Fix vcf input to ancestry analysis

.github/workflows/ancestry-vcf.yml

@@ -0,0 +1,160 @@
+name: Run ancestry test with singularity or docker profiles with VCF input
+
+on:
+  workflow_call:
+    inputs:
+      container-cache-key:
+        type: string
+        required: true
+      ancestry-cache-key:
+        type: string
+        required: true
+      docker:
+        type: boolean
+      singularity:
+        type: boolean
+
+env:
+  NXF_SINGULARITY_CACHEDIR: ${{ github.workspace }}/singularity
+  SINGULARITY_VERSION: 3.8.3
+
+jobs:
+  docker:
+    if: ${{ inputs.docker }}
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Set environment variables
+        run: |
+          echo "ANCESTRY_REF_DIR=$RUNNER_TEMP" >> $GITHUB_ENV
+          echo "ANCESTRY_TARGET_DIR=$RUNNER_TEMP" >> $GITHUB_ENV
+
+      - name: Check out pipeline code
+        uses: actions/checkout@v3
+
+      - uses: nf-core/setup-nextflow@v1
+
+      - name: Restore docker images
+        id: restore-docker
+        uses: actions/cache/restore@v3
+        with:
+          path: ${{ runner.temp }}/docker
+          key: ${{ inputs.container-cache-key }}
+          fail-on-cache-miss: true
+
+      - name: Load docker images from cache
+        run: |
+          find $HOME -name '*.tar'
+          find ${{ runner.temp }}/docker/ -name '*.tar' -exec sh -c 'docker load < {}' \;
+
+      - name: Restore reference data
+        uses: actions/cache/restore@v3
+        with:
+          path: |
+            ${{ env.ANCESTRY_TARGET_DIR }}/GRCh38_HAPNEST_TARGET_ALL.pgen
+            ${{ env.ANCESTRY_TARGET_DIR }}/GRCh38_HAPNEST_TARGET_ALL.psam
+            ${{ env.ANCESTRY_TARGET_DIR }}/GRCh38_HAPNEST_TARGET_ALL.pvar.zst
+            ${{ env.ANCESTRY_REF_DIR }}/GRCh38_HAPNEST_reference.tar.zst
+          key: ${{ inputs.ancestry-cache-key }}
+          fail-on-cache-miss: true
+
+      - name: Install plink2 to recode
+        run: sudo apt-get install -y plink2
+
+      - name: Recode VCF
+        run: plink2 --pfile ${ANCESTRY_TARGET_DIR}/GRCh38_HAPNEST_TARGET_ALL vzs --export vcf bgz --out ${ANCESTRY_TARGET_DIR}/GRCh38_HAPNEST_TARGET_ALL
+
+      - name: Set up test requirements
+        uses: actions/setup-python@v3
+        with:
+          python-version: '3.10'
+          cache: 'pip'
+
+      - run: pip install -r ${{ github.workspace }}/tests/requirements.txt
+
+      - name: Run ancestry test
+        run: TMPDIR=~ PROFILE=docker pytest --kwdof --symlink --git-aware --wt 2 --tag "ancestry vcf" --ignore tests/bin
+
+      - name: Upload logs on failure
+        if: failure()
+        uses: actions/upload-artifact@v3
+        with:
+          name: logs-singularity-ancestry
+          path: |
+            /home/runner/pytest_workflow_*/*/.nextflow.log
+            /home/runner/pytest_workflow_*/*/log.out
+            /home/runner/pytest_workflow_*/*/log.err
+            /home/runner/pytest_workflow_*/*/output/*
+
+  singularity:
+    if: ${{ inputs.singularity }}
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Set environment variables
+        run: |
+          echo "ANCESTRY_REF_DIR=$RUNNER_TEMP" >> $GITHUB_ENV
+          echo "ANCESTRY_TARGET_DIR=$RUNNER_TEMP" >> $GITHUB_ENV
+
+      - name: Check out pipeline code
+        uses: actions/checkout@v3
+
+      - uses: nf-core/setup-nextflow@v1
+
+      - name: Restore singularity setup
+        id: restore-singularity-setup
+        uses: actions/cache@v3
+        with:
+          path: /opt/hostedtoolcache/singularity/${{ env.SINGULARITY_VERSION }}/x64
+          key: ${{ runner.os }}-singularity-${{ env.SINGULARITY_VERSION }}
+          fail-on-cache-miss: true
+
+      - name: Add singularity to path
+        run: |
+          echo "/opt/hostedtoolcache/singularity/${{ env.SINGULARITY_VERSION }}/x64/bin" >> $GITHUB_PATH
+
+      - name: Restore singularity container images
+        id: restore-singularity
+        uses: actions/cache@v3
+        with:
+          path: ${{ env.NXF_SINGULARITY_CACHEDIR }}
+          key: ${{ inputs.container-cache-key }}
+
+      - name: Restore reference data
+        uses: actions/cache/restore@v3
+        with:
+          path: |
+            ${{ env.ANCESTRY_TARGET_DIR }}/GRCh38_HAPNEST_TARGET_ALL.pgen
+            ${{ env.ANCESTRY_TARGET_DIR }}/GRCh38_HAPNEST_TARGET_ALL.psam
+            ${{ env.ANCESTRY_TARGET_DIR }}/GRCh38_HAPNEST_TARGET_ALL.pvar.zst
+            ${{ env.ANCESTRY_REF_DIR }}/GRCh38_HAPNEST_reference.tar.zst
+          key: ${{ inputs.ancestry-cache-key }}
+          fail-on-cache-miss: true
+
+      - name: Install plink2 to recode
+        run: sudo apt-get install -y plink2
+
+      - name: Recode VCF
+        run: plink2 --pfile ${ANCESTRY_TARGET_DIR}/GRCh38_HAPNEST_TARGET_ALL vzs --export vcf bgz --out ${ANCESTRY_TARGET_DIR}/GRCh38_HAPNEST_TARGET_ALL
+
+      - name: Set up test requirements
+        uses: actions/setup-python@v3
+        with:
+          python-version: '3.10'
+          cache: 'pip'
+
+      - run: pip install -r ${{ github.workspace }}/tests/requirements.txt
+
+      - name: Run ancestry test
+        run: TMPDIR=~ PROFILE=singularity pytest --kwdof --symlink --git-aware --wt 2 --tag "ancestry vcf" --ignore tests/bin
+
+      - name: Upload logs on failure
+        if: failure()
+        uses: actions/upload-artifact@v3
+        with:
+          name: logs-singularity-ancestry
+          path: |
+            /home/runner/pytest_workflow_*/*/.nextflow.log
+            /home/runner/pytest_workflow_*/*/log.out
+            /home/runner/pytest_workflow_*/*/log.err
+            /home/runner/pytest_workflow_*/*/output/*

