fix: get sra download to work and test it

.github/workflows/conventional-prs.yaml

@@ -13,6 +13,6 @@ jobs:
     name: Validate PR title
     runs-on: ubuntu-latest
     steps:
-      - uses: amannn/action-semantic-pull-request@v5
+      - uses: amannn/action-semantic-pull-request@v6
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/main.yml

@@ -11,60 +11,106 @@ jobs:
   formatting:
     runs-on: ubuntu-latest
     steps:
-    - name: Checkout with submodules
-      uses: actions/checkout@v3
-      with:
-        submodules: recursive
-        fetch-depth: 0
-    - name: Formatting
-      uses: github/super-linter@v5
-      env:
-        VALIDATE_ALL_CODEBASE: false
-        DEFAULT_BRANCH: master
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        VALIDATE_SNAKEMAKE_SNAKEFMT: true
+      - name: Checkout with submodules
+        uses: actions/checkout@v6
+        with:
+          submodules: recursive
+          fetch-depth: 0
+      - name: Formatting
+        uses: super-linter/super-linter@v8
+        env:
+          VALIDATE_ALL_CODEBASE: false
+          DEFAULT_BRANCH: master
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          VALIDATE_SNAKEMAKE_SNAKEFMT: true
   linting:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
-    - name: Linting
-      uses: snakemake/snakemake-github-action@v1.22.0
-      with:
-        directory: .test
-        snakefile: workflow/Snakefile
-        args: "--configfile .test/config_complex/config.yaml --lint"
+      - uses: actions/checkout@v6
+      - name: Linting
+        uses: snakemake/snakemake-github-action@v2
+        with:
+          directory: .test
+          snakefile: workflow/Snakefile
+          args: "--configfile .test/config_complex/config.yaml --lint"
 
-  run-workflow:
+  testing:
     runs-on: ubuntu-latest
     needs:
       - linting
       - formatting
+    strategy:
+      fail-fast: true
+      matrix:
+        case:
+          - name: basic model, no batch_effects
+            args: >-
+              --configfile .test/config_basic/config.yaml
+            report: true
+            free_disk_space: false
+
+          - name: multiple variables_of_interest, include batch_effects
+            args: >-
+              --configfile .test/config_complex/config.yaml
+            report: true
+            free_disk_space: false
+          - name: sra file download, no batch_effects
+            args: >-
+              --configfile .test/config_sra/config.yaml
+            report: true
+            free_disk_space: true
+
+    name: test ${{ matrix.case.name }}
+
     steps:
-    - name: Checkout repository with submodules
-      uses: actions/checkout@v3
-      with:
-        submodules: recursive
-    - name: Test workflow (basic model, no batch_effects)
-      uses: snakemake/[email protected]
-      with:
-        directory: .test
-        snakefile: workflow/Snakefile
-        args: "--configfile .test/config_basic/config.yaml --use-conda --show-failed-logs --cores 2 --conda-cleanup-pkgs cache"
-    - name: Test report (basic model, no batch_effects)
-      uses: snakemake/[email protected]
-      with:
-        directory: .test
-        snakefile: workflow/Snakefile
-        args: "--configfile .test/config_basic/config.yaml --report report.zip"
-    - name: Test workflow (multiple variables_of_interest, include batch_effects)
-      uses: snakemake/[email protected]
-      with:
-        directory: .test
-        snakefile: workflow/Snakefile
-        args: "--configfile .test/config_complex/config.yaml --use-conda --show-failed-logs --cores 2 --conda-cleanup-pkgs cache"
-    - name: Test report (multiple variables_of_interest, include batch_effects)
-      uses: snakemake/[email protected]
-      with:
-        directory: .test
-        snakefile: workflow/Snakefile
-        args: "--configfile .test/config_complex/config.yaml --report report.zip"
+      - name: update apt
+        if: ${{ matrix.case.free_disk_space }}
+        run: sudo apt-get update
+
+      - name: Free Disk Space (Ubuntu)
+        if: ${{ matrix.case.free_disk_space }}
+        uses: jlumbroso/[email protected]
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: false
+
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+
+      - name: Checkout repository with submodules
+        uses: actions/checkout@v6
+        with:
+          submodules: recursive
+
+      - name: run workflow
+        uses: snakemake/snakemake-github-action@v2
+        with:
+          directory: .test
+          snakefile: workflow/Snakefile
+          args: >-
+            --conda-cleanup-pkgs cache
+            --software-deployment-method conda
+            --show-failed-logs
+            --cores 8
+            ${{ matrix.case.args }}
+          show-disk-usage-on-error: true
+
+      - name: generate report
+        if: ${{ matrix.case.report }}
+        uses: snakemake/snakemake-github-action@v2
+        with:
+          directory: .test
+          snakefile: workflow/Snakefile
+          args: >-
+            --software-deployment-method conda
+            --cores 1
+            --report report.zip
+            ${{ matrix.case.args }}
+          show-disk-usage-on-error: true

.github/workflows/release-please.yaml

@@ -13,7 +13,7 @@ jobs:
   release-please:
     runs-on: ubuntu-latest
     steps:
-      - uses: google-github-actions/release-please-action@v3
+      - uses: googleapis/release-please-action@v4
         with:
           release-type: simple
           token: ${{ secrets.GITHUB_TOKEN }}

