From 567279a5047d6f3ba17d3a0475d78d9ed8af90fe Mon Sep 17 00:00:00 2001
From: Victor Lin <13424970+victorlin@users.noreply.github.com>
Date: Thu, 26 Sep 2024 16:05:10 -0700
Subject: [PATCH] Use only the 21L sequence from references

data/references_sequences.fasta contains both `Wuhan/Hu-1/2019` and
`21L`. The aligned input is expected to contain `Wuhan/Hu-1/2019` so the
merging with references_sequences.fasta is really only for 21L.
---
 nextstrain_profiles/nextstrain-gisaid-21L/prefilter.smk | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/nextstrain_profiles/nextstrain-gisaid-21L/prefilter.smk b/nextstrain_profiles/nextstrain-gisaid-21L/prefilter.smk
index 23a38ee8d..01be8ad67 100644
--- a/nextstrain_profiles/nextstrain-gisaid-21L/prefilter.smk
+++ b/nextstrain_profiles/nextstrain-gisaid-21L/prefilter.smk
@@ -92,7 +92,8 @@ rule gisaid_21L_aligned:
         exec 2> {log:q}
 
         < {input.references:q} \
-          zstd \
+          seqkit grep --by-name --pattern 21L \
+        | zstd \
         > {output.aligned}
 
         < {input.aligned:q} \