Skip to content

Ncbench

Ncbench #2

Workflow file for this run

name: NCBench Zenodo Upload
# This workflow can be triggered manually with the GitHub actions workflow dispatch button.
on:
# upload can only be triggered manually for now
workflow_dispatch:
inputs:
germline_wes:
description: "Trigger NCBench upload"
type: boolean
default: true
pull_request:
jobs:
ncbench-upload:
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
include:
- profile: germline_wes
enabled: ${{ ( github.repository == 'nf-core/sarek' ) && ( github.event_name != 'workflow_dispatch' || inputs.germline_wes ) }}
env:
pipeline_version: 3.2.3
steps:
- name: Download files from AWS
uses: keithweaver/[email protected]
if: ${{ matrix.enabled }}
with:
revision: ${{ github.sha }}
source: s3://${{ secrets.AWS_S3_BUCKET }}/sarek/results-test-59026dc07633edb83aab3bfb2f65f79db38437a1/test_full/variant_calling/strelka/
command: sync
destination: ./variant_calling
flags: --no-sign-request --include ".vcf.gz" --exclude "g.vcf.gz"
- name: Download metadata file for Zenodo
uses: actions/checkout@v4
with:
sparse-checkout: |
assets/zenodo_ncbench.json
sparse-checkout-cone-mode: false
- name: Create new Zenodo entry
uses: popperized/zenodo/create@master
env:
ZENODO_METADATA_PATH: assets/zenodo_ncbench.json
with:
secrets: ${{ secrets.ZENODO_API_TOKEN }}
- name: Upload file to Zenodo
uses: popperized/zenodo/upload@master
env:
ZENODO_DEPOSIT_ID: #TODO get the dposit ID from the previous step
ZENODO_UPLOAD_PATH: ./variant_calling_v$pipeline_version
ZENODO_USE_SANDBOX: true
with:
secrets: ${{ secrets.ZENODO_API_TOKEN }}
# - name: Install jq
# uses: sergeysova/jq-action@v2
# - name: NCBench set config
# uses: actions/checkout@v4
# with:
# repository: FriederikeHanssen/ncbench
# path: ncbench
# ref: main
# token: ${{ github.token }}
# sparse-checkout: |
# config/config.yaml
# sparse-checkout-cone-mode: false
# run: |
# jq --help >> config.yaml
# with:
# repository: github.com/FriederikeHanssen/ncbench
# path: ncbench
# ref: main
# TODO: how to retrieve the pipeline and tool versions
# TODO: how to get the zenodo id
#run: |
# jq --version
# git checkout -b ${{ github.sha }}
# echo " nf-core-sarek-$pipeline_version-deepvariants-agilent-200M:" >> config.yaml
# echo " labels:" >> config.yaml
# echo " site: nf-core" >> config.yaml
# echo " pipeline: nf-core/sarek v$" >> config.yaml
# echo " trimming: Fastp v0.23." >> config.yaml
# echo " read-mapping: bwa mem v0.7." >> config.yaml
# echo " base-quality-recalibration: gatk4 v4.4.0." >> config.yaml
# echo " realignment: " >> config.yaml
# echo " variant-detection: deepvariant v1.5." >> config.yaml
# echo " genotyping: " >> config.yaml
# echo " reads: " >> config.yaml
# echo " subcategory: NA12878-agilent" >> config.yaml
# echo " zenodo:" >> config.yaml
# echo " deposition: ?" >> config.yaml
# echo " filename: nf-core-sarek-$pipeline_version/deepvariant/NA12878_200M/NA12878_200M.deepvariant.vcf." >> config.yaml
# echo " benchmark: giab-NA12878-agilent-" >> config.yaml
# echo " rename-contigs: resources/rename-contigs/ucsc-to-ensembl.txt" >> config.yaml
# git config user.name github-actions
# git config user.email [email protected]
# git add .
# git commit -m "Benchmarking ${{ github.sha }}"
# git push origin ${{ github.sha }}
# TB-sarek311-freebayes-agilent-200M:
# labels:
# site: TB QBiC
# pipeline: nf-core/sarek v3.1.1
# trimming: Fastp v0.23.2
# read-mapping: bwa mem v0.7.17
# base-quality-recalibration: gatk4 v4.3.0.0
# realignment: none
# variant-detection: freebayes v1.3.6
# genotyping: none
# reads: 200M
# subcategory: NA12878-agilent
# zenodo:
# deposition: 7376244
# filename: WES_agilent_high_cov_sarek311_NA12878_freebayes.vcf.gz
# benchmark: giab-NA12878-agilent-200M
# rename-contigs: resources/rename-contigs/ucsc-to-ensemb
# TB-sarek311-haplotypecaller-agilent-200M:
# labels:
# site: TB QBiC
# pipeline: nf-core/sarek v3.1.1
# trimming: Fastp v0.23.2
# read-mapping: bwa mem v0.7.17
# base-quality-recalibration: gatk4 v4.3.0.0
# realignment: none
# variant-detection: gatk-haplotypecaller v4.3.0.0
# genotyping: none
# reads: 200M
# subcategory: NA12878-agilent
# zenodo:
# deposition: 7376244
# filename: WES_agilent_high_cov_sarek311_NA12878_haplotypecaller.vcf.gz
# benchmark: giab-NA12878-agilent-200M
# rename-contigs: resources/rename-contigs/ucsc-to-ensemb
# TB-sarek311-strelka-agilent-200M:
# labels:
# site: TB QBiC
# pipeline: nf-core/sarek v3.1.1
# trimming: Fastp v0.23.2
# read-mapping: bwa mem v0.7.17
# base-quality-recalibration: gatk4 v4.3.0.0
# realignment: none
# variant-detection: strelka2 v2.9.10
# genotyping: none
# reads: 200M
# subcategory: NA12878-agilent
# zenodo:
# deposition: 7376244
# filename: WES_agilent_high_cov_sarek311_NA12878_strelka.vcf.gz
# benchmark: giab-NA12878-agilent-200M
# rename-contigs: resources/rename-contigs/ucsc-to-ensemb
# TB-sarek311-deepvariants-agilent-75M:
# labels:
# site: TB QBiC
# pipeline: nf-core/sarek v3.1.1
# trimming: Fastp v0.23.2
# read-mapping: bwa mem v0.7.17
# base-quality-recalibration: gatk4 v4.3.0.0
# realignment: none
# variant-detection: DeepVariant v1.3.6
# genotyping: none
# reads: 75M
# subcategory: NA12878-agilent
# zenodo:
# deposition: 7376244
# filename: WES_agilent_low_cov_sarek311_NA12878_freebayes.vcf.gz
# benchmark: giab-NA12878-agilent-75M
# rename-contigs: resources/rename-contigs/ucsc-to-ensemb
# TB-sarek311-freebayes-agilent-75M:
# labels:
# site: TB QBiC
# pipeline: nf-core/sarek v3.1.1
# trimming: Fastp v0.23.2
# read-mapping: bwa mem v0.7.17
# base-quality-recalibration: gatk4 v4.3.0.0
# realignment: none
# variant-detection: freebayes v1.3.6
# genotyping: none
# reads: 75M
# subcategory: NA12878-agilent
# zenodo:
# deposition: 7376244
# filename: WES_agilent_low_cov_sarek311_NA12878_freebayes.vcf.gz
# benchmark: giab-NA12878-agilent-75M
# rename-contigs: resources/rename-contigs/ucsc-to-ensemb
# nfcore-sarek-${{ github.sha }}-haplotypecaller-agilent-75M:
# labels:
# site: nf-core
# pipeline: nf-core/sarek v
# trimming: Fastp v0.23.2
# read-mapping: bwa mem v0.7.17
# base-quality-recalibration: gatk4 v4.3.0.0
# realignment: none
# variant-detection: gatk-haplotypecaller v4.3.0.0
# genotyping: none
# reads: 75M
# subcategory: NA12878-agilent
# zenodo:
# deposition:
# filename: WES_agilent_low_cov_sarek311_NA12878_haplotypecaller.vcf.gz
# benchmark: giab-NA12878-agilent-75M
# rename-contigs: resources/rename-contigs/ucsc-to-ensemb
# TB-sarek311-strelka-agilent-75M:
# labels:
# site: TB QBiC
# pipeline: nf-core/sarek v3.1.1
# trimming: Fastp v0.23.2
# read-mapping: bwa mem v0.7.17
# base-quality-recalibration: gatk4 v4.3.0.0
# realignment: none
# variant-detection: strelka2 v2.9.10
# genotyping: none
# reads: 75M
# subcategory: NA12878-agilent
# zenodo:
# deposition: 7376244
# filename: WES_agilent_low_cov_sarek311_NA12878_strelka.vcf.gz
# benchmark: giab-NA12878-agilent-75M
# rename-contigs: resources/rename-contigs/ucsc-to-ensemb