Mercurial > repos > devteam > cuffquant

comparison cuffquant_wrapper.xml @ 0:5d8b9dcaf17d draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author devteam
date Fri, 19 Dec 2014 12:01:59 -0500
parents
children 986b63735a5e
comparison
equal deleted inserted replaced
-1:000000000000 0:5d8b9dcaf17d
1 <tool id="cuffquant" name="Cuffquant" version="@VERSION@.0">
2 <!-- Wrapper supports Cuffdiff versions 2.2.1 -->
3 <description>Precompute gene expression levels</description>
4 <expand macro="requirements" />
5 <expand macro="stdio" />
6 <macros>
7 <import>cuff_macros.xml</import>
8 </macros>
9 <version_command>cuffquant 2>&amp;1 | head -n 1</version_command>
10 <command>
11 cuffquant
12 --no-update-check
13 --num-threads=\${GALAXY_SLOTS:-4}
14 ## Set advanced SE data parameters?
15 #if $additional.sAdditional == "Yes":
16 -m $additional.frag_mean_len
17 -s $additional.frag_len_std_dev
18 #end if
19
20 ## Multi-read correct?
21 #if $multiread_correct :
22 -u
23 #end if
24
25 ## Bias correction?
26 #if $bias_correction.do_bias_correction == "Yes":
27 -b
28 #if $bias_correction.seq_source.index_source == "history":
29 ## Custom genome from history.
30 $bias_correction.seq_source.ref_file
31 #else:
32 ## Built-in genome.
33 "${ bias_correction.seq_source.index.fields.path }"
34 #end if
35 #end if
36
37 $length_correction
38
39 ## Set advanced parameters for cufflinks
40 #if $advanced_settings.sAdvanced == "Yes":
41 #if str($advanced_settings.library_type) != 'auto':
42 --library-type=$advanced_settings.library_type
43 #end if
44 #if $advanced_settings.mask_file:
45 --mask-file=$advanced_settings.mask_file
46 #end if
47 --max-mle-iterations=$advanced_settings.max_mle_iterations
48 --max-bundle-frags=$advanced_settings.max_bundle_frags
49 #end if
50 ## Inputs.
51 $gtf_input
52 #set samplestring = ','.join( [ str( $sample.sample ) for $sample in $samples ] )
53 $samplestring
54 </command>
55 <inputs>
56 <param format="gtf,gff3" name="gtf_input" type="data" label="Transcripts"
57 help="A transcript annotation (GFF3 or GTF) file produced by cufflinks, cuffcompare, or other source."/>
58
59 <repeat name="samples" title="Replicate" min="1">
60 <param name="sample" label="Add replicate" type="data" format="sam,bam"/>
61 </repeat>
62
63 <param name="multiread_correct" type="boolean" label="Use multi-read correct"
64 help="Tells Cufflinks to do an initial estimation procedure to more accurately weight reads mapping to multiple locations in the genome." />
65
66 <conditional name="bias_correction">
67 <param name="do_bias_correction" type="select" label="Perform Bias Correction"
68 help="Bias detection and correction can significantly improve accuracy of transcript abundance estimates.">
69 <option value="No">No</option>
70 <option value="Yes">Yes</option>
71 </param>
72 <when value="Yes">
73 <conditional name="seq_source">
74 <param name="index_source" type="select" label="Reference sequence data">
75 <option value="cached">Locally cached</option>
76 <option value="history">History</option>
77 </param>
78 <when value="cached">
79 <param name="index" type="select" label="Using reference genome">
80 <options from_data_table="fasta_indexes">
81 <filter type="data_meta" ref="gtf_input" key="dbkey" column="1" />
82 <validator type="no_options" message="No reference genome is available for the build associated with the selected input dataset" />
83 </options>
84 </param>
85 </when>
86 <when value="history">
87 <param name="ref_file" type="data" format="fasta" label="Using reference file" />
88 </when>
89 </conditional>
90 </when>
91 <when value="No"></when>
92 </conditional>
93
94 <param name="length_correction" type="select" label="apply length correction" help="mode of length normalization to transcript fpkm.">
95 <option value="" selected="true">cufflinks effective length correction</option>
96 <option value="--no-effective-length-correction">standard length correction</option>
97 <option value="--no-length-correction">no length correction at all (use raw counts)</option>
98 </param>
99
100 <conditional name="additional">
101 <param name="sAdditional" type="select" label="Set Additional Parameters for single end reads? (not recommended for paired-end reads)">
102 <option value="No" selected="True">No</option>
103 <option value="Yes">Yes</option>
104 </param>
105 <when value="No"></when>
106 <when value="Yes">
107 <param name="frag_mean_len" type="integer" value="200" label="Average Fragment Length"/>
108 <param name="frag_len_std_dev" type="integer" value="80" label="Fragment Length Standard Deviation"/>
109 </when>
110 </conditional>
111
112 <conditional name="advanced_settings">
113 <param name="sAdvanced" type="select" label="Set Advanced Cuffquant parameters? ">
114 <option value="No" selected="True">No</option>
115 <option value="Yes">Yes</option>
116 </param>
