From 8b7731c276cb8d51affc15c252625235bb29ec18 Mon Sep 17 00:00:00 2001
From: Chris Tomkins-Tinch <tomkinsc@broadinstitute.org>
Date: Tue, 5 Nov 2024 15:12:37 -0500
Subject: [PATCH] add deduplication of sequences by ID in augur_from_assemblies
 (#564)

add deduplication of sequences by ID in augur_from_assemblies, after filtering by length, prior to MSA via MAFFT.
---
 pipes/WDL/workflows/augur_from_assemblies.wdl | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/pipes/WDL/workflows/augur_from_assemblies.wdl b/pipes/WDL/workflows/augur_from_assemblies.wdl
index 08c3ab87e..0eb30b244 100644
--- a/pipes/WDL/workflows/augur_from_assemblies.wdl
+++ b/pipes/WDL/workflows/augur_from_assemblies.wdl
@@ -67,9 +67,13 @@ workflow augur_from_assemblies {
             sequences_fasta = zcat.combined,
             min_non_N       = min_unambig_genome
     }
+    call nextstrain.nextstrain_deduplicate_sequences as dedup_seqs {
+        input:
+            sequences_fasta = filter_sequences_by_length.filtered_fasta
+    }
     call nextstrain.mafft_one_chr as mafft {
         input:
-            sequences = filter_sequences_by_length.filtered_fasta,
+            sequences = dedup_seqs.sequences_deduplicated_fasta,
             ref_fasta = ref_fasta,
             basename  = "all_samples_aligned.fasta"
     }