Merge branch 'master' into patch-4

cov-lineages · Jul 24, 2023 · 2f165e4 · 2f165e4
2 parents 0bae7d2 + f1b813c
commit 2f165e4
Show file tree

Hide file tree

Showing 4 changed files with 35 additions and 103 deletions.
diff --git a/automated-issue-ref.ipynb b/automated-issue-ref.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 7,
    "id": "f64573a2",
    "metadata": {},
    "outputs": [],
@@ -15,6 +15,8 @@
     "# the number of milestone we start to read\n",
     "start_milestone=1\n",
     "start_sub_milestone=1\n",
+    "end_milestone=795\n",
+    "end_sub_milestone=13\n",
     "def read_milestone(num,di='cov-lineages/pango-designation'):\n",
     "    # or sars-cov-2 proj if it starts to add milestones\n",
     "    url=\"https://github.com/\"+di+\"/milestone/\"+str(num)\n",
@@ -38,21 +40,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 8,
    "id": "769f2d32",
    "metadata": {
     "scrolled": false
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "796 HTTP Error 404: Not Found\n",
-      "8 HTTP Error 404: Not Found\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# read milestones \n",
     "milestone_end=False\n",
@@ -63,6 +56,7 @@
     "import os \n",
     "listd=os.listdir()\n",
     "\n",
+    "\n",
     "if not(\"autoref\" in listd):\n",
     "    os.mkdir(\"autoref\")\n",
     "lista=os.listdir(\"autoref\")\n",
@@ -80,7 +74,7 @@
     "                milestone_list.append([linsp[0],linsp[1]])\n",
     "            # don't read twice for old milestones\n",
     "            if issue>=milestone:\n",
-    "                milestone=issue+1          \n",
+    "                milestone=issue+1\n",
     "    w.close()\n",
     "\n",
     "if (\"milestone_sub.txt\" in lista):\n",
@@ -104,15 +98,15 @@
     "    print(item[0],item[1],file=w)\n",
     "\n",
     "\n",
-    "while not(milestone_end):\n",
+    "while (milestone<=end_milestone):\n",
     "    try:\n",
     "        title=read_milestone(milestone)\n",
     "        for item in title:\n",
     "            milestone_list.append([milestone,item])\n",
     "            print(milestone,item,file=w)\n",
     "    except Exception as e:\n",
     "        print(milestone,e)\n",
-    "        milestone_end=True\n",
+    "        \n",
     "    milestone+=1\n",
     "    if milestone%10==0:\n",
     "        print(\"Reading Milestone\",milestone)\n",
@@ -124,17 +118,17 @@
     "    print(item[0],item[1],file=w)\n",
     "\n",
     "milestone_end=False\n",
-    "while not(milestone_end):\n",
+    "while (milestone_sub<=end_sub_milestone):\n",
     "    try:\n",
     "        title=read_milestone(milestone_sub,di=\"sars-cov-2-variants/lineage-proposals\")\n",
     "        for item in title:\n",
     "            milestone_list_sub.append([milestone_sub,item])\n",
     "            print(milestone_sub,item,file=w)\n",
     "    except Exception as e:\n",
     "        print(milestone_sub,e)\n",
-    "        milestone_end=True\n",
+    "        \n",
     "    milestone_sub+=1\n",
-    "    if milestone%10==0:\n",
+    "    if milestone_sub%10==0:\n",
     "        print(\"Reading Milestone in sars-cov-2-variants \",milestone)\n",
     "\n",
     "w.close()\n",
@@ -146,7 +140,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 9,
    "id": "88a367db",
    "metadata": {},
    "outputs": [],
@@ -175,49 +169,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
    "id": "a56544a8",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "['BA.2.75.9', '#1098']\n",
-      "['CB.1', '#1098']\n",
-      "['CK.2', '#1190']\n",
-      "['CK.2.1.1', '#1190']\n",
-      "['BA.5.2.36', '#1203']\n",
-      "['CT.1', '#1203']\n",
-      "['BA.5.2.38', '#1254']\n",
-      "['DA.1', '#1254']\n",
-      "['AY.13', '#198']\n",
-      "['AY.14', '#198']\n",
-      "['AY.15', '#198']\n",
-      "['AY.16', '#198']\n",
-      "['AY.17', '#198']\n",
-      "['AY.18', '#198']\n",
-      "['AY.19', '#198']\n",
-      "['AY.20', '#198']\n",
-      "['AY.21', '#198']\n",
-      "['AY.22', '#198']\n",
-      "['AY.34.1.1', '#255']\n",
-      "['AY.58', '#286']\n",
-      "['AY.63', '#286']\n",
-      "['AY.99', '#258']\n",
-      "['AY.99.1', '#258']\n",
-      "['AY.99.2', '#258']\n",
-      "['AY.112.1', '#283']\n",
-      "['AY.121.1', '#344']\n",
-      "['AY.122', '#320']\n",
-      "['EG.4.2', 'sars-cov-2-variants/lineage-proposals/#46']\n",
-      "['GY.6', 'sars-cov-2-variants/lineage-proposals/#308']\n",
-      "['XBB.1.32', '#1827']\n",
-      "['XBB.1.37', '#1929']\n",
-      "['XBF.1.1', '#1651']\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# read lineage_notes.txt\n",
     "\n",
@@ -239,7 +194,7 @@
     "        item_to_milestone[to_add]=item[1]\n",
     "        \n",
     "for item in milestone_list_sub:\n",
-    "    to_add='sars-cov-2-variants/lineage-proposals/#'+str(item[0])\n",
+    "    to_add='sars-cov-2-variants/lineage-proposals#'+str(item[0])\n",
     "    all_milestones[item[1]]=to_add\n",
     "    if to_add in item_to_milestone:\n",
     "        item_to_milestone[to_add]+='+'+item[1]\n",
@@ -260,7 +215,7 @@
     "                if 'sars' in all_milestones[title]:\n",
     "                    issue_num=read_milestone_issues(title,di='sars-cov-2-variants/lineage-proposals')\n",
     "                    if issue_num!=0:\n",
-    "                        missing_milestones.append([title,'sars-cov-2-variants/lineage-proposals/#'+str(issue_num)])\n",
+    "                        missing_milestones.append([title,'sars-cov-2-variants/lineage-proposals#'+str(issue_num)])\n",
     "                        print(missing_milestones[-1])\n",
     "                else:\n",
     "                    issue_num=read_milestone_issues(title)\n",

diff --git a/autoref/milestone_sub.txt b/autoref/milestone_sub.txt
@@ -4,3 +4,8 @@
