Mercurial > repos > workflow4metabolomics > correlation_analysis
comparison abims_correlation_analysis.xml @ 0:58997c28b268 draft default tip
"planemo upload for repository https://github.com/workflow4metabolomics/tools-metabolomics/blob/master/tools/correlation_analysis/ commit 35a01e4ef59a91f43d0b1de1d08db29dcc7aae1e"
author | workflow4metabolomics |
---|---|
date | Tue, 19 Jan 2021 16:41:47 +0000 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:58997c28b268 |
---|---|
1 <tool id="correlation_analysis" name="Metabolites Correlation Analysis" version="1.0.1+galaxy0" > | |
2 | |
3 <description>to highlight ion correlations considering PC-groups</description> | |
4 | |
5 <requirements> | |
6 <requirement type="package" version="1.1_5">r-batch</requirement> | |
7 <requirement type="package" version="0.8.8">r-reshape</requirement> | |
8 <requirement type="package" version="7.3_53">r-mass</requirement> | |
9 </requirements> | |
10 | |
11 <command detect_errors='exit_code'> | |
12 Rscript '$__tool_directory__/correlation_analysis.r' | |
13 | |
14 #if $cond_input_type.select_input_type == "select_input_from_w4m" and $cond_input_type.cond_function.select_funtion == "sort_only" : | |
15 sorting 1 variable_metadata '$cond_input_type.variableMetadata' | |
16 data_matrix '$cond_input_type.dataMatrix' | |
17 sample_metadata '$cond_input_type.sampleMetadata' | |
18 corrdel 0 | |
19 param_correlation "" | |
20 param_cytoscape "" | |
21 matrix_corr 0 | |
22 user_matrix_corr "" | |
23 corr_method "" | |
24 #end if | |
25 #if $cond_input_type.select_input_type == "select_input_from_w4m" and $cond_input_type.cond_function.select_funtion == "sort_and_corr" : | |
26 sorting 1 | |
27 variable_metadata '$cond_input_type.variableMetadata' | |
28 data_matrix '$cond_input_type.dataMatrix' | |
29 sample_metadata '$cond_input_type.sampleMetadata' | |
30 corrdel 1 | |
31 param_correlation $cond_input_type.cond_function.param_correlation | |
32 param_cytoscape $cond_input_type.cond_function.param_cytoscape | |
33 matrix_corr 0 | |
34 user_matrix_corr "" | |
35 corr_method $cond_input_type.cond_function.corr_method | |
36 #end if | |
37 ##Create correlation matrix from a user table file.## | |
38 #if $cond_input_type.select_input_type == "select_input_other" : | |
39 sorting 0 | |
40 variable_metadata "" | |
41 data_matrix "" | |
42 sample_metadata "" | |
43 corrdel 0 | |
44 param_correlation "" | |
45 param_cytoscape $cond_input_type.param_cytoscape | |
46 matrix_corr 1 | |
47 user_matrix_corr '$cond_input_type.user_matrix_corr' | |
48 corr_method $cond_input_type.corr_method | |
49 #end if | |
50 | |
51 </command> | |
52 | |
53 <inputs> | |
54 | |
55 | |
56 <conditional name="cond_input_type" > | |
57 <param name="select_input_type" type="select" label="Choice of your input files" help="" > | |
58 <option value="select_input_from_w4m" selected="true">Files from the metabolomic workflow</option> | |
59 <option value="select_input_other" >Your table file</option> | |
60 </param> | |
61 <when value="select_input_from_w4m"> | |
62 <param name="dataMatrix" type="data" label="Data matrix" format="tabular" help="dataMatrix file from the CAMERA.annotate step for example" /> | |
63 <param name="sampleMetadata" type="data" label="Sample metadata" format="tabular" help="sampleMetadata file from the xcms.xcmsSet step for example" /> | |
64 <param name="variableMetadata" type="data" label="Variable metadata" format="tabular" help="variableMetadata file from the CAMERA.annotate step for example" /> | |
65 <conditional name="cond_function" > | |
66 <param name="select_funtion" type="select" label="Function to be used" help="" > | |
67 <option value="sort_only" selected="true">Sorting your table</option> | |
68 <option value="sort_and_corr" >Sorting your table and doing correlation analysis</option> | |
69 </param> | |
70 <when value="sort_only" /> | |
71 <when value="sort_and_corr"> | |
72 <param name="corrdel" type="hidden" value="1"/> | |
73 <param name="param_correlation" type="float" label="Correlation threshold for pcgroup" value="0.60" help="Threshold value for selecting edges (i.e. correlations) that will be exported to the Cytoscape sif format file" /> | |
