Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Preprocessing of specified datasets | |
| on: | |
| workflow_dispatch: | |
| inputs: | |
| datasets: | |
| description: 'Datasets to preprocess, separated by space. Example: 0001 0002 0044' | |
| required: True | |
| type: string | |
| do_standardize: | |
| description: 'Whether to standardize compounds' | |
| type: boolean | |
| default: true | |
| do_classyfire: | |
| description: 'Whether to compute ClassyFire classes' | |
| type: boolean | |
| default: true | |
| jobs: | |
| preprocess: | |
| name: Preprocess raw data | |
| # NOTE: on windows as computing of descriptors has a bug on linux right now | |
| runs-on: ubuntu-latest | |
| env: | |
| GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }} # needed for pulling R packages from github | |
| steps: | |
| - name: Checkout repository | |
| uses: actions/checkout@v3 | |
| with: | |
| lfs: true | |
| - name: List all files for selected datasets | |
| run: | | |
| for f in ${{ inputs.datasets }}; do | |
| ls -lh raw_data/$f || true | |
| ls -lh processed_data/$f || true | |
| done | |
| continue-on-error: true | |
| - name: Standardize compounds | |
| using: 'docker' | |
| image: 'Dockerfile' | |
| args: | |
| - Rscript scripts/R_ci/compounds_standardize.R | |
| - ${{ inputs.datasets }} | |
| if: ${{ inputs.do_standardize }} | |
| - name: Compounds classyfire classes | |
| using: 'docker' | |
| image: 'Dockerfile' | |
| args: | |
| - Rscript scripts/R_ci/compounds_classyfire.R | |
| - ${{ inputs.datasets }} | |
| if: ${{ inputs.do_classyfire }} | |
| - name: Commit preprocessing | |
| run: | | |
| git config --global user.email '[email protected]' | |
| git config --global user.name 'Github Actions' | |
| # Use LFS storage of main repository: no push access to fork LFS storage | |
| # TODO: change once repository is moved | |
| git add processed_data raw_data | |
| git commit -m "Preprocessing ${{ inputs.datasets }}" -m "Tasks: | |
| - standardize compounds: ${{ inputs.do_standardize }} | |
| - compute classyfire classes: ${{ inputs.do_classyfire }} | |
| - compute descriptors: ${{ inputs.do_descriptors }} | |
| - compute fingerprints: ${{ inputs.do_fingerprints }} | |
| - standardize metadata: ${{ inputs.do_metadata }}" | |
| git lfs push origin HEAD # first push LFS, otherwise failure because of lfs.url | |
| git push origin HEAD | |
| - name: Debug with tmate on failure | |
| if: ${{ failure() }} | |
| uses: mxschmitt/action-tmate@v3 |