsevalue="" checked="false" label="Use sampling for BAM">
|
|
|
190 <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)
|
|
|
191 </help>
|
|
|
192 </param>
|
|
|
193 </macro>
|
|
|
194 </macros>
|
|
|
195
|
|
|
196 <inputs>
|
|
|
197 <param name="sample" type="text" value="rsem_sample" label="Sample name" />
|
|
|
198 <conditional name="reference">
|
|
|
199 <param name="refSrc" type="select" label="RSEM Reference Source">
|
|
|
200 <option value="cached">Locally cached</option>
|
|
|
201 <option value="history">From your history</option>
|
|
|
202 </param>
|
|
|
203 <when value="cached">
|
|
|
204 <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">
|
|
|
205 <options from_data_table="rsem_indexes">
|
|
|
206 <filter type="sort_by" column="2" />
|
|
|
207 <validator type="no_options" message="No indexes are available" />
|
|
|
208 </options>
|
|
|
209 </param>
|
|
|
210 </when>
|
|
|
211 <when value="history">
|
|
|
212 <param name="rsem_ref" type="data" format="rsem_ref" label="RSEM reference" />
|
|
|
213 </when>
|
|
|
214 </conditional>
|
|
|
215 <conditional name="input">
|
|
|
216 <param name="format" type="select" label="RSEM Input file type">
|
|
|
217 <option value="fastq">FASTQ</option>
|
|
|
218 <option value="fasta">FASTA</option>
|
|
|
219 <option value="sam">SAM/BAM</option>
|
|
|
220 </param>
|
|
|
221 <when value="fastq">
|
|
|
222 <param name="fastq_select" size="15" type="select" label="FASTQ type" >
|
|
|
223 <option value="--phred33-quals" selected="true">phred33 qualities (default for sanger)</option>
|
|
|
224 <option value="--solexa-quals">solexa qualities</option>
|
|
|
225 <option value="--phred64-quals">phred64 qualities</option>
|
|
|
226 </param>
|
|
|
227 <conditional name="fastq">
|
|
|
228 <param name="matepair" type="select" label="Library type">
|
|
|
229 <option value="single">Single End Reads</option>
|
|
|
230 <option value="paired">Paired End Reads</option>
|
|
|
231 </param>
|
|
|
232 <when value="single">
|
|
|
233 <param name="singlefastq" type="data" format="fastq" label="FASTQ file" />
|
|
|
234 </when>
|
|
|
235 <when value="paired">
|
|
|
236 <param name="fastq1" type="data" format="fastq" label="Read 1 fastq file" />
|
|
|
237 <param name="fastq2" type="data" format="fastq" label="Read 2 fastq file" />
|
|
|
238 </when>
|
|
|
239 </conditional>
|
|
|
240 <expand macro="bowtie_options"/>
|
|
|
241 </when>
|
|
|
242 <when value="fasta">
|
|
|
243 <conditional name="fasta">
|
|
|
244 <param name="matepair" type="select" label="Library Type">
|
|
|
245 <option value="single">Single End Reads</option>
|
|
|
246 <option value="paired">Paired End Reads</option>
|
|
|
247 </param>
|
|
|
248 <when value="single">
|
|
|
249 <param name="singlefasta" type="data" format="fasta" label="fasta file" />
|
|
|
250 </when>
|
|
|
251 <when value="paired">
|
|
|
252 <param name="fasta1" type="data" format="fasta" label="Read 1 fasta file" />
|
|
|
253 <param name="fasta2" type="data" format="fasta" label="Read 2 fasta file" />
|
|
|
254 </when>
|
|
|
255 </conditional>
|
|
|
256 <expand macro="bowtie_options"/>
|
|
|
257 </when>
|
|
|
258 <when value="sam">
|
|
|
259 <!-- convert-sam-for-rsem /ref/mouse_125 input.sam -o input_for_rsem.sam -->
|
|
|
260 <param name="matepair" type="select" label="Library Type">
|
|
|
261 <option value="single">Single End Reads</option>
|
|
|
262 <option value="paired">Paired End Reads</option>
|
|
|
263 </param>
|
|
|
264 <param name="rsem_sam" type="data" format="rsem_sam" label="RSEM formatted SAM file" />
|
|
|
265 </when>
|
|
|
266 </conditional>
|
|
|
267 <expand macro="rsem_options"/>
|
|
|
268 <conditional name="rsem_outputs">
|
|
|
269 <param name="result_bams" type="select" label="Create bam results files"
|
|
|
270 help="In addition to the transcript-coordinate-based BAM file output, also output a BAM file with the read alignments in genomic coordinates" >
