Mercurial > repos > iuc > dimet_pca_plot

comparison dimet_pca_plot.xml @ 0:952808ffa842 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/DIMet commit abca848510cb4ac8d09d95634147626ea578cdf0
author iuc
date Tue, 10 Oct 2023 11:51:59 +0000
parents
children 23f87b8cc62b
comparison
equal deleted inserted replaced
-1:000000000000 0:952808ffa842
1 <tool id="dimet_@EXECUTABLE@" name="dimet @TOOL_LABEL@" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.05">
2 <description>
3 Figures of Principal Component Analysis for tracer metabolomics (by DIMet)
4 </description>
5 <macros>
6 <token name="@TOOL_LABEL@">pca plot</token>
7 <token name="@EXECUTABLE@">pca_plot</token>
8 <import>macros.xml</import>
9 </macros>
10 <expand macro="requirements"/>
11 <command detect_errors="exit_code"><![CDATA[
12 @INIT_CONFIG@
13 @INIT_PCA@
14 @INIT_IMPUTE_VALUES@
15 @INIT_CONDITIONS@
16 HYDRA_FULL_ERROR=1 python -m dimet
17 -cp '$__new_file_path__/config'
18 '++hydra.run.dir=pca-plot'
19 '++figure_path=figures'
20 '++table_path=tables'
21 '++analysis={
22 dataset:{
23 _target_:dimet.data.DatasetConfig,
24 name: "Galaxy DIMet run"
25 },
26 method:{
27 _target_: dimet.method.PcaPlotConfig,
28 label: pca-plot,
29 name: "Generate Principal Component Analysis plots",
30 pca_split_further:['timepoint'],
31 draw_ellipses: null,
32 run_iris_demo: false,
33 color: condition,
34 style: timepoint,
35 figure_format:${output_options.figure_format},
36 impute_values:${impute_values}
37 },
38 label: pca-plot
39 }'
40 '++analysis.dataset.subfolder='
41 '++analysis.dataset.label='
42 '++analysis.dataset.conditions=${conds}'
43 #if $metadata_path:
44 '++analysis.dataset.metadata=metadata'
45 #end if
46 #if $abundance_file:
47 '++analysis.dataset.abundances=abundance'
48 #end if
49 #if $me_or_frac_contrib_file:
50 '++analysis.dataset.mean_enrichment=me_or_frac_contrib'
51 #end if
52 @REMOVE_CONFIG@
53
54 ]]></command>
55 <inputs>
56 <expand macro="input_parameters_pca"/>
57 <expand macro="conditions"/>
58 <section name="output_options" title="Output options">
59 <param name="figure_format" type="select" value="pdf" display="radio" label="Select output figure format" help="Please enter at max 1 format">
60 <option value="pdf">Pdf</option>
61 <option value="svg">Svg</option>
62 </param>
63 </section>
64 </inputs>
65
66 <outputs>
67 <collection name="report" type="list">
68 <discover_datasets pattern="__designation_and_ext__" directory="figures"/>
69 </collection>
70 </outputs>
71 <tests>
72 <test>
73 <param name="abundance_file" ftype="tabular" value="rawAbundances.csv" />
74 <param name="metadata_path" ftype="tabular" value="example2_metadata.csv"/>
75 <param name="conditions" value='Control,L-Cycloserine'/>
76 <section name="output_options">
77 <param name="figure_format" value="svg"/>
78 </section>
79 <output_collection name="report" type="list" count="18">
80 <element file="abundances--T0--cell_var.svg" name="abundances--T0--cell_var" ftype="svg" compare="sim_size" delta="100"/>
81 <element file="abundances--T0--cell--label-n_pc.svg" name="abundances--T0--cell--label-n_pc" ftype="svg" compare="sim_size" delta="100"/>
82 <element file="abundances--T0--cell--label-y_pc.svg" name="abundances--T0--cell--label-y_pc" ftype="svg" compare="sim_size" delta="100"/>
83 <element file="abundances--T0--med_var.svg" name="abundances--T0--med_var" ftype="svg" compare="sim_size" delta="100"/>
84 <element file="abundances--T0--med--label-n_pc.svg" name="abundances--T0--med--label-n_pc" ftype="svg" compare="sim_size" delta="100"/>
85 <element file="abundances--T0--med--label-y_pc.svg" name="abundances--T0--med--label-y_pc" ftype="svg" compare="sim_size" delta="100"/>
86 <element file="abundances--T2h--cell--label-n_pc.svg" name="abundances--T2h--cell--label-n_pc" ftype="svg" compare="sim_size" delta="100"/>
87 <element file="abundances--T2h--cell--label-y_pc.svg" name="abundances--T2h--cell--label-y_pc" ftype="svg" compare="sim_size" delta="100"/>
88 <element file="abundances--T2h--cell_var.svg" name="abundances--T2h--cell_var" ftype="svg" compare="sim_size" delta="100"/>
89 <element file="abundances--T2h--med--label-n_pc.svg" name="abundances--T2h--med--label-n_pc" ftype="svg" compare="sim_size" delta="100"/>
90 <element file="abundances--T2h--med--label-y_pc.svg" name="abundances--T2h--med--label-y_pc" ftype="svg" compare="sim_size" delta="100"/>
