Mercurial > repos > ppericard > viscorvar
comparison mixomics_blocksplsda.xml @ 4:d4e9f7546dfa draft
"planemo upload for repository https://gitlab.com/bilille/galaxy-viscorvar commit 579dc54316e8ede493f86f434a87d3d7b692b023"
author | ppericard |
---|---|
date | Tue, 17 Nov 2020 13:01:44 +0000 |
parents | c8533e9298e5 |
children | 88c1fd2ac110 |
comparison
equal
deleted
inserted
replaced
3:df8428358b7f | 4:d4e9f7546dfa |
---|---|
1 <tool id="mixomics_blocksplsda" name="mixOmics block.splsda" version="@TOOL_VERSION@+galaxy1" profile="16.04" workflow_compatible="true"> | 1 <tool id="mixomics_blocksplsda" name="mixOmics block.splsda" version="@TOOL_VERSION@+galaxy2" profile="16.04" workflow_compatible="true"> |
2 | 2 |
3 <description>performs N-integration and feature selection with Projection to Latent Structures models (PLS) with sparse Discriminant Analysis</description> | 3 <description>performs N-integration and feature selection with Projection to Latent Structures models (PLS) with sparse Discriminant Analysis</description> |
4 | 4 |
5 <macros> | 5 <macros> |
6 <import>macros.xml</import> | 6 <import>macros.xml</import> |
44 | 44 |
45 --rdata_out ${rdata_out} | 45 --rdata_out ${rdata_out} |
46 ##--sample_metadata_out ${sample_metadata_out} | 46 ##--sample_metadata_out ${sample_metadata_out} |
47 --variable_metadata_outdir outdir | 47 --variable_metadata_outdir outdir |
48 | 48 |
49 @COMMAND_LOG_EXIT@ | |
50 | |
51 ]]></command> | 49 ]]></command> |
52 | 50 |
53 <inputs> | 51 <inputs> |
54 <repeat name="blocks" title="Blocks"> | 52 <repeat name="blocks" title="Blocks"> |
55 <param name="block_name" type="text" label="Block name" /> | 53 <param name="block_name" type="text" label="Block name" /> |
56 <param name="keep" type="integer" value="0" min="0" | 54 <param name="keep" type="integer" value="0" min="0" |
57 label="Number of variables to select for each component" | 55 label="Number of variables to select for each component" |
58 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." /> | 56 help="estimation of the number of variables of the block correlated with variables of the other blocks and correlated with response variables. If set to 0, all variables will be selected" /> |
59 <param name="data_matrix" type="data" format="tabular" | 57 <param name="data_matrix" type="data" format="tabular" |
60 label="Data matrix" | 58 label="Data matrix" |
61 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." /> | 59 help="data matrix contains the values of the variables. For the file structure, see below in the section Input files" /> |
62 <param name="variable_metadata" type="data" format="tabular" optional="true" | 60 <param name="variable_metadata" type="data" format="tabular" optional="true" |
63 label="Variables metadata [optional]" | 61 label="Variables metadata [optional]" |
64 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." /> | 62 help="variables metadata contains the metadata of the variables. For the file structure, see below in the section Input files" /> |
65 </repeat> | 63 </repeat> |
66 <param name="sample_metadata_in" type="data" format="tabular" | 64 <param name="sample_metadata_in" type="data" format="tabular" |
67 label="Samples metadata" | 65 label="Samples metadata" |
68 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." /> | 66 help="samples metadata contains the metadata of the samples. For the file structure, see below in the section Global input files" /> |
69 <param name="sample_description_col" type="integer" value="0" min="0" | 67 <param name="sample_description_col" type="integer" value="0" min="0" |
70 label="Samples groups column number" | 68 label="Samples groups column number" |
71 help="Column from the samples metadata file containing samples groups. If set to 0, the last column will be used." /> | 69 help="column from the samples metadata file containing samples groups. If set to 0, the last column will be used" /> |
72 <param name="correlation" type="boolean" truevalue="--correlation" | 70 <param name="correlation" type="boolean" truevalue="--correlation" |
73 falsevalue="" checked="false" | 71 falsevalue="" checked="false" |