74 <param name="corr_method" type="select" label="Choice of the correlation method" help="" > | |
75 <option value="pearson" selected="true">pearson</option> | |
76 <option value="kendall">kendall</option> | |
77 <option value="spearman">spearman</option> | |
78 </param> | |
79 <param name="param_cytoscape" type="float" label="Cytoscape correlation threshold" value="0.75" help="Choose a threshold value for selecting metabolites that will be exported to a cytoscape sif format" /> | |
80 </when> | |
81 </conditional> | |
82 </when> | |
83 | |
84 <when value="select_input_other"> | |
85 <param name="user_matrix_corr" type="data" label="Your table file (tabular format)" format="tabular" help="Your metabolites (variables) intensity table file (tabular format)" /> | |
86 <param name="corr_method" type="select" label="Choice of the correlation method" help="" > | |
87 <option value="pearson" selected="true">pearson</option> | |
88 <option value="kendall">kendall</option> | |
89 <option value="spearman">spearman</option> | |
90 </param> | |
91 <param name="param_cytoscape" type="float" label="Cytoscape correlation threshold" value="0.75" help="Threshold value for selecting edges (i.e. correlations) that will be exported to the Cytoscape sif format file" /> | |
92 </when> | |
93 </conditional> | |
94 </inputs> | |
95 | |
96 <outputs> | |
97 <data name="sorted_table" format="tabular" from_work_dir="sorted_table.tsv" label="sorted_variableMetadata.tsv"> | |
98 <filter>(cond_input_type['select_input_type'] == 'select_input_from_w4m')</filter> | |
99 </data> | |
100 <data name="correlation_matrix_selected" format="tabular" from_work_dir="correlation_matrix_selected.tsv" label="correlation_matrix_selected.tsv"> | |
101 <filter>(cond_input_type['select_input_type'] == 'select_input_from_w4m' and cond_input_type['cond_function']['select_funtion']== 'sort_and_corr' and cond_input_type['cond_function']['corrdel']== '1' )</filter> | |
102 </data> | |
103 <data name="siff_table" format="tabular" from_work_dir="siff_table.tsv" label="sif_table.tsv"> | |
104 <filter>(cond_input_type['select_input_type'] == 'select_input_from_w4m' and cond_input_type['cond_function']['select_funtion']== 'sort_and_corr' and cond_input_type['cond_function']['corrdel']== '1' )</filter> | |
105 </data> | |
106 <data name="correlation_matrix_user" format="tabular" from_work_dir="correlation_matrix.tsv" label="correlation_matrix.tsv"> | |
107 <filter>(cond_input_type['select_input_type'] == 'select_input_other')</filter> | |
108 </data> | |
109 <data name="siff_table_user_user" format="tabular" from_work_dir="siff_table.tsv" label="sif_table.tsv"> | |
110 <filter>(cond_input_type['select_input_type'] == 'select_input_other')</filter> | |
111 </data> | |
112 </outputs> | |
113 | |
114 <tests> | |
115 <test expect_num_outputs="3"> | |
116 <conditional name="cond_input_type" > | |
117 <param name="select_input_type" value="select_input_from_w4m" /> | |
118 <param name="dataMatrix" value="in_DM1.tabular" ftype="tabular" /> | |
119 <param name="sampleMetadata" value="in_SM1.tabular" ftype="tabular" /> | |
120 <param name="variableMetadata" value="in_VM1.tabular" ftype="tabular" /> | |
121 <conditional name="cond_function" > | |
122 <param name="select_funtion" value="sort_and_corr" /> | |
123 </conditional> | |
124 </conditional> | |
125 <output name="sorted_table" file="out_VM1.tabular"/> | |
126 <output name="correlation_matrix_selected" file="out_corr1.tabular"/> | |
127 <output name="siff_table" file="out_sif1.tabular"/> | |
128 </test> | |
129 </tests> | |
130 | |
131 <help> | |
132 | |
133 .. class:: infomark | |
134 | |
135 **Authors** Antoine Gravot (Protocole conception) and Misharl Monsoor (for initial galaxy wrapper and R script). | |
136 | |
137 **Additional W4M contributors** ABiMS TEAM (SU/CNRS - Station biologique de Roscoff) and PFEM (INRAE - MetaboHUB) | |
138 | |
139 --------------------------------------------------- | |
140 | |