91 <element file="abundances--T2h--med_var.svg" name="abundances--T2h--med_var" ftype="svg" compare="sim_size" delta="100"/>
92 <element file="abundances--cell--label-n_pc.svg" name="abundances--cell--label-n_pc" ftype="svg" compare="sim_size" delta="100"/>
93 <element file="abundances--cell--label-y_pc.svg" name="abundances--cell--label-y_pc" ftype="svg" compare="sim_size" delta="100"/>
94 <element file="abundances--cell_var.svg" name="abundances--cell_var" ftype="svg" compare="sim_size" delta="100"/>
95 <element file="abundances--med--label-n_pc.svg" name="abundances--med--label-n_pc" ftype="svg" compare="sim_size" delta="100"/>
96 <element file="abundances--med--label-y_pc.svg" name="abundances--med--label-y_pc" ftype="svg" compare="sim_size" delta="100"/>
97 <element file="abundances--med_var.svg" name="abundances--med_var" ftype="svg" compare="sim_size" delta="100"/>
98 </output_collection>
99 </test>
100 </tests>
101 <help><![CDATA[
102 This module is part of DIMet: Differential analysis of Isotope-labeled targeted Metabolomics data (https://pypi.org/project/DIMet/).
103
104 This tool performs the Principal Components Analysis (PCA) on your data,
105 generating the figures with the results of the PCA, it is, the scatter-plot of the two first principal components or dimensions (eigenvalues), and the barplot of the percentage of explained variances across all the principal components detected in your data.
106
107 The figures in .pdf format are of publication quality, and as they are vectorial images you can open them and customize aesthetics with a professional image software such as Inkscape, Adobe Illustrator, Sketch, CorelDRAW, etc.
108
109
110 **Input data files**
111
112 This tool requires (at max.) 3 tab-delimited .csv files as inputs. There are two types of files:
113
114 - The measures' (or quantifications') files, that can be of 4 types.
115
116 - The metadata, a unique file with the description of the samples in your measures' files. This is compulsory.
117
118 For running DIMet @EXECUTABLE@ you need **at least one file** of measures:
119
120 - The total **abundances** (of the metabolites) file
121
122 - The mean **enrichment** or labelled fractional contributions
123
124
125 and one metadata file, WHICH IS COMPULSORY, see section **Metadata File Information**.
126
127
128 **Measures' files**
129
130 The measure's files must be organized as matrices:
131
132 - The first column must contain Metabolite IDs that are unique (not repeated) within the file.
133
134 - The rest of the columns correspond to the samples
135
136 - The rows correspond to the metabolites
137
138 - The values must be tab separated, with the first row containing the sample/column labels.
139
140 See the following examples of measures files:
141
142
143 Example - Metabolites **abundances**:
144
145 =============== ================== ================== ================== ================== ================== ==================
146 ID **MCF001089_TD01** **MCF001089_TD02** **MCF001089_TD03** **MCF001089_TD04** **MCF001089_TD05** **MCF001089_TD06**
147 =============== ================== ================== ================== ================== ================== ==================
148 2_3-PG 8698823.9926 10718737.7217 10724373.9 8536484.5 22060650 28898956
149 2-OHGLu 36924336 424336 92060650 45165 84951950 965165051
150 Glc6P 2310 2142 2683 1683 012532068 1252172
151 Gly3P 399298 991656565 525195 6365231 89451625 4952651963
152 IsoCit 0 0 0 84915613 856236 954651610
153 =============== ================== ================== ================== ================== ================== ==================
154
155 Example - mean **enrichment** or labeled fractional contributions:
156
157 =============== ================== ================== ================== ================== ================== ==================
158 ID **MCF001089_TD01** **MCF001089_TD02** **MCF001089_TD03** **MCF001089_TD04** **MCF001089_TD05** **MCF001089_TD06**
159 =============== ================== ================== ================== ================== ================== ==================
160 2_3-PG 0.9711 0.968 0.9909 0.991 0.40 0.9
161 2-OHGLu 0.01719 0.0246 0.554 0.555 0.73 0.68
162 Glc6P 0.06 0.66 2683 0.06 2068 2172
163 Gly3P 0.06 0.06 0.06 1 5 3
164 IsoCit 0.06 1 0.49 0.36 6 10
165 =============== ================== ================== ================== ================== ================== ==================
