Create datasets.yml

.github/workflows/datasets.yml

@@ -0,0 +1,59 @@
+name: Test datasets
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: '30 4 * * TUE'
+
+jobs:
+  check:
+    runs-on: ubuntu-20.04
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: download datasets
+        run: |
+          DATASETS_VER=$(grep container modules/datasets.nf | sort | uniq | head -n 1 | awk '{print $2}' | sed 's/'\''//g' | cut -f 2 -d ":")
+        
+          RUN wget https://github.com/ncbi/datasets/releases/download/v${DATASETS_VER}/linux-amd64.cli.package.zip && \
+            unzip linux-amd64.cli.package.zip && \
+            rm linux-amd64.cli.package.zip && \
+            chmod +x dataformat datasets
+          
+      - name: get accessions
+        run: |
+          taxons=("Acinetobacter baumannii",
+            "Burkholderia cenocepacia",
+            "Campylobacter jejuni",
+            "Citrobacter sp",
+            "Elizabethkingia meningoseptica",
+            "Escherichia coli",
+            "Klebsiella oxytoca",
+            "Legionella pneumophila",
+            "Pseudomonas sp",
+            "Raoultella ornithinolytica",
+            "Salmonella enterica")
+          
+          for taxon in ${taxons[@]} 
+          do
+            echo "the taxon is now $taxon"
+            organism=$(echo $taxon | sed 's/ /_/g')
+
+            echo "Getting the representative genome"
+            ./datasets summary genome taxon "$taxon" --reference --limit 5 --as-json-lines | \
+              dataformat tsv genome --fields accession,assminfo-refseq-category,assminfo-level,organism-name,assmstats-total-ungapped-len | \
+              grep -v Homo | \
+              tr '\\t' ',' \
+              | tee ${organism}_genomes.csv
+            
+            echo "Getting additional genomes"
+            ./datasets summary genome taxon "$taxon" --limit 5 --as-json-lines | \
+              dataformat tsv genome --fields accession,assminfo-refseq-category,assminfo-level,organism-name,assmstats-total-ungapped-len | \
+              grep -v Homo | \
+              grep -v "Assembly Accession" | \
+              tr '\\t' ',' \
+              | tee -a ${organism}_genomes.csv
+          done
+          
+          head *genomes.csv