Skip to content

add vecscreen test set on ci, checkin coverage related scripts, updat… #78

add vecscreen test set on ci, checkin coverage related scripts, updat…

add vecscreen test set on ci, checkin coverage related scripts, updat… #78

Workflow file for this run

name: nf-core CI
# This workflow runs the pipeline with the minimal test dataset to check that it completes without any syntax errors
on:
push:
branches:
- dev
pull_request:
release:
types: [published]
env:
NXF_ANSI_LOG: false
concurrency:
group: "${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}"
cancel-in-progress: true
jobs:
test:
name: Run pipeline with test data
# Only run on push if this is the nf-core dev branch (merged PRs)
if: "${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'sanger-tol/ascc') }}"
runs-on: ubuntu-latest
strategy:
matrix:
NXF_VER:
- "23.04.0"
- "latest-everything"
steps:
- name: Check out pipeline code
uses: actions/checkout@v3
- name: Install Nextflow
uses: nf-core/setup-nextflow@v1
with:
version: "${{ matrix.NXF_VER }}"
- name: Download test data
# Download A fungal test data set that is full enough to show some real output.
run: |
curl https://tolit.cog.sanger.ac.uk/test-data/resources/ascc/asccTinyTest.tar.gz | tar xzf -
- name: Download the NCBI taxdump database
run: |
mkdir ncbi_taxdump
curl -L https://ftp.ncbi.nih.gov/pub/taxonomy/new_taxdump/new_taxdump.tar.gz | tar -C ncbi_taxdump -xzf -
- name: Download the FCS-gx database
run: |
mkdir FCS_gx
wget -c https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/FCS/database/test-only/test-only.taxa.tsv -O FCS_gx/all.taxa.tsv
wget -c https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/FCS/database/test-only/test-only.gxi -O FCS_gx/all.gxi
wget -c https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/FCS/database/test-only/test-only.gxs -O FCS_gx/all.gxs
wget -c https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/FCS/database/test-only/test-only.meta.jsonl -O FCS_gx/all.meta.jsonl
wget -c https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/FCS/database/test-only/test-only.blast_div.tsv.gz -O FCS_gx/all.blast_div.tsv.gz
- name: Download the BUSCO lineage database
run: |
mkdir busco_database
curl -L https://tolit.cog.sanger.ac.uk/test-data/resources/busco/blobtoolkit.GCA_922984935.2.2023-08-03.lineages.tar.gz | tar -C busco_database -xzf -
- name: Download the kraken2 database
run: |
mkdir kraken2
curl -L https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/sarscov2/genome/db/kraken2.tar.gz | tar -C kraken2 -xzf -
- name: Download the subset of NT database
run: |
mkdir NT_database
curl -L https://ftp.ncbi.nlm.nih.gov/blast/db/18S_fungal_sequences.tar.gz | tar -C NT_database -xzf -
- name: Download the subset of Diamond database
run: |
mkdir diamond
wget -c https://tolit.cog.sanger.ac.uk/test-data/resources/diamond/UP000000212_1234679_tax.dmnd -O diamond/UP000000212_1234679_tax.dmnd
- name: Download the vecscreen test data
run: |
mkdir vecscreen
wget -c https://tolit.cog.sanger.ac.uk/test-data/resources/vecscreen/GCA_900155405.1_PRJEB18760_genomic.fna -O vecscreen/GCA_900155405.1_PRJEB18760_genomic.fna
- name: Run pipeline with test data
# TODO nf-core: You can customise CI pipeline run tests as required
# For example: adding multiple test runs with different parameters
# Remember that you can parallelise this by using strategy.matrix
run: |
nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results