Preprocessing of specified datasets #31
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 | |
| do_descriptors: | |
| description: 'Whether to compute descriptors' | |
| type: boolean | |
| default: true | |
| do_fingerprints: | |
| description: 'Whether to compute fingerprints' | |
| type: boolean | |
| default: true | |
| do_metadata: | |
| description: 'Whether to standardize metadata' | |
| type: boolean | |
| default: true | |
| do_validation: | |
| description: 'Whether to run validation procedures' | |
| 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: windows-2019 | |
| 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 | |
| shell: bash {0} | |
| run: | | |
| for f in ${{ inputs.datasets }}; do | |
| ls -lh raw_data/$f || true | |
| ls -lh processed_data/$f || true | |
| done | |
| continue-on-error: true | |
| - name: Pyton dependencies | |
| run: pip install -r scripts/Python/requirements.txt | |
| # needed for every task | |
| - name: Setup java | |
| uses: actions/setup-java@v3 | |
| with: | |
| distribution: 'temurin' | |
| java-version: '17' | |
| # needed for every task | |
| - name: Set RENV_PATHS_ROOT | |
| shell: bash | |
| run: | | |
| echo "RENV_PATHS_ROOT=${{ runner.temp }}/renv" >> $GITHUB_ENV | |
| # needed for every task | |
| - name: Setup R | |
| uses: r-lib/actions/setup-r@v2 | |
| with: | |
| use-public-rspm: true | |
| r-version: 4.2.2 | |
| # needed for every task | |
| - name: Restore Renv package cache | |
| uses: actions/cache@v3 | |
| with: | |
| path: ${{ env.RENV_PATHS_ROOT }} | |
| key: ${{ runner.os }}-renv-${{ hashFiles('**/renv.lock') }} | |
| restore-keys: | | |
| ${{ runner.os }}-renv- | |
| # needed for every task | |
| - name: Activate renv | |
| shell: Rscript {0} | |
| run: | | |
| options(renv.config.mran.enabled = FALSE) | |
| renv::restore() | |
| # needed for every task | |
| - name: Standardize compounds | |
| run: Rscript scripts/R_ci/compounds_standardize.R ${{ inputs.datasets }} | |
| if: ${{ inputs.do_standardize }} | |
| - name: Compounds classyfire classes | |
| run: Rscript scripts/R_ci/compounds_classyfire.R ${{ inputs.datasets }} | |
| if: ${{ inputs.do_classyfire }} | |
| - name: Compounds descriptors | |
| run: Rscript scripts/R_ci/compounds_descriptors.R ${{ inputs.datasets }} | |
| if: ${{ inputs.do_descriptors }} | |
| - name: Compounds fingerprints | |
| run: Rscript scripts/R_ci/compounds_fingerprints.R ${{ inputs.datasets }} | |
| if: ${{ inputs.do_fingerprints }} | |
| - name: Metadata standardization | |
| run: Rscript scripts/R_ci/metadata_standardize.R ${{ inputs.datasets }} | |
| if: ${{ inputs.do_metadata }} | |
| - name: Generate dataset reports | |
| run: Rscript scripts/R_ci/compounds_overview.R ${{ inputs.datasets }} | |
| - name: Verify that required files are present | |
| run: Rscript scripts/R_ci/files_complete.R ${{ inputs.datasets }} | |
| - name: Update overview table of all datasets | |
| run: python3 scripts/Python/datasets_overview.py | |
| continue-on-error: true | |
| - name: QSPR-based validation | |
| run: python3 scripts/Python/validation_qspr.py ${{ inputs.datasets }} | |
| continue-on-error: true | |
| if: ${{ inputs.do_validation }} | |
| - name: Retention order-based validation for datasets with nominally identical setups | |
| run: python3 scripts/Python/validation_order.py --mode same_condition ${{ inputs.datasets }} | |
| continue-on-error: true | |
| if: ${{ inputs.do_validation }} | |
| - name: Retention order-based validation for datasets of systematic measurements | |
| run: python3 scripts/Python/validation_order.py --mode systematic ${{ inputs.datasets }} | |
| continue-on-error: true | |
| if: ${{ inputs.do_validation }} | |
| - 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 |