Mercurial > repos > sblanck > mpagenomics

comparison segcall.xml @ 0:4d539083cf7f draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/sblanck/MPAgenomics4Galaxy/tree/master/mpagenomics_wrappers commit 689d0d8dc899a683ee18700ef385753559850233-dirty
author sblanck
date Tue, 12 May 2020 10:40:36 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:4d539083cf7f
1 <tool id="segcall" name="Segmentation and calling" force_history_refresh="True" version="1.1.0">
2 <description>of the normalized data</description>
3 <requirement type="package" version="1.1.2">mpagenomics</requirement>
4 <command>
5 <![CDATA[
6 Rscript
7 ${__tool_directory__}/segcall.R
8 --chrom '$chrom'
9 --input '$input'
10 --output '$output'
11 --new_file_path '$__new_file_path__'
12 --nbcall '$nbcall'
13 #if $settings.settingsType == "file":
14 --settingsType '$settings.inputs'
15 #end if
16 #if $settings.settingsType == "dataset":
17 --settingsType '$settings.settingsType'
18 #end if
19 --outputgraph '$outputgraph'
20 --snp '$snp'
21 --zipfigures '$zipfigures'
22 #if $settingsTumor.settingsTypeTumor == "standard":
23 --settingsTypeTumor 'none'
24 #end if
25 #if $settingsTumor.settingsTypeTumor == "tumor":
26 --settingsTypeTumor '$tumorcsv'
27 #end if
28 --cellularity '$cellularity'
29 --outputlog '$outputlog'
30 --log '$log'
31 --userid '$__user_id__'
32 --method '$method'
33 ]]>
34 </command>
35 <inputs>
36 <!--param name="input" type="data" format="m:cel" label="Cel dataset" refresh="TRUE" help="cel files dataset previously normalized with the Data Normalization tool"/-->
37 <!--param name="inputXml" type="data" format="xml" label="Workspace" help="cel files dataset previously normalized with the Data Normalization tool"/-->
38 <param name="input" type="data" format="dsf" label="Dataset summary file" help="Summary text file generated by the Data Normalization tool"/>
39
40 <conditional name="settings">
41 <param name="settingsType" type="select" label="Files selection Mode" help="Select the whole cel files dataset or pick-up only few files from the dataset">
42 <option value="dataset">Select whole dataset</option>
43 <option value="file">Select file(s) individually</option>
44 </param>
45 <when value="dataset" />
46 <when value="file">
47 <param name="inputs" type="select" format="cel" multiple="true" label="Cel files">
48 <options from_dataset="input">
49 <column name="name" index="0"/>
50 <column name="value" index="0"/>
51 </options>
52 </param>
53 </when>
54 </conditional>
55 <conditional name="settingsTumor">
56 <param name="settingsTypeTumor" type="select" label="Reference">
57 <option value="standard">Study without reference</option>
58 <option value="tumor">Normal-tumor study</option>
59 </param>
60 <when value="standard" />
61 <when value="tumor">
62 <param name="tumorcsv" type="data" format="csv" label="TumorBoost csv file" help="Normal-tumor csv file. See below for more information."/>
63 </when>
64 </conditional>
65
66 <param name="snp" type="select" label="Select Probes">
67 <option value="FALSE">CN and SNP probes</option>
68 <option value="TRUE">Only SNP probes</option>
69 </param>
70
71 <!--param name="chrom" type="text" value="All" label="Chromosomes" help="Chromosomes to segment. Use comma to choose multiple chromosomes: e.g. 1, 3, 8. Use 'All' for a segmentation on all chromosomes" /-->
72
73 <param name="chrom" type="select" size="6" multiple="true" label="Chromosomes" help="leave blank for all chromosomes">
74 <option value="All">All</option>
75 <option value="1">chr 1</option>
76 <option value="2">chr 2</option>
77 <option value="3">chr 3</option>
78 <option value="4">chr 4</option>
79 <option value="5">chr 5</option>
80 <option value="6">chr 6</option>
81 <option value="7">chr 7</option>
82 <option value="8">chr 8</option>
83 <option value="9">chr 9</option>
84 <option value="10">chr 10</option>
85 <option value="11">chr 11</option>
86 <option value="12">chr 12</option>
87 <option value="13">chr 13</option>
88 <option value="14">chr 14</option>
89 <option value="15">chr 15</option>
90 <option value="16">chr 16</option>
91 <option value="17">chr 17</option>
92 <option value="18">chr 18</option>
93 <option value="19">chr 19</option>
94 <option value="20">chr 20</option>
95 <option value="21">chr 21</option>
96 <option value="22">chr 22</option>
97 <option value="23">chr 23</option>
98 <option value="24">chr 24</option>
99 <option value="25">chr 25</option>
100 </param>
101 <param name="method" type="select" label="Segmentation method" help="">
102 <option value="cghseg">cghseg</option>
103 <option value="PELT">PELT</option>
104 </param>
105
106 <param name="nbcall" type="select" label="Number of calling classes" help="The number of levels to be used for calling. Either 3 (loss, normal, gain), 4 (including amplifications), 5 (including double deletions) ">
107 <option value="3">3</option>
108 <option value="4">4</option>
109 <option value="5">5</option>
110 </param>
111 <param name="cellularity" type="float" size="5" value="1" min="0" max="1" label="Cellularity" help="Ratio of tumor cells in the sample. Real value between 0 and 1"/>
112 <param name="outputgraph" type="select" label="Output figures">
113 <option value="TRUE">Yes</option>
114 <option value="FALSE">No</option>
115 </param>
116 <param name="outputlog" type="select" label="Output log">
117 <option value="TRUE">Yes</option>
118 <option value="FALSE">No</option>
119 </param>
120 </inputs>
121 <outputs>
122 <data format="scr" name="output" label="seg. and call of ${input.name}" />
123 <data format="zip" name="zipfigures" label="seg. and call figures of ${input.name}">
124 <filter>outputgraph == "TRUE"</filter>
125 </data>
126 <data format="log" name="log" label="log of segmentation of ${input.name}">
127 <filter>outputlog == "TRUE"</filter>
128 </data>
129 </outputs>
130 <stdio>
131 <exit_code range="1:" level="fatal" description="See logs for more details" />
132 </stdio>
133 <help>
134 .. class:: warningmark
135
136 Data normalization must be run with the Data Normalization tool prior to segmentation. Otherwise, the standalone version can be used to perform marker selection from matrices containing data normalized with tools different from the one proposed in this instance.
