Merge pull request #226 from WackerO/multiqc_update

Multiqc update
qbic-pipelines · Apr 30, 2024 · e155229 · e155229
2 parents 139b7e3 + 41afb06
commit e155229
Show file tree

Hide file tree

Showing 18 changed files with 212 additions and 73 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -40,14 +40,14 @@ jobs:
             environment.yml
       - name: Build new docker image
         if: env.MATCHED_FILES
-        run: docker build --no-cache . -t ghcr.io/qbic-pipelines/rnadeseq:2.3dev
+        run: docker build --no-cache . -t ghcr.io/qbic-pipelines/rnadeseq:dev
 
       # Change the version above and the third version below before/after release
       - name: Pull docker image
         if: ${{ !env.MATCHED_FILES }}
         run: |
           docker pull ghcr.io/qbic-pipelines/rnadeseq:dev
-          docker tag ghcr.io/qbic-pipelines/rnadeseq:dev ghcr.io/qbic-pipelines/rnadeseq:2.3dev
+          docker tag ghcr.io/qbic-pipelines/rnadeseq:dev ghcr.io/qbic-pipelines/rnadeseq:dev
 
       - name: Install Nextflow
         uses: nf-core/setup-nextflow@v1
@@ -94,14 +94,14 @@ jobs:
             environment.yml
       - name: Build new docker image
         if: env.MATCHED_FILES
-        run: docker build --no-cache . -t ghcr.io/qbic-pipelines/rnadeseq:2.3dev
+        run: docker build --no-cache . -t ghcr.io/qbic-pipelines/rnadeseq:dev
 
       # Change the version above and the third version below before/after release
       - name: Pull docker image
         if: ${{ !env.MATCHED_FILES }}
         run: |
           docker pull ghcr.io/qbic-pipelines/rnadeseq:dev
-          docker tag ghcr.io/qbic-pipelines/rnadeseq:dev ghcr.io/qbic-pipelines/rnadeseq:2.3dev
+          docker tag ghcr.io/qbic-pipelines/rnadeseq:dev ghcr.io/qbic-pipelines/rnadeseq:dev
 
       - name: Install Nextflow
         uses: nf-core/setup-nextflow@v1

diff --git a/Dockerfile b/Dockerfile
@@ -5,14 +5,14 @@ LABEL org.opencontainers.image.authors="Gisela Gabernet, Alexander Peltzer, Oska
 LABEL org.opencontainers.image.licenses=MIT
 COPY environment.yml /
 #RUN conda install -c conda-forge mamba
-RUN mamba env create --file /environment.yml -p /opt/conda/envs/qbic-pipelines-rnadeseq-2.3dev && \
+RUN mamba env create --file /environment.yml -p /opt/conda/envs/qbic-pipelines-rnadeseq-dev && \
     mamba clean --all --yes
 RUN apt-get update -qq && \
     apt-get install -y zip procps ghostscript
 # Add conda installation dir to PATH
-ENV PATH /opt/conda/envs/qbic-pipelines-rnadeseq-2.3dev/bin:$PATH
+ENV PATH /opt/conda/envs/qbic-pipelines-rnadeseq-dev/bin:$PATH
 # Dump the details of the installed packates to a file for posterity
-RUN mamba env export --name qbic-pipelines-rnadeseq-2.3dev > qbic-pipelines-rnadeseq-2.3dev.yml
+RUN mamba env export --name qbic-pipelines-rnadeseq-dev > qbic-pipelines-rnadeseq-dev.yml
 # Instruct R processes to use these empty files instead of clashing with a local config
 RUN touch .Rprofile
 RUN touch .Renviron
diff --git a/assets/RNAseq_report.Rmd b/assets/RNAseq_report.Rmd
diff --git a/conf/test.config b/conf/test.config
@@ -28,6 +28,7 @@ params {
     software_versions = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/software_versions.csv'
     multiqc = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/MultiQC.zip'
     run_pathway_analysis = true
+    datasources = 'KEGG,REAC'
     genome = 'GRCm38'
     quote = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/offer_example.pdf'
 }
diff --git a/conf/test_custom_gmt.config b/conf/test_custom_gmt.config
@@ -28,6 +28,7 @@ params {
     software_versions = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/software_versions.csv'
     multiqc = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/MultiQC.zip'
     run_pathway_analysis = true
+    datasources = 'KEGG,REAC'
     genome = 'GRCm38'
     custom_gmt = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/gprofiler_full_mmusculus.ENSG.gmt'
     datasources = 'KEGG,REAC'