166
167
168 **Metadata File Information**
169
170 Provide a tab-separated file that has the names of the samples in the first column and one header row.
171 Column names must be exactly in this order:
172
173 name_to_plot
174 condition
175 timepoint
176 timenum
177 compartment
178 original_name
179
180
181 Example **Metadata File**:
182
183
184 ==================== =============== ============= ============ ================ =================
185 **name_to_plot** **condition** **timepoint** **timenum** **compartment** **original_name**
186 -------------------- --------------- ------------- ------------ ---------------- -----------------
187 Control_cell_T0-1 Control T0 0 cell MCF001089_TD01
188 Control_cell_T0-2 Control T0 0 cell MCF001089_TD02
189 Control_cell_T0-3 Control T0 0 cell MCF001089_TD03
190 Tumoral_cell_T0-1 Tumoral T0 0 cell MCF001089_TD04
191 Tumoral_cell_T0-2 Tumoral T0 0 cell MCF001089_TD05
192 Tumoral_cell_T0-3 Tumoral T0 0 cell MCF001089_TD06
193 Tumoral_cell_T24-1 Tumoral T24 24 cell MCF001089_TD07
194 Tumoral_cell_T24-2 Tumoral T24 24 cell MCF001089_TD08
195 Tumoral_cell_T24-3 Tumoral T24 24 cell MCF001090_TD01
196 Control_med_T24-1 Control T24 24 med MCF001090_TD02
197 Control_med_T24-2 Control T24 24 med MCF001090_TD03
198 Tumoral_med_T24-1 Tumoral T24 24 med MCF001090_TD04
199 Tumoral_med_T24-2 Tumoral T24 24 med MCF001090_TD05
200 Control_med_T0-1 Control T0 0 med MCF001090_TD06
201 Tumoral_med_T0-1 Tumoral T0 0 med MCF001090_TD07
202 Tumoral_med_T0-2 Tumoral T0 0 med MCF001090_TD08
203 ==================== =============== ============= ============ ================ =================
204
205
206 The column **original_name** must have the names of the samples as given in your data.
207
208 The column **name_to_plot** must have the names as you want them to be (or set identical to original_name if you prefer). To set names that
209 are meaningful is a better choice, as we will take them to display the results.
210
211 The column **timenum** must contain only the numeric part of the timepoint, for example 2,0, 10, 100 (this means, without letters ("T", "t", "s", "h" etc)
212 nor any other symbol). Make sure these time numbers are in the same units (but do not write the units here!).
213
214 The column **compartment** is an abbreviation, coined by you, for the compartments. This will be used for the results' files names: the longer the
215 compartments names are, the longer the output files' names! Please pick short and clear abbreviations to fill this column.
216
217
218 **Running the analysis**
219
220 You can precise how you want your analysis to be executed, there exist hints on use that will guide you, next to the parameters.
221
222 Our tool automatically processes the integrality of your data (global PCA plots), and also splits your data by timepoint to generate PCA plots by timepoint (which is convenient to explore the "grouping" of conditions), but if you only have one condition you can discard them.
223
224 The output, for the global PCA, and for each timepoint PCA, consists of :
225
226 - a scatter-plot of the first two Principal Components (PC), with labels corresponding to 'name_to_plot'.
227
228 - the same scatter-plot as above but without labels.
229
230 - a bar-plot of the percentage of explained variances.
231
232
233
234 **Available data for testing**
235
236 You can test our tool with the data from our manuscript https://zenodo.org/record/8378887 (the pertinent
237 files for you are located in the subfolders inside the data folder).
238 You can also use the minimal data examples from https://zenodo.org/record/8380706
239
240 ]]>
241 </help>
242 <expand macro="citations" />
243 </tool>