|
|
|
271 <option value="none">No BAM results files</option>
|
|
|
272 <option value="default" selected="true">Transcript BAM results file</option>
|
|
|
273 <option value="both">Transcript and genome BAM results files</option>
|
|
|
274 </param>
|
|
|
275 <when value="none"/>
|
|
|
276 <when value="default">
|
|
|
277 <expand macro="sampling_for_bam"/>
|
|
|
278 </when>
|
|
|
279 <when value="both">
|
|
|
280 <expand macro="sampling_for_bam"/>
|
|
|
281 </when>
|
|
|
282 </conditional>
|
|
|
283 </inputs>
|
|
|
284 <stdio>
|
|
|
285 <exit_code range="1:" level="fatal" description="Error Running RSEM" />
|
|
|
286 </stdio>
|
|
|
287 <outputs>
|
|
|
288 <data format="tabular" name="gene_abundances" label="${sample}.gene_abundances" from_work_dir="rsem_output.genes.results"/>
|
|
|
289 <data format="tabular" name="isoform_abundances" label="${sample}.isoform_abundances" from_work_dir="rsem_output.isoforms.results"/>
|
|
|
290 <data format="bam" name="transcript_bam" label="${sample}.transcript.bam" from_work_dir="rsem_output.transcript.bam" >
|
|
|
291 <filter>rsem_outputs['result_bams'] != "none"</filter>
|
|
|
292 </data>
|
|
|
293 <data format="bam" name="transcript_sorted_bam" label="${sample}.transcript.bam" from_work_dir="rsem_output.transcript.sorted.bam" >
|
|
|
294 <filter>rsem_outputs['result_bams'] != "none"</filter>
|
|
|
295 </data>
|
|
|
296 <data format="bam" name="genome_bam" label="${sample}.genome.bam" from_work_dir="rsem_output.genome.bam">
|
|
|
297 <filter>rsem_outputs['result_bams'] == "both"</filter>
|
|
|
298 </data>
|
|
|
299 <data format="bam" name="genome_sorted_bam" label="${sample}.genome.sorted.bam" from_work_dir="rsem_output.genome.sorted.bam">
|
|
|
300 <filter>rsem_outputs['result_bams'] == "both"</filter>
|
|
|
301 </data>
|
|
|
302 <data format="txt" name="log" label="${sample}.rsem_log"/>
|
|
|
303 </outputs>
|
|
|
304 <tests>
|
|
|
305 <test>
|
|
|
306 <param name="sample" value="rsem_sample"/>
|
|
|
307 <param name="refSrc" value="history"/>
|
|
|
308 <param name="rsem_ref" value="RSEM_ref_reference.rsem_ref" ftype="rsem_ref"/>
|
|
|
309 <param name="format" value="fastq"/>
|
|
|
310 <param name="matepair" value="single"/>
|
|
|
311 <param name="singlefastq" value="test.fastq" ftype="fastqsanger"/>
|
|
|
312 <param name="result_bams" value="none"/>
|
|
|
313 <output name="gene_abundances">
|
|
|
314 <assert_contents>
|
|
|
315 <has_text text="ENST00000423562,ENST00000438504,ENST00000488147,ENST00000538476,ENST00000541675" />
|
|
|
316 </assert_contents>
|
|
|
317 </output>
|
|
|
318 <output name="isoform_abundances">
|
|
|
319 <assert_contents>
|
|
|
320 <has_text text="ENST00000332831" />
|
|
|
321 </assert_contents>
|
|
|
322 </output>
|
|
|
323 <output name="log">
|
|
|
324 <assert_contents>
|
|
|
325 <has_text text="Expression Results are written" />
|
|
|
326 </assert_contents>
|
|
|
327 </output>
|
|
|
328 </test>
|
|
|
329 </tests>
|
|
|
330 <help>
|
|
|
331
|
|
|
332
|
|
|
333 RSEM HOME PAGE - http://deweylab.biostat.wisc.edu/rsem/
|
|
|
334
|
|
|
335 NAME
|
|
|
336 rsem-calculate-expression
|
|
|
337
|
|
|
338 SYNOPSIS
|
|
|
339 rsem-calculate-expression [options] upstream_read_file(s) reference_name sample_name
|
|
|
340 rsem-calculate-expression [options] --paired-end upstream_read_file/s downstream_read_file/s reference_name sample_name
|
|
|
341 rsem-calculate-expression [options] --sam/--bam [--paired-end] input reference_name sample_name
|
|
|
342
|
|
|
343 ARGUMENTS
|
|
|
344 upstream_read_files/s
|
|
|
345 Comma-separated list of files containing single-end reads or
|
|
|
346 upstream reads for paired-end data. By default, these files are
|
|
|
347 assumed to be in FASTQ format. If the --no-qualities option is
|
|
|
348 specified, then FASTA format is expected.
