Merge pull request #62 from genomic-medicine-sweden/develop

chore: dev to master first relaese

.github/CODEOWNERS

@@ -2,4 +2,4 @@
 # the repo. Unless a later match takes precedence,
 # @global-owner1 and @global-owner2 will be requested for
 # review when someone opens a pull request.
-* @ljmesi
+* @Smeds @jonca79 @pyrevo @ljmesi @chels0

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,20 @@
+### This PR:
+
+(If this is a release PR, no need to add following. Leave this part empty)
+(Use the following lines to create a PR text body. Make sure to remove all non-relevant one after you're done)
+(Repeat each field as many times as necessary)
+
+Added: for new features.
+Changed: for changes in existing functionality.
+Deprecated: for soon-to-be removed features.
+Removed: for now removed features.
+Fixed: for any bug fixes.
+Security: in case of vulnerabilities.
+
+### Review and tests:
+- [ ] Tests pass
+- [ ] If you've fixed a bug or added code that should be tested, add tests!
+- [ ] Code review
+- [ ] `CHANGELOG.md` is updated
+- [ ] New code is executed and covered by tests, and test approve
+- [ ] Module compatibility section in `README.md` is up to date

.github/workflows/integration1.yaml

@@ -12,32 +12,6 @@ on:
   workflow_dispatch:
 
 jobs:
-  integration-small-conda:
-    name: integration small data set conda
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v2
-      - name: Set up Python 3.8
-        uses: actions/setup-python@v2
-        with:
-          python-version: 3.8
-      - name: Add conda to system path
-        run: |
-          echo $CONDA/bin >> $GITHUB_PATH
-      - name: Install dependencies
-        run: |
-          conda install -c conda-forge mamba
-      - name: Install requirements.txt
-        run: |
-          pip install -r requirements.txt
-      - name: Install requirements.test.txt
-        run: |
-          pip install -r requirements.test.txt
-      - name: Integration test - small dataset
-        working-directory: .tests/integration
-        run: |
-          mamba install -c conda-forge -c bioconda snakemake
-          snakemake -s ../../workflow/Snakefile -j 1 --use-conda
   integration-small-singularity:
     name: integration small data set singularity
     runs-on: ubuntu-latest
@@ -47,12 +21,19 @@ jobs:
         uses: actions/setup-python@v2
         with:
           python-version: 3.8
+      - name: Setup Mambaforge
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+            miniforge-variant: Mambaforge
+            miniforge-version: latest
+            activate-environment: my-env
+            use-mamba: true
       - name: Add conda to system path
         run: |
           echo $CONDA/bin >> $GITHUB_PATH
-      - name: Install dependencies
+      - name: Set strict channels
         run: |
-          conda install -c conda-forge mamba
+          conda config --set channel_priority strict
       - name: Install requirements.txt
         run: |
           pip install -r requirements.txt
@@ -61,8 +42,8 @@ jobs:
           pip install -r requirements.test.txt
       - name: Install singularity
         run: |
-          mamba install -c conda-forge -c bioconda singularity
+          mamba install -c conda-forge -c bioconda singularity=3.8.6
       - name: Integration test - small dataset
         working-directory: .tests/integration
         run: |
-          snakemake -s ../../workflow/Snakefile -j 1 --show-failed-logs --use-singularity --singularity-args  " --cleanenv --bind /home/runner "
+          snakemake -s ../../workflow/Snakefile -j 1 --configfile config/config.yaml --show-failed-logs --use-singularity --singularity-args  " --cleanenv --bind /home/runner "

.github/workflows/lint.yaml

@@ -20,12 +20,18 @@ jobs:
     name: Lint workflow
     runs-on: ubuntu-latest
     steps:
-      - name: Check out the repo
-        uses: actions/checkout@v2
-      - name: Linting
-        uses: snakemake/[email protected]
+      - uses: actions/checkout@v3
+      - name: Set up Python 3.8
+        uses: actions/setup-python@v3
         with:
-          directory: ".tests/integration"
-          snakefile: "workflow/Snakefile"
-          args: "--lint"
-          stagein: "pip install -r requirements.txt"
+          python-version: 3.8
+      - name: Add conda to system path
+        run: |
+          echo $CONDA/bin >> $GITHUB_PATH
+      - name: Install requirements.txt
+        run: |
+          pip install -r requirements.txt
+      - name: Linting
+        working-directory: .tests/integration
+        run: |
+          snakemake --lint -n -s ../../workflow/Snakefile --configfile config/config.yaml

.github/workflows/pycodestyl.yaml

@@ -28,9 +28,13 @@ jobs:
       - name: Add conda to system path
         run: |
           echo $CONDA/bin >> $GITHUB_PATH
-      - name: Install dependencies
-        run: |
-          conda install -c conda-forge mamba
+      - name: Setup Mambaforge
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+            miniforge-variant: Mambaforge
+            miniforge-version: latest
+            activate-environment: my-env
+            use-mamba: true
       - name: Install requirements.txt
         run: |
           pip install -r requirements.txt

.github/workflows/pytest.yaml

@@ -25,12 +25,16 @@ jobs:
         uses: actions/setup-python@v2
         with:
           python-version: 3.8
+      - name: Setup Mambaforge
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+            miniforge-variant: Mambaforge
+            miniforge-version: latest
+            activate-environment: my-env
+            use-mamba: true
       - name: Add conda to system path
         run: |
           echo $CONDA/bin >> $GITHUB_PATH
-      - name: Install dependencies
-        run: |
-          conda install -c conda-forge mamba
       - name: Install requirements.txt
         run: |
           pip install -r requirements.txt

.github/workflows/snakemake-dry-run.yaml

@@ -25,12 +25,16 @@ jobs:
         uses: actions/setup-python@v2
         with:
           python-version: 3.8
+      - name: Setup Mambaforge
+        uses: conda-incubator/setup-miniconda@v2
+        with:
+            miniforge-variant: Mambaforge
+            miniforge-version: latest
+            activate-environment: my-env
+            use-mamba: true
       - name: Add conda to system path
         run: |
           echo $CONDA/bin >> $GITHUB_PATH
-      - name: Install dependencies
-        run: |
-          conda install -c conda-forge mamba
       - name: Install requirements.txt
         run: |
           pip install -r requirements.txt
@@ -41,4 +45,4 @@ jobs:
         working-directory: .tests/integration
         run: |
           mamba install -c conda-forge -c bioconda snakemake singularity
-          snakemake -n -s ../../workflow/Snakefile
+          snakemake -n -s ../../workflow/Snakefile  --configfile config/config.yaml

.gitignore

@@ -1,6 +1,15 @@
 .eggs
 __pycache__
-.snakemake
+.snakemake/
+.tests/integration/.snakemake/
 describe_workflow.rst
 describe_jupyter_notebook.txt
-pgx
+pgx/
+data/
+prealignment/
+alignment/
+snv_indels/
+logs/
+tmp/
+*.bai
+*.tsv

.tests/integration/config/config.yaml

@@ -0,0 +1,82 @@
+resources: "config/resources.yaml"
+samples: "samples.tsv"
+units: "units.tsv"
+output: "../../config/output_files.yaml"
+
+default_container: "docker://hydragenetics/common:0.3.0"
+
+trimmer_software: "fastp_pe"
+
+bwa_mem:
+  container: "docker://hydragenetics/bwa_mem:0.7.17"
+  amb: "reference/hg19.chr6.fasta.amb"
+  ann: "reference/hg19.chr6.fasta.ann"
+  bwt: "reference/hg19.chr6.fasta.bwt"
+  pac: "reference/hg19.chr6.fasta.pac"
+  sa: "reference/hg19.chr6.fasta.sa"
+
+fastp_pe:
+  container: "docker://hydragenetics/fastp:0.20.1"
+
+picard_mark_duplicates:
+  container: "docker://hydragenetics/picard:2.25.0"
+
+haplotypecaller:
+  container: "docker://hydragenetics/gatk4:4.1.9.0"
+  extra: "--dbsnp reference/dbsnp_138.sub.vcf.gz --standard-min-confidence-threshold-for-calling 1.0"
+
+get_padded_bed:
+  padding: 100
+
+picard_mark_duplicates:
+  container: "docker://hydragenetics/picard:2.25.0"
+
+snv_indels_haplotypecaller:
+  container: "docker://hydragenetics/gatk4:4.1.9.0"
+
+variant_filtration:
+  read_ratio: 0.2
+  read_depth: 100
+
+variant_annotator:
+  container: "docker://hydragenetics/gatk4:4.1.9.0"
+
+detected_variants:
+  file_type: "VCF"
+
+sample_target_list:
+  padding: 0
+
+get_padded_baits:
+  padding: 100
+  file_format: "list"
+
+depth_of_baits:
+  container: "docker://hydragenetics/gatk4:4.1.9.0"
+  extra: "--output-format TABLE"
+
+depth_of_targets:
+  container: "docker://hydragenetics/gatk4:4.1.9.0"
+  extra: "--output-format TABLE"
+
+append_id_to_gdf:
+  file_type: "GDF"
+
+get_clinical_guidelines:
+  haplotype_definitions: "reference/haplotype_definitions.csv"
+  haplotype_activity: "reference/haplotype_activity_score.csv"
+  clinical_guidelines: "reference/clinical_guidelines.csv"
+  hidden_haplotypes: "reference/hidden_haplotypes.csv"
+
+get_interaction_guidelines:
+  interaction_guidelines: "reference/interaction_guidelines.csv"
+
+reference:
+  design_bed: "reference/exons_variants_pharmacogenomics.TPMT.bed"
+  design_rsid: "reference/target_rsid.TPMT.bed"
+  fasta: "reference/hg19.chr6.fasta"
+  fai: "reference/hg19.chr6.fasta.fai"
+  dbsnp: "reference/dbsnp_138.sub.vcf.gz"
+
+generate_pgx_report:
+  report_template: "reference/report_template.txt"

.tests/integration/config/resources.yaml

@@ -0,0 +1,9 @@
+default_resources:
+  threads: 1
+  time: "12:00:00"
+  mem_mb: 1024
+  mem_per_cpu: 3072
+  partition: core
+
+haplotypecaller:
+  threads: 8