diff --git a/CONTRIBUTORS.yaml b/CONTRIBUTORS.yaml index baf85b926dd48d..61b1a3c594eac4 100644 --- a/CONTRIBUTORS.yaml +++ b/CONTRIBUTORS.yaml @@ -2800,6 +2800,10 @@ tbrown91: orcid: 0000-0001-8293-4816 joined: 2024-08 +tStehling: + name: Thorben Stehling + joined: 2024-11 + rmassei: name: Riccardo Massei email: riccardo.massei@ufz.de @@ -2807,4 +2811,3 @@ rmassei: joined: 2024-11 affiliations: - nfdi4bioimage - diff --git a/topics/proteomics/images/p-value.png b/topics/proteomics/images/p-value.png new file mode 100644 index 00000000000000..6909f04c4d839e Binary files /dev/null and b/topics/proteomics/images/p-value.png differ diff --git a/topics/proteomics/tutorials/multiGSEA-tutorial/data-library.yaml b/topics/proteomics/tutorials/multiGSEA-tutorial/data-library.yaml new file mode 100644 index 00000000000000..ba935f5c1131de --- /dev/null +++ b/topics/proteomics/tutorials/multiGSEA-tutorial/data-library.yaml @@ -0,0 +1,27 @@ +--- +destination: + type: library + name: GTN - Material + description: Galaxy Training Network Material + synopsis: Galaxy Training Network Material. See https://training.galaxyproject.org +items: +- name: The new topic + description: Summary + items: + - name: Using MultiGSEA + items: + - name: 'DOI: 10.5281/zenodo.14216972' + description: latest + items: + - url: https://zenodo.org/api/records/14216972/files/metabolome.tsv/content + src: url + ext: auto + info: https://zenodo.org/records/14216972 + - url: https://zenodo.org/api/records/14216972/files/proteome.tsv/content + src: url + ext: auto + info: https://zenodo.org/records/14216972 + - url: https://zenodo.org/api/records/14216972/files/transcriptome.tsv/content + src: url + ext: auto + info: https://zenodo.org/records/14216972 diff --git a/topics/proteomics/tutorials/multiGSEA-tutorial/faqs/index.md b/topics/proteomics/tutorials/multiGSEA-tutorial/faqs/index.md new file mode 100644 index 00000000000000..9ce3fe4fce824b --- /dev/null +++ b/topics/proteomics/tutorials/multiGSEA-tutorial/faqs/index.md @@ -0,0 +1,3 @@ +--- +layout: faq-page +--- diff --git a/topics/proteomics/tutorials/multiGSEA-tutorial/tutorial.bib b/topics/proteomics/tutorials/multiGSEA-tutorial/tutorial.bib new file mode 100644 index 00000000000000..da3de5ec9b1cea --- /dev/null +++ b/topics/proteomics/tutorials/multiGSEA-tutorial/tutorial.bib @@ -0,0 +1,26 @@ + +# This is the bibliography file for your tutorial. +# +# To add bibliography (bibtex) entries here, follow these steps: +# 1) Find the DOI for the article you want to cite +# 2) Go to https://doi2bib.org and fill in the DOI +# 3) Copy the resulting bibtex entry into this file +# +# To cite the example below, in your tutorial.md file +# use {% cite Batut2018 %} +# +# If you want to cite an online resourse (website etc) +# you can use the 'online' format (see below) +# +# You can remove the examples below + +@misc{https://doi.org/10.18129/b9.bioc.multigsea, + doi = {10.18129/B9.BIOC.MULTIGSEA}, + url = {https://bioconductor.org/packages/multiGSEA}, + author = {{Sebastian Canzler, J\"{o}rg Hackerm\"{u}ller}}, + title = {multiGSEA}, + publisher = {Bioconductor}, + year = {2020} +} + + diff --git a/topics/proteomics/tutorials/multiGSEA-tutorial/tutorial.md b/topics/proteomics/tutorials/multiGSEA-tutorial/tutorial.md new file mode 100644 index 00000000000000..d5f4b170d738f8 --- /dev/null +++ b/topics/proteomics/tutorials/multiGSEA-tutorial/tutorial.md @@ -0,0 +1,123 @@ +--- +layout: tutorial_hands_on + +title: Multiomics data analysis using MultiGSEA +subtopic: multi-omics +tags: + - multi-omics + - transcriptomics + - proteomics + - metabolomics +zenodo_link: 'https://zenodo.org/records/14216972' +questions: +- How to use MultiGSEA for GSEA-based pathway enrichment for multiple omics layers? +objectives: +- Perform GSEA-based pathway enrichment for transcriptomics, proteomics, and metabolomics