|
|
|
349
|
|
|
350 downstream_read_file/s
|
|
|
351 Comma-separated list of files containing downstream reads which are
|
|
|
352 paired with the upstream reads. By default, these files are assumed
|
|
|
353 to be in FASTQ format. If the --no-qualities option is specified,
|
|
|
354 then FASTA format is expected.
|
|
|
355
|
|
|
356 input
|
|
|
357 SAM/BAM formatted input file. If "-" is specified for the filename,
|
|
|
358 SAM/BAM input is instead assumed to come from standard input. RSEM
|
|
|
359 requires all alignments of the same read group together. For
|
|
|
360 paired-end reads, RSEM also requires the two mates of any alignment
|
|
|
361 be adjacent. See Description section for how to make input file obey
|
|
|
362 RSEM's requirements.
|
|
|
363
|
|
|
364 reference_name
|
|
|
365 The name of the reference used. The user must have run
|
|
|
366 'rsem-prepare-reference' with this reference_name before running
|
|
|
367 this program.
|
|
|
368
|
|
|
369 sample_name
|
|
|
370 The name of the sample analyzed. All output files are prefixed by
|
|
|
371 this name (e.g., sample_name.genes.results)
|
|
|
372
|
|
|
373 OPTIONS
|
|
|
374
|
|
|
375 --paired-end
|
|
|
376 Input reads are paired-end reads. (Default: off)
|
|
|
377
|
|
|
378 --no-qualities
|
|
|
379 Input reads do not contain quality scores. (Default: off)
|
|
|
380
|
|
|
381 --strand-specific
|
|
|
382 The RNA-Seq protocol used to generate the reads is strand specific,
|
|
|
383 i.e., all (upstream) reads are derived from the forward strand. This
|
|
|
384 option is equivalent to --forward-prob=1.0. With this option set, if
|
|
|
385 RSEM runs the Bowtie aligner, the '--norc' Bowtie option will be
|
|
|
386 used, which disables alignment to the reverse strand of transcripts.
|
|
|
387 (Default: off)
|
|
|
388
|
|
|
389 --sam
|
|
|
390 Input file is in SAM format. (Default: off)
|
|
|
391
|
|
|
392 --bam
|
|
|
393 Input file is in BAM format. (Default: off)
|
|
|
394
|
|
|
395 --sam-header-info [file]
|
|
|
396 RSEM reads header information from input by default. If this option
|
|
|
397 is on, header information is read from the specified file. For the
|
|
|
398 format of the file, please see SAM official website. (Default: "")
|
|
|
399
|
|
|
400 -p/--num-threads [int]
|
|
|
401 Number of threads to use. Both Bowtie and expression estimation will
|
|
|
402 use this many threads. (Default: 1)
|
|
|
403
|
|
|
404 --no-bam-output
|
|
|
405 Do not output any BAM file. (Default: off)
|
|
|
406
|
|
|
407 --output-genome-bam
|
|
|
408 Generate a BAM file, 'sample_name.genome.bam', with alignments
|
|
|
409 mapped to genomic coordinates and annotated with their posterior
|
|
|
410 probabilities. In addition, RSEM will call samtools (included in
|
|
|
411 RSEM package) to sort and index the bam file.
|
|
|
412 'sample_name.genome.sorted.bam' and
|
|
|
413 'sample_name.genome.sorted.bam.bai' will be generated. (Default:
|
|
|
414 off)
|
|
|
415
|
|
|
416 --sampling-for-bam
|
|
|
417 When RSEM generates a BAM file, instead of outputing all alignments
|
|
|
418 a read has with their posterior probabilities, one alignment is
|
|
|
419 sampled and outputed according to the posterior probabilities. If
|
|
|
420 the sampling result is that the read comes from the "noise"
|
|
|
421 transcript, nothing is outputed. (Default: off)
