Mercurial > repos > fcaramia > contra

comparison Contra/contra.xml @ 0:7564f3b1e675

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author fcaramia
date Thu, 13 Sep 2012 02:31:43 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:7564f3b1e675
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="2.11.2">bedtools</requirement>
5 </requirements>
6 <command interpreter="perl">
7
8 contra_wrapper.pl
9
10 ##Ref Genome
11 #if $genomeSource.refGenomeSource == "history":
12 "PLAYEROPTION::-f=${genomeSource.ownFile}"
13 #else:
14 ##use precomputed indexes
15 "PLAYEROPTION::-f=${genomeSource.indices.fields.path}"
16 #end if
17
18 ##Required files
19 "PLAYEROPTION::-t=$target_file"
20 "PLAYEROPTION::-s=$alignment_file"
21 #if $controlSource.refControlSource == "history":
22 "PLAYEROPTION::-c=${controlSource.control_file}"
23 #else:
24 ##use precomputed indexes
25 "PLAYEROPTION::-c=${controlSource.indices.fields.path}"
26 #end if
27
28 ##Optional parameter
29
30 #if $option.option == "modify_parameters":
31
32 "PLAYEROPTION::--numBin=$option.numBin"
33 "PLAYEROPTION::--minReadDepth=$option.minReadDepth"
34 "PLAYEROPTION::--minNBases=$option.minNbases"
35
36 #if str($option.sam) == "true":
37 "PLAYEROPTION::--sam"
38 #end if
39
40 #if str($option.bed) == "true":
41 "PLAYEROPTION::--bed"
42 #end if
43
44 "PLAYEROPTION::--pval=$option.pval"
45 "PLAYEROPTION::--sampleName=$option.sampleName"
46
47 #if str($option.nomultimapped) == "true":
48 "PLAYEROPTION::--nomultimapped"
49 #end if
50
51 #if str($option.plot) == "true":
52 "PLAYEROPTION::--plot"
53 #end if
54
55 "PLAYEROPTION::--minExon=$option.minExon"
56 "PLAYEROPTION::--minControlRdForCall=$option.minControlRdForCall"
57 "PLAYEROPTION::--minTestRdForCall=$option.minTestRdForCall"
58 "PLAYEROPTION::--minAvgForCall=$option.minAvgForCall"
59 "PLAYEROPTION::--maxRegionSize=$option.maxRegionSize"
60 "PLAYEROPTION::--targetRegionSize=$option.targetRegionSize"
61
62 #if str($option.largedeletion) == "true":
63 "PLAYEROPTION::--largedeletion"
64 #end if
65
66 "PLAYEROPTION::--smallSegment=$option.smallSegment"
67 "PLAYEROPTION::--targetRegionSize=$option.targetRegionSize"
68 "PLAYEROPTION::--largeSegment=$option.largeSegment"
69 "PLAYEROPTION::--lrCallStart=$option.lrCallStart"
70 "PLAYEROPTION::--lrCallEnd=$option.lrCallEnd"
71 "PLAYEROPTION::--passSize=$option.passSize"
72 #end if
73
74 ##File to generate the bam list
75 CONTRAOUTPUT::$html_file
76 CONTRADIR::$html_file.files_path
77
78 </command>
79 <inputs>
80
81 <conditional name="genomeSource">
82 <param name="refGenomeSource" type="select" label="Will you select a reference from your history or use a built-in fasta file?">
83 <option value="indexed">Use a built-in index</option>
84 <option value="history">Use one from the history</option>
85 </param>
86 <when value="indexed">
87 <param name="indices" type="select" label="Select a reference genome">
88 <options from_data_table="all_fasta">
89 <filter type="sort_by" column="2" />
90 <validator type="no_options" message="No indexes are available" />
91 </options>
92 </param>
93 </when>
94 <when value="history">
95 <param name="ownFile" type="data" format="fasta" label="Select a reference from history" />
96 </when>
97 </conditional>
98
99 <param name="target_file" type="data" format="bed" help="" optional="false" />
100 <param name="alignment_file" type="data" format="bam,sam" help="" optional="false" />
101
102
103 <conditional name="controlSource">
104 <param name="refControlSource" type="select" label="Will you select a reference from your history or use a built-in control file?">
105 <option value="indexed">Use a built-in control</option>
106 <option value="history">Use one from the history</option>
107 </param>
108 <when value="indexed">
109 <param name="indices" type="select" label="Select a baseline control">
110 <options from_data_table="baseline_files">
111 <filter type="sort_by" column="2" />
112 <validator type="no_options" message="No files available" />
113 </options>
114 </param>
115 </when>
116 <when value="history">
117 <param name="control_file" type="data" format="bam,sam,bed,tabular" help="" optional="false" />
118 </when>
119 </conditional>
120
121 <conditional name="option">
122 <param name="option" type="select" label="Optional Parameters" help="" optional="true">
123 <option value="default_parameters" selected="true">Default Parameters</option>
124 <option value="modify_parameters">Modify Parameters</option>
125 </param>
126 <when value="modify_parameters">
127 <param name="numBin" type="integer" value="20" optional="true" />
128 <param name="minReadDepth" type="integer" value="10" optional="true" />
129 <param name="minNbases" type="integer" value="10" optional="true" />
130 <param name="sam" type="select" label="sam" help="" optional="true">
131 <option value="true" >true</option>
132 <option value="false" selected="true">false</option>
133 </param>
134 <param name="bed" type="select" label="bed" help="" optional="true">
135 <option value="true" >true</option>
136 <option value="false" selected="true">false</option>
137 </param>
138 <param name="pval" type="float" value="0.05" optional="true" />
139 <param name="sampleName" value="Contra_Output" type="text" optional="true" />
140 <param name="nomultimapped" type="select" label="no multimapped" help="" optional="true">
141 <option value="true" >true</option>
142 <option value="false" selected="true">false</option>
143 </param>
144 <param name="plot" type="select" label="plot" help="" optional="true">
145 <option value="true" >true</option>
146 <option value="false" selected="true">false</option>
147 </param>
148 <param name="minExon" type="integer" value="2000" optional="true" />
149 <param name="minControlRdForCall" type="integer" value="5" optional="true" />
150 <param name="minTestRdForCall" type="integer" value="0" optional="true" />
151 <param name="minAvgForCall" type="integer" value="20" optional="true" />
152 <param name="maxRegionSize" type="integer" value="0" optional="true" />
153 <param name="targetRegionSize" type="integer" value="200" optional="true" />
154 <param name="largedeletion" type="select" label="large deletion" help="" optional="true">
155 <option value="true" >true</option>
156 <option value="false" selected="true">false</option>
157 </param>
158
159 <param name="smallSegment" type="integer" value="1" optional="true" />
160 <param name="largeSegment" type="integer" value="25" optional="true" />
161 <param name="lrCallStart" type="float" value="-0.3" optional="true" />
162 <param name="lrCallEnd" type="float" value="0.3" optional="true" />
163 <param name="passSize" type="float" value="0.5" optional="true" />
164
165 </when>
166 </conditional>
167 </inputs>
168 <outputs>
169 <data name="html_file" format="html" label="Contra Output" />
170 </outputs>
171 <help>
172 |
173
174
175 **Reference**
176 http://contra-cnv.sourceforge.net/
177
178 -----
179
180 **What it does**
181
182 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.
183
184
185 -----
186
187 **Required Parameters**
188
189 ::
190
191 -t, --target Target region definition file [BED format]
192
193 -s, --test Alignment file for the test sample [BAM/SAM]
194
195 -c, --control Alignment file for the control sample
196 [BAM/SAM/BED – baseline file]
197
198 --bed **option has to be supplied for control
199 with baseline file.**
200
201 -f, --fasta Reference genome [FASTA]
202
203 -o, --outFolder the folder name (and its path) to store the output
204 of the analysis (this new folder will be created –
205 error message occur if the folder exists)
206
207 -----
208
209 **Optional Parameters**
210
211 ::
212
213 --numBin Numbers of bins to group the regions. User can
214 specify multiple experiments with different numbers
215 of bins (comma separated). [Default: 20]
216
217 --minReadDepth The threshold for minimum read depth for each bases
218 (see Step 2 in CONTRA workflow) [Default: 10]
219
220 --minNBases The threshold for minimum number of bases for each
221 target regions (see Step 2 in CONTRA workflow)
222 [Default: 10]
223
224 --sam If the specified test and control samples are in
225 SAM format. [Default: False] (It will always take
226 BAM samples as default)
227
228 --bed If specified, control will be a baseline file in
229 BED format. [Default: False]
230 Please refer to the Baseline Script section for
231 instruction how to create baseline files from set
232 of BAMfiles. A set of baseline files from different
233 platform have also been provided in the CONTRA
234 download page.
235
236 --pval The p-value threshold for filtering. Based on Adjusted
237 P-Values. Only regions that pass this threshold will
238 be included in the VCF file. [Default: 0.05]
239
240 --sampleName The name to be appended to the front of the default output
241 name. By default, there will be nothing appended.
242
243 --nomultimapped The option to remove multi-mapped reads
244 (using SAMtools with mapping quality > 0).
245 [default: FALSE]
246
247 -p, --plot If specified, plots of log-ratio distribution for each
248 bin will be included in the output folder [default: FALSE]
249
250 --minExon Minimum number of exons in one bin (if less than this number
251 , bin that contains small number of exons will be merged to
252 the adjacent bins) [Default : 2000]
253
254 --minControlRdForCall Minimum Control ReadDepth for call [Default: 5]
255
256 --minTestRdForCall Minimum Test ReadDepth for call [Default: 0]
257
258 --minAvgForCall Minimum average coverage for call [Default: 20]
259
260 --maxRegionSize Maximum region size in target region (for breaking
261 large regions into smaller regions. By default,
262 maxRegionSize=0 means no breakdown). [Default : 0]
263
264 --targetRegionSize Target region size for breakdown (if maxRegionSize
265 is non-zero) [Default: 200]
266
267 -l, --largeDeletion If specified, CONTRA will run large deletion analysis (CBS).
268 User must have DNAcopy R-library installed to run the
269 analysis. [False]
270
271 --smallSegment CBS segment size for calling large variations [Default : 1]
272
273 --largeSegment CBS segment size for calling large variations [Default : 25]
274
275 --lrCallStart Log ratios start range that will be used to call CNV
276 [Default : -0.3]
277
278 --lrCallEnd Log ratios end range that will be used to call CNV
279 [Default : 0.3]
280
281 --passSize Size of exons that passed the p-value threshold compare
282 to the original exons size [Default: 0.5]
283 </help>
284 </tool>
285
286