|
5
|
1 <tool id="contra_tool" name="Contra Copy number analysis" version="1.0.0">
|
|
|
2 <description>: Copy Number Analysis for Targeted Resequencing</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="2.17.0">bedtools</requirement>
|
|
|
5 <requirement type="package" name="samtools" version="0.1.18">samtools</requirement>
|
|
|
6 <requirement type="package" name="contra" version="2.0.4">contra</requirement>
|
|
|
7 </requirements>
|
|
|
8 <command interpreter="perl">
|
|
|
9
|
|
|
10 contra_wrapper.pl
|
|
|
11
|
|
|
12 ##Ref Genome
|
|
|
13 #if $genomeSource.refGenomeSource == "history":
|
|
|
14 "PLAYEROPTION::-f=${genomeSource.ownFile}"
|
|
|
15 #else:
|
|
|
16 ##use precomputed indexes
|
|
|
17 "PLAYEROPTION::-f=${genomeSource.indices.fields.path}"
|
|
|
18 #end if
|
|
|
19
|
|
|
20 ##Required files
|
|
|
21 "PLAYEROPTION::-t=$target_file"
|
|
|
22 "PLAYEROPTION::-s=$alignment_file"
|
|
|
23 #if $controlSource.refControlSource == "history":
|
|
|
24 "PLAYEROPTION::-c=${controlSource.control_file}"
|
|
|
25 #else:
|
|
|
26 ##use precomputed indexes
|
|
|
27 "PLAYEROPTION::-c=${controlSource.indices.fields.path}"
|
|
|
28 #end if
|
|
|
29
|
|
|
30 ##Optional parameter
|
|
|
31
|
|
|
32 #if $option.option == "modify_parameters":
|
|
|
33
|
|
|
34 "PLAYEROPTION::--numBin=$option.numBin"
|
|
|
35 "PLAYEROPTION::--minReadDepth=$option.minReadDepth"
|
|
|
36 "PLAYEROPTION::--minNBases=$option.minNbases"
|
|
|
37
|
|
|
38 #if str($option.sam) == "true":
|
|
|
39 "PLAYEROPTION::--sam"
|
|
|
40 #end if
|
|
|
41
|
|
|
42 #if str($option.bed) == "true":
|
|
|
43 "PLAYEROPTION::--bed"
|
|
|
44 #end if
|
|
|
45
|
|
|
46 "PLAYEROPTION::--pval=$option.pval"
|
|
|
47 "PLAYEROPTION::--sampleName=$option.sampleName"
|
|
|
48
|
|
|
49 #if str($option.nomultimapped) == "true":
|
|
|
50 "PLAYEROPTION::--nomultimapped"
|
|
|
51 #end if
|
|
|
52
|
|
|
53 #if str($option.plot) == "true":
|
|
|
54 "PLAYEROPTION::--plot"
|
|
|
55 #end if
|
|
|
56
|
|
|
57 "PLAYEROPTION::--minExon=$option.minExon"
|
|
|
58 "PLAYEROPTION::--minControlRdForCall=$option.minControlRdForCall"
|
|
|
59 "PLAYEROPTION::--minTestRdForCall=$option.minTestRdForCall"
|
|
|
60 "PLAYEROPTION::--minAvgForCall=$option.minAvgForCall"
|
|
|
61 "PLAYEROPTION::--maxRegionSize=$option.maxRegionSize"
|
|
|
62 "PLAYEROPTION::--targetRegionSize=$option.targetRegionSize"
|
|
|
63
|
|
|
64 #if str($option.largedeletion) == "true":
|
|
|
65 "PLAYEROPTION::--largedeletion"
|
|
|
66 #end if
|
|
|
67
|
|
|
68 "PLAYEROPTION::--smallSegment=$option.smallSegment"
|
|
|
69 "PLAYEROPTION::--targetRegionSize=$option.targetRegionSize"
|
|
|
70 "PLAYEROPTION::--largeSegment=$option.largeSegment"
|
|
|
71 "PLAYEROPTION::--lrCallStart=$option.lrCallStart"
|
|
|
72 "PLAYEROPTION::--lrCallEnd=$option.lrCallEnd"
|
|
|
73 "PLAYEROPTION::--passSize=$option.passSize"
|
|
|
74 #end if
|
|
|
75
|
|
|
76 ##File to generate the bam list