.github/workflows/ci.yml

@@ -9,6 +9,7 @@ on:
     branches:
       - dev
       - main
+      - fix_vcf
   release:
     types: [published]
 
@@ -123,3 +124,19 @@ jobs:
       container-cache-key: ${{ needs.preload_singularity.outputs.cache-key }}
       ancestry-cache-key: ${{ needs.preload_ancestry.outputs.cache-key }}
       singularity: true
+
+  ancestry_vcf_docker:
+    needs: [preload_ancestry, preload_docker]
+    uses: ./.github/workflows/ancestry-vcf.yml
+    with:
+      container-cache-key: ${{ needs.preload_docker.outputs.cache-key }}
+      ancestry-cache-key: ${{ needs.preload_ancestry.outputs.cache-key }}
+      docker: true
+
+  ancestry_vcf_singularity:
+    needs: [preload_ancestry, preload_singularity]
+    uses: ./.github/workflows/ancestry.yml
+    with:
+      container-cache-key: ${{ needs.preload_singularity.outputs.cache-key }}
+      ancestry-cache-key: ${{ needs.preload_ancestry.outputs.cache-key }}
+      singularity: true

modules/local/plink2_vcf.nf

@@ -23,7 +23,7 @@ process PLINK2_VCF {
     tuple val(newmeta), path("*.pgen"), emit: pgen
     tuple val(newmeta), path("*.psam"), emit: psam
     tuple val(newmeta), path("*.zst") , emit: pvar
-    tuple val(meta), path("*.vmiss.gz"), emit: vmiss
+    tuple val(newmeta), path("*.vmiss.gz"), emit: vmiss
     path "versions.yml"            , emit: versions
 
     script:

subworkflows/local/ancestry/ancestry_project.nf

@@ -71,7 +71,7 @@ workflow ANCESTRY_PROJECT {
     //
 
     ch_genomes
-        .join(vmiss)
+        .join(vmiss, failOnMismatch: true)
         .combine( ch_db.map{ it.tail() } ) // (drop hashmap)
         .flatten()
         .buffer(size: 8)

tests/ancestry/samplesheet_vcf.csv

@@ -0,0 +1,2 @@
+sampleset,path_prefix,chrom,format
+test,ANCESTRY_TARGET_DIR/GRCh38_HAPNEST_TARGET_ALL,,vcf

tests/ancestry/test_ancestry_vcf.yml

@@ -0,0 +1,30 @@
+# ancestry test notes:
+# need to stage reference in $ANCESTRY_REF_DIR
+# extract target in $ANCESTRY_TARGET_DIR
+# need to convert target to VCF
+
+- name: test ancestry projection and scoring with VCF input
+  command: >
+    bash -c "
+    sed \"s|ANCESTRY_TARGET_DIR|$ANCESTRY_TARGET_DIR|\" tests/ancestry/samplesheet.csv > samplesheet.csv;
+    nextflow run main.nf -c ./tests/config/nextflow.config \
+      --input samplesheet.csv \
+      --run_ancestry $ANCESTRY_REF_DIR/GRCh38_HAPNEST_reference.tar.zst \
+      --target_build GRCh38 \
+      --pgs_id PGS001229 \
+      --min_overlap 0.50 \
+      --target_build GRCh38 \
+      --scorefile false
+    "
+  tags:
+    - ancestry vcf
+    - slow
+  stdout:
+    contains:
+      - "Pipeline completed successfully"
+  files:
+    - path: "output/test/score/pop_summary.csv"
+      contains:
+        - "AFR,100 (33.33%)"
+        - "EAS,100 (33.33%)"
+        - "EUR,100 (33.33%)"

workflows/pgscalc.nf

@@ -128,7 +128,7 @@ if (params.only_projection) {
     run_ancestry_bootstrap = true
     run_input_check = true
     run_make_compatible = true
-    run_match = false
+    run_match = true
     run_ancestry_assign = true
     run_apply_score = false
     run_report = false