74 label="Correlation between all blocks" | 72 label="Correlation between all blocks" |
75 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)." /> | 73 help="if set to Yes, data integration will take into account correlations between all the blocks. If set to No, data integration will only take into account correlations between the blocks and the response" /> |
76 <section name="adv" title="Advanced Options" expanded="false"> | 74 <section name="adv" title="Advanced Options" expanded="false"> |
77 <param name="ncomp" type="integer" value="2" min="1" | 75 <param name="ncomp" type="integer" value="2" min="1" |
78 label="Number of components to include in the model" | 76 label="Number of components to include in the model" |
79 help="[ncomp] Number of new variables (components) computed by the data integration." /> | 77 help="number of new variables (components) computed by the data integration" /> |
80 <!-- <param name="scheme" type="select" label="Scheme"> | 78 <!-- <param name="scheme" type="select" label="Scheme"> |
81 <option value="horst" selected="true">horst</option> | 79 <option value="horst" selected="true">horst</option> |
82 <option value="factorial" >factorial</option> | 80 <option value="factorial" >factorial</option> |
83 <option value="centroid" >centroid</option> | 81 <option value="centroid" >centroid</option> |
84 </param> | 82 </param> |
88 <option value="invariant" >invariant</option> | 86 <option value="invariant" >invariant</option> |
89 <option value="classic" >classic</option> | 87 <option value="classic" >classic</option> |
90 </param> --> | 88 </param> --> |
91 <param name="maxiter" type="integer" value="100" min="1" | 89 <param name="maxiter" type="integer" value="100" min="1" |
92 label="Maximum number of iterations" | 90 label="Maximum number of iterations" |
93 help="[max.iter] Maximum number of iterations performed by block.splsda." /> | 91 help="maximum number of iterations performed by block.splsda" /> |
94 <!-- <param name="scale" type="boolean" truevalue="-\-scale" falsevalue="" checked="true" | 92 <!-- <param name="scale" type="boolean" truevalue="-\-scale" falsevalue="" checked="true" |
95 label="Scale" | 93 label="Scale" |
96 help="if checked, each block is standardized to zero means and unit variances" /> --> | 94 help="if checked, each block is standardized to zero means and unit variances" /> --> |
97 <param name="check_missing_values" type="boolean" truevalue="-\-check_missing_values" falsevalue="" checked="true" | 95 <param name="check_missing_values" type="boolean" truevalue="-\-check_missing_values" falsevalue="" checked="true" |
98 label="Check for missing values" | 96 label="Check for missing values" |
128 <repeat name="blocks"> | 126 <repeat name="blocks"> |
129 <param name="block_name" value="Block2" /> | 127 <param name="block_name" value="Block2" /> |
130 <param name="data_matrix" value="in_block2_data.tabular" /> | 128 <param name="data_matrix" value="in_block2_data.tabular" /> |
131 </repeat> | 129 </repeat> |
132 <param name="sample_metadata_in" value="in_sample_meta.tabular" /> | 130 <param name="sample_metadata_in" value="in_sample_meta.tabular" /> |
133 <output name="rdata_out" value="out_rdata.rdata" /> | 131 <!-- <param name="correlation" value=true /> --> |
132 <output name="rdata_out" value="mixomics_blocksplsda_output.rdata" /> | |
134 <!-- <output name="sample_metadata_out" value="out_sample_meta.tabular" /> --> | 133 <!-- <output name="sample_metadata_out" value="out_sample_meta.tabular" /> --> |
135 </test> | 134 </test> |
136 </tests> | 135 </tests> |
137 | 136 |
138 <help><![CDATA[ | 137 <help><![CDATA[ |
145 | 144 |
146 ----------- | 145 ----------- |
147 Description | 146 Description |
148 ----------- | 147 ----------- |
149 | 148 |
150 The blocks.splsda function is part of the mixOmics package for exploration and integration of Omics datasets. | 149 The blocks.splsda function is part of the mixOmics package for exploration and integration of omics datasets. |
151 Performs N-integration and feature selection with Projection to Latent Structures models (PLS) with sparse Discriminant Analysis. | 150 This data integration takes as input parameters different omics datasets |
