Mercurial > repos > sblanck > mpagenomics

comparison selection.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="selection" name="Markers selection" force_history_refresh="True" version="0.1.0">
2 <command>
3 <![CDATA[
4 Rscript
5 ${__tool_directory__}/selection.R
6 --input '$input'
7 --response '$response'
8 --chrom '$chromosome'
9 --new_file_path '$__new_file_path__'
10 --settingsSignal '$settingsSNP.signal'
11 #if $settingsSNP.signal == "CN":
12 --settingsSnp '$settingsSNP.snp'
13 #end if
14 #if $settingsSNP.signal == "fracB":
15 --settingsSnp 'none'
16 #end if
17 --settingsType '$settings.settingsType'
18 #if $settings.settingsType == "tumor":
19 --settingsType '$tumorcsv'
20 #end if
21 #if $settings.settingsType == "standard":
22 --settingsType 'none'
23 #end if
24 --folds '$folds'
25 --settingsLoss '$settingsLoss.loss'
26 --outputgraph '$outputgraph'
27 --output '$output'
28 --pdffigures '$pdffigures'
29 --outputlog '$outputlog'
30 --log '$log'
31 --userId '$__user_id__'
32 #if $settingsLoss.loss == "linear":
33 --settingsPackage '$settingsLoss.package'
34 #end if
35 #if $settingsLoss.loss == "logistic":
36 --settingsPackage'HDPenReg'
37 #end if
38 ]]>
39 </command>
40 <inputs>
41 <param name="input" type="data" format="dsf" label="Dataset summary file" help="Summary text file generated by the Data normalization tool"/>
42
43 <param name="response" type="data" format="csv" label="Data response" help="Data response csv file. See below for more information on file format" />
44
45 <param name="chromosome" type="select" size="6" multiple="true" label="Chromosomes">
46 <option value="1">chr 1</option>
47 <option value="2">chr 2</option>
48 <option value="3">chr 3</option>
49 <option value="4">chr 4</option>
50 <option value="5">chr 5</option>
51 <option value="6">chr 6</option>
52 <option value="7">chr 7</option>
53 <option value="8">chr 8</option>
54 <option value="9">chr 9</option>
55 <option value="10">chr 10</option>
56 <option value="11">chr 11</option>
57 <option value="12">chr 12</option>
58 <option value="13">chr 13</option>
59 <option value="14">chr 14</option>
60 <option value="15">chr 15</option>
61 <option value="16">chr 16</option>
62 <option value="17">chr 17</option>
63 <option value="18">chr 18</option>
64 <option value="19">chr 19</option>
65 <option value="20">chr 20</option>
66 <option value="21">chr 21</option>
67 <option value="22">chr 22</option>
68 <option value="23">chr 23</option>
69 <option value="24">chr 24</option>
70 <option value="25">chr 25</option>
71 </param>
72 <conditional name="settingsSNP">
73 <param name="signal" type="select" multiple="false" label="Signal you want to work on">
74 <option value="CN">CN</option>
75 <option value="fracB">fracB</option>
76 </param>
77 <when value="fracB"/>
78 <when value="CN">
79 <param name="snp" type="select" label="Select Probes">
80 <option value="FALSE">CN and SNP probes</option>
81 <option value="TRUE">Only SNP probes</option>
82 </param>
83 </when>
84 </conditional>
85 <conditional name="settings">
86 <param name="settingsType" type="select" label="Reference" help="">
87 <option value="standard">Study without reference</option>
88 <option value="tumor">Normal-tumor study</option>
89 </param>
90 <when value="standard" />
91 <when value="tumor">
92 <param name="tumorcsv" type="data" format="csv" label="tumor boost csv file" help="Normal-tumor csv file. See below for more information."/>
93 </when>
94 </conditional>
95
96 <param name="folds" type="integer" min="1" value="10" label ="Number of folds for cross validation" help="Integer between 1 and number of file in the .cel file dataset"/>
97 <conditional name="settingsLoss">
98 <param name="loss" type="select" multiple="false" label="Response type">
99 <option value="linear">Linear</option>
100 <option value="logistic">Logistic</option>
101 </param>
102 <when value="logistic" />
103 <when value="linear">
104 <param name="package" type="select" multiple="false" label="Method" help="Either “HDPenReg” or “spikeslab”. Used package in linear case">
105 <option value="HDPenReg">HDPenReg</option>
106 <option value="spikeslab">spikeslab</option>
107 </param>
108 </when>
109 </conditional>
110 <param name="outputgraph" type="select" multiple="false" label="Plot figures">
111 <option value="TRUE">Yes</option>
112 <option value="FALSE">No</option>
113 </param>
114 <param name="outputlog" type="select" label="Output log">
115 <option value="TRUE">Yes</option>
116 <option value="FALSE">No</option>
117 </param>
118
119 </inputs>
120 <outputs>
121 <data format="tabular" name="output" label="selection of ${input.name}" />
122 <data format="pdf" name="pdffigures" label="figures of SNPs selection of ${input.name}">
123 <filter>outputgraph == "TRUE"</filter>
124 <filter>(settingsLoss['package'] != 'spikeslab')</filter>
125 </data>
126 <data format="log" name="log" label="log of SNPs selection 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 SNPs selection. 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 **What it does**
141
142 This tool selects some relevant markers according to a response using penalized regressions.
143
144 Output:
145
146 A tabular text file containing 5 columns which describe all the selected SNPs (1 line per SNPs):
147
148 - chr: Chromosome containing the selected SNP.
149 - position: Position of the selected SNP.
150 - index: Index of the selected SNP.
151 - names: Name of the selected SNP.
152 - coefficient: Regression coefficient of the selected SNP.
153
154 -----
155
156 **Data Response csv file**
157
158 Data response csv file format:
159
160 - The first column contains the names of the different files of the data-set.
161
162 - The second column contains the response associated with each file.
163
164 - Column names of these two columns are respectively files and response.
165
166 - Columns are separated by a comma
167
168 - *Extensions of the files (.CEL for example) should be removed*
169
170
171
172 **Example**
173
174 Let 3 .cel files in the studied dataset ::
175
176 patient1.cel
177 patient2.cel
178 patient3.cel
179
180 The csv file should look like this ::
181
182 files,response
183 patient1,1.92145
184 patient2,2.12481
185 patient3,1.23545
186
187
188 -----
189
190 **Normal-tumor study**
191
192 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 :
193
194 - The first column contains the names of the files corresponding to normal samples of the dataset.
195
196 - The second column contains the names of the tumor samples files.
197
198 - Column names of these two columns are respectively normal and tumor.
199
200 - Columns are separated by a comma.
201
202 - *Extensions of the files (.CEL for example) should be removed*
203
204
205 **Example**
206
207 Let 6 .cel files in the studied dataset (3 patients, each of them being represented by a couple of normal and tumor cel file.) ::
208
209 patient1_normal.cel
210 patient1_tumor.cel
211 patient2_normal.cel
212 patient2_tumor.cel
213 patient3_normal.cel
214 patient3_tumor.cel
215
216
217 The csv file should look like this ::
218
219 normal,tumor
220 patient1_normal,patient1_tumor
221 patient2_normal,patient2_tumor
222 patient3_normal,patient3_tumor
223
224 -----
225
226
227
228 **Citation**
229
230 If you use this tool please cite :
231
232 `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;`_
233
234 </help>
235 </tool>