|
|
|
77 CONTRAOUTPUT::$html_file
|
|
|
78 CONTRADIR::$html_file.files_path
|
|
|
79
|
|
|
80 </command>
|
|
|
81 <inputs>
|
|
|
82
|
|
|
83 <conditional name="genomeSource">
|
|
|
84 <param name="refGenomeSource" type="select" label="Will you select a reference from your history or use a built-in fasta file?">
|
|
|
85 <option value="indexed">Use a built-in index</option>
|
|
|
86 <option value="history">Use one from the history</option>
|
|
|
87 </param>
|
|
|
88 <when value="indexed">
|
|
|
89 <param name="indices" type="select" label="Select a reference genome">
|
|
|
90 <options from_data_table="all_fasta">
|
|
|
91 <filter type="sort_by" column="2" />
|
|
|
92 <validator type="no_options" message="No indexes are available" />
|
|
|
93 </options>
|
|
|
94 </param>
|
|
|
95 </when>
|
|
|
96 <when value="history">
|
|
|
97 <param name="ownFile" type="data" format="fasta" label="Select a reference from history" />
|
|
|
98 </when>
|
|
|
99 </conditional>
|
|
|
100
|
|
|
101 <param name="target_file" type="data" format="bed" help="" optional="false" />
|
|
|
102 <param name="alignment_file" type="data" format="bam,sam" help="" optional="false" />
|
|
|
103
|
|
|
104
|
|
|
105 <conditional name="controlSource">
|
|
|
106 <param name="refControlSource" type="select" label="Will you select a reference from your history or use a built-in control file?">
|
|
|
107 <option value="indexed">Use a built-in control</option>
|
|
|
108 <option value="history">Use one from the history</option>
|
|
|
109 </param>
|
|
|
110 <when value="indexed">
|
|
|
111 <param name="indices" type="select" label="Select a baseline control">
|
|
|
112 <options from_data_table="baseline_files">
|
|
|
113 <filter type="sort_by" column="2" />
|
|
|
114 <validator type="no_options" message="No files available" />
|
|
|
115 </options>
|
|
|
116 </param>
|
|
|
117 </when>
|
|
|
118 <when value="history">
|
|
|
119 <param name="control_file" type="data" format="bam,sam,bed,tabular" help="" optional="false" />
|
|
|
120 </when>
|
|
|
121 </conditional>
|
|
|
122
|
|
|
123 <conditional name="option">
|
|
|
124 <param name="option" type="select" label="Optional Parameters" help="" optional="true">
|
|
|
125 <option value="default_parameters" selected="true">Default Parameters</option>
|
|
|
126 <option value="modify_parameters">Modify Parameters</option>
|
|
|
127 </param>
|
|
|
128 <when value="modify_parameters">
|
|
|
129 <param name="numBin" type="integer" value="20" optional="true" />
|
|
|
130 <param name="minReadDepth" type="integer" value="10" optional="true" />
|
|
|
131 <param name="minNbases" type="integer" value="10" optional="true" />
|
|
|
132 <param name="sam" type="select" label="sam" help="" optional="true">
|
|
|
133 <option value="true" >true</option>
|
|
|
134 <option value="false" selected="true">false</option>
|
|
|
135 </param>
|
|
|
