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