test_relatedness.yml

name: Test SARS-CoV-2 msa workflow

on: [pull_request, workflow_dispatch]

run-name: Test MSA

jobs:

  msa:
    runs-on: ubuntu-20.04
    steps:
      - name: Checkout
        uses: actions/checkout@master
        with:
          lfs: true

      - name: Checkout LFS objects
        run: git lfs checkout
          
      - name: Install Nextflow
        run: |
          wget -qO- get.nextflow.io | bash
          sudo mv nextflow /usr/local/bin/
      
      - name: Install Datasets
        run: |
          wget https://ftp.ncbi.nlm.nih.gov/pub/datasets/command-line/LATEST/linux-amd64/datasets
          chmod +x datasets
          sudo mv datasets /usr/local/bin/

      - name: Download fasta files
        run: |
          mkdir fastas
          cd fastas

          # have to download separately because I don't want them in the same file
          for accession in OQ255990.1 OQ255991.1 OQ255992.1 OQ255993.1 OQ255994.1
          do
            datasets download virus genome accession $accession
            unzip ncbi_dataset.zip
            cp ncbi_dataset/data/genomic.fna $accession.fasta
            rm -rf ncbi_dataset*
            rm -rf README.md
          done

          cd ../

      - name: Run Cecret
        run: |
          nextflow run . -profile docker -c .github/workflows/github_actions.config --maxcpus 2 --medcpus 2 --relatedness true --outdir cecret1

          nextflow run . -profile docker -resume -c .github/workflows/github_actions.config --maxcpus 2 --medcpus 2 --relatedness true --outdir cecret2 --msa nextclade

          ls cecret*
            
          head cecret*/cecret_results.txt

          head cecret*/iqtree2/iqtree2.treefile

      - name: Clean
        run: rm -rf work .nextflow*