Merge pull request #54 from nextstrain/ingest/streamline-sort

ingest: improve sorting of RSV A and RSV B with nextclade 3.2
nextstrain · Feb 22, 2024 · 67e4d34 · 67e4d34
2 parents 28e7f8e + 91c6651
commit 67e4d34
Showing 1 changed file with 4 additions and 3 deletions.
diff --git a/ingest/workflow/snakemake_rules/sort.smk b/ingest/workflow/snakemake_rules/sort.smk
@@ -18,9 +18,10 @@ rule sort:
         "data/b/sequences.fasta"
     shell:
         '''
-        nextclade3 sort {input.sequences} --output-dir tmp
-        seqkit rmdup tmp/nextstrain/rsv/b/sequences.fasta > data/b/sequences.fasta
-        seqkit rmdup tmp/nextstrain/rsv/a/sequences.fasta > data/a/sequences.fasta
+        seqkit rmdup {input.sequences} | \
+        nextclade3 sort - --output-dir tmp
+        mv tmp/nextstrain/rsv/b/sequences.fasta > data/b/sequences.fasta
+        mv tmp/nextstrain/rsv/a/sequences.fasta > data/a/sequences.fasta
         rm -r tmp
         '''