diff --git a/conf/test_smrnaseq.config b/conf/test_smrnaseq.config
@@ -24,6 +24,7 @@ params {
     genelist = 'testdata/smrnaseq/requested_genes.txt'
     input_type = 'smrnaseq'
     run_pathway_analysis = true
+    datasources = 'KEGG,REAC'
     genome = 'GRCh37'
     batch_effect = true
     set_background = false // This is solely to get some enriched pathways so that the github tests also check the pathway analysis output

diff --git a/conf/test_star_rsem.config b/conf/test_star_rsem.config
@@ -23,11 +23,11 @@ params {
     //report_options = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/report_options.yml'
     project_summary = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/summary.tsv'
     software_versions = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/software_versions_rsem.yml'
-    multiqc = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/MultiQC.zip'
+    multiqc = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/QDESQ/new_rsem_multiqc.zip'
     input_type = 'rsem'
     run_pathway_analysis = true
+    datasources = 'GO:CC,KEGG'
     genome = 'GRCh37'
-    datasources = 'GO:CC'
     // species_library     = "org.Hs.eg.db"
     // organism    = "hsapiens"
     // keytype     = "ENSEMBL"

diff --git a/conf/test_star_salmon.config b/conf/test_star_salmon.config
@@ -23,9 +23,10 @@ params {
     //report_options = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/report_options.yml'
     project_summary = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/summary.tsv'
     software_versions = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/software_versions_salmon.yml'
-    multiqc = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/MultiQC.zip'
+    multiqc = 'https://raw.githubusercontent.com/qbic-pipelines/rnadeseq/dev/testdata/QDESQ/new_salmon_multiqc.zip'
     input_type = 'salmon'
     run_pathway_analysis = true
+    datasources = 'KEGG,REAC'
     //  genome = 'GRCh37'
     species_library = "org.Hs.eg.db"
     organism    = "hsapiens"

diff --git a/docs/usage.md b/docs/usage.md
@@ -89,7 +89,7 @@ The `qbic-pipelines/rnadeseq` pipeline relies on the output from the `nf-core/rn
 The typical command for running the pipeline is as follows:
 
 ```bash
-nextflow run qbic-pipelines/rnadeseq -r 2.0.1 -profile docker \
+nextflow run qbic-pipelines/rnadeseq -r 2.2 -profile docker \
 --gene_counts 'merged_gene_counts.txt' \
 --input 'QXXXX_sample_preparations.tsv' \
 --model 'linear_model.txt' \
@@ -157,7 +157,7 @@ curl https://codeload.github.com/qbic-pipelines/rnadeseq/tar.gz/master | tar -xz
 Afterwards, you should be able to also run test_star_rsem and test_star_salmon from qbic-pipelines/rnadeseq without manually cloning, e.g.:
 
