Mercurial > repos > iuc > dimet_metabologram
view dimet_metabologram.xml @ 7:06f8d9ba09cd draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/DIMet commit 6da96d865a3a557cfa3ad09e1cfa830519e73748
| author | iuc |
|---|---|
| date | Tue, 06 Aug 2024 17:36:05 +0000 |
| parents | c7ff01bd331b |
| children |
line wrap: on
line source
<tool id="dimet_@EXECUTABLE@" name="dimet @EXECUTABLE@" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.05"> <description> Integration of transcriptomics and (tracer) metabolomics differential data (by DIMet) </description> <macros> <token name="@EXECUTABLE@">metabologram</token> <import>macros.xml</import> </macros> <expand macro="requirements"/> <command detect_errors="exit_code"><![CDATA[ @INIT_CONFIG@ @INIT_METABOLOGRAM@ @INIT_TRANSCRIPTS@ @INIT_GROUPS@ @INIT_COMPARISONS_METABOLOGRAM@ @INIT_PATHWAYS@ @INIT_STAT_TEST@ HYDRA_FULL_ERROR=1 python -m dimet '++hydra.run.dir=.' '++figure_path=figures' '++table_path=tables' '++analysis={ dataset:{ _target_: dimet.data.DataIntegrationConfig, name: "I am a synthetic data example" }, method:{ _target_: dimet.method.MetabologramIntegrationConfig, label: "metabologram", name: "Perform data integration via metabologram visualization", abs_values_scale_color_bar: {transcripts: null, metabolites:null}, colors_divergent_palette: ['royalblue', 'white', 'red'], edge_color: ['black','black'], line_width:['1','1.2'], display_label_and_value: ${output_options.write_values}, font_size: ${output_options.font_size}, fig_width: ${output_options.fig_width}, figure_format:${output_options.figure_format}, color_nan_elements:'gray', fig_height: ${output_options.fig_height} }, columns_metabolites: {ID: metabolite, values: log2FC}, columns_transcripts: {ID: ${deg_one_id}, values: ${deg_one_values}}, compartment: ${compartments}, label: metabologram }' '++analysis.method.qualityDistanceOverSpan='${qualityDistanceOverSpan}'' '++analysis.dataset.label=' '+analysis.timepoints=${timepoints}' '++analysis.method.statistical_test=${statistical_test}' '++analysis.method.grouping=${groups}' '++analysis.method.correction_method=${correction_method}' '++analysis.method.impute_values=${impute_values}' '++analysis.statistical_test=${statistical_test}' '++analysis.method.disfit_tail_option="auto"' '++analysis.dataset.subfolder=' '++analysis.dataset.conditions=${$conditions}' '++analysis.dataset.pathways=${pathways}' '++analysis.dataset.transcripts=${transcripts}' '++analysis.comparisons=${comparisons}' #if $metadata_path: '++analysis.dataset.metadata=metadata' #end if #if str( $data_input.data_input_selector ) == "abundance": #if $data_input.abundance_file: '++analysis.dataset.abundances=abundance' #end if #else: #if $data_input.me_or_frac_contrib_file: '++analysis.dataset.mean_enrichment=me_or_frac_contrib' #end if #end if @REMOVE_CONFIG@ ]]></command> <inputs> <expand macro="input_parameters_metabologram"/> <expand macro="deg_list"/> <expand macro="compartments_metabologram"/> <param name="correction_method" type="select" value="bonferroni" display="radio" label="Select multiple test correction to apply" help="Please enter at max 1 method"> <option value="bonferroni">bonferroni</option> <option value="holm-sidak">holm-sidak</option> <option value="holm">holm</option> <option value="simes-hochberg">simes-hochberg</option> <option value="hommel">hommel</option> <option value="fdr_bh">fdr_bh</option> <option value="fdr_by">fdr_by</option> <option value="fdr_tsbh">fdr_tsbh</option> <option value="fdr_tsbky">fdr_tsbky</option> </param> <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."/> <section name="output_options" title="Output options"> <param name="figure_format" type="select" value="pdf" display="radio" label="Select output figure format" help="Please enter at max 1 format"> <option value="pdf">Pdf</option> <option value="svg">Svg</option> </param> <param name="write_values" type="boolean" value="false" label="Write the values alongside the metabolites and genes names (e.g. L-Alanine: -0.44)" help="Default value is false."/> <param name="fig_width" type="integer" min="5" max="20" value="7" label="width of figures" help="Default value is 7."/> <param name="fig_height" type="integer" min="5" max="20" value="7" label="heigt of each figure" help="Default value is 7."/> <param name="font_size" type="integer" min="1" max="20" value="12" label=" figure font size" help="Default value is 12."