From 3780fc08503588019c1601e37ea9fe27ab2d3b28 Mon Sep 17 00:00:00 2001
From: John Huddleston <huddlej@gmail.com>
Date: Tue, 15 Oct 2024 10:29:33 -0700
Subject: [PATCH 1/2] Run Nextclade on all 8 genes for H1 and H3

Adds remaining gene segments to the default list of segments to process
with Nextclade. Since B/Vic only has HA and NA Nextclades datasets right
now, this commit modifies the logic of the workflow to look for a
build-specific list of segments and defines that list for the Vic build.
---
 profiles/nextclade.yaml              | 9 +++++++++
 profiles/nextclade/run-nextclade.smk | 2 +-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/profiles/nextclade.yaml b/profiles/nextclade.yaml
index 44346bc3..0396cb18 100644
--- a/profiles/nextclade.yaml
+++ b/profiles/nextclade.yaml
@@ -7,6 +7,12 @@ s3_dst: "s3://nextstrain-data-private/files/workflows/seasonal-flu"
 segments:
   - ha
   - na
+  - pb2
+  - pb1
+  - pa
+  - np
+  - mp
+  - ns
 
 builds:
   h1n1pdm:
@@ -15,3 +21,6 @@ builds:
     lineage: h3n2
   vic:
     lineage: vic
+    segments:
+      - ha
+      - na
diff --git a/profiles/nextclade/run-nextclade.smk b/profiles/nextclade/run-nextclade.smk
index d4a8c41e..e1a4445e 100644
--- a/profiles/nextclade/run-nextclade.smk
+++ b/profiles/nextclade/run-nextclade.smk
@@ -4,7 +4,7 @@ rule upload_all_nextclade_files:
             "data/upload/s3/{filetype}_{lineage}_{segment}.done".format(filetype=filetype, lineage=build["lineage"], segment=segment)
             for filetype in ("alignment", "nextclade")
             for build in config["builds"].values()
-            for segment in config["segments"]
+            for segment in build.get("segments", config["segments"])
         ]
 
 rule get_nextclade_dataset_for_lineage_and_segment:

From 582236f7b752065430c972286f42b1e791897da1 Mon Sep 17 00:00:00 2001
From: John Huddleston <huddlej@gmail.com>
Date: Tue, 15 Oct 2024 10:44:25 -0700
Subject: [PATCH 2/2] Use full Nextclade names for all gene segments

Not all gene segments define shorter aliases (e.g., "flu_h3n2_ha"), so
we need to use the full names (e.g., "nextstrain/flu/h3n2/ha") to
download each dataset.
---
 profiles/nextclade/run-nextclade.smk | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/profiles/nextclade/run-nextclade.smk b/profiles/nextclade/run-nextclade.smk
index e1a4445e..4adfdebb 100644
--- a/profiles/nextclade/run-nextclade.smk
+++ b/profiles/nextclade/run-nextclade.smk
@@ -13,7 +13,7 @@ rule get_nextclade_dataset_for_lineage_and_segment:
     shell:
         """
         nextclade3 dataset get \
-            -n flu_{wildcards.lineage}_{wildcards.segment} \
+            -n 'nextstrain/flu/{wildcards.lineage}/{wildcards.segment}' \
             --output-dir {output.nextclade_dir}
         """