Instead of "fixed" root, use mid_point rooting #46

phylogenetic/defaults/config.yaml

@@ -31,15 +31,11 @@ tree:
 refine:
   coalescent: "opt"
   date_inference: "marginal"
-  clock_rate: 0.0006
-  # Rooting to outgroup clade based on strains
-  # Pinneo-NIG-1969 (L accession KM822127 and S accession KM822128)
-  # and strain 812285 (L accession MG812674 and S accession MG812675)
-  # TreeTime needs two tips to root to common ancestor of these tips
+  # Root the tree based on "mid_point" for treetime
   root:
-    l: "KM822127 MG812674"
-    s: "KM822128 MG812675"
-    gpc: "KM822128"
+    l: "mid_point"
+    s: "mid_point"
+    gpc: "mid_point"
 
 ancestral:
   inference: "joint"

phylogenetic/defaults/exclude.txt

@@ -6,3 +6,10 @@ KU978809 # GUINEA_Z_185a L segment
 KU978810 # GUINEA_Z_185a S segment
 KU978811 # NIGERIA_IKEJI S segment
 KU978812 # NIGERIA_IKEJI L segment
+OR493499 # Large insertion off the end of the S segment
+OR493501 # Large insertion off the end of the S segment
+OR493502 # Large insertion off the end of the S segment
+OR493503 # Large insertion off the end of the S segment
+OR493504 # Large insertion off the end of the S segment
+OM735982 # Large insertion of Ns in the S segment
+MK117995 # 6 base insersion in the S segment

phylogenetic/rules/construct_phylogeny.smk

@@ -63,7 +63,6 @@ rule refine:
         strain_id_field = config["strain_id_field"],
         coalescent = config['refine']['coalescent'],
         date_inference = config['refine']['date_inference'],
-        clock_rate = config['refine']['clock_rate'],
         root = lambda wildcards: config['refine']['root'][wildcards.segment],
     shell:
         """
@@ -76,7 +75,6 @@ rule refine:
             --output-node-data {output.node_data} \
             --timetree \
             --coalescent {params.coalescent} \
-            --clock-rate {params.clock_rate} \
             --date-confidence \
             --date-inference {params.date_inference} \
             --root {params.root} \