136 <param name="bed" type="select" label="bed" help="" optional="true">
|
|
|
137 <option value="true" >true</option>
|
|
|
138 <option value="false" selected="true">false</option>
|
|
|
139 </param>
|
|
|
140 <param name="pval" type="float" value="0.05" optional="true" />
|
|
|
141 <param name="sampleName" value="Contra_Output" type="text" optional="true" />
|
|
|
142 <param name="nomultimapped" type="select" label="no multimapped" help="" optional="true">
|
|
|
143 <option value="true" >true</option>
|
|
|
144 <option value="false" selected="true">false</option>
|
|
|
145 </param>
|
|
|
146 <param name="plot" type="select" label="plot" help="" optional="true">
|
|
|
147 <option value="true" >true</option>
|
|
|
148 <option value="false" selected="true">false</option>
|
|
|
149 </param>
|
|
|
150 <param name="minExon" type="integer" value="2000" optional="true" />
|
|
|
151 <param name="minControlRdForCall" type="integer" value="5" optional="true" />
|
|
|
152 <param name="minTestRdForCall" type="integer" value="0" optional="true" />
|
|
|
153 <param name="minAvgForCall" type="integer" value="20" optional="true" />
|
|
|
154 <param name="maxRegionSize" type="integer" value="0" optional="true" />
|
|
|
155 <param name="targetRegionSize" type="integer" value="200" optional="true" />
|
|
|
156 <param name="largedeletion" type="select" label="large deletion" help="" optional="true">
|
|
|
157 <option value="true" >true</option>
|
|
|
158 <option value="false" selected="true">false</option>
|
|
|
159 </param>
|
|
|
160
|
|
|
161 <param name="smallSegment" type="integer" value="1" optional="true" />
|
|
|
162 <param name="largeSegment" type="integer" value="25" optional="true" />
|
|
|
163 <param name="lrCallStart" type="float" value="-0.3" optional="true" />
|
|
|
164 <param name="lrCallEnd" type="float" value="0.3" optional="true" />
|
|
|
165 <param name="passSize" type="float" value="0.5" optional="true" />
|
|
|
166
|
|
|
167 </when>
|
|
|
168 </conditional>
|
|
|
169 </inputs>
|
|
|
170 <outputs>
|
|
|
171 <data name="html_file" format="html" label="Contra Output" />
|
|
|
172 </outputs>
|
|
|
173 <help>
|
|
|
174 |
|
|
|
175
|
|
|
176
|
|
|
177 **Reference**
|
|
|
178 http://contra-cnv.sourceforge.net/
|
|
|
179
|
|
|
180 -----
|
|
|
181
|
|
|
182 **What it does**
|
|
|
183
|
|
|
184 CONTRA is a tool for copy number variation (CNV) detection for targeted resequencing data such as those from whole-exome capture data. CONTRA calls copy number gains and losses for each target region with key strategies include the use of base-level log-ratios to remove GC-content bias, correction for an imbalanced library size effect on log-ratios, and the estimation of log-ratio variations via binning and interpolation. It takes standard alignment formats (BAM/SAM) and output in variant call format (VCF 4.0) for easy integration with other next generation sequencing analysis package.
