Merge pull request #49 from broadinstitute/dp-fasta-handling

refine_assembly: tolerate whitespace in fasta headers
broadinstitute · Sep 20, 2024 · 42f3182 · 42f3182
2 parents a5a6b7a + f0685b4
commit 42f3182
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 3 deletions.
diff --git a/Dockerfile b/Dockerfile
@@ -1,4 +1,4 @@
-FROM quay.io/broadinstitute/viral-core:2.3.5
+FROM quay.io/broadinstitute/viral-core:2.3.6
 
 LABEL maintainer "[email protected]"
 

diff --git a/assembly.py b/assembly.py
@@ -915,9 +915,10 @@ def refine_assembly(
     novoalign = tools.novoalign.NovoalignTool(license_path=novoalign_license_path)
     gatk = tools.gatk.GATKTool(path=gatk_path)
 
-    # Create deambiguated genome for GATK
+    # Sanitize fasta header & create deambiguated genome for GATK
     deambigFasta = util.file.mkstempfname('.deambig.fasta')
-    deambig_fasta(inFasta, deambigFasta)
+    with util.file.fastas_with_sanitized_ids(inFasta, use_tmp=True) as sanitized_fastas:
+        deambig_fasta(sanitized_fastas[0], deambigFasta)
     picard_index.execute(deambigFasta, overwrite=True)
     samtools.faidx(deambigFasta, overwrite=True)