 ```bash
-nextflow run qbic-pipelines/rnadeseq -r 2.0.1 -profile docker,test_star_salmon
+nextflow run qbic-pipelines/rnadeseq -r 2.2 -profile docker,test_star_salmon
 ```
 
 ### Reproducibility

diff --git a/environment.yml b/environment.yml
@@ -1,7 +1,7 @@
 # You can use this file to create a conda environment for this pipeline:
 #   conda env create -f environment.yml
 # use this to find packages: https://anaconda.org/
-name: qbic-pipelines-rnadeseq-2.3dev
+name: qbic-pipelines-rnadeseq-dev
 channels:
   - bioconda
   - conda-forge

diff --git a/modules/local/report.nf b/modules/local/report.nf
@@ -1,6 +1,6 @@
 process REPORT {
 
-    container 'ghcr.io/qbic-pipelines/rnadeseq:2.3dev'
+    container 'ghcr.io/qbic-pipelines/rnadeseq:dev'
 
     input:
     path gene_counts
@@ -48,7 +48,7 @@ process REPORT {
     if [ "$multiqc" != "NO_FILE4" ]; then
         unzip $multiqc
         mkdir QC
-        mv MultiQC/multiqc_plots/ MultiQC/multiqc_data/ MultiQC/multiqc_report.html QC/
+        mv MultiQC/multiqc_plots/ MultiQC/multiqc_data/ MultiQC/multiqc_report.html QC/ || mv multiqc/*/multiqc_plots/ multiqc/*/multiqc_data/ multiqc/*/multiqc_report.html QC/ || mv multiqc_plots/ multiqc_data/ multiqc_report.html QC/
     fi
     Execute_report.R \
         --report '$baseDir/assets/RNAseq_report.Rmd' \
@@ -102,4 +102,3 @@ process REPORT {
     """
 
 }
-
diff --git a/nextflow.config b/nextflow.config
@@ -258,7 +258,7 @@ manifest {
     description     = """Differential gene expression analysis and pathway analysis of RNAseq data"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=23.04.0'
-    version         = '2.3dev'
+    version         = 'dev'
     doi             = ''
 }
 

diff --git a/testdata/QDESQ/new_rsem_multiqc.zip b/testdata/QDESQ/new_rsem_multiqc.zip
diff --git a/testdata/QDESQ/new_salmon_multiqc.zip b/testdata/QDESQ/new_salmon_multiqc.zip
diff --git a/tests/test.yml b/tests/test.yml
@@ -67,7 +67,7 @@
     - path: results_test/pathway_analysis/DE_contrast_condition_genotype_WT_vs_KO/gost_pathway_gostplot.png
     - path: results_test/pathway_analysis/DE_contrast_condition_genotype_WT_vs_KO/gost_pathway_gostplot.svg
     - path: results_test/pathway_analysis/DE_contrast_condition_genotype_WT_vs_KO/pathway_enrichment_results.tsv
-      md5sum: 21b907d52008f66f9a85190400fd211e
+      md5sum: 92736a4c802ebd4e644682308ecf46dc
     - path: results_test/pathway_analysis/DE_contrast_condition_genotype_WT_vs_KO/KEGG_pathway_enrichment_results.tsv
       md5sum: 92115e662e0e2489ad05d28f3981fa3a
     - path: results_test/pathway_analysis/DE_contrast_condition_genotype_WT_vs_KO/REAC_pathway_enrichment_results.tsv
@@ -83,7 +83,7 @@
     - path: results_test/pathway_analysis/DE_contrast_condition_genotype_WT_vs_KO/KEGG_pathways/mmu04610.png
     - path: results_test/pathway_analysis/DE_contrast_condition_genotype_WT_vs_KO/KEGG_pathways/mmu04610.xml
     - path: results_test/pathway_analysis/DE_contrast_condition_treatment_Treated_vs_Control/pathway_enrichment_results.tsv
-      md5sum: bdc0167b8b33a0da44e34768eead8376
+      md5sum: 0a425c10e229bb775597be176c414705
     - path: results_test/pathway_analysis/DE_contrast_condition_treatment_Treated_vs_Control/REAC_pathway_enrichment_results.tsv
       md5sum: 6594fdb8c0eb591fa131982a8be00877
     - path: results_test/pathway_analysis/DE_contrast_condition_treatment_Treated_vs_Control/gost_pathway_venn_diagram.pdf

diff --git a/tests/test_smrnaseq.yml b/tests/test_smrnaseq.yml
@@ -78,12 +78,12 @@
     - path: results_test/pathway_analysis/DE_contrast_condition_treatment_clone9_vs_clone1/KEGG_pathway_enrichment_results.tsv
       md5sum: 326f3495ca42dbc527484cef3ee0e58d
     - path: results_test/pathway_analysis/DE_contrast_condition_treatment_clone9_vs_clone1/pathway_enrichment_results.tsv
-      md5sum: b77e2839aa95ce3a9562d03a13629eb4
+      md5sum: d63d4d96de3c49cc38c91cb863a7da06
     - path: results_test/pathway_analysis/DE_contrast_condition_treatment_control_vs_clone1/enrichment_plots/KEGG_pathway_enrichment_plot.pdf
