Add new prefix: smc.* (#1301)

PubMed: https://pubmed.ncbi.nlm.nih.gov/39540430/ Database: https://smc.jgi.doe.gov/ This pull request curates 2 new prefixes for the Secondary Metabolism Collaboratory: `smc.source` and `smc.bgc` This resource has two distinct semantic spaces: - `smc.source` provides basic information about the microbial source, including its name, taxonomic information, and public sequence database. - `smc.bgc` provides information about individual biosynthetic gene clusters (BGCs) linked to a specific microbial source. --------- Co-authored-by: Benjamin M. Gyori <[email protected]>
biopragmatics · Dec 19, 2024 · 9de4d1d · 9de4d1d
1 parent 88c771f
commit 9de4d1d
Show file tree

Hide file tree

Showing 2 changed files with 69 additions and 0 deletions.
diff --git a/src/bioregistry/data/bioregistry.json b/src/bioregistry/data/bioregistry.json
@@ -107304,6 +107304,74 @@
       "uri_format": "https://smart.embl.de/smart/do_annotation.pl?DOMAIN=$1"
     }
   },
+  "smc.bgc": {
+    "contact": {
+      "email": "[email protected]",
+      "name": "Daniel W Udwary",
+      "orcid": "0000-0002-3491-0198"
+    },
+    "contributor": {
+      "email": "[email protected]",
+      "github": "nagutm",
+      "name": "Mufaddal Naguthanawala",
+      "orcid": "0009-0009-5240-7463"
+    },
+    "description": "The secondary metabolism collaboratory is a database for secondary metabolite biosynthetic gene clusters. This prefix represents identifiers for individual biosynthetic gene clusters (BGCs) linked to their corresponding bacterial or archaeal source.",
+    "example": "12039302",
+    "github_request_issue": 1301,
+    "homepage": "https://smc.jgi.doe.gov",
+    "name": "Secondary Metabolism Collaboratory",
+    "pattern": "^\\d+$",
+    "publications": [
+      {
+        "doi": "10.1093/nar/gkae1060",
+        "pubmed": "39540430",
+        "title": "The secondary metabolism collaboratory: a database and web discussion portal for secondary metabolite biosynthetic gene clusters",
+        "year": 2024
+      }
+    ],
+    "reviewer": {
+      "email": "[email protected]",
+      "github": "bgyori",
+      "name": "Benjamin M. Gyori",
+      "orcid": "0000-0001-9439-5346"
+    },
+    "uri_format": "https://smc.jgi.doe.gov/bgc/$1"
+  },
+  "smc.source": {
+    "contact": {
+      "email": "[email protected]",
+      "name": "Daniel W Udwary",
+      "orcid": "0000-0002-3491-0198"
+    },
+    "contributor": {
+      "email": "[email protected]",
+      "github": "nagutm",
+      "name": "Mufaddal Naguthanawala",
+      "orcid": "0009-0009-5240-7463"
+    },
+    "description": "The secondary metabolism collaboratory is a database for secondary metabolite biosynthetic gene clusters. This prefix represents identifiers for bacteria and archaea sources linked to their associated set of biosynthetic gene clusters (BGCs).",
+    "example": "1",
+    "github_request_issue": 1301,
+    "homepage": "https://smc.jgi.doe.gov",
+    "name": "Secondary Metabolism Collaboratory",
+    "pattern": "^\\d+$",
+    "publications": [
+      {
+        "doi": "10.1093/nar/gkae1060",
+        "pubmed": "39540430",
+        "title": "The secondary metabolism collaboratory: a database and web discussion portal for secondary metabolite biosynthetic gene clusters",
+        "year": 2024
+      }
+    ],
+    "reviewer": {
+      "email": "[email protected]",
+      "github": "bgyori",
+      "name": "Benjamin M. Gyori",
+      "orcid": "0000-0001-9439-5346"
+    },
+    "uri_format": "https://smc.jgi.doe.gov/sources/$1"
+  },
   "smid": {
     "contributor": {
       "email": "[email protected]",

diff --git a/src/bioregistry/data/curated_papers.tsv b/src/bioregistry/data/curated_papers.tsv
@@ -90,6 +90,7 @@ pubmed	relevant	orcid	date_curated	relevancy_type	pr_added	notes
 39535874	1	0009-0009-5240-7463	2024-12-05	not_notable	1296	This database website is very low quality and fails to resolve many of its own IDs
 39535874	1	0009-0009-5240-7463	2024-12-05	not_notable	1296	This database website is very low quality and fails to resolve many of its own IDs
 39540428	1	0009-0009-5240-7463	2024-12-14	new_publication	1329	Publication for pfam
+39540430	1	0009-0009-5240-7463	2024-12-10	new_prefix	1301	Identifiers for secondary metabolite biosynthetic gene clusters and sources
 39540736	0	0009-0009-5240-7463	2024-12-11	irrelevant_other	1305	
 39540856	0	0009-0009-5240-7463	2024-12-05	no_website	1296	
 39540856	0	0009-0009-5240-7463	2024-12-05	no_website	1296