Skip to content

added check for duplicated rows in submission file #555

added check for duplicated rows in submission file

added check for duplicated rows in submission file #555

Workflow file for this run

name: Run tutorials (ingestion)
on:
push:
branches:
- main
pull_request:
branches:
- main
env:
debug: 'true'
jobs:
ingestion:
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
os: ["ubuntu-latest"] # , "macos-latest", "windows-latest"
python-version: ["3.10"]
steps:
- uses: actions/checkout@v4
- name: File tree
if: env.debug == 'true'
run: tree
- uses: conda-incubator/setup-miniconda@v3
with:
miniforge-version: latest
auto-activate-base: true
auto-update-conda: true
channels: conda-forge
channel-priority: strict
activate-environment: pipeline_env
environment-file: pipeline_env.yaml
- name: Install Panpipes
shell: bash -el {0}
run: |
pip install -e .
conda list
- name: Conda info
if: env.debug == 'true'
shell: bash -el {0}
run: conda info
- name: Conda list
if: env.debug == 'true'
shell: pwsh
run: conda list
# Note: all three files are renamed during the download to trim the "subsample_" prefix
- name: Preparing the data
run: |
mkdir -p teaseq/ingest/data.dir
cd teaseq/ingest/data.dir
curl -L -o adt.h5ad https://figshare.com/ndownloader/files/41671551
curl -L -o atac.h5ad https://figshare.com/ndownloader/files/41671554
curl -L -o rna.h5ad https://figshare.com/ndownloader/files/41671557
# Note: we run the following to test that the commands works
# However, the following task will replacing the file anyway
- name: Preparing the configuration file
shell: bash -el {0}
run: |
cd teaseq/ingest
panpipes ingest config
- name: Edit the submission file
run: |
cd teaseq/ingest
curl -o pipeline.yml https://panpipes-tutorials.readthedocs.io/en/latest/_downloads/9a4fcbc3c0a4fdc8e6578d086a88730f/pipeline.yml
- name: Preparing the submission file
run: |
cd teaseq/ingest
curl -o sample_file_qc.txt https://panpipes-tutorials.readthedocs.io/en/latest/_downloads/40ed291bf9a7ff73c4f396ec63cff2f7/sample_file_qc.txt
- name: Preparing the QC gene lists
run: |
cd teaseq/ingest
curl -o qc_genelist_1.0.csv https://panpipes-tutorials.readthedocs.io/en/latest/_downloads/fd38f25644105ea357a26e78a59139bb/qc_genelist_1.0.csv
- name: File tree
if: env.debug == 'true'
run: tree teaseq
- name: Review pipeline tasks
shell: bash -el {0}
run: |
cd teaseq/ingest
panpipes ingest show full --local
- name: Run pipeline tasks
shell: bash -el {0}
run: |
cd teaseq/ingest
panpipes ingest make full --local
- name: File tree
if: env.debug == 'true'
run: tree teaseq
- uses: actions/upload-artifact@v4
with:
name: teaseq_unfilt.h5mu
path: teaseq/ingest/teaseq_unfilt.h5mu
retention-days: 1