 4 CM.7.1.1
 5 EG.4.2
 7 GY.6
+8 GK.1.3
+9 XBB.1.41.1
+11 FL.4.3
+12 GJ.1.1
+13 GW.1
diff --git a/autoref/missing_refs.txt b/autoref/missing_refs.txt
@@ -1,32 +1,4 @@
-BA.2.75.9 #1098
-CB.1 #1098
-CK.2 #1190
-CK.2.1.1 #1190
-BA.5.2.36 #1203
-CT.1 #1203
-BA.5.2.38 #1254
-DA.1 #1254
-AY.13 #198
-AY.14 #198
-AY.15 #198
-AY.16 #198
-AY.17 #198
-AY.18 #198
-AY.19 #198
-AY.20 #198
-AY.21 #198
-AY.22 #198
-AY.34.1.1 #255
-AY.58 #286
-AY.63 #286
-AY.99 #258
-AY.99.1 #258
-AY.99.2 #258
-AY.112.1 #283
-AY.121.1 #344
-AY.122 #320
-EG.4.2 sars-cov-2-variants/lineage-proposals/#46
-GY.6 sars-cov-2-variants/lineage-proposals/#308
-XBB.1.32 #1827
-XBB.1.37 #1929
-XBF.1.1 #1651
+GK.1.3 sars-cov-2-variants/lineage-proposals#179
+FL.4.3 sars-cov-2-variants/lineage-proposals#153
+XBB.1.41.1 sars-cov-2-variants/lineage-proposals#150
+GJ.1.1 sars-cov-2-variants/lineage-proposals#109
diff --git a/lineage_notes.txt b/lineage_notes.txt
@@ -2718,7 +2718,7 @@ XBB.1.5.27	S:K478R, on T11431C branch, USA
 XBB.1.5.28	S:K478R, on 17124C polytomy, USA
 XBB.1.5.29	S:A348V, USA-NE
 XBB.1.5.30	S:A348T, USA From #1660
-HM.1	Alias of XBB.1.5.30.1, S:N481K, Canada/Australia from https://github.com/sars-cov-2-variants/lineage-proposals/issues/59
+HM.1	Alias of XBB.1.5.30.1, S:N481K, Canada/Australia, from https://github.com/sars-cov-2-variants/lineage-proposals/issues/59
 XBB.1.5.31	T24976C, USA
 XBB.1.5.32	ORF1a:T2823I, USA
 XBB.1.5.33	G370A, USA
@@ -2777,7 +2777,7 @@ XBB.1.5.70	S:L455F, S:F456L (T22928C), ORF1a:A4068S, Brazil, from #1982
 GK.1	Alias of XBB.1.5.70.1, S:S704L, Brazil, from #2025
 GK.1.1	Alias of XBB.1.5.70.1.1, S:T573I, Brazil
 GK.1.2	Alias of XBB.1.5.70.1.2, S:N185D, Brazil from  #2093
-GK.1.3	Alias of XBB.1.5.70.1.3, ORF1a:E633A, ORF1b:D1130G, USA/Canada
+GK.1.3	Alias of XBB.1.5.70.1.3, ORF1a:E633A, ORF1b:D1130G, USA/Canada From sars-cov-2-variants/lineage-proposals#179
 GK.2	Alias of XBB.1.5.70.2, S:V511I, from sars-cov-2-variants/lineage-proposals#300
 XBB.1.5.71	S:V511I, Spain
 XBB.1.5.72	S:F456L (T22928C), ORF1a:G445S, T9823C, T10204C, South America
@@ -2846,7 +2846,7 @@ FL.4	Alias of XBB.1.9.1.4, ORF1b:V1092F
 FL.4.1	Alias of XBB.1.9.1.4.1, S:N450I
 FL.4.1.1	Alias of XBB.1.9.1.4.1.1, S:K478R, ORF1a:I2286T, Indonesia/Australia, from sars-cov-2-variants/lineage-proposals#107
 FL.4.2	Alias of XBB.1.9.1.4.2, ORF1a:T951I, China
-FL.4.3	Alias of XBB.1.9.1.4.3, S:A766S, G7393T, Myanmar
+FL.4.3	Alias of XBB.1.9.1.4.3, S:A766S, G7393T, Myanmar From sars-cov-2-variants/lineage-proposals#153
 FL.4.4	Alias of XBB.1.9.1.4.4, ORF1a:T1542I, T24544C, S:478T (reversion), Indonesia
 FL.4.5	Alias of XBB.1.9.1.4.5, ORF8:S67F, ORF1a:D1228G, C23635T, from #2018
 FL.4.6	Alias of XBB.1.9.1.4.6, T5098C, C13965T, Australia/China
@@ -2977,7 +2977,7 @@ HF.1	XBB.1.16.13.1, S:K304N, South Korea/Japan from #2083
 XBB.1.16.14	S:L452Q, after A11782G, India/France/Canada, from sars-cov-2-variants/lineage-proposals#329