117 <when value="No"></when>
118 <when value="Yes">
119 <param type="select" name="library_type" label="Library prep used for input reads" help="">
120 <option value="auto" selected="True">Auto Detect</option>
121 <option value="ff-firststrand">ff-firststrand</option>
122 <option value="ff-secondstrand">ff-secondstrand</option>
123 <option value="ff-unstranded">ff-unstranded</option>
124 <option value="fr-firststrand">fr-firststrand</option>
125 <option value="fr-secondstrand">fr-secondstrand</option>
126 <option value="fr-unstranded" >fr-unstranded</option>
127 <option value="transfrags">transfrags</option>
128 </param>
129 <param name="mask_file" type="data" format="gtf,gff3" label="Mask File" help="Ignore all alignment within transcripts in this file" optional="True" />
130 <param name="max_mle_iterations" value="5000" type="integer" label="Max MLE iterations" help="Maximum iterations allowed for Maximal Likelyhood Estimation calculations" />
131 <param name="max_bundle_frags" type="integer" value="500000" label="Maximum number of fragments per locus"
132 help="Sets the maximum number of fragments a locus may have before being skipped. Default: 500,000" />
133 </when>
134 </conditional>
135 </inputs>
136 <outputs>
137 <!-- Standard datasets. -->
138 <data format="cxb" name="out_file" label="${tool.name} on ${on_string}: Abundances.cxb" from_work_dir="abundances.cxb" />
139 </outputs>
140 <tests>
141 <test>
142 <!--
143 cuffquant cuffcompare_out5.gtf cuffdiff_in1.sam,cuffdiff_in2.sam
144 -->
145 <param name="gtf_input" value="cuffquant_in.gtf" ftype="gtf" />
146 <repeat name="samples">
147 <param name="sample" value="cuffquant_in1.sam" ftype="sam" />
148 </repeat>
149 <repeat name="samples">
150 <param name="sample" value="cuffquant_in2.sam" ftype="sam" />
151 </repeat>
152 <param name="length_correction" value="" />
153 <param name="do_bias_correction" value="No" />
154 <param name="multiread_correct" value="No"/>
155 <param name="sAdditional" value="No"/>
156 <param name="sAdvanced" value="No" />
157 <output name="out_file" file="cuffquant_out1.cxb" compare="sim_size" />
158 </test>
159 </tests>
160
161 <help>
162 **Cuffquant Overview**
163
164 Cuffquant is part of Cufflinks_. Cuffquant provides pre-calculation of gene expression levels. The resulting file can be provided to cuffdiff or cuffnorm for further processing. Please cite: Trapnell C, Williams BA, Pertea G, Mortazavi AM, Kwan G, van Baren MJ, Salzberg SL, Wold B, Pachter L. Transcript assembly and abundance estimation from RNA-Seq reveals thousands of new transcripts and switching among isoforms. Nature Biotechnology doi:10.1038/nbt.1621
165
166 .. _Cufflinks: http://cole-trapnell-lab.github.io/cufflinks/
167
168 ------
169
170 **Know what you are doing**
171
172 .. class:: warningmark
173
174 There is no such thing (yet) as an automated gearshift in expression analysis. It is all like stick-shift driving in San Francisco. In other words, running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy.
175
176 .. __: http://cole-trapnell-lab.github.io/cufflinks/cuffquant/
177
178 ------
179
180 **Input format**
181
182 Cuffquant takes Cufflinks or Cuffcompare GTF files as input along with two or more SAM files containing the fragment alignments for two or more samples.
183
184 ------
185
186 **Outputs**
187
188 Cuffquant produces one output file:
189
190 1. Transcript expression values in binary format.
191
192 -------
193
194 **Settings**
195
196 All of the options have a default value. You can change any of them. Most of the options in Cuffdiff have been implemented here.
197
198 ------
199
200 **Cuffdiff parameter list**
201
202 This is a list of implemented Cuffdiff options::
203
204 -m INT Average fragment length (SE reads); default 200
205 -s INT Fragment legnth standard deviation (SE reads); default 80
206 --max-mle-iterations INT Sets the number of iterations allowed during maximum likelihood estimation of abundances. Default: 5000
207 -u Multi read correction tells Cufflinks to do an initial estimation procedure to more accurately weight reads mapping to multiple locations in the genome.
208 -b ref.fasta bias correction. Bias detection and correction can significantly improve accuracy of transcript abundance estimates.
209 --no-effective-length-correction Use standard length correction
210 --no-length-correction Disable all length correction.
211 --library-type ff-firststrand,ff-secondstrand,ff-unstranded,fr-firstrand,fr-secondstrand,fr-unstranded,transfrags
212 --mask-file (gff3/gtf) Ignore all alignment within transcripts in this file
213 --max-bundle-frags Sets the maximum number of fragments a locus may have before being skipped. Skipped loci are listed in skipped.gtf.
214 </help>
215 <citations>
216 <citation type="doi">10.1038/nbt.1621</citation>
217 </citations>
218 </tool>