data. +- Understand how to combine p-values across multiple omics layers. +time_estimation: 1H +key_points: +- MultiGSEA provides an integrated workflow for pathway enrichment analysis across multi-omics data. +- Supports pathway definitions from several databases and robust ID mapping. +contributions: + authorship: + - tStehling + + +--- + + +The multiGSEA package was designed to run a robust GSEA-based pathway enrichment for multiple omics layers. The enrichment is calculated for each omics layer separately and aggregated p-values are calculated afterwards to derive a composite multi-omics pathway enrichment. + +Pathway definitions can be downloaded from up to eight different pathway databases by means of the graphite Bioconductor package (Sales, Calura, and Romualdi 2018). Feature mapping for transcripts and proteins is supported towards Entrez Gene IDs, Uniprot, Gene Symbol, RefSeq, and Ensembl IDs. The mapping is accomplished through the AnnotationDbi package (Pagès et al. 2019) and currently supported for 11 different model organisms including human, mouse, and rat. ID conversion of metabolite features to Comptox Dashboard IDs (DTXCID, DTXSID), CAS-numbers, Pubchem IDs (CID), HMDB, KEGG, ChEBI, Drugbank IDs, or common metabolite names is accomplished through the AnnotationHub package metabliteIDmapping. This package provides a comprehensive ID mapping for more than 1.1 million entries. + +This tutorial covers a simple example workflow illustrating how the multiGSEA package works. The omics data sets that will be used throughout the example were originally provided by Quiros et al. (Quirós et al. 2017). In their publication the authors analyzed the mitochondrial response to four different toxicants, including Actinonin, Diclofenac, FCCB, and Mito-Block (MB), within the transcriptome, proteome, and metabolome layer. +In this tutorial we will solely focus on the Actinonin data set. + + +> +> +> In this tutorial, we will cover: +> +> 1. TOC +> {:toc} +> +{: .agenda} + +# Preparing the Data + +To perform pathway enrichment with MultiGSEA, you'll need omics datasets in the file type TSV . Each individual data set contains four columns representing the feature (denoted as Symbol), the log2 fold change (logFC), the p-value (pValue), and the adjusted p-values (adj.pValue). We'll use example data provided on Zenodo. + +## Get data + +### Data Upload + +> Getting datasets +> 1. Create a new history for this tutorial. +> +> {% snippet faqs/galaxy/histories_create_new.md %} +> +> 2. Import the datasets from [Zenodo]({{ page.zenodo_link }}) into your Galaxy instance: +> ``` +> https://zenodo.org/records/14216972/files/transcriptome.tsv +> https://zenodo.org/records/14216972/files/proteome.tsv +> https://zenodo.org/records/14216972/files/metabolome.tsv +> ``` +{: .hands_on} + + +# Running MultiGSEA + +In this step, you'll use the MultiGSEA tool to perform GSEA-based pathway enrichment on the uploaded datasets. + +> Task description +> +> 1. Run {% tool [multiGSEA](toolshed.g2.bx.psu.edu/repos/iuc/multigsea/multigsea/1.12.0+galaxy0) %} with the following parameters +> - *"Select transcriptomics data"*: `Enabled` +> - {% icon param-file %} *"Transcriptomics data"*: `Transcriptomics` +> - {% icon param-select %} *"Gene ID format in transcriptomics data"*: `SYMBOL` +> - *"Select proteomics data"*: `Enabled` +> - {% icon param-file %} *"Proteomics data"*: `Proteomics` +> - {% icon param-select %} *"Gene ID format in proteomics data"*: `SYMBOL` +> - *"Select metabolomics data"*: `Enabled` +> - {% icon param-file %} *"Metabolomics data"*: `Metabolomics` +> - {% icon param-select %} *"Metabolite ID format"*: `HMDB` +> - *"Supported organisms"*: `Homo sapiens (Human)`. +> - *"Pathway databases"*: `KEGG` +> - *"Combine p-values method"*: `Stouffer` +> - *"P-value correction method"*: `BH` +> +> > About the