Ingest output Pathoplexus group URL, surface in phylogenetic

Author: corneliusroemer

ingest/defaults/config.yaml

@@ -32,6 +32,7 @@ curate:
     dataUseTermsRestrictedUntil: restrictedUntil
     dataUseTermsUrl: dataUseTerms__url
     groupId: Pathoplexus_group_id
+    groupName: Pathoplexus_group
     # TODO: There are more fields I should look into porting
   # Standardized strain name regex
   # Currently accepts any characters because we do not have a clear standard for strain names
@@ -97,8 +98,9 @@ curate:
     'dataUseTerms__url',
     'restrictedUntil',
     'displayName',
+    'Pathoplexus_group',
     'Pathoplexus_group_id',
-    'Pathoplexus_group_id__url',
+    'Pathoplexus_group__url',
     'submission_database',
   ]
 

ingest/scripts/curate-urls.py

@@ -27,7 +27,7 @@ def run(args: argparse.Namespace, records: Iterable[dict]) -> Iterable[dict]:
         record['INSDC_accession_version__url'] = f"https://www.ncbi.nlm.nih.gov/nuccore/{insdc_accession_version}" \
             if insdc_accession_version \
             else ""
-        record['Pathoplexus_group_id__url'] = f"https://pathoplexus.org/group/{group_id}" \
+        record['Pathoplexus_group__url'] = f"https://pathoplexus.org/group/{group_id}" \
             if group_id \
             else ""
         record['submission_database'] = "INSDC" if str(group_id) == "1" else "Pathoplexus"

phylogenetic/defaults/clade-i/auspice_config.json

@@ -105,6 +105,16 @@
       "title": "Authors",
       "type": "categorical"
     },
+    {
+      "key": "submission_database",
+      "title": "Database of original submission",
+      "type": "categorical"
+    },
+    {
+      "key": "Pathoplexus_group",
+      "title": "Pathoplexus Group ID",
+      "type": "categorical"
+    },
     {
       "key": "restrictedUntil",
       "title": "Restricted Until",
@@ -130,5 +140,12 @@
     "distance_measure": "div",
     "transmission_lines": false
   },
-  "filters": ["country", "region", "recency", "host", "author"]
+  "filters": [
+    "country",
+    "region",
+    "recency",
+    "host",
+    "author",
+    "Pathoplexus_group"
+  ]
 }

phylogenetic/defaults/hmpxv1/auspice_config.json

@@ -1,7 +1,7 @@
 {
   "title": "Genomic epidemiology of mpox clade IIb viruses",
   "maintainers": [
-    {"name": "Nextstrain team", "url": "http://nextstrain.org"}
+    { "name": "Nextstrain team", "url": "http://nextstrain.org" }
   ],
   "data_provenance": [
     {
@@ -65,8 +65,19 @@
       "title": "Collection date",
       "type": "categorical"
     },
+    {
+      "key": "submission_database",
+      "title": "Database of original submission",
+      "type": "categorical"
+    },
+    {
+      "key": "Pathoplexus_group",
+      "title": "Pathoplexus Group ID",
+      "type": "categorical"
+    },
     {
       "key": "restrictedUntil",
+
       "title": "Restricted Until",
       "type": "categorical"
     },
@@ -76,9 +87,7 @@
       "type": "categorical"
     }
   ],
-  "geo_resolutions": [
-    "country"
-  ],
+  "geo_resolutions": ["country"],
   "metadata_columns": [
     "strain",
     "PPX_accession",
@@ -96,6 +105,7 @@
     "clade_membership",
     "lineage",
     "country",
+    "Pathoplexus_group",
     "region",
     "recency",
     "host",

phylogenetic/defaults/hmpxv1_big/auspice_config.json

@@ -1,7 +1,7 @@
 {
   "title": "Genomic epidemiology of mpox lineage B.1 viruses",
   "maintainers": [
-    {"name": "Nextstrain team", "url": "http://nextstrain.org"}
+    { "name": "Nextstrain team", "url": "http://nextstrain.org" }
   ],
   "data_provenance": [
     {
@@ -70,6 +70,16 @@
       "title": "Collection date",
       "type": "categorical"
     },
+    {
+      "key": "submission_database",
+      "title": "Database of original submission",
+      "type": "categorical"
+    },
+    {
+      "key": "Pathoplexus_group",
+      "title": "Pathoplexus Group ID",
+      "type": "categorical"
+    },
     {
       "key": "restrictedUntil",
       "title": "Restricted Until",
@@ -81,9 +91,7 @@
       "type": "categorical"
     }
   ],
-  "geo_resolutions": [
-    "country"
-  ],
+  "geo_resolutions": ["country"],
   "metadata_columns": [
     "strain",
     "PPX_accession",
@@ -101,6 +109,7 @@
     "clade_membership",
     "lineage",
     "country",
+    "Pathoplexus_group",
     "region",
     "recency",
     "host",

phylogenetic/defaults/mpxv/auspice_config.json

@@ -1,7 +1,7 @@
 {
   "title": "Genomic epidemiology of mpox viruses across clades",
   "maintainers": [
-    {"name": "Nextstrain team", "url": "http://nextstrain.org"}
+    { "name": "Nextstrain team", "url": "http://nextstrain.org" }
   ],
   "data_provenance": [
     {
@@ -75,6 +75,16 @@
       "title": "Collection date",
       "type": "categorical"
     },
+    {
+      "key": "submission_database",
+      "title": "Database of original submission",
+      "type": "categorical"
+    },
+    {
+      "key": "Pathoplexus_group",
+      "title": "Pathoplexus Group",
+      "type": "categorical"
+    },
     {
       "key": "restrictedUntil",
       "title": "Restricted Until",
@@ -86,9 +96,7 @@
       "type": "categorical"
     }
   ],
-  "geo_resolutions": [
-    "country"
-  ],
+  "geo_resolutions": ["country"],
   "metadata_columns": [
     "strain",
     "PPX_accession",
@@ -106,6 +114,7 @@
     "clade_membership",
     "lineage",
     "country",
+    "Pathoplexus_group",
     "region",
     "recency",
     "host",