.test/config_basic/config.yaml

@@ -4,13 +4,11 @@
 samples: config_basic/samples.tsv
 units: config_basic/units.tsv
 
-
 ref:
   species: saccharomyces_cerevisiae
-  release: 100
+  release: 115
   build: R64-1-1
 
-
 trimming:
   activate: True
 

.test/config_complex/config.yaml

@@ -4,13 +4,11 @@
 samples: config_complex/samples.tsv
 units: config_complex/units.tsv
 
-
 ref:
   species: saccharomyces_cerevisiae
-  release: 100
+  release: 115
   build: R64-1-1
 
-
 trimming:
   activate: False
 
@@ -44,4 +42,3 @@ params:
   star:
     index: ""
     align: ""
-

.test/config_sra/config.yaml

@@ -0,0 +1,40 @@
+# For a fully commented config.yaml file, see the main `config/config.yaml`
+# example file.
+
+samples: config_sra/samples.tsv
+# This data comes from:
+# * https://www.ncbi.nlm.nih.gov/bioproject/PRJEB30262
+# * https://www.ncbi.nlm.nih.gov/Traces/study/?acc=PRJEB30262&o=acc_s%3Aa
+units: config_sra/units.tsv
+
+ref:
+  species: saccharomyces_cerevisiae
+  release: 115
+  build: R64-1-1
+
+trimming:
+  activate: True
+
+mergeReads:
+  activate: False
+
+pca:
+  activate: True
+  labels:
+    - genotype
+
+diffexp:
+  variables_of_interest:
+    genotype:
+      base_level: control
+  batch_effects: ""
+  contrasts:
+    stb5_vs_control:
+      variable_of_interest: genotype
+      level_of_interest: stb5
+  model: ~genotype
+
+params:
+  star:
+    index: ""
+    align: ""

.test/config_sra/samples.tsv

@@ -0,0 +1,5 @@
+sample_name	genotype
+control_g_1	control
+control_g_2	control
+stb5_g_1	stb5
+stb5_g_2	stb5

.test/config_sra/units.tsv

@@ -0,0 +1,9 @@
+sample_name	unit_name	fq1	fq2	sra	fastp_adapters	fastp_extra	strandedness
+control_g_1	lane1			ERR2985811			
+control_g_1	lane2			ERR2985812			
+control_g_2	lane1			ERR2985815			
+control_g_2	lane2			ERR2985816			
+stb5_g_1	lane1			ERR2985827			
+stb5_g_1	lane2			ERR2985828			
+stb5_g_2	lane1			ERR2985831			
+stb5_g_2	lane2			ERR2985832			

config/config.yaml

@@ -5,13 +5,36 @@ samples: config/samples.tsv
 # sample).
 units: config/units.tsv
 
-
 ref:
-  # Ensembl species name
+  # ensembl species name:
+  # This species needs to be available for download via the Ensembl FTP site.
+  # For a quick check, see the Ensembl species list:
+  # https://www.ensembl.org/info/about/species.html
+  # For full valid species names, consult the respective table for the release
+  # you specify, for example for ‘115’ this is at:
+  # https://ftp.ensembl.org/pub/release-115/species_EnsemblVertebrates.txt
+  # And to browse available downloads in more detail, see the FTP server:
+  # https://ftp.ensembl.org/pub/
   species: homo_sapiens
-  # Ensembl release (make sure to take one where snpeff data is available, check 'snpEff databases' output)
-  release: 100
-  # Genome build
+  # ensembl release version:
+  # Update this to the latest working version, when you first set up a new
+  # analysis on a dataset. You can usually find the latest release in the
+  # Ensembl blog, by looking at the latest posts of the release category:
+  # https://www.ensembl.info/category/01-release/
+  # Later, it only makes sense to update (or downgrade) the release versions
+  # if either (a) the version you are using consistently fails to download
+  # (some Ensembl release versions are just broken) or (b) you know that a
+  # newer version will include changes that will fix some error or adds
+  # transcripts that will be relevant to your analysis.
+  release: 115
+  # genome build:
+  # Usually, this should just be the main build listed in:
+  # https://ftp.ensembl.org/pub/release-115/species_EnsemblVertebrates.txt
+  # For example, for homo_sapiens, you strip the assembly column entry
+  # "GRCh38.p12" down to "GRCh38". If in doubt, navigate to the respective
+  # cdna folder on the FTP server, and look for the correct build in the
+  # file names there. For example "GRCh38" in:
+  # https://ftp.ensembl.org/pub/release-115/fasta/homo_sapiens/cdna/
   build: GRCh38
 
 trimming:
@@ -64,7 +87,6 @@ diffexp:
   # model: ~jointly_handled + treatment_1 + treatment_2
   model: ""
 
-
 # passing extra parameters to respective rules in the workflow
 params:
   star:

workflow/rules/common.smk

@@ -57,7 +57,7 @@ def get_units_fastqs(wildcards):
         return expand(
             "sra/{accession}_{read}.fastq",
             accession=accession,
-            read=["R1", "R2"],
+            read=["1", "2"],
         )
     if not is_paired_end(wildcards.sample):
         return [

workflow/rules/trim.smk

@@ -4,6 +4,8 @@ rule get_sra:
         "sra/{accession}_2.fastq",
     log:
         "logs/get-sra/{accession}.log",
+    params:
+        extra="-x",
     wrapper:
         "v7.2.0/bio/sra-tools/fasterq-dump"