151 (transcriptomic, metabolomic, metagenomic, ...) and a response variable (e.g. for a sample, the value of the response | |
152 variable is equal to « Treated » or « Control »). This data integration returns, for each omics dataset, variables | |
153 which are correlated with the variables of the other omic datasets and the response variable. The other functions of | |
154 this pipeline allow visualizing this correlated variables thanks to correlation circles and networks. | |
152 | 155 |
153 ----------------- | 156 ----------------- |
154 Workflow position | 157 Workflow position |
155 ----------------- | 158 ----------------- |
156 | 159 |
181 | 1 : Data matrix | tabular | | 184 | 1 : Data matrix | tabular | |
182 +------------------------------+------------+ | 185 +------------------------------+------------+ |
183 | 2 : [opt] Variables metadata | tabular | | 186 | 2 : [opt] Variables metadata | tabular | |
184 +------------------------------+------------+ | 187 +------------------------------+------------+ |
185 | 188 |
189 1. Data matrix structure | |
190 The data matrix is in tabular format (.tsv). | |
191 The first column contains the variables names. | |
192 The first row contains the samples names. | |
193 Samples names must be in the same order for all blocks and the sample metadata (transposed). The data must not contain missing values. | |
194 | |
195 2. Variables metadata structure | |
196 The variables metadata is in tabular format (.tsv). | |
197 The first colum contains the variables names. | |
198 The first row contains the metadata column names. | |
199 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. | |
200 | |
186 Variables metadata files are optional. | 201 Variables metadata files are optional. |
187 If a file is provided, output metadata will be appended to the input file, otherwise a new output file will be created. | 202 If a file is provided, output metadata will be appended to the input file, otherwise a new output file will be created. |
188 | 203 |
189 1. Data matrix format | |
190 * Rows = variables, Columns = samples | |
191 * 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) | |
192 * First column = variables name | |
193 | |
194 2. Variables metadata format | |
195 * Rows = variables, Columns = metadata | |
196 * First row = metadata column names | |
197 * First column = variables names. MUST be the same and in the same order than in the associated data matrix | |
198 | 204 |
199 Global input files: | 205 Global input files: |
200 ------------------- | 206 ------------------- |
201 | 207 |
202 +-----------------------------+------------+ | 208 +-----------------------------+------------+ |
203 | Parameter : num + label | Format | | 209 | Parameter : num + label | Format | |
204 +=============================+============+ | 210 +=============================+============+ |
205 | 1 : Samples metadata | tabular | | 211 | 1 : Samples metadata | tabular | |
206 +-----------------------------+------------+ | 212 +-----------------------------+------------+ |
207 | 213 |
208 By default, the last column of the samples metadata matrix will be used as samples description factors. | 214 1. Samples metadata structure |
209 If it's not the case, the column number can be inputed in the `Sample description column number` parameter. | 215 Samples metadata is in tabular format (.tsv). |
210 | 216 The first column contains the sample names. |
211 1. Samples metadata format | 217 The first row contains the metadata column names. |
212 * Rows = samples, Columns = metadata | 218 Samples names must be in the same order in samples metadata (transposed) and all the blocks. One of the column (the last by default) must contain the samples groups for integration. |
213 * First row = metadata column names | |
214 * First column = sample names. These names must be identical (transposed) and in the same order than for the blocks data matrices | |
215 | 219 |
216 ---------- | 220 ---------- |
217 Parameters | 221 Parameters |
218 ---------- | 222 ---------- |
219 | 223 |