Mercurial > repos > ppericard > viscorvar

comparison mixomics_blocksplsda.xml @ 0:d0b77b926863 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://gitlab.com/bilille/galaxy-viscorvar commit 85dac6b13a9adce48b47b2b8cb28d2319ae9c1ca-dirty"
author ppericard
date Tue, 23 Jun 2020 19:57:35 -0400
parents
children e93350dc99f1
comparison
equal deleted inserted replaced
-1:000000000000 0:d0b77b926863
1 <tool id="mixomics_blocksplsda" name="mixOmics block.splsda" version="1.0" profile="16.04" workflow_compatible="true">
2
3 <description>performs N-integration and feature selection with Projection to Latent Structures models (PLS) with sparse Discriminant Analysis</description>
4
5 <requirements>
6 <requirement type="package" version="6.12">bioconductor-mixomics</requirement>
7 <requirement type="package" version="2.0">r-argparse</requirement>
8 </requirements>
9
10 <!-- <stdio>
11 <exit_code range="1:" level="fatal" />
12 </stdio> -->
13
14 <command detect_errors="aggressive">
15 <![CDATA[
16 mkdir outdir
17 && Rscript
18 ${__tool_directory__}/mixomics_blocksplsda_script.R
19 #for $b in $blocks
20 --block
21 #if $b.block_name
22 ${b.block_name}
23 #else
24 ${b.data_matrix.name}
25 #end if
26 ${b.keep}
27 ${b.data_matrix}
28 ${b.variable_metadata}
29 #end for
30 --sample_metadata_in ${sample_metadata_in}
31 --sample_description_col ${sample_description_col}
32 --ncomp ${adv.ncomp}
33 ${correlation}
34 ##--scheme ${adv.scheme}
35 ##--mode ${adv.mode}
36 --maxiter ${adv.maxiter}
37 ##${adv.scale}
38 --scale ## always activated hidden param
39 ${adv.check_missing_values}
40 ##--init ${adv.init}
41 ##--tol ${adv.tol}
42 ##${adv.nearzerovar}
43 --rdata_out ${rdata_out}
44 --sample_metadata_out ${sample_metadata_out}
45 --variable_metadata_outdir outdir
46 ]]>
47 </command>
48
49 <inputs>
50 <repeat name="blocks" title="Blocks">
51 <param name="block_name" type="text" label="Block name" />
52 <param name="keep" type="integer" value="0" min="0"
53 label="Number of variables to select for each component"
54 help="[keep] Estimation of the number of variables in the block correlated with variables from the other blocks and correlated with response variables. If set to 0, all variables will be selected." />
55 <param name="data_matrix" type="data" format="tabular"
56 label="Data matrix"
57 help="Block data in tabular format (rows = variables, columns = samples). The first column contains the variables names and the first row contains the samples names. Samples names must be in the same order for all blocks and the sample metadata (transposed). The data must not contain missing values." />
58 <param name="variable_metadata" type="data" format="tabular" optional="true"
59 label="Variables metadata [optional]"
60 help="Variables metadata in tabular format (rows = variables). The first colum contains the variables names. The first row contains the metadata column names. The number of rows in the metadata file must be the same than the number of rows in the block data file, and the variables need to be in the same order. If a metadata file is provided, block.splsda output will be appended as new columns, otherwise a new file will be created." />
61 </repeat>
62 <param name="sample_metadata_in" type="data" format="tabular"
63 label="Samples metadata"
64 help="Samples metadata in tabular format (rows = samples). The first column contains the sample names. The first row contains the metadata column names. Samples names must be in the same order (transposed) than all the blocks. One of the column (the last by default) must contain the samples groups for integration." />
65 <param name="sample_description_col" type="integer" value="0" min="0"
66 label="Samples groups column number"
67 help="Column from the samples metadata file containing samples groups. If set to 0, the last column will be used." />
68 <param name="correlation" type="boolean" truevalue="--correlation"
69 falsevalue="" checked="false"
70 label="Correlation between all blocks"
71 help="[design] If set to Yes, data integration will take into account correlations between all the blocks (design matrix with diagonal coefficients set to 0 and the rest of the coefficients set to 1)." />
72 <section name="adv" title="Advanced Options" expanded="false">
73 <param name="ncomp" type="integer" value="2" min="1"
74 label="Number of components to include in the model"
75 help="[ncomp] Number of new variables (components) computed by the data integration." />
76 <!-- <param name="scheme" type="select" label="Scheme">
77 <option value="horst" selected="true">horst</option>
78 <option value="factorial" >factorial</option>
79 <option value="centroid" >centroid</option>
80 </param>
81 <param name="mode" type="select" label="Mode">
82 <option value="regression" selected="true">regression</option>
83 <option value="canonical" >canonical</option>
84 <option value="invariant" >invariant</option>
85 <option value="classic" >classic</option>
86 </param> -->
87 <param name="maxiter" type="integer" value="100" min="1"
88 label="Maximum number of iterations"
89 help="[max.iter] Maximum number of iterations performed by block.splsda." />
90 <!-- <param name="scale" type="boolean" truevalue="-\-scale" falsevalue="" checked="true"
91 label="Scale"
92 help="if checked, each block is standardized to zero means and unit variances" /> -->
93 <param name="check_missing_values" type="boolean" truevalue="-\-check_missing_values" falsevalue="" checked="true"
94 label="Check for missing values"
95 help="will raise an error if missing values are found in data matrices" />
96 <!-- <param name="init" type="select" label="Init">
