Mercurial > repos > iuc > dimet_timecourse_analysis

comparison dimet_timecourse_analysis.xml @ 0:cb8c4ae59da9 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 11:54:05 +0000
parents
children 40edef7d7f74
comparison
equal deleted inserted replaced
-1:000000000000 0:cb8c4ae59da9
1 <tool id="dimet_@EXECUTABLE@" name="dimet @TOOL_LABEL@" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.05">
2 <description>
3 Differential analysis of tracer metabolomics data comparing consecutive time-points (by DIMet)
4 </description>
5 <macros>
6 <token name="@TOOL_LABEL@">timecourse analysis</token>
7 <token name="@EXECUTABLE@">timecourse_analysis</token>
8 <import>macros.xml</import>
9 </macros>
10 <expand macro="requirements"/>
11 <command detect_errors="exit_code"><![CDATA[
12 @INIT_CONFIG@
13 @INIT_DIFF_ANALYSIS@
14 @INIT_STAT_TEST@
15 @INIT_GROUPS@
16 @INIT_CONDITIONS_TIMECOURSE@
17 HYDRA_FULL_ERROR=1 python -m dimet
18 -cp '$__new_file_path__/config'
19 '++figure_path=figures'
20 '++table_path=tables'
21 '++hydra.run.dir=time_course_analysis'
22 '++analysis={
23 dataset:{
24 _target_: dimet.data.DatasetConfig,
25 name: "I am a synthetic data example"
26 },
27 method:{
28 _target_: dimet.method.TimeCourseAnalysisConfig,
29 label: "time_course_analysis",
30 name: "Time wise computation of statistical differences"
31 },
32 label: time_course_analysis-example
33 }'
34 '++analysis.method.qualityDistanceOverSpan='${qualityDistanceOverSpan}''
35 '++analysis.statistical_test=${statistical_test}'
36 '++analysis.method.statistical_test=${statistical_test}'
37 '++analysis.method.grouping=${groups}'
38 '++analysis.method.correction_method=${correction_method}'
39 '++analysis.method.impute_values=${impute_values}'
40 '++analysis.dataset.subfolder='
41 '++analysis.dataset.label='
42 '++analysis.dataset.conditions=${conds}'
43 #if $metadata_path:
44 '++analysis.dataset.metadata=metadata'
45 #end if
46 #if str( $data_input.data_input_selector ) == "abundance":
47 #if $data_input.abundance_file:
48 '++analysis.dataset.abundances=abundance'
49 #end if
50 #elif str( $data_input.data_input_selector ) == "mean_enrichment":
51 #if $data_input.me_or_frac_contrib_file:
52 '++analysis.dataset.mean_enrichment=me_or_frac_contrib'
53 #end if
54 #elif str( $data_input.data_input_selector ) == "isotop_prop":
55 #if $data_input.isotop_prop_file:
56 '++analysis.dataset.isotopologue_proportions=isotop_prop'
57 #end if
58 #else
59 #if $data_input.isotop_abs_file:
60 '+analysis.dataset.isotopologues=isotop_abs'
61 #end if
62 #end if
63 @REMOVE_CONFIG@
64 ]]></command>
65 <inputs>
66 <expand macro="input_parameters_diff_analysis"/>
67 <expand macro="conditions"/>
68 <expand macro="correction_method"/>
69 <param name="qualityDistanceOverSpan" type="float" min="-1.0" max="-0.1" value="-0.3" label="quality Distance Over Span" help="Default value is -0.3."/>
70 </inputs>
71 <outputs>
72 <collection name="report" type="list">
73 <discover_datasets pattern="__designation__" directory="tables" format="tabular"/>
74 </collection>
75 </outputs>
76 <tests>
77 <test>
78 <param name="data_input_selector" value="abundance" />
79 <param name="abundance_file" ftype="tabular" value="rawAbundances.csv"/>
80 <param name="metadata_path" ftype="tabular" value="example2_metadata.csv"/>
81 <param name="correction_method" value="bonferroni"/>
82 <param name="qualityDistanceOverSpan" value="-0.3"/>
83 <param name="stat_test" value="Tt"/>
84 <param name="conditions" value='Control,L-Cycloserine'/>
85 <output_collection name="report" type="list" count="4">
86 <element file="abundance--cell-Control-T2h-Control-T0-Tt.tsv" name="abundance--cell-Control-T2h-Control-T0-Tt.tsv" ftype="tabular"/>
87 <element file="abundance--cell-L-Cycloserine-T2h-L-Cycloserine-T0-Tt.tsv" name="abundance--cell-L-Cycloserine-T2h-L-Cycloserine-T0-Tt.tsv" ftype="tabular"/>
88 <element file="abundance--med-Control-T2h-Control-T0-Tt.tsv" name="abundance--med-Control-T2h-Control-T0-Tt.tsv" ftype="tabular"/>
89 <element file="abundance--med-L-Cycloserine-T2h-L-Cycloserine-T0-Tt.tsv" name="abundance--med-L-Cycloserine-T2h-L-Cycloserine-T0-Tt.tsv" ftype="tabular"/>
90 </output_collection>
91
92 </test>
93 </tests>
94 <help><![CDATA[
95 This module is part of DIMet: Differential analysis of Isotope-labeled targeted Metabolomics data (https://pypi.org/project/DIMet/).
