Skip to content

Reworked dereplication of alleles to be more efficient #621

Reworked dereplication of alleles to be more efficient

Reworked dereplication of alleles to be more efficient #621

Workflow file for this run

name: Test Geneshot
on: [push, pull_request]
jobs:
full:
runs-on: ubuntu-22.04
env:
NXF_ANSI_LOG: 0
steps:
- uses: actions/checkout@v1
- name: Install Nextflow
run: |
wget -qO- get.nextflow.io | bash
sudo mv nextflow /usr/local/bin/
- name: Free disk space
run: |
sudo swapoff -a
sudo rm -f /swapfile
sudo apt clean
docker rmi $(docker image ls -aq)
df -h
- name: Run preprocess
run: |
NXF_VER=23.10.0 nextflow run main.nf --manifest data/mock.manifest.csv --output output --savereads --host_index data/hg_chr_21_bwa_index.tar.gz -w work/ -with-docker ubuntu:22.04 -c nextflow.config.sample -profile testing
- name: Validate results
run: |
tree output/
[[ -s output/qc/manifest.qc.csv ]]
[[ -s output/qc/Mock__11.R1.fastq.gz ]]
[[ -s output/qc/Mock__13__R1.noadapt.nohuman.fq.gz ]]
[[ -s output/MetaPhlAn2/metaphlan2.results.csv.gz ]]
[[ -s output/MetaPhlAn2/metaphlan2.species.h5ad ]]
[[ -s output/alleles/allele_info.csv.gz ]]
[[ -s output/alleles/alleles.faa.gz ]]
[[ -s output/alleles/alleles.faa.gz.dmnd ]]
[[ -s output/alleles/Allele_Cluster_info.csv.gz ]]
[[ -s output/alleles/centroids.C100.fastp.gz ]]
[[ -s output/alleles/centroids.C90.fastp.gz ]]
[[ -s output/alleles/centroids.C50.fastp.gz ]]
[[ -s output/alleles/centroids.C100.fastp.gz.dmnd ]]
[[ -s output/alleles/centroids.C90.fastp.gz.dmnd ]]
[[ -s output/alleles/centroids.C50.fastp.gz.dmnd ]]
[[ -s output/quantify/specimen_allele_quantity.h5ad ]]
preproccessing:
runs-on: ubuntu-22.04
env:
NXF_ANSI_LOG: 0
steps:
- uses: actions/checkout@v1
- name: Install Nextflow
run: |
wget -qO- get.nextflow.io | bash
sudo mv nextflow /usr/local/bin/
- name: Free disk space
run: |
sudo swapoff -a
sudo rm -f /swapfile
sudo apt clean
docker rmi $(docker image ls -aq)
df -h
- name: Run preprocess
run: |
NXF_VER=23.10.0 nextflow run modules/preprocess.nf --manifest data/mock.manifest.csv --output output --host_index data/hg_chr_21_bwa_index.tar.gz -w work/ -with-docker ubuntu:22.04 -c nextflow.config.sample -profile testing
- name: Validate results
run: |
tree output/
[[ -s output/qc/manifest.qc.csv ]]
[[ -s output/qc/Mock__11.R1.fastq.gz ]]
[[ -s output/qc/Mock__13__R1.noadapt.nohuman.fq.gz ]]
composition_metaphlan2:
runs-on: ubuntu-22.04
env:
NXF_ANSI_LOG: 0
steps:
- uses: actions/checkout@v1
- name: Install Nextflow
run: |
wget -qO- get.nextflow.io | bash
sudo mv nextflow /usr/local/bin/
- name: Free disk space
run: |
sudo swapoff -a
sudo rm -f /swapfile
sudo apt clean
docker rmi $(docker image ls -aq)
df -h
- name: Run geneshot
run: |
NXF_VER=23.10.0 nextflow run modules/composition.nf --manifest data/example_output/qc/manifest.qc.se.csv --output output -w work/ -with-docker ubuntu:22.04 -c nextflow.config.sample -profile testing
- name: Validate results
run: |
tree output/
[[ -s output/MetaPhlAn2/metaphlan2.results.csv.gz ]]
[[ -s output/MetaPhlAn2/metaphlan2.species.h5ad ]]
allele_catalog:
runs-on: ubuntu-22.04
env:
NXF_ANSI_LOG: 0
steps:
- uses: actions/checkout@v1
- name: Install Nextflow
run: |
wget -qO- get.nextflow.io | bash
sudo mv nextflow /usr/local/bin/
- name: Free disk space
run: |
sudo swapoff -a
sudo rm -f /swapfile
sudo apt clean
docker rmi $(docker image ls -aq)
df -h
- name: Run geneshot
run: |
NXF_VER=23.10.0 nextflow run modules/allele_catalog.nf --manifest data/example_output/qc/manifest.qc.csv --output output -w work/ -with-docker ubuntu:22.04 -c nextflow.config.sample -profile testing
- name: Validate results
run: |
tree output/
[[ -s output/alleles/allele_info.csv.gz ]]
[[ -s output/alleles/alleles.faa.gz ]]
[[ -s output/alleles/alleles.faa.gz.dmnd ]]
allele_clustering:
runs-on: ubuntu-22.04
env:
NXF_ANSI_LOG: 0
steps:
- uses: actions/checkout@v1
- name: Install Nextflow
run: |
wget -qO- get.nextflow.io | bash
sudo mv nextflow /usr/local/bin/
- name: Free disk space
run: |
sudo swapoff -a
sudo rm -f /swapfile
sudo apt clean
docker rmi $(docker image ls -aq)
df -h
- name: Run geneshot
run: |
NXF_VER=23.10.0 nextflow run modules/allele_clustering.nf --alleles data/example_output/alleles/alleles.faa.gz --allele_info data/example_output/alleles/allele_info.csv.gz --output output -w work/ -with-docker ubuntu:22.04 -c nextflow.config.sample -profile testing
- name: Validate results
run: |
tree output/
[[ -s output/alleles/Allele_Cluster_info.csv.gz ]]
[[ -s output/alleles/centroids.C100.fastp.gz ]]
[[ -s output/alleles/centroids.C90.fastp.gz ]]
[[ -s output/alleles/centroids.C50.fastp.gz ]]
[[ -s output/alleles/centroids.C100.fastp.gz.dmnd ]]
[[ -s output/alleles/centroids.C90.fastp.gz.dmnd ]]
[[ -s output/alleles/centroids.C50.fastp.gz.dmnd ]]
allele_quantification:
runs-on: ubuntu-22.04
env:
NXF_ANSI_LOG: 0
steps:
- uses: actions/checkout@v1
- name: Install Nextflow
run: |
wget -qO- get.nextflow.io | bash
sudo mv nextflow /usr/local/bin/
- name: Free disk space
run: |
sudo swapoff -a
sudo rm -f /swapfile
sudo apt clean
docker rmi $(docker image ls -aq)
df -h
- name: Run geneshot
run: |
NXF_VER=23.10.0 nextflow run modules/quantify.nf --manifest data/example_output/qc/manifest.qc.csv --allele_fasta data/example_output/alleles/alleles.faa.gz --output output -w work/ -with-docker ubuntu:22.04 -c nextflow.config.sample -profile testing
- name: Validate results
run: |
tree output/
[[ -s output/quantify/specimen_allele_quantity.h5ad ]]