|
|
|
422
|
|
|
423 --calc-ci
|
|
|
424 Calculate 95% credibility intervals and posterior mean estimates.
|
|
|
425 (Default: off)
|
|
|
426
|
|
|
427 --seed-length [int]
|
|
|
428 Seed length used by the read aligner. Providing the correct value is
|
|
|
429 important for RSEM. If RSEM runs Bowtie, it uses this value for
|
|
|
430 Bowtie's seed length parameter. Any read with its or at least one of
|
|
|
431 its mates' (for paired-end reads) length less than this value will
|
|
|
432 be ignored. If the references are not added poly(A) tails, the
|
|
|
433 minimum allowed value is 5, otherwise, the minimum allowed value is
|
|
|
434 25. Note that this script will only check if the value less or equal than
|
|
|
435 5 and give a warning message if the value less than 25 but greter or equal than
|
|
|
436 5. (Default: 25)
|
|
|
437
|
|
|
438 --tag [string]
|
|
|
439 The name of the optional field used in the SAM input for identifying
|
|
|
440 a read with too many valid alignments. The field should have the
|
|
|
441 format [tagName]:i:[value], where a [value] bigger than 0 indicates
|
|
|
442 a read with too many alignments. (Default: "")
|
|
|
443
|
|
|
444 --bowtie-path [path]
|
|
|
445 The path to the bowtie executables. (Default: the path to the bowtie
|
|
|
446 executables is assumed to be in the user's PATH environment
|
|
|
447 variable)
|
|
|
448
|
|
|
449 --bowtie-n [int]
|
|
|
450 (Bowtie parameter) max # of mismatches in the seed. (Range: 0-3,
|
|
|
451 Default: 2)
|
|
|
452
|
|
|
453 --bowtie-e [int]
|
|
|
454 (Bowtie parameter) max sum of mismatch quality scores across the
|
|
|
455 alignment. (Default: 99999999)
|
|
|
456
|
|
|
457 --bowtie-m [int]
|
|
|
458 (Bowtie parameter) suppress all alignments for a read if greater then [int]
|
|
|
459 valid alignments exist. (Default: 200)
|
|
|
460
|
|
|
461 --bowtie-chunkmbs [int]
|
|
|
462 (Bowtie parameter) memory allocated for best first alignment
|
|
|
463 calculation (Default: 0 - use bowtie's default)
|
|
|
464
|
|
|
465 --phred33-quals
|
|
|
466 Input quality scores are encoded as Phred+33. (Default: on)
|
|
|
467
|
|
|
468 --phred64-quals
|
|
|
469 Input quality scores are encoded as Phred+64 (default for GA
|
|
|
470 Pipeline ver. less than 1.3). (Default: off)
|
|
|
471
|
|
|
472 --solexa-quals
|
|
|
473 Input quality scores are solexa encoded (from GA Pipeline ver. less
|
|
|
474 than 1.3). (Default: off)
|
|
|
475
|
|
|
476 --forward-prob [double]
|
|
|
477 Probability of generating a read from the forward strand of a
|
|
|
478 transcript. Set to 1 for a strand-specific protocol where all
|
|
|
479 (upstream) reads are derived from the forward strand, 0 for a
|
|
|
480 strand-specific protocol where all (upstream) read are derived from
|
|
|
481 the reverse strand, or 0.5 for a non-strand-specific protocol.