96
97 **Input data files**
98
99 This tool performs a time course differential analysis on your time series data.
100 For illustration see the section **Metadata File Information** which contains several time points.
101
102 This time course differential analysis is sequential: by each individual condition, a comparison between the timepoints t_x+1 vs t_x
103 (e.g. [Control, 90min] vs [Control, 60min]), for all the timepoints present in the data.
104 Our tool automatically detects the conditions and timepoints, and automatically organizes the comparisons
105 (you do not need to set this part yourself, DIMet does it for you).
106
107 Note that if you need only to compare specific [condition, timepoint] pairs not comprised by
108 our automatic time course analysis, you can use the differential analysis in the pairwise mode instead.
109
110
111 This tool requires (at max.) 5 tab-delimited .csv files as inputs. There are two types of files:
112
113 - The measures' (or quantifications') files, that can be of 4 types.
114
115 - The metadata, a unique file with the description of the samples in your measures' files. This is compulsory.
116
117 For running DIMet @EXECUTABLE@ you need **at least one** file of measures:
118
119 - The total **abundances** (of the metabolites) file
120
121 - The mean **enrichment** or labelled fractional contributions
122
123 - The **isotopologues** absolute values files (optional)
124
125 - The **isotopologue proportions** file (optional)
126
127 and one metadata file, WHICH IS COMPULSORY, see section **Metadata File Information**.
128
129 The measure's files must be organized as matrices:
130
131 - The first column must contain Metabolite IDs that are unique (not repeated) within the file.
132
133 - The rest of the columns correspond to the samples
134
135 - The rows correspond to the metabolites
136
137 - The values must be tab separated, with the first row containing the sample/column labels.
138
139 See the following examples of measures' files:
140
141
142 Example - Metabolites **abundances**:
143
144 =============== ================== ================== ================== ================== ================== ==================
145 ID **MCF001089_TD01** **MCF001089_TD02** **MCF001089_TD03** **MCF001089_TD04** **MCF001089_TD05** **MCF001089_TD06**
146 =============== ================== ================== ================== ================== ================== ==================
147 2_3-PG 8698823.9926 10718737.7217 10724373.9 8536484.5 22060650 28898956
148 2-OHGLu 36924336 424336 92060650 45165 84951950 965165051
149 Glc6P 2310 2142 2683 1683 012532068 1252172
150 Gly3P 399298 991656565 525195 6365231 89451625 4952651963
151 IsoCit 0 0 0 84915613 856236 954651610
152 =============== ================== ================== ================== ================== ================== ==================
153
154 Example - mean **enrichment** or labeled fractional contributions:
155
156 =============== ================== ================== ================== ================== ================== ==================
157 ID **MCF001089_TD01** **MCF001089_TD02** **MCF001089_TD03** **MCF001089_TD04** **MCF001089_TD05** **MCF001089_TD06**
158 =============== ================== ================== ================== ================== ================== ==================
159 2_3-PG 0.9711 0.968 0.9909 0.991 0.40 0.9
160 2-OHGLu 0.01719 0.0246 0.554 0.555 0.73 0.68
161 Glc6P 0.06 0.66 2683 0.06 2068 2172
162 Gly3P 0.06 0.06 0.06 1 5 3
163 IsoCit 0.06 1 0.49 0.36 6 10
164 =============== ================== ================== ================== ================== ================== ==================
165
166 Example - **Isotopologues**
167
168 =============== ================== ================== ================== ================== ================== ==================
169 ID **MCF001089_TD01** **MCF001089_TD02** **MCF001089_TD03** **MCF001089_TD04** **MCF001089_TD05** **MCF001089_TD06**
170 =============== ================== ================== ================== ================== ================== ==================
171 2_3-PG_m+0 206171.4626 285834.0353 36413.27637 27367.17784 6171.4626 119999
172 2_3-PG_m+1 123 432 101 127 206171.4626 119999
173 2_3-PG_m+2 133780.182 161461.2364 182631.3947 132170.3807 358749.348 848754.36
174 2_3-PG_m+3 8358749.348 10271010.45 10505228.3 8376820.028 62163.30727 1088.8963
175 2-OHGLu_m+0 5550339.322 6072872.833 3855047.791 3216178.72 8358749.348 10271010.45
176 2-OHGLu_m+1 0.0 0.0 0.0 0.0 206171.4626 285834.0353
177 =============== ================== ================== ================== ================== ================== ==================
178
179
180 Example - **Isotopologue proportions**:
181
182 =============== ================== ================== ================== ================== ================== ==================
183 ID **MCF001089_TD01** **MCF001089_TD02** **MCF001089_TD03** **MCF001089_TD04** **MCF001089_TD05** **MCF001089_TD06**
184 =============== ================== ================== ================== ================== ================== ==================
185 2_3-PG_m+0 0.023701408 0.026667837 0.003395407 0.05955 0.034383527 0.12
186 2_3-PG_m+1 0.0 0.0 0.0 0.0 0.4 0.12
187 2_3-PG_m+2 0.015379329 0.01506 0.017029723 0.35483229 0.54131313 0.743
188 2_3-PG_m+3 0.960919263 0.958268099 0.97957487 0.581310816 0.017029723 0.017
189 2-OHGLu_m+0 0.972778716 0.960016157 0.238843937 0.234383527 0.9998888 0.015064063
190 2-OHGLu_m+1 0.0 0.0 0.0 0.0 0.0001112 0.960919263
191 =============== ================== ================== ================== ================== ================== ==================