/> </section> </inputs> <outputs> <collection name="report" type="list"> <discover_datasets pattern="__designation_and_ext__" directory="figures"/> </collection> </outputs> <tests> <test> <param name="path_kegg_metabolites" ftype="tabular" value="pathways_kegg_metabolites.csv"/> <param name="path_kegg_transcripts" ftype="tabular" value="pathways_kegg_transcripts.csv"/> <param name="abundance_file" ftype="tabular" value="rawAbundances.csv"/> <param name="metadata_path" ftype="tabular" value="example2_metadata.csv"/> <param name="statistical_test_type" value="parametric"/> <param name="stat_test" value="Tt"/> <repeat name="deg_list"> <param name="input" ftype="tabular" value="DEG_comparison_1.csv"/> <param name="idcol" ftype="integer" value="2"/> <param name="valuecol" ftype="integer" value="3"/> <param name="timepoint" value='T0'/> <repeat name="factor_list"> <param name="condition" value="L-Cycloserine"/> </repeat> <repeat name="factor_list"> <param name="condition" value="Control"/> </repeat> </repeat> <section name="output_options"> <param name="show_values" value="false"/> <param name="figure_format" value="svg"/> <param name="figure_width" value="7"/> <param name="figure_height" value="7"/> <param name="font_size" value="12"/> </section> <output_collection name="report" type="list" count="3"> <element file="AMINOACIDS-L-Cycloserine-T0-Control-T0--DEG_comparison1-abundances-cell.svg" name="AMINOACIDS-L-Cycloserine-T0-Control-T0--DEG_comparison1-abundances-cell" ftype="svg" compare="sim_size" delta="100"/> <element file="CENTRAL_CARBON_METABOLISM-L-Cycloserine-T0-Control-T0--DEG_comparison1-abundances-cell.svg" name="CENTRAL_CARBON_METABOLISM-L-Cycloserine-T0-Control-T0--DEG_comparison1-abundances-cell" ftype="svg" compare="sim_size" delta="100"/> <element file="legend-abundances-cell.svg" name="legend-abundances-cell" ftype="svg" compare="sim_size" delta="100"/> </output_collection> </test> </tests> <help><![CDATA[ This module is part of DIMet: Differential analysis of Isotope-labeled targeted Metabolomics data (https://pypi.org/project/DIMet/). DIMet Metabologram integrates tracer metabolomics and transcriptomics, in a pathway based fashion. More precisely, the differential information (Fold Changes (log2 transformed, or not)) of both types of omics must be given as input, plus the files defining the pathways. You can use the minimal data examples from https://zenodo.org/records/10579891 that contain a minimal example data for running our DIMet Metabologram tool. 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. **Input data files** This tool requires the following tab-delimited .csv files: 1. **The metabolomics data**: 1.1 The measures' (or quantifications') files, that can be of two types: - The total **abundances** (of the metabolites) file, OR, - The mean **enrichment** or labelled fractional contributions 1.2 The metadata, a unique file with the description of the samples in your measures' files. This is compulsory, see section **Metadata File Information**. 2. **The transcriptomics data**: 2.1 The table with the results of the differential expression analysis (performed with an external tool). Please provide the file with the results of the differential expression analysis of your transcriptomics data. It is recommended to use only the statistically significant **Differentially Expressed Genes (DEG)**. We provide examples in the zenodo (see section **Available data for testing**) 3. **The pathways files**: 3.1 A file with the pathways and respective gene symbols, which must match with those present in the transcriptomics data. The names of the columns must be the pathways' names, see the minimal data example downloaded from zenodo as explained above. Example: ====================== ================== ================== **PENTHOSE PHOSPHATE** **FATTY ACIDS** ... ====================== ================== ================== RPE SCD ... PGM1 FADS1 ... PKF BAAT ... DERA ACOT2 ... ... ... ... ====================== ================== ================== 3.2 A file with the pathways and respective metabolites ID, that must match with those in your metabolomics data. The names of the columns must be the pathways' names, see the minimal data example downloaded from zenodo as explained above. Example: ====================== ================== ================== **PENTHOSE PHOSPHATE** **FATTY ACIDS** ... ====================== ================== ================== Xyl_P Acetyl_CoA ... Glc_6P Palmitate ... Rib_6P Stearate ... ... ... ... ====================== ================== ================== **Measures' files** The measure's files must be organized as matrices: - The first column must contain Metabolite IDs that are unique (not repeated) within the file. - The rest of the columns correspond to the samples - The rows correspond to the metabolites - The values must be tab separated, with the first row containing the sample/column labels. See the following examples of measures files: Example - Metabolites **abundances**: =============== ================== ================== ================== ================== ================== ================== ID **MCF001089_TD01** **MCF001089_TD02** **MCF001089_TD03** **MCF001089_TD04** **MCF001089_TD05** **MCF001089_TD06** =============== ================== ================== ================== ================== ================== ================== 2_3-PG 8698823.9926 10718737.7217 10724373.9 8536484.5 22060650 28898956 2-OHGLu 36924336 424336 92060650 45165 84951950 965165051 Glc6P 2310 2142 2683 1683 012532068 1252172 Gly3P 399298 991656565 525195 6365231 89451625 4952651963 IsoCit 0 0 0 84915613 856236 954651610 =============== ================== ================== ================== ================== ================== ================== Example - mean **enrichment** or labeled fractional contributions: =============== ================== ================== ================== ================== ================== ================== ID **MCF001089_TD01** **MCF001089_TD02** **MCF001089_TD03** **MCF001089_TD04** **MCF001089_TD05** **MCF001089_TD06** =============== ================== ================== ================== ================== ================== ================== 2_3-PG 0.9711 0.968 0.9909 0.991 0.40 0.9 2-OHGLu 0.01719 0.0246 0.554 0.555 0.73 0.68 Glc6P 0.06 0.66 2683 0.06 2068 2172 Gly3P 0.06 0.06 0.06 1 5 3 IsoCit 0.06 1 0.49 0.36 6 10 =============== ================== ================== ================== ================== ================== ================== **Metadata File Information** Provide a tab-separated file that has the names of the samples in the first column and one header row. Column names must be exactly in this order: name_to_plot condition timepoint timenum compartment original_name Example **Metadata File**: ==================== =============== ============= ============ ================ ================= **name_to_plot** **condition** **timepoint** **timenum** **compartment** **original_name** -------------------- --------------- ------------- ------------ ---------------- ----------------- Control_cell_T0-1 Control T0 0 cell MCF001089_TD01 Control_cell_T0-2 Control T0 0 cell MCF001089_TD02 Control_cell_T0-3 Control T0 0 cell MCF001089_TD03 Tumoral_cell_T0-1 Tumoral T0 0 cell MCF001089_TD04 Tumoral_cell_T0-2 Tumoral T0 0 cell MCF001089_TD05 Tumoral_cell_T0-3 Tumoral T0 0 cell MCF001089_TD06 Tumoral_cell_T24-1 Tumoral T24 24 cell MCF001089_TD07 Tumoral_cell_T24-2 Tumoral T24 24 cell MCF001089_TD08 Tumoral_cell_T24-3 Tumoral T24 24 cell MCF001090_TD01 Control_med_T24-1 Control T24 24 med MCF001090_TD02 Control_med_T24-2 Control T24 24 med MCF001090_TD03 Tumoral_med_T24-1 Tumoral T24 24 med MCF001090_TD04 Tumoral_med_T24-2 Tumoral T24 24 med MCF001090_TD05 Control_med_T0-1 Control T0 0 med MCF001090_TD06 Tumoral_med_T0-1 Tumoral T0 0 med MCF001090_TD07 Tumoral_med_T0-2 Tumoral T0 0 med MCF001090_TD08 ==================== =============== ============= ============ ================ ================= The column **original_name** must have the names of the samples as given in your data. 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. 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!). 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. **Running the analysis** You can precise how you want your analysis to be executed with the parameters, which are of two types: **a. Parameters proper to the metabolome differential analysis (that runs automatically before the integration)**: - **Conditions and timepoint**: For each comparison to run on the metabolomics data, you can define the Conditions to compare, at a chosen time point, through the box 'Deregulated gene set': follow the instructions and choose the correct order of Conditions (the last must be the reference or control). To add a second comparison, click the 'Insert Deregulated gene set' button. You can insert and define as many boxes ('Deregulated gene set') as comparisons you want to perform. - **statistical_test**: choose the specific statistical test to be applied. Kruskal-Wallis, Mann-Whitney, Wilcoxon’s signed rank test, Wilcoxon’s rank sum test 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). For the permutation test, we have established as test statistic, the absolute difference of geometric means of the two compared groups. - **qualityDistanceOverSpan**: a normalized distance between the intervals of values of the compared groups, that is the cutoff for considering a minimal acceptable "separation", and therefore, to be suitable for statistical testing. 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) - **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). - **compartment**: one of the compartments present in your data. **b. Parameters proper to the integration with transcriptomics (that runs automatically after the metabolome differential analysis)**: - **Deregulated genes set file**: Corresponds to the transcriptomics data, as explained in **Input data files** section. For each 'Deregulated gene set' box, a single **Differentially Expressed Genes (DEG)** file must be added, and must match with the metabolomics comparison set in the same box. Additional files can be added with the 'Insert deregulated gene set' button, see also the subsection 'Conditions and timepoint' above. - **pathways** : files for the pathways, as explained in **Input data files** section Overall, the metabologram module provides hints on use that will guide you, in the same menus and boxes of the parameters. **Output** The output consists of one figure by metabologram, and a color key bar legend valid for all metabolograms produced **Available data for testing** You can test our tool with the data from our manuscript https://zenodo.org/record/10579862 (the pertinent files for you are located in the subfolders inside the data folder). You can also use the minimal data examples from https://zenodo.org/record/10579891 ]]> </help> <expand macro="citations" /> </tool>