 XBB.1.16.15	S:K147N, S:P521S, T10756C, T14067C, on C27513T branch, from #2092
 XBB.1.16.16	S:Q613H, S:S412N, India-GJ/USA/Pakistan from sars-cov-2-variants/lineage-proposals#54
-XBB.1.16.17	S:E554K
+XBB.1.16.17	S:E554K, mainly in NZ, from https://github.com/sars-cov-2-variants/lineage-proposals/issues/354
 XBB.1.17	Defined by T27995C and ORF1a:L469F, from issue #1712
 XBB.1.17.1	Defined by S:215H, S:S486P, from issue #1712
 GA.1	Alias of XBB.1.17.1.1, ORF1a:G728C
@@ -3013,15 +3013,15 @@ FY.1.1	Alias of XBB.1.22.1.1.1, S:A83S, Malaysia/Japan
 FY.1.2	Alias of XBB.1.22.1.1.2, S:T572I, ORF1b:P218L, Europe
 FY.1.3	Alias of XBB.1.22.1.1.3, S:E583D, South Korea
 FY.2	Alias of XBB.1.22.1.2, S:I197T, ORF1b:S997P, Indonesia, from #1859
-FY.2.1	Alias of XBB.1.22.1.2.1, S:A684V
+FY.2.1	Alias of XBB.1.22.1.2.1, S:A684V, from #2080
 FY.3	Alias of XBB.1.22.1.3, ORF1a:E750K, C23191T, China
 FY.3.1	Alias of XBB.1.22.1.3.1, S:I210T, China，from #2009
 FY.4	Alias of XBB.1.22.1.4, S:Y451H, A8374G, C25517T, Kenya, from #1979
 FY.4.1	Alias of XBB.1.22.1.4.1, S:S494P, Kenya
-FY.4.1.1	Alias of XBB.1.22.1.4.1.1, S:S704L
+FY.4.1.1	Alias of XBB.1.22.1.4.1.1, S:S704L, from https://github.com/sars-cov-2-variants/lineage-proposals/issues/302
 FY.5	Alias of XBB.1.22.1.5, S:478R, Indonesia, from #1965
 FY.6	Alias of XBB.1.22.1.6, T2935C, ORF1a:A591V, France
-FY.7	Alias of XBB.1.22.1.7, S:G769A, S:D1168E
+FY.7	Alias of XBB.1.22.1.7, S:G769A, S:D1168E, from https://github.com/sars-cov-2-variants/lineage-proposals/issues/257
 XBB.1.22.2	Defined by ORF1a:L3829F, C15237T
 XBB.1.23	Defined by E:S68F, on 28297C branch, South East Asia
 XBB.1.24	Defined by S:F486P, on T13704C branch, South East Asia from #1654
@@ -3057,7 +3057,7 @@ XBB.1.38.1	S:T883I, Russia
 XBB.1.39	ORF1a:V2866M, Singapore/Malaysia
 XBB.1.40	S:Y453F, ORF1a:G519S, ORF1a:L2609F, ORF3a:P104S, Malaysia
 XBB.1.41	S:L335S, S:R403K, S:486P, possibly common  in Central/West Africa, from #1997
-XBB.1.41.1	S:478R, France
+XBB.1.41.1	S:478R, France From sars-cov-2-variants/lineage-proposals#150
 XBB.1.42	S:486P, S:Q613H, on ORF1a:T4175I branch with XBB.1.9, Indonesia/Malaysia/China，from #1954
 XBB.1.42.1	S:478R from https://github.com/sars-cov-2-variants/lineage-proposals/issues/198
 XBB.1.42.2	C6040T, G9049A
@@ -3085,7 +3085,7 @@ HH.1.1	Alias of XBB.2.3.2.1.1, S:G181A from  sars-cov-2-variants/lineage-proposa
 HH.2	Alias of XBB.2.3.2.2, ORF1a:D48Y
 XBB.2.3.3	S:182N, India/USA From #1810
 GJ.1	Alias of XBB.2.3.3.1, found mainly in China and USA, from pango-designation issue #2005
-GJ.1.1	Alias of XBB.2.3.3.1.1, S:A222V, N:R319H, ORF1a:V1915I
+GJ.1.1	Alias of XBB.2.3.3.1.1, S:A222V, N:R319H, ORF1a:V1915I From sars-cov-2-variants/lineage-proposals#109
 GJ.1.2	Alias of XBB.2.3.3.1.2, ORF1b:V1110I, from #2059
 GJ.2	Alias of XBB.2.3.3.2, S:I1114S, Europe
 GJ.3	Alias of XBB.2.3.3.3, ORF1a:P971S, ORF1b:V2371L