|
|
|
482 (Default: 0.5)
|
|
|
483
|
|
|
484 --fragment-length-min [int]
|
|
|
485 Minimum read/insert length allowed. This is also the value for the
|
|
|
486 bowtie -I option. (Default: 1)
|
|
|
487
|
|
|
488 --fragment-length-max [int]
|
|
|
489 Maximum read/insert length allowed. This is also the value for the
|
|
|
490 bowtie -X option. (Default: 1000)
|
|
|
491
|
|
|
492 --fragment-length-mean [double]
|
|
|
493 (single-end data only) The mean of the fragment length distribution,
|
|
|
494 which is assumed to be a Gaussian. (Default: -1, which disables use
|
|
|
495 of the fragment length distribution)
|
|
|
496
|
|
|
497 --fragment-length-sd [double]
|
|
|
498 (single-end data only) The standard deviation of the fragment length
|
|
|
499 distribution, which is assumed to be a Gaussian. (Default: 0, which
|
|
|
500 assumes that all fragments are of the same length, given by the
|
|
|
501 rounded value of --fragment-length-mean)
|
|
|
502
|
|
|
503 --estimate-rspd
|
|
|
504 Set this option if you want to estimate the read start position
|
|
|
505 distribution (RSPD) from data. Otherwise, RSEM will use a uniform
|
|
|
506 RSPD. (Default: off)
|
|
|
507
|
|
|
508 --num-rspd-bins [int]
|
|
|
509 Number of bins in the RSPD. Only relevant when '--estimate-rspd' is
|
|
|
510 specified. Use of the default setting is recommended. (Default: 20)
|
|
|
511
|
|
|
512 --ci-memory [int]
|
|
|
513 Maximum size (in memory, MB) of the auxiliary buffer used for
|
|
|
514 computing credibility intervals (CI). Set it larger for a faster CI
|
|
|
515 calculation. However, leaving 2 GB memory free for other usage is
|
|
|
516 recommended. (Default: 1024)
|
|
|
517
|
|
|
518 --keep-intermediate-files
|
|
|
519 Keep temporary files generated by RSEM. RSEM creates a temporary
|
|
|
520 directory, 'sample_name.temp', into which it puts all intermediate
|
|
|
521 output files. If this directory already exists, RSEM overwrites all
|
|
|
522 files generated by previous RSEM runs inside of it. By default,
|
|
|
523 after RSEM finishes, the temporary directory is deleted. Set this
|
|
|
524 option to prevent the deletion of this directory and the
|
|
|
525 intermediate files inside of it. (Default: off)
|
|
|
526
|
|
|
527 --time
|
|
|
528 Output time consumed by each step of RSEM to 'sample_name.time'.
|
|
|
529 (Default: off)
|
|
|
530
|
|
|
531 -q/--quiet
|
|
|
532 Suppress the output of logging information. (Default: off)
|
|
|
533
|
|
|
534 -h/--help
|
|
|
535 Show help information.
|
|
|
536
|
|
|
537 DESCRIPTION
|
|
|
538 In its default mode, this program aligns input reads against a reference
|
|
|
539 transcriptome with Bowtie and calculates expression values using the
|
|
|
540 alignments. RSEM assumes the data are single-end reads with quality
|
|
|
541 scores, unless the '--paired-end' or '--no-qualities' options are
|
|
|
542 specified. Users may use an alternative aligner by specifying one of the
|
|
|
543 --sam and --bam options, and providing an alignment file in the
|
|
|
544 specified format. However, users should make sure that they align
|
|
|
545 against the indices generated by 'rsem-prepare-reference' and the
|
|
|
546 alignment file satisfies the requirements mentioned in ARGUMENTS
|
|
|
547 section.
|
|
|
548
|
|
|
549 One simple way to make the alignment file satisfying RSEM's requirements
|
|
|
550 (assuming the aligner used put mates in a paired-end read adjacent) is
|
|
|
551 to use 'convert-sam-for-rsem' script. This script only accept SAM format
|
|
|
552 files as input. If a BAM format file is obtained, please use samtools to
|
|
|
553 convert it to a SAM file first. For example, if '/ref/mouse_125' is the
|
|
|
554 'reference_name' and the SAM file is named 'input.sam', you can run the
|
|
|
555 following command:
|
|
|
556
|
|
|
557 convert-sam-for-rsem /ref/mouse_125 input.sam -o input_for_rsem.sam
|
|
|
558
|
|
|
559 For details, please refer to 'convert-sam-for-rsem's documentation page.
|
|
|
560
|
|
|
561 The SAM/BAM format RSEM uses is v1.4. However, it is compatible with old
|
|
|
562 SAM/BAM format. However, RSEM cannot recognize 0x100 in the FLAG field.
|
|
|
563 In addition, RSEM requires SEQ and QUAL are not '*'.
|
|
|
564
|
|
|
565 The user must run 'rsem-prepare-reference' with the appropriate
|
|
|
566 reference before using this program.
|
|
|
567
|
|
|
568 For single-end data, it is strongly recommended that the user provide
|
|
|
569 the fragment length distribution parameters (--fragment-length-mean and
|
|
|
570 --fragment-length-sd). For paired-end data, RSEM will automatically
|
|
|
571 learn a fragment length distribution from the data.
|
|
|
572
|
|
|
573 Please note that some of the default values for the Bowtie parameters
|
|
|
574 are not the same as those defined for Bowtie itself.