192
193
194
195 **Metadata File Information**
196
197 Provide a tab-separated file that has the names of the samples in the first column and one header row.
198 Column names must be exactly in this order:
199
200 name_to_plot
201 condition
202 timepoint
203 timenum
204 compartment
205 original_name
206
207 Example **Metadata File**:
208
209
210 ==================== =============== ============= ============ ================ =================
211 **name_to_plot** **condition** **timepoint** **timenum** **compartment** **original_name**
212 -------------------- --------------- ------------- ------------ ---------------- -----------------
213 Spleen1_cell_0-1 Spleen1 0min 0 cell MCF001089_TD01
214 Spleen1_cell_0-2 Spleen1 0min 0 cell MCF001089_TD02
215 Spleen1_cell_10-1 Spleen1 10min 10 cell MCF001089_TD03
216 Spleen1_cell_10-2 Spleen1 10min 10 cell MCF001089_TD04
217 Spleen1_cell_30-1 Spleen1 30min 30 cell MCF001089_TD05
218 Spleen1_cell_30-2 Spleen1 30min 30 cell MCF001089_TD06
219 Spleen1_cell_60-1 Spleen1 60min 60 cell MCF001089_TD07
220 Spleen1_cell_60-2 Spleen1 60min 60 cell MCF001089_TD08
221 Spleen1_cell_90-1 Spleen1 90min 90 cell MCF001089_TD09
222 Spleen1_cell_90-2 Spleen1 90min 90 cell MCF001089_TD011
223 Spleen1_med_30-3 Spleen1 30min 30 med MCF001089_TD025
224 Spleen1_med_30-2 Spleen1 30min 30 med MCF001089_TD023
225 ==================== =============== ============= ============ ================ =================
226
227
228 The column **original_name** must have the names of the samples as given in your data.
229
230 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 are meaningful is a better choice, as we will take them to display the results.
231
232 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) nor any other symbol). Make sure these time numbers are in the same units (but do not write the units here!).
233
234 The column **compartment** is an abbreviation, coined by you, for the compartments. This will be used for the results' files names: the longer the compartments names are, the longer the output files' names! Please pick short and clear abbreviations to fill this column.
235
236
237
238 **Running the analysis**
239
240
241
242 You can precise how you want your analysis to be executed, with the parameters:
243
244 - **datatypes** : the measures type(s) that you want to run
245
246 - **statistical_test** : choose, by type of measure, the specific statistical test to be applied.
247
248 Kruskal-Wallis, Mann-Whitney, Wilcoxon’s signed rank test, Wilcoxon’s rank sum test
249 t-test, and permutation test are currently offered (we use the trusted functions from scipy library https://docs.scipy.org/doc/scipy/reference/stats.html).
250
251 For the permutation test, we have established as test statistic, the absolute difference of geometric means of the two compared groups.
252
253 - **qualityDistanceOverSpan**: a normalized distance between the intervals of values of the compared groups, that is the cutoff for considering a minimal acceptable "separation". A 'distance/span' == 1 is a perfect separation, whereas if 'distance/span' < 0 there is no separation. To use with caution in case of important dispersion of your intra-group values. Default is -0.3 (not stringent)
254
255 - **correction_method** : one of the methods for multiple testing correction available in statsmodels library (bonferroni, fdr_bh, sidak, among others, see https://www.statsmodels.org/dev/generated/statsmodels.stats.multitest.multipletests.html).
256
257 There exist hints on use that will guide you, next to the parameters.
258
259 The output consists of tables with the computed metrics, one by each pair of timepoints compared.
260 The number of output tables = number-of-conditions x (number-of-timepoints)-1 x number-of-compartments.
261
262 **Available data for testing**
263
264 You can test our tool with the data from our manuscript https://zenodo.org/record/8378887 (the pertinent
265 files for you are located in the subfolders inside the data folder).
266 You can also use the minimal data examples from https://zenodo.org/record/8380706
267
268 ]]>
269 </help>
270 <expand macro="citations" />
271 </tool>