Include vaccine strains in trees

Explicitly add vaccine strains to genome tree and N450 tree, following up on #23 These strains currently end up in the trees due to our subsampling parameters and lack of other sequences from 1954, but this commit explicitly adds them.
nextstrain · Apr 19, 2024 · a81915e · a81915e
1 parent 6dc1603
commit a81915e
Show file tree

Hide file tree

Showing 5 changed files with 24 additions and 2 deletions.
diff --git a/phylogenetic/defaults/config.yaml b/phylogenetic/defaults/config.yaml
@@ -1,6 +1,8 @@
 strain_id_field: "accession"
 files:
     exclude: "defaults/dropped_strains.txt"
+    include_genome: "defaults/include_strains_genome.txt"
+    include_N450: "defaults/include_strains_N450.txt"
     reference: "defaults/measles_reference.gb"
     reference_N450: "defaults/measles_reference_N450.gb"
     reference_N450_fasta: "defaults/measles_reference_N450.fasta"

diff --git a/phylogenetic/defaults/include_strains_N450.txt b/phylogenetic/defaults/include_strains_N450.txt
@@ -0,0 +1,9 @@
+# Vaccine strain information from Parks et al. Comparison of predicted amino acid
+# sequences of measles virus strains in the Edmonston vaccine lineage
+# https://doi.org/10.1128/jvi.75.2.910-920.2001
+AF266288
+AF266287
+AF266290
+AF266289
+AF266291
+AF266286
diff --git a/phylogenetic/defaults/include_strains_genome.txt b/phylogenetic/defaults/include_strains_genome.txt
@@ -0,0 +1,9 @@
+# Vaccine strain information from Parks et al. Comparison of predicted amino acid
+# sequences of measles virus strains in the Edmonston vaccine lineage
+# https://doi.org/10.1128/jvi.75.2.910-920.2001
+AF266288
+AF266287
+AF266290
+AF266289
+AF266291
+AF266286
diff --git a/phylogenetic/rules/prepare_sequences.smk b/phylogenetic/rules/prepare_sequences.smk
@@ -42,7 +42,8 @@ rule filter:
     input:
         sequences = "data/sequences.fasta",
         metadata = "data/metadata.tsv",
-        exclude = config["files"]["exclude"]
+        exclude = config["files"]["exclude"],
+        include = config["files"]["include_genome"]
     output:
         sequences = "results/genome/filtered.fasta"
     params:

diff --git a/phylogenetic/rules/prepare_sequences_N450.smk b/phylogenetic/rules/prepare_sequences_N450.smk
@@ -34,7 +34,8 @@ rule filter_N450:
     input:
         sequences = "results/N450/sequences.fasta",
         metadata = "data/metadata.tsv",
-        exclude = config["files"]["exclude"]
+        exclude = config["files"]["exclude"],
+        include = config["files"]["include_N450"]
     output:
         sequences = "results/N450/aligned.fasta"
     params: