Skip to content

Step1 Create Reference #53

Step1 Create Reference

Step1 Create Reference #53

Workflow file for this run

name: Step1 Create Reference
on:
workflow_dispatch:
jobs:
list_reference_genomes:
runs-on: ubuntu-latest
steps:
- name: Check Out Repository
uses: actions/checkout@main
- name: Download Datasets Tools
run: |
wget -q https://ftp.ncbi.nlm.nih.gov/pub/datasets/command-line/v2/linux-amd64/datasets
wget -q https://ftp.ncbi.nlm.nih.gov/pub/datasets/command-line/v2/linux-amd64/dataformat
chmod +x datasets dataformat
- name: Generate Master List (ids.txt)
run: |
./datasets summary genome taxon 2 --reference --as-json-lines | \
./dataformat tsv genome --fields accession,organism-name --elide-header | \
sed 's/\[//g; s/\]//g; s/["'\'']//g; s/endosymbiont of /endosymbiont_of_/g' > ids.txt
if [ -f data/include_anyway.txt ]; then
awk '{print $1 "\t" $2 " " $3 }' data/include_anyway.txt >> ids.txt
fi
grep ^"G" ids.txt > ids_clean.txt
mv ids_clean.txt ids.txt
- name: Split into 100 Chunks
run: |
split -n l/100 ids.txt -d -a 3 --additional-suffix=.txt x
echo "Created $(ls x*.txt | wc -l) chunk files."
- name: Upload Master List
uses: actions/upload-artifact@main
with:
name: master-id-list
path: ids.txt
retention-days: 1
- name: Upload Chunks
uses: actions/upload-artifact@main
with:
name: genome-chunks
path: x*.txt
retention-days: 7
update_repo_master_list:
needs: list_reference_genomes
runs-on: ubuntu-latest
steps:
- name: Check Out Repository
uses: actions/checkout@main
- name: Download Master List Artifact
uses: actions/download-artifact@main
with:
name: master-id-list
- name: Move to Data Folder
run: |
mkdir -p data
mv ids.txt data/ids.txt
- name: Create Pull Request
uses: peter-evans/create-pull-request@main
with:
commit-message: "Update master prokaryotic reference list"
title: "Update Master ID List"
branch: "update-master-ids"
add-paths: |
data/ids.txt
body: |
Updated the master reference list.
The 100 split chunks have been stored as workflow artifacts.