Prepare phylogenetic workflow for Nextclade workflow #57

phylogenetic/config/config_dengue.yaml

@@ -9,6 +9,7 @@ display_strain_field: "strain"
 
 filter:
   exclude: "config/exclude.txt"
+  include: "config/include_{serotype}.txt"
   group_by: "year region"
   min_length:
     genome: 5000

phylogenetic/config/include_all.txt

@@ -0,0 +1 @@
+# Format: <GenBank accession> [# <documentation on reason for inclusion>]

phylogenetic/config/include_denv1.txt

@@ -0,0 +1 @@
+# Format: <GenBank accession> [# <documentation on reason for inclusion>]

phylogenetic/config/include_denv2.txt

@@ -0,0 +1 @@
+# Format: <GenBank accession> [# <documentation on reason for inclusion>]

phylogenetic/config/include_denv3.txt

@@ -0,0 +1 @@
+# Format: <GenBank accession> [# <documentation on reason for inclusion>]

phylogenetic/config/include_denv4.txt

@@ -0,0 +1 @@
+# Format: <GenBank accession> [# <documentation on reason for inclusion>]

phylogenetic/rules/annotate_phylogeny.smk

@@ -25,7 +25,8 @@ rule ancestral:
     """Reconstructing ancestral sequences and mutations"""
     input:
         tree = "results/{gene}/tree_{serotype}.nwk",
-        alignment = "results/{gene}/aligned_{serotype}.fasta"
+        alignment = "results/{gene}/aligned_{serotype}.fasta",
+        root_sequence = lambda wildcard: "config/reference_{serotype}_genome.gb" if wildcard.gene in ['genome'] else "results/config/reference_{serotype}_{gene}.gb",
     output:
         node_data = "results/{gene}/nt-muts_{serotype}.json"
     params:
@@ -36,6 +37,7 @@ rule ancestral:
             --tree {input.tree} \
             --alignment {input.alignment} \
             --output-node-data {output.node_data} \
+            --root-sequence {input.root_sequence} \
             --inference {params.inference}
         """
 

phylogenetic/rules/prepare_sequences.smk

@@ -55,6 +55,7 @@ rule filter:
         sequences = lambda wildcard: "data/sequences_{serotype}.fasta" if wildcard.gene in ['genome'] else "results/{gene}/sequences_{serotype}.fasta",
         metadata = "data/metadata_{serotype}.tsv",
         exclude = config["filter"]["exclude"],
+        include = config["filter"]["include"],
     output:
         sequences = "results/{gene}/filtered_{serotype}.fasta"
     params:
@@ -69,6 +70,7 @@ rule filter:
             --metadata {input.metadata} \
             --metadata-id-columns {params.strain_id} \
             --exclude {input.exclude} \
+            --include {input.include} \
             --output {output.sequences} \
             --group-by {params.group_by} \
             --sequences-per-group {params.sequences_per_group} \