|
|
|
185
|
|
|
186
|
|
|
187 -----
|
|
|
188
|
|
|
189 **Required Parameters**
|
|
|
190
|
|
|
191 ::
|
|
|
192
|
|
|
193 -t, --target Target region definition file [BED format]
|
|
|
194
|
|
|
195 -s, --test Alignment file for the test sample [BAM/SAM]
|
|
|
196
|
|
|
197 -c, --control Alignment file for the control sample
|
|
|
198 [BAM/SAM/BED – baseline file]
|
|
|
199
|
|
|
200 --bed **option has to be supplied for control
|
|
|
201 with baseline file.**
|
|
|
202
|
|
|
203 -f, --fasta Reference genome [FASTA]
|
|
|
204
|
|
|
205 -o, --outFolder the folder name (and its path) to store the output
|
|
|
206 of the analysis (this new folder will be created –
|
|
|
207 error message occur if the folder exists)
|
|
|
208
|
|
|
209 -----
|
|
|
210
|
|
|
211 **Optional Parameters**
|
|
|
212
|
|
|
213 ::
|
|
|
214
|
|
|
215 --numBin Numbers of bins to group the regions. User can
|
|
|
216 specify multiple experiments with different numbers
|
|
|
217 of bins (comma separated). [Default: 20]
|
|
|
218
|
|
|
219 --minReadDepth The threshold for minimum read depth for each bases
|
|
|
220 (see Step 2 in CONTRA workflow) [Default: 10]
|
|
|
221
|
|
|
222 --minNBases The threshold for minimum number of bases for each
|
|
|
223 target regions (see Step 2 in CONTRA workflow)
|
|
|
224 [Default: 10]
|
|
|
225
|
|
|
226 --sam If the specified test and control samples are in
|
|
|
227 SAM format. [Default: False] (It will always take
|
|
|
228 BAM samples as default)
|
|
|
229
|
|
|
230 --bed If specified, control will be a baseline file in
|
|
|
231 BED format. [Default: False]
|
|
|
232 Please refer to the Baseline Script section for
|
|
|
233 instruction how to create baseline files from set
|
|
|
234 of BAMfiles. A set of baseline files from different
|
|
|
235 platform have also been provided in the CONTRA
|
|
|
236 download page.
|
|
|
237
|
|
|
238 --pval The p-value threshold for filtering. Based on Adjusted
|
|
|
239 P-Values. Only regions that pass this threshold will
|
|
|
240 be included in the VCF file. [Default: 0.05]
|
|
|
241
|
|
|
242 --sampleName The name to be appended to the front of the default output
|
|
|
243 name. By default, there will be nothing appended.
|
|
|
244
|
|
|
245 --nomultimapped The option to remove multi-mapped reads
|
|
|
246 (using SAMtools with mapping quality > 0).
|
|
|
247 [default: FALSE]
|
|
|
248
|
|
|
249 -p, --plot If specified, plots of log-ratio distribution for each
|
|
|
250 bin will be included in the output folder [default: FALSE]
|
|
|
251
|
|
|
252 --minExon Minimum number of exons in one bin (if less than this number
|
|
|
253 , bin that contains small number of exons will be merged to
|
|
|
254 the adjacent bins) [Default : 2000]
|
|
|
255
|
|
|
256 --minControlRdForCall Minimum Control ReadDepth for call [Default: 5]
|
|
|
257
|
|
|
258 --minTestRdForCall Minimum Test ReadDepth for call [Default: 0]
|
|
|
259
|
|
|
260 --minAvgForCall Minimum average coverage for call [Default: 20]
|
|
|
261
|
|
|
262 --maxRegionSize Maximum region size in target region (for breaking
|
|
|
263 large regions into smaller regions. By default,
|
|
|
264 maxRegionSize=0 means no breakdown). [Default : 0]
|
|
|
265
|
|
|
266 --targetRegionSize Target region size for breakdown (if maxRegionSize
|
|
|
267 is non-zero) [Default: 200]
|
|
|
268
|
|
|
269 -l, --largeDeletion If specified, CONTRA will run large deletion analysis (CBS).
|
|
|
270 User must have DNAcopy R-library installed to run the
|
|
|
271 analysis. [False]
|
|
|
272
|
|
|
273 --smallSegment CBS segment size for calling large variations [Default : 1]
|
|
|
274
|
|
|
275 --largeSegment CBS segment size for calling large variations [Default : 25]
|
|
|
276
|
|
|
277 --lrCallStart Log ratios start range that will be used to call CNV
|
|
|
278 [Default : -0.3]
|
|
|
279
|
|
|
280 --lrCallEnd Log ratios end range that will be used to call CNV
|
|
|
281 [Default : 0.3]
|
|
|
282
|
|
|
283 --passSize Size of exons that passed the p-value threshold compare
|
|
|
284 to the original exons size [Default: 0.5]
|
|
|
285 </help>
|
|
|
286 </tool>
|
|
|
287
|
|
|
288
|