97 <option value="svd" selected="true">svd</option>
98 <option value="svd.single" >svd.single</option>
99 </param>
100 <param name="tol" type="float" value="1e-06" min="0"
101 label="Convergence stopping value"
102 help="[tol]" />
103 <param name="nearzerovar" type="boolean" truevalue="-\-nearzerovar" falsevalue="" checked="true"
104 label="Should be set to TRUE in particular for data with many zero values" /> -->
105 </section>
106 </inputs>
107
108 <outputs>
109 <data name="rdata_out" format="rdata" label="${tool.name}_output.rdata" />
110 <data name="sample_metadata_out" format="tabular"
111 label="${tool.name}_${sample_metadata_in.name}" />
112 <collection name="blocks_output" type="list" label="${tool.name}_blocks_output">
113 <discover_datasets pattern="(?P&lt;designation&gt;.+)\.tsv"
114 directory="outdir" format="tabular" />
115 </collection>
116 </outputs>
117
118 <tests>
119 <test>
120 <repeat name="blocks">
121 <param name="block_name" value="Block1" />
122 <param name="data_matrix" value="in_block1_data.tabular" />
123 </repeat>
124 <repeat name="blocks">
125 <param name="block_name" value="Block2" />
126 <param name="data_matrix" value="in_block2_data.tabular" />
127 </repeat>
128 <param name="sample_metadata_in" value="in_sample_meta.tabular" />
129 <output name="rdata_out" value="out_rdata.rdata" />
130 <output name="sample_metadata_out" value="out_sample_meta.tabular" />
131 </test>
132 </tests>
133
134 <help>
135 <![CDATA[
136 .. class:: infomark
137
138 **Authors** Pierre Pericard (pierre.pericard@pasteur-lille.fr)
139
140 ---------------------------------------------------
141
142 .. class:: infomark
143
144 **Please cite**
145
146 Rohart F, Gautier B, Singh A, Lê Cao KA (2017) mixOmics: An R package for ‘omics feature selection and multiple data integration.
147 PLOS Computational Biology 13(11): e1005752. https://doi.org/10.1371/journal.pcbi.1005752
148
149 ---------------------------------------------------
150
151 ======================
152 mixOmics blocks.splsda
153 ======================
154
155 -----------
156 Description
157 -----------
158
159 The blocks.splsda function is part of the mixOmics package for exploration and integration of Omics datasets.
160 Performs N-integration and feature selection with Projection to Latent Structures models (PLS) with sparse Discriminant Analysis.
161
162 -----------
163 Input files
164 -----------
165
166 For each block (min 2 blocks):
167 ==============================
168
169 +------------------------------+------------+
170 | Parameter : num + label | Format |
171 +==============================+============+
172 | 1 : Data matrix | tabular |
173 +------------------------------+------------+
174 | 2 : [opt] Variables metadata | tabular |
175 +------------------------------+------------+
176
177 Variables metadata files are optional.
178 If a file is provided, output metadata will be appended to the input file, otherwise a new output file will be created.
179
180 1. Data matrix format
181 * Rows = variables, Columns = samples
182 * First row = samples name. MUST be the same and in the same order in every block as well as in the sample metadata file (transposed)
183 * First column = variables name
184
185 2. Variables metadata format
186 * Rows = variables, Columns = metadata
187 * First row = metadata column names
188 * First column = variables names. MUST be the same and in the same order than in the associated data matrix
189
190 Global input files:
191 ===================
192
193 +-----------------------------+------------+
194 | Parameter : num + label | Format |
195 +=============================+============+
196 | 1 : Samples metadata | tabular |
197 +-----------------------------+------------+
198
199 By default, the last column of the samples metadata matrix will be used as samples description factors.
200 If it's not the case, the column number can be inputed in the `Sample description column number` parameter.
201
202 1. Samples metadata format
203 * Rows = samples, Columns = metadata
204 * First row = metadata column names
205 * First column = sample names. These names must be identical (transposed) and in the same order than for the blocks data matrices
206
207 ----------
208 Parameters
209 ----------
210
211 For each block (min 2 blocks):
212 ==============================
213
214 Block name
215 Name of the block. If not provided, this will default to the input filename
216
217 Number of variables to select for each component
218 If set to 0 (default), all variables will be considered in the model
219
220 Global parameters:
221 ==================
222
223 Sample description column number
224
225 Number of components to include in the model
226
227 Correlation between all blocks
228
229 Advanced options:
230 =================
231
232 Scheme
233
234 Mode
235
236 Maximum number of iterations
237
238 Scale
239
240 Init
241
242 Convergence stopping value (tol)
243
244 Near zero var
245
246 ------------
247 Output files
248 ------------
249
250 mixomics_blocksplsda_output.rdata
251 | rData output
252 | Contains the `mixomics_result` R object containing the result of the block.splsda function
253
254 mixomics_blocksplsda_{input_sample_metadata_name}
255 | tabular output
256 | Identical to the input Sample metadata file with appended columns from the result of block.splsda function
257
258 mixomics_blocksplsda_blocks_output
259 A collection with the variable metadata output files (mixomics_blocksplsda_block_{block name}_variable_metadata) for each input block
260
261 ]]>
262 </help>
263
264 <citations>
265 <citation type="doi">10.1371/journal.pcbi.1005752</citation>
266 </citations>
267
268 </tool>