     - path: results_test/pathway_analysis/DE_contrast_condition_treatment_control_vs_clone1/enrichment_plots/KEGG_pathway_enrichment_plot.png
     - path: results_test/pathway_analysis/DE_contrast_condition_treatment_control_vs_clone1/enrichment_plots/KEGG_pathway_enrichment_plot.svg
     - path: results_test/pathway_analysis/DE_contrast_condition_treatment_control_vs_clone1/KEGG_pathway_enrichment_results.tsv
       md5sum: 64b3a3716b779900e99f56688c4b27e8
     - path: results_test/pathway_analysis/DE_contrast_condition_treatment_control_vs_clone1/pathway_enrichment_results.tsv
-      md5sum: 05e83209e36face6ead8b066155fdbe5
+      md5sum: e7a051d8623043a3849eae8900b99f71
     - path: results_test/RNAseq_report.html
diff --git a/tests/test_star_rsem.yml b/tests/test_star_rsem.yml
@@ -85,9 +85,9 @@
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_H1_vs_GM12878/gost_pathway_venn_diagram.png
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_H1_vs_GM12878/gost_pathway_venn_diagram.svg
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_H1_vs_GM12878/pathway_enrichment_results.tsv
-      md5sum: 9eef4eab3da88b4b7e465f982be72acb
+      md5sum: 57e56666c0d561659f5aaec478f04cee
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_K562_vs_GM12878/GO.CC_pathway_enrichment_results.tsv
-      md5sum: 2bbbf2de30f9da36e4c5b2df7a4ef5e7
+      md5sum: 098f12540b4cad2ea1c950af1fd304b6
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_K562_vs_GM12878/enrichment_plots/GO.CC_pathway_enrichment_plot.pdf
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_K562_vs_GM12878/enrichment_plots/GO.CC_pathway_enrichment_plot.png
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_K562_vs_GM12878/enrichment_plots/GO.CC_pathway_enrichment_plot.svg
@@ -98,9 +98,9 @@
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_K562_vs_GM12878/gost_pathway_venn_diagram.png
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_K562_vs_GM12878/gost_pathway_venn_diagram.svg
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_K562_vs_GM12878/pathway_enrichment_results.tsv
-      md5sum: cbda28eeba947c53847ea28fdaa0cebd
+      md5sum: 73fdb835cede09c13f0ab2684b1cda73
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_MCF7_vs_GM12878/GO.CC_pathway_enrichment_results.tsv
-      md5sum: 6b79ce64567f94ad3fc492e1a56fce58
+      md5sum: 2ebd84e4ed2029659294a09d49b62048
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_MCF7_vs_GM12878/enrichment_plots/GO.CC_pathway_enrichment_plot.pdf
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_MCF7_vs_GM12878/enrichment_plots/GO.CC_pathway_enrichment_plot.png
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_MCF7_vs_GM12878/enrichment_plots/GO.CC_pathway_enrichment_plot.svg
@@ -111,7 +111,7 @@
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_MCF7_vs_GM12878/gost_pathway_venn_diagram.png
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_MCF7_vs_GM12878/gost_pathway_venn_diagram.svg
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_MCF7_vs_GM12878/pathway_enrichment_results.tsv
-      md5sum: 68f919b58d7fe5cc1b9a38665abccf78
+      md5sum: b7f67bc86475b218965b173b753199b1
     - path: results_test/pathway_analysis/heatmap_gene_list/Heatmap_normalized_counts_gene_list.pdf
     - path: results_test/pathway_analysis/heatmap_gene_list/Heatmap_normalized_counts_gene_list.svg
     - path: results_test/pathway_analysis/metadata/gprofiler_full_hsapiens.ENSG.gmt
diff --git a/tests/test_star_salmon.yml b/tests/test_star_salmon.yml
@@ -70,7 +70,7 @@
     - path: results_test/differential_gene_expression/plots/PCA_plot.png
     - path: results_test/differential_gene_expression/plots/PCA_plot.svg
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_H1_vs_GM12878/pathway_enrichment_results.tsv
-      md5sum: 30af65ef53ef7e389e116c31d31bd1d6
+      md5sum: 68b329da9893e34099c7d8ad5cb9c940
     - path: results_test/pathway_analysis/DE_contrast_condition_cellline_K562_vs_GM12878/pathway_enrichment_results.tsv
-      md5sum: 4a3e61c2b4fea94c327acc63c83c0a4a
+      md5sum: 68b329da9893e34099c7d8ad5cb9c940
     - path: results_test/RNAseq_report.html