Merge pull request #32 from nextstrain/james/ref-gaps

Treat missing data as Ns not gaps
nextstrain · May 29, 2024 · f02c0c1 · f02c0c1
2 parents 297ded6 + b623aed
commit f02c0c1
Show file tree

Hide file tree

Showing 3 changed files with 414 additions and 2 deletions.
diff --git a/Snakefile.genome b/Snakefile.genome
@@ -74,6 +74,7 @@ rule align:
             --reference-sequence {input.reference} \
             --output {output.alignment} \
             --remove-reference \
+            --fill-gaps \
             --nthreads {threads}
         """
 
@@ -188,6 +189,7 @@ rule ancestral:
     input:
         tree = "results/{build_name}/genome/tree.nwk",
         alignment = "results/{build_name}/genome/aligned.fasta",
+        root_sequence = "config/h5_cattle_genome_root.gb",
     output:
         node_data = "results/{build_name}/genome/nt-muts.json"
     params:
@@ -198,7 +200,8 @@ rule ancestral:
             --tree {input.tree} \
             --alignment {input.alignment} \
             --output-node-data {output.node_data} \
-            --inference {params.inference}\
+            --inference {params.inference} \
+            --root-sequence {input.root_sequence} \
             --keep-ambiguous
         """
 
@@ -207,7 +210,7 @@ rule translate:
     input:
         tree = "results/{build_name}/genome/tree.nwk",
         node_data = "results/{build_name}/genome/nt-muts.json",
-        reference = "results/{build_name}/genome/reference.gb",
+        reference = "config/h5_cattle_genome_root.gb",
     output:
         node_data = "results/{build_name}/genome/aa-muts.json"
     shell:
@@ -219,6 +222,7 @@ rule translate:
             --output {output.node_data}
         """
 
+
 rule traits:
     message: "Inferring ancestral traits for {params.columns!s}"
     input:

diff --git a/config/auspice_config_h5n1-cattle-outbreak.json b/config/auspice_config_h5n1-cattle-outbreak.json
@@ -14,6 +14,31 @@
       "name": "GISAID"
     }
   ],
+  "extensions": {
+    "nextclade": {
+      "pathogen": {
+        "schemaVersion":"3.0.0",
+        "defaultCds": "HA",
+        "cdsOrderPreference":[
+          "PB2",
+          "PB1",
+          "PA",
+          "HA",
+          "NP",
+          "NA",
+          "M1",
+          "M2",
+          "NS1",
+          "NS2"
+      ],
+      "attributes": {
+        "name": "H5N1 dairy cattle outbreak",
+        "reference name": "concatenated ancestral sequences",
+        "reference accession": "none"
+        }
+      }
+    }
+  },
   "colorings": [
     {
       "key": "gt",