parameters +> > - **Pathway databases**: `KEGG`Databases often contain their own format in which pathway definitions are provided. So you can select a relevant > > database. For the tutorial we choose `KEGG` +> > - **Combine p-values method**: Choose a method (here `Stouffer` for balanced weighting). To more comprehensively measure a pathway response, multiGSEA provides different approaches to compute an aggregated p value over multiple omics layers. Because no single approach for aggregating p values performs best under all circumstances, Loughin proposed basic recommendations on which method to use depending on structure and expectation of the problem. If small p values should be emphasized, Fisher’s method should be chosen. In cases where p values should be treated equally, Stouffer’s method is preferable. If large p values should be emphasized, the user should select Edgington’s method. Figure 2 indicates the difference between those three methods. +> > ![P-Value](../../images/p-value.png "P-value methods") +> > - **P-value correction method** Type I and type II errors depend on each other and thus reducing type I errors through a p value adjustment will likely increase the chance of making a type II error and an appropriate trade-off has to be made. Choose one of the different methods for controlling false discovery rate: For the tutorial choose `BH` (Benjamini-Hochberg). +> {: .tip} +> +{: .hands_on} + + + +> +> +> 1. What file format is required for the input data in MultiGSEA? +> 2. What is the purpose of the “Combine p-values method” parameter, and which method was selected in this tutorial? +> 3. Why is it important to select pathway databases (e.g., KEGG) when using MultiGSEA? +> +> > +> > +> > 1. The required file format is TSV. +> > 2. The “Combine p-values method” parameter is used to aggregate p-values across omics layers. In this tutorial, the method Stouffer was selected to apply balanced weighting. +> > 3. Selecting pathway databases ensures that the analysis uses appropriate and relevant pathway definitions for enrichment. +> > +> {: .solution} +> +{: .question} + + +# Conclusion + +In this tutorial, you explored the capabilities of MultiGSEA for performing pathway enrichment analysis across multiple omics layers, including transcriptomics, proteomics, and metabolomics data. By following the steps, you learned how to: + + - Prepare and upload the required omics datasets. + - Configure and execute the MultiGSEA tool within Galaxy. + - Combine p-values from different omics layers to derive a unified perspective on pathway enrichment. diff --git a/topics/proteomics/tutorials/multiGSEA-tutorial/workflows/index.md b/topics/proteomics/tutorials/multiGSEA-tutorial/workflows/index.md new file mode 100644 index 00000000000000..e092e0ae66ddd4 --- /dev/null +++ b/topics/proteomics/tutorials/multiGSEA-tutorial/workflows/index.md @@ -0,0 +1,3 @@ +--- +layout: workflow-list +--- diff --git a/topics/proteomics/tutorials/multiGSEA-tutorial/workflows/main_workflow.ga b/topics/proteomics/tutorials/multiGSEA-tutorial/workflows/main_workflow.ga new file mode 100644 index 00000000000000..3d986bc2793284 --- /dev/null +++ b/topics/proteomics/tutorials/multiGSEA-tutorial/workflows/main_workflow.ga @@ -0,0 +1 @@ +{"a_galaxy_workflow": "true", "annotation": "The", "comments": [], "format-version": "0.1", "name": "multiGSEA Workflow", "report": {"markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n"}, "steps": {"0": {"annotation": "The input files (transcriptome.tsv, proteome.tsv, metabolome.tsv) are converted into the output file using the preset parameters of the tool.", "content_id": null, "errors": null, "id": 0, "input_connections": {}, "inputs": [{"description": "The input files (transcriptome.tsv, proteome.tsv, metabolome.tsv) are converted into the output file using the preset parameters of the tool.", "name": "transcriptome.tsv"}], "label": "transcriptome.tsv", "name": "Input dataset", "outputs": [], "position": {"left": 0, "top": 0}, "tool_id": null, "tool_state": "{\"optional\": false, \"tag\": \"\"}", "tool_version": null, "type": "data_input", "uuid": "cb1f6368-5d1a-43a9-a5c3-12186ae326d9", "when": null, "workflow_outputs": []}, "1": {"annotation": "", "content_id": null, "errors": null, "id": 1, "input_connections": {}, "inputs": [{"description": "", "name": "proteome.tsv"}], "label": "proteome.tsv", "name": "Input dataset", "outputs": [], "position": {"left": 1, "top": 90}, "tool_id": null, "tool_state": "{\"optional\": false, \"tag\": null}", "tool_version": null, "type": "data_input", "uuid": "ac32b15a-c6df-4e1d-bcfb-94c909c0b3ee", "when": null, "workflow_outputs": []}, "2": {"annotation": "", "content_id": null, "errors": null, "id": 2, "input_connections": {}, "inputs": [{"description": "", "name": "metabolome.tsv"}], "label": "metabolome.tsv", "name": "Input dataset", "outputs": [], "position": {"left": 2, "top": 180}, "tool_id": null, "tool_state": "{\"optional\": false, \"tag\": null}", "tool_version": null, "type": "data_input", "uuid": "3a38df50-6904-4366-958a-7ccfa12539da", "when": null, "workflow_outputs": []}, "3": {"annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/multigsea/multigsea/1.12.0+galaxy0", "errors": null, "id": 3, "input_connections": {"metabolomics_data|metabolomics": {"id": 2, "output_name": "output"}, "proteomics_data|proteomics": {"id": 1, "output_name": "output"}, "transcriptomics_data|transcriptomics": {"id": 0, "output_name": "output"}}, "inputs": [{"description": "runtime parameter for tool multiGSEA", "name": "metabolomics_data"}, {"description": "runtime parameter for tool multiGSEA", "name": "proteomics_data"}, {"description": "runtime parameter for tool multiGSEA", "name": "transcriptomics_data"}], "label": null, "name": "multiGSEA", "outputs": [{"name": "output", "type": "tabular"}], "position": {"left": 332, "top": 44.51666259765624}, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/multigsea/multigsea/1.12.0+galaxy0", "tool_shed_repository": {"changeset_revision": "e48b10ce08b8", "name": "multigsea", "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu"}, "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/opt/galaxy/tool-data/shared/ucsc/chrom/?.len\", \"combine_pvalues\": \"stouffer\", \"databases\": \"all\", \"metabolomics_data\": {\"selector\": \"true\", \"__current_case__\": 0, \"metabolomics\": {\"__class__\": \"ConnectedValue\"}, \"metabolome_ids\": \"HMDB\"}, \"organism\": \"hsapiens\", \"padj_method\": \"BH\", \"proteomics_data\": {\"selector\": \"true\", \"__current_case__\": 0, \"proteomics\": {\"__class__\": \"ConnectedValue\"}, \"proteome_ids\": \"SYMBOL\"}, \"transcriptomics_data\": {\"selector\": \"true\", \"__current_case__\": 0, \"transcriptomics\": {\"__class__\": \"ConnectedValue\"}, \"transcriptome_ids\": \"SYMBOL\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", "tool_version": "1.12.0+galaxy0", "type": "tool", "uuid": "f1ba258f-1a9e-410e-8366-0d3966843fff", "when": null, "workflow_outputs": []}}, "tags": [], "uuid": "d3d42f71-18e4-4c0a-9b21-052f37907c61", "version": 3} \ No newline at end of file diff --git a/topics/statistics/index.md b/topics/statistics/index.md index 0e1ac2bc902525..7a621862e709dd 100644 --- a/topics/statistics/index.md +++ b/topics/statistics/index.md @@ -1,4 +1,4 @@ --- layout: topic topic_name: statistics ---- +--- \ No newline at end of file diff --git a/topics/statistics/metadata.yaml b/topics/statistics/metadata.yaml index b7727ec9f9316d..465899df1eb314 100644 --- a/topics/statistics/metadata.yaml +++ b/topics/statistics/metadata.yaml @@ -15,4 +15,4 @@ requirements: editorial_board: - marziacremona - cumbof - - anuprulez + - anuprulez \ No newline at end of file