Move rules for constructing phylogeny to its own smk file

Part of work to update this repo to match the pathogen-repo-template.

phylogenetic/Snakefile

@@ -18,55 +18,7 @@ files = rules.files.params
 
 include: "workflow/snakemake_rules/usvi.smk"
 include: "workflow/snakemake_rules/prepare_sequences.smk"
-
-rule tree:
-    """Building tree"""
-    input:
-        alignment = "results/aligned.fasta"
-    output:
-        tree = "results/tree_raw.nwk"
-    shell:
-        """
-        augur tree \
-            --alignment {input.alignment} \
-            --output {output.tree}
-        """
-
-rule refine:
-    """
-    Refining tree
-      - estimate timetree
-      - use {params.coalescent} coalescent timescale
-      - estimate {params.date_inference} node dates
-      - filter tips more than {params.clock_filter_iqd} IQDs from clock expectation
-    """
-    input:
-        tree = "results/tree_raw.nwk",
-        alignment = "results/aligned.fasta",
-        metadata = "data/metadata_all.tsv"
-    output:
-        tree = "results/tree.nwk",
-        node_data = "results/branch_lengths.json"
-    params:
-        coalescent = "opt",
-        date_inference = "marginal",
-        clock_filter_iqd = 4,
-        strain_id = config.get("strain_id_field", "strain"),
-    shell:
-        """
-        augur refine \
-            --tree {input.tree} \
-            --alignment {input.alignment} \
-            --metadata {input.metadata} \
-            --metadata-id-columns {params.strain_id} \
-            --output-tree {output.tree} \
-            --output-node-data {output.node_data} \
-            --timetree \
-            --coalescent {params.coalescent} \
-            --date-confidence \
-            --date-inference {params.date_inference} \
-            --clock-filter-iqd {params.clock_filter_iqd}
-        """
+include: "workflow/snakemake_rules/construct_phylogeny.smk"
 
 rule ancestral:
     """Reconstructing ancestral sequences and mutations"""

phylogenetic/workflow/snakemake_rules/construct_phylogeny.smk

@@ -0,0 +1,69 @@
+"""
+This part of the workflow constructs the phylogenetic tree.
+
+REQUIRED INPUTS:
+
+    metadata            = data/metadata_all.tsv
+    prepared_sequences  = results/aligned.fasta
+
+OUTPUTS:
+
+    tree            = results/tree.nwk
+    branch_lengths  = results/branch_lengths.json
+
+This part of the workflow usually includes the following steps:
+
+    - augur tree
+    - augur refine
+
+See Augur's usage docs for these commands for more details.
+"""
+
+rule tree:
+    """Building tree"""
+    input:
+        alignment = "results/aligned.fasta"
+    output:
+        tree = "results/tree_raw.nwk"
+    shell:
+        """
+        augur tree \
+            --alignment {input.alignment} \
+            --output {output.tree}
+        """
+
+rule refine:
+    """
+    Refining tree
+      - estimate timetree
+      - use {params.coalescent} coalescent timescale
+      - estimate {params.date_inference} node dates
+      - filter tips more than {params.clock_filter_iqd} IQDs from clock expectation
+    """
+    input:
+        tree = "results/tree_raw.nwk",
+        alignment = "results/aligned.fasta",
+        metadata = "data/metadata_all.tsv"
+    output:
+        tree = "results/tree.nwk",
+        node_data = "results/branch_lengths.json"
+    params:
+        coalescent = "opt",
+        date_inference = "marginal",
+        clock_filter_iqd = 4,
+        strain_id = config.get("strain_id_field", "strain"),
+    shell:
+        """
+        augur refine \
+            --tree {input.tree} \
+            --alignment {input.alignment} \
+            --metadata {input.metadata} \
+            --metadata-id-columns {params.strain_id} \
+            --output-tree {output.tree} \
+            --output-node-data {output.node_data} \
+            --timetree \
+            --coalescent {params.coalescent} \
+            --date-confidence \
+            --date-inference {params.date_inference} \
+            --clock-filter-iqd {params.clock_filter_iqd}
+        """