141 ================================ | |
142 Metabolites correlation analysis | |
143 ================================ | |
144 | |
145 ----------- | |
146 Description | |
147 ----------- | |
148 | |
149 This tool takes as inputs either tabular table files from the metabolomic workflow (variableMetadata, dataMatrix and sampleMetadata) or a table file of your own | |
150 and can execute three different functions ("sorting", "corrdel" and "corr_matrix"). | |
151 | |
152 **The "sorting" function:** *used for metabolomic workflow* | |
153 | |
154 | 1) First of all, it sorts the data by pcgroup. | |
155 | 2) It computes the mean operation of all the signal values of the metabolites by sample, and put the results in a new column "signal_moy". | |
156 | 3) It finally creates a tabular output "sorted_variableMetadata.tsv". | |
157 | |
158 **The "corrdel" function:** *used for metabolomic workflow* | |
159 | |
160 | **For each pcgroup** of the previous sorted tabular file "sorted_table.tsv", it does the following things: | |
161 | - it computes a correlation matrix | |
162 | - it determines the metabolites which are not correlated to others from the same pcgroup based on the threshold value filled in the "Correlation threshold for pcgroup" parameter | |
163 | - the metabolites are sorted by the mean signal intensity (form the highest to the lowest), and each metabolite is tested to the previous ones in the list ; if the tested metabolite is at least correlated to one previous one, it is tagged as DEL (for "deleted", written in a column called "suppress") | |
164 | | |
165 | It creates two additional tabular files: | |
166 | - "correlation_matrix_selected.tsv" (correlation matrix of selected metabolites only) | |
167 | - "sif_table.tsv" (for visualization in CytoScape, based on selected metabolites and "Cytoscape correlation threshold" filled value) | |
168 | |
169 | |
170 **The "corr_matrix" function:** *used for user table file* | |
171 | |
172 | It computes a correlation matrix named "correlation_matrix.tsv" and creates a sif file named "sif_table.tsv" (for visualization in CytoScape). | |
173 | |
174 | |
175 | |
176 ----------------- | |
177 Workflow position | |
178 ----------------- | |
179 | |
180 | |
181 **Examples of upstream tools** | |
182 | |
183 +---------------------------+--------------------------+--------+------------------------+ | |
184 | Name | Output file | Format | parameter | | |
185 +===========================+==========================+========+========================+ | |
186 |xcms findChromPeaks Merger |sampleMetada.tsv | Tabular| Sample metadata | | |
187 +---------------------------+--------------------------+--------+------------------------+ | |
188 |xcms fillChromPeaks |dataMatrix.tsv | Tabular| Data matrix | | |
189 +---------------------------+--------------------------+--------+------------------------+ | |
190 |CAMERA.annotate |variableMetadata.tsv | Tabular| Variable metadata | | |
191 +---------------------------+--------------------------+--------+------------------------+ | |
192 | |
193 | |
194 | |
195 **Examples of downstream tools** | |
196 | |
197 +---------------------------+--------------------------------------+--------+ | |
198 | Name | Output file | Format | | |
199 +===========================+======================================+========+ | |
200 |Hierarchical Clustering |selected_metabolites_transpo.tsv | Tabular| | |
201 +---------------------------+--------------------------------------+--------+ | |
202 |ANOVA |selected_metabolites_transpo.tsv | Tabular| | |
203 +---------------------------+--------------------------------------+--------+ | |
204 | |
205 | |
206 | |
207 **General schema of the metabolomic workflow** | |
208 | |
209 .. image:: MetaboAnalysisCorrelation_workflow.png | |
210 | |
211 ----------- | |
212 Input files | |
213 ----------- | |
214 | |
215 +--------------------------------+------------+ | |
216 | Parameter: label | Format | | |
217 +================================+============+ | |
218 | Data matrix | Tabular | | |
219 +--------------------------------+------------+ | |
220 | Sample metadata | Tabular | | |
221 +--------------------------------+------------+ | |
222 | Variable metadata | Tabular | | |
223 +--------------------------------+------------+ | |
224 | User table file | Tabular | | |
225 +--------------------------------+------------+ | |
226 | |
227 | |
228 ---------- | |
229 Parameters | |
230 ---------- | |
231 | |
232 **Choice of your input files** | |
233 | |
234 | **variableMetadata** | |
235 | | |
236 | For example, the "variableMetadata.tsv" tabular file generated by the CAMERA.annotate step of the workflow. | |
237 | This table must contain in particular two columns named "**pcgroup**" and "**rt**" (it is case-sensitive). | |
238 | | |
239 | **dataMatrix** | |
240 | | |
241 | For example, the "dataMatrix.tsv" tabular file generated by the CAMERA.annotate step of the workflow. | |
242 | | |
243 | **sampleMetadata** | |
244 | | |
245 | For example, the tabular file with the samples metadata generated by the xcmsSet step: one sample per line and at least two columns: ids and one variable. | |
246 | | |
247 | **user table** | |
248 | | |
249 | Tabular containing intensities where your variables (metabolites) are in columns (for example a transposition of your datamatrix file) | |
250 | |
251 **Correlation threshold for pcgroup** *(metabolomic workflow only)* | |
252 | |
253 The threshold value that will determine if two metabolites are correlated inside a same pcgroup after the creation of the global correlation matrix. | |
254 If you do not want to use the intra-pcgroup filter (see "corrdel" function in the description section), put this threshold to 1 and all ions will be kept. | |
255 | |
256 **Choice of the correlation method** | |
257 | |
258 Choose the correlation method (pearson, kendall or spearman). | |
259 | |
260 **Cytoscape correlation threshold** | |
261 | |
262 Choose a threshold value for selecting edges (i.e. correlations between metabolites) that will be exported to the Cytoscape sif format file. | |
263 | |
264 ------------ | |
265 Output files | |
266 ------------ | |
267 | |
268 | |
269 | |
270 **sorted_variableMetadata.tsv** *(metabolomic workflow only)* | |
271 | |
272 | A tabular file which: | |
273 | 1) contains the original variable metadata columns | |
274 | 2) is sorted by the pcgroup column | |
275 | 3) contains a new column "signal_moy" (mean of all the signal values of the metabolites by sample) | |
276 | 4) (depending of parameters) contains a "suppress" column | |
277 | |
278 **correlation_matrix_selected.tsv** *(metabolomic workflow only)* | |
279 | |
280 | A correlation matrix containing only the metabolites selected in each pcgroup (metabolites tagged as "DEL" in "suppress" column are removed), | |
281 | completed with two columns "rtmed" and "signal_moy". | |
282 | |
283 **sif_table.tsv** | |
284 | |
285 | A tabular file (three columns: Metabolite1, Correlation coefficient, Metabolite 2) that can be used in Cytoscape. | |
286 | |
287 ------ | |
288 | |
289 .. class:: infomark | |
290 | |
291 The output **selected_metabolites_dataMatrix.tsv** is a tabular file. You can continue your analysis using it for example in the following statistical tools: | |
292 | Hierarchical Clustering | |
293 | ANOVA | |
294 | |
295 | |
296 --------------------------------------------------- | |
297 | |
298 Changelog/News | |
299 -------------- | |
300 | |
301 | |
302 **Version 1.0.1+galaxy0 - 10/12/2020** | |
303 | |
304 - Update of some of the outputs' formats to match standard W4M table format | |
305 - Standard output (stdout) log improvement | |
306 - Change of testing data for faster job running for tests | |
307 - Fix: generation of the outputs for "Your table file" option | |
308 | |
309 **Version 1.0.1 - 20/09/2016** | |
310 | |
311 - TEST: refactoring to pass functional test using conda dependencies | |
312 - Help improvement | |
313 | |
314 | |
315 **Version 20141118 - 18/11/2014** | |
316 | |
317 </help> | |
318 <citations> | |
319 <citation type="doi">10.1093/bioinformatics/btu813</citation> | |
320 </citations> | |
321 | |
322 </tool> |