Use clade I reference KJ642613 for clade I build, mask correctly

phylogenetic/defaults/clade-i/auspice_config.json

@@ -56,6 +56,46 @@
       "title": "Release Date",
       "type": "categorical"
     },
+    {
+      "key": "sra_accession",
+      "title": "SRA Accession",
+      "type": "categorical"
+    },
+    {
+      "key": "coverage",
+      "title": "Coverage",
+      "type": "continuous"
+    },
+    {
+      "key": "missing_data",
+      "title": "Missing Data",
+      "type": "continuous"
+    },
+    {
+      "key": "nonACGTN",
+      "title": "Non-ACGTN",
+      "type": "continuous"
+    },
+    {
+      "key": "institution",
+      "title": "Institution",
+      "type": "categorical"
+    },
+    {
+      "key": "division",
+      "title": "Division",
+      "type": "categorical"
+    },
+    {
+      "key": "location",
+      "title": "Location",
+      "type": "categorical"
+    },
+    {
+      "key": "abbr_authors",
+      "title": "Abbreviated Authors",
+      "type": "categorical"
+    },
     {
       "key": "date",
       "title": "Collection date",

phylogenetic/defaults/clade-i/config.yaml

@@ -1,12 +1,12 @@
-reference: "defaults/reference.fasta"
-genome_annotation: "defaults/genome_annotation.gff3"
-genbank_reference: "defaults/reference.gb"
+reference: "defaults/clade-i/reference.fasta"
+genome_annotation: "defaults/clade-i/genome_annotation.gff3"
+genbank_reference: "defaults/clade-i/reference.gb"
 include: "defaults/clade-i/include.txt"
 clades: "defaults/clades.tsv"
 lat_longs: "defaults/lat_longs.tsv"
 auspice_config: "defaults/clade-i/auspice_config.json"
 description: "defaults/description.md"
-tree_mask: "defaults/tree_mask.tsv"
+tree_mask: "defaults/clade-i/tree_mask.tsv"
 
 # Use `accession` as the ID column since `strain` currently contains duplicates¹.
 # ¹ https://github.com/nextstrain/mpox/issues/33
@@ -18,7 +18,7 @@ auspice_name: "mpox_clade-I"
 
 filter:
   min_date: 1900
-  min_length: 100000
+  min_length: 170000
 
 
 ### Filter to only Clade I sequences
@@ -56,7 +56,7 @@ recency: true
 mask:
   from_beginning: 800
   from_end: 6422
-  maskfile: "defaults/mask.bed"
+  maskfile: "defaults/clade-i/mask.bed"
 
 colors:
   ignore_categories: "division location"

phylogenetic/defaults/clade-i/mask.bed

@@ -0,0 +1,25 @@
+Chrom	ChromStart	ChromEnd	locus tag	Comment
+chr	8340	8480		indel variation and long repetitive elements
+chr	17960	17980		Next to stretch of Ns, suspicious
+chr	18930	19050		termini of clade Ib deletion are sometimes incorrectly called
+chr	19900	20100		termini of clade Ib deletion are sometimes incorrectly called
+chr	20250	20280		triple mutation in Ib is inconsistently called
+chr	22890	22920		homopolymer stretch
+chr	31570	31610		Indel often incorrectly called
+chr	77870	77880		Likely reversion to reference in some INRB sequences only
+chr	109460	109470		Lots of ambiguous right next to start of Ns
+chr	109730	109750		Indel often incorrectly called
+chr	123370	123400		Right next to stretch of Ns in INRB sequences only
+chr	138000	138300		indel variation and long repetitive elements
+chr	141700	141800		indel variation and long repetitive elements
+chr	144750	144830		indel variation and long repetitive elements
+chr	148440	148660		indel variation and long repetitive elements
+chr	149970	150020		indel variation and long repetitive elements
+chr	152170	152300		indel variation and long repetitive elements
+chr	157520	157570		homopolymer/tandem repeats
+chr	158790	158800		Mutation right next to stretch of Ns, INRB sequences only
+chr	162580	162610		indel variation and long repetitive elements
+chr	169000	169350		indel variation and long repetitive elements
+chr	177250	177350		indel variation and long repetitive elements
+chr	178500	178900		indel variation and long repetitive elements
+chr	180650	180710		Indel sometimes called messily