|
|
|
575
|
|
|
576 The temporary directory and all intermediate files will be removed when
|
|
|
577 RSEM finishes unless '--keep-intermediate-files' is specified.
|
|
|
578
|
|
|
579 With the '--calc-ci' option, 95% credibility intervals and posterior
|
|
|
580 mean estimates will be calculated in addition to maximum likelihood
|
|
|
581 estimates.
|
|
|
582
|
|
|
583 OUTPUT
|
|
|
584 sample_name.genes.results
|
|
|
585 File containing gene level expression estimates. The format of each
|
|
|
586 line in this file is:
|
|
|
587
|
|
|
588 gene_id expected_counts tau_value [pmc_value tau_pme_value
|
|
|
589 tau_ci_lower_bound tau_ci_upper_bound] transcript_id_list
|
|
|
590
|
|
|
591 Fields are separated by the tab character. Fields within "[]" are
|
|
|
592 only presented if '--calc-ci' is set. pme stands for posterior mean
|
|
|
593 estimation. pmc stands for posterior mean counts. ci_lower_bound(l)
|
|
|
594 means the lower bound of the credibility intervals,
|
|
|
595 ci_upper_bound(u) means the upper bound of the credibility
|
|
|
596 intervals. So the credibility interval is [l, u].
|
|
|
597 'transcript_id_list' is a space-separated list of transcript_ids
|
|
|
598 belonging to the gene. If no gene information is provided, this file
|
|
|
599 has the same content as 'sample_name.isoforms.results'.
|
|
|
600
|
|
|
601 sample_name.isoforms.results
|
|
|
602 File containing isoform level expression values. The format of each
|
|
|
603 line in this file is:
|
|
|
604
|
|
|
605 transcript_id expected_counts tau_value [pmc_value tau_pme_value
|
|
|
606 tau_ci_lower_bound tau_ci_upper_bound] gene_id
|
|
|
607
|
|
|
608 Fields are separated by the tab character. 'gene_id' is the gene_id
|
|
|
609 of the gene which this transcript belongs to. If no gene information
|
|
|
610 is provided, 'gene_id' and 'transcript_id' are the same.
|
|
|
611
|
|
|
612 sample_name.transcript.bam, sample_name.transcript.sorted.bam and
|
|
|
613 sample_name.transcript.sorted.bam.bai
|
|
|
614 Only generated when --no-bam-output is not specified.
|
|
|
615
|
|
|
616 'sample_name.transcript.bam' is a BAM-formatted file of read
|
|
|
617 alignments in transcript coordinates. The MAPQ field of each
|
|
|
618 alignment is set to min(100, floor(-10 * log10(1.0 - w) + 0.5)),
|
|
|
619 where w is the posterior probability of that alignment being the
|
|
|
620 true mapping of a read. In addition, RSEM pads a new tag ZW:f:value,
|
|
|
621 where value is a single precision floating number representing the
|
|
|
622 posterior probability.
|
|
|
623
|
|
|
624 'sample_name.transcript.sorted.bam' and
|
|
|
625 'sample_name.transcript.sorted.bam.bai' are the sorted BAM file and
|
|
|
626 indices generated by samtools (included in RSEM package).
|
|
|
627
|
|
|
628 sample_name.genome.bam, sample_name.genome.sorted.bam and
|
|
|
629 sample_name.genome.sorted.bam.bai
|
|
|
630 Only generated when --no-bam-output is not specified and
|
|
|
631 --output-genome-bam is specified.
|
|
|
632
|
|
|
633 'sample_name.genome.bam' is a BAM-formatted file of read alignments
|
|
|
634 in genomic coordinates. Alignments of reads that have identical
|
|
|
635 genomic coordinates (i.e., alignments to different isoforms that
|
|
|
636 share the same genomic region) are collapsed into one alignment. The
|
|
|
637 MAPQ field of each alignment is set to min(100, floor(-10 *
|
|
|
638 log10(1.0 - w) + 0.5)), where w is the posterior probability of that
|
|
|
639 alignment being the true mapping of a read. In addition, RSEM pads a
|
|
|
640 new tag ZW:f:value, where value is a single precision floating
|
|
|
641 number representing the posterior probability. If an alignment is
|
|
|
642 spliced, a XS:A:value tag is also added, where value is either '+'
|
|
|
643 or '-' indicating the strand of the transcript it aligns to.
|
|
|
644
|
|
|
645 'sample_name.genome.sorted.bam' and
|
|
|
646 'sample_name.genome.sorted.bam.bai' are the sorted BAM file and
|
|
|
647 indices generated by samtools (included in RSEM package).
|
|
|
648
|
|
|
649 sample_name.sam.gz
|
|
|
650 Only generated when the input files are raw reads instead of SAM/BAM
|
|
|
651 format files
|
|
|
652
|
|
|
653 It is the gzipped SAM output produced by bowtie aligner.
|
|
|
654
|
|
|
655 sample_name.time
|
|
|
656 Only generated when --time is specified.
|
|
|
657
|
|
|
658 It contains time (in seconds) consumed by aligning reads, estimating
|
|
|
659 expression levels and calculating credibility intervals.
|
|
|
660
|
|
|
661 sample_name.stat
|
|
|
662 This is a folder instead of a file. All model related statistics are
|
|
|
663 stored in this folder. Use 'rsem-plot-model' can generate plots
|
|
|
664 using this folder.
|
|
|
665
|
|
|
666 EXAMPLES
|
|
|
667 Assume the path to the bowtie executables is in the user's PATH
|
|
|
668 environment variable. Reference files are under '/ref' with name
|
|
|
669 'mouse_125'.
|
|
|
670
|
|
|
671 1) '/data/mmliver.fq', single-end reads with quality scores. Quality
|
|
|
672 scores are encoded as for 'GA pipeline version >= 1.3'. We want to use 8
|
|
|
673 threads and generate a genome BAM file:
|
|
|
674
|
|
|
675 rsem-calculate-expression --phred64-quals \
|
|
|
676 -p 8 \
|
|
|
677 --output-genome-bam \
|
|
|
678 /data/mmliver.fq \
|
|
|
679 /ref/mouse_125 \
|
|
|
680 mmliver_single_quals
|
|
|
681
|
|
|
682 2) '/data/mmliver_1.fq' and '/data/mmliver_2.fq', paired-end reads with
|
|
|
683 quality scores. Quality scores are in SANGER format. We want to use 8
|
|
|
684 threads and do not generate a genome BAM file:
|
|
|
685
|
|
|
686 rsem-calculate-expression -p 8 \
|
|
|
687 --paired-end \
|
|
|
688 /data/mmliver_1.fq \
|
|
|
689 /data/mmliver_2.fq \
|
|
|
690 /ref/mouse_125 \
|
|
|
691 mmliver_paired_end_quals
|
|
|
692
|
|
|
693 3) '/data/mmliver.fa', single-end reads without quality scores. We want
|
|
|
694 to use 8 threads:
|
|
|
695
|
|
|
696 rsem-calculate-expression -p 8 \
|
|
|
697 --no-qualities \
|
|
|
698 /data/mmliver.fa \
|
|
|
699 /ref/mouse_125 \
|
|
|
700 mmliver_single_without_quals
|
|
|
701
|
|
|
702 4) Data are the same as 1). We want to take a fragment length
|
|
|
703 distribution into consideration. We set the fragment length mean to 150
|
|
|
704 and the standard deviation to 35. In addition to a BAM file, we also
|
|
|
705 want to generate credibility intervals. We allow RSEM to use 1GB of
|
|
|
706 memory for CI calculation:
|
|
|
707
|
|
|
708 rsem-calculate-expression --bowtie-path /sw/bowtie \
|
|
|
709 --phred64-quals \
|
|
|
710 --fragment-length-mean 150.0 \
|
|
|
711 --fragment-length-sd 35.0 \
|
|
|
712 -p 8 \
|
|
|
713 --output-genome-bam \
|
|
|
714 --calc-ci \
|
|
|
715 --ci-memory 1024 \
|
|
|
716 /data/mmliver.fq \
|
|
|
717 /ref/mouse_125 \
|
|
|
718 mmliver_single_quals
|
|
|
719
|
|
|
720 5) '/data/mmliver_paired_end_quals.bam', paired-end reads with quality
|
|
|
721 scores. We want to use 8 threads:
|
|
|
722
|
|
|
723 rsem-calculate-expression --paired-end \
|
|
|
724 --bam \
|
|
|
725 -p 8 \
|
|
|
726 /data/mmliver_paired_end_quals.bam \
|
|
|
727 /ref/mouse_125 \
|
|
|
728 mmliver_paired_end_quals
|
|
|
729 </help>
|
|
|
730 </tool>
|
