Update assembly-config of hiv1 to use CA, PR, RT, and IN for assembling

hivdb · Jun 16, 2022 · f839500 · f839500
1 parent 1eb96f4
commit f839500
Show file tree

Hide file tree

Showing 2 changed files with 73 additions and 8 deletions.
diff --git a/data/assembly-config_hiv1.json b/data/assembly-config_hiv1.json
@@ -7,21 +7,51 @@
       "refEnd": 789
     },
     {
-      "name": "gag",
+      "name": "gagPreCA",
       "geneName": "HIV1gag",
+      "type": "GENE",
+      "trim": [
+        [
+          397,
+          1500
+        ]
+      ]
+    },
+    {
+      "name": "CA",
+      "geneName": "HIV1CA",
       "type": "GENE"
     },
     {
-      "name": "pol",
-      "geneName": "HIV1pol",
+      "name": "gagPostCA",
+      "geneName": "HIV1gag",
       "type": "GENE",
       "trim": [
         [
           1,
-          202
+          1089
+        ],
+        [
+          1464,
+          1500
         ]
       ]
     },
+    {
+      "name": "PR",
+      "geneName": "HIV1PR",
+      "type": "GENE"
+    },
+    {
+      "name": "RT",
+      "geneName": "HIV1RT",
+      "type": "GENE"
+    },
+    {
+      "name": "IN",
+      "geneName": "HIV1IN",
+      "type": "GENE"
+    },
     {
       "name": "vif",
       "geneName": "HIV1vif",

diff --git a/data/assembly-config_hiv1.yml b/data/assembly-config_hiv1.yml
@@ -3,13 +3,48 @@ HIV1:
   type: UNTRANS_REGION
   refStart: 1
   refEnd: 789
-- name: gag
+
+# The gag gene is assembled from four pieces of regions:
+# - Piece 1: gagPreCA
+# - Piece 2: CA
+# - Piece 3: gagPostCAPrePR
+# - Piece 4: PR
+#
+#  | Piece 1  | Piece 2          | Piece 3 | Piece 4 ...
+#  |----------------- gag ---------------------|
+#  1 (hxb2=790)                              1500
+#             |------ CA --------|         |--- PR ...
+#            397 (hxb2=1186)   1089       1464
+- name: gagPreCA
   geneName: HIV1gag
   type: GENE
-- name: pol
-  geneName: HIV1pol
+  #   Start of CA
+  #        v
+  trim: [[397, 1500]]
+  #              ^
+  #          End of gag
+- name: CA
+  geneName: HIV1CA
+  type: GENE
+- name: gagPostCA
+  geneName: HIV1gag
+  type: GENE
+  #        End of CA
+  #            v
+  trim: [[1, 1089], [1464, 1500]]
+  #                    ^
+  #               Start of PR
+- name: PR
+  geneName: HIV1PR
+  type: GENE
+# gag gene ends in PR
+
+- name: RT
+  geneName: HIV1RT
+  type: GENE
+- name: IN
+  geneName: HIV1IN
   type: GENE
-  trim: [[1, 202]]
 - name: vif
   geneName: HIV1vif
   type: GENE