137
138
139 -----
140
141 **What it does**
142 This tool segments the previously normalized profiles and labels segments found in the copy-number profiles. Otherwise, the standalone version can be used to perform segmentation from matrices containing data normalized with tools different from the one proposed in this instance.
143
144 Outputs:
145
146 *A tabular text file containing 7 columns which describe all the segments (1 line per segment):*
147
148 - sampleNames: Names of the original .CEL files.
149 - chrom: Chromosome of the segment.
150 - chromStart: Starting position (in bp) of the segment. This position is not included in the segment.
151 - chromEnd: Ending position (in bp) of the segment. This position is included in the segment.
152 - probes: Number of probes in the segment.
153 - means: Mean of the segment.
154 - calls: Calling of the segment (”double loss”, ”loss”, ”normal”, ”gain” or ”amplification”).
155
156 *A .zip file containing all the figures (optionnal)*
157
158 -----
159
160 **Normal-tumor study**
161
162 In cases where normal (control) samples match to tumor samples, they are taken as references to extract copy number profile. In this case, a normal-tumor csv file must be provided :
163
164 - The first column contains the names of the files corresponding to normal samples of the dataset.
165
166 - The second column contains the names of the tumor samples files.
167
168 - Column names of these two columns are respectively normal and tumor.
169
170 - Columns are separated by a comma.
171
172 - *Extensions of the files (.CEL for example) should be removed*
173
174
175
176 **Example**
177
178 Let 6 .cel files in the studied dataset (3 patients, each of them being represented by a couple of normal and tumor cel files.) ::
179
180 patient1_normal.cel
181 patient1_tumor.cel
182 patient2_normal.cel
183 patient2_tumor.cel
184 patient3_normal.cel
185 patient3_tumor.cel
186
187
188 The csv file should look like this ::
189
190 normal,tumor
191 patient1_normal,patient1_tumor
192 patient2_normal,patient2_tumor
193 patient3_normal,patient3_tumor
194
195 -----
196
197
198 **Citation**
199
200 If you use this tool please cite :
201
202 `Q. Grimonprez, A. Celisse, M. Cheok, M. Figeac, and G. Marot. MPAgenomics : An R package for multi-patients analysis of genomic markers, 2014. Preprint &lt;http://fr.arxiv.org/abs/1401.5035&gt;`_
203
204 As segmentation is performed with PELT, please also cite `R. Killick, P. Fearnhead, and I. A. Eckley. Optimal detection of changepoints with a linear computational cost. Journal of the American Statistical Association, 107(500):1590–1598, 2012. &lt;http://arxiv.org/abs/1101.1438&gt;`_
205
206 As segmentation is performed by cghseg, please cite `Picard, F., Robin, S., Lavielle, M., Vaisse, C., and Daudin, J.-J. (2005). A statistical approach for array CGH data analysis. BMC Bioinformatics, 6(1):27. &lt;http://www.ncbi.nlm.nih.gov/pubmed/15705208&gt;`_ ,
207 and also cite Rigaill, G. (2010). `Pruned dynamic programming for optimal multiple change-point detection. &lt;http://arxiv.org/abs/1004.0887&gt;`_
208
209 When using the labels of the segments, please cite CGHCall `M. A. van de Wiel, K. I. Kim, S. J. Vosse, W. N. van Wieringen, S. M. Wilting, and B. Ylstra. CGHcall: calling aberrations for array CGH tumor profiles. Bioinformatics, 23(7):892–894, 2007. &lt;http://bioinformatics.oxfordjournals.org/content/23/7/892.abstract&gt;`_
210
211 </help>
212 </tool>