Update curated papers, add new PDB provider (FURNA).

src/bioregistry/constants.py

@@ -33,6 +33,17 @@
 COLLECTIONS_PATH = DATA_DIRECTORY / "collections.json"
 MISMATCH_PATH = DATA_DIRECTORY / "mismatch.json"
 CONTEXTS_PATH = DATA_DIRECTORY / "contexts.json"
+CURATED_PAPERS_PATH = DATA_DIRECTORY / "curated_papers.txt"
+CURATED_PAPERS_RELEVANCY_VOCAB = [
+    "new_prefix",
+    "new_provider",
+    "new_publication",
+    "not_identifiers_resource",
+    "no_website",
+    "existing",
+    "unclear",
+    "irrelevant_other",
+]
 
 BIOREGISTRY_MODULE = pystow.module("bioregistry")
 

src/bioregistry/data/bioregistry.json

@@ -85749,6 +85749,15 @@
       "prefix": "pdbj",
       "uri_format": "http://service.pdbj.org/mine/Detail?PDBID=$1&PAGEID=Summary"
     },
+    "providers": [
+      {
+        "code": "furna",
+        "description": "FURNA (Functions of RNAs) is a database of ligand-RNA interactions and Gene Ontology annotations for RNAs in the Protein Data Bank (PDB).",
+        "homepage": "https://seq2fun.dcmb.med.umich.edu/furna/",
+        "name": "furna",
+        "uri_format": "https://seq2fun.dcmb.med.umich.edu/furna/pdb.cgi?pdbid=$1"
+      }
+    ],
     "publications": [
       {
         "doi": "10.1002/pro.4211",

src/bioregistry/data/curated_papers.txt

@@ -0,0 +1,21 @@
+pmid	relevant	relevancy_type	notes	orcid	date_curated
+39104285	1	new_provider	"Provider for UniProt IDs, issue with curation due to multiple URI formats depending on plant species"	0009-0009-5240-7463	2024-09-24
+39074139	1	new_provider	Resolver for PDB IDs	0009-0009-5240-7463	2024-09-24
+39014503	0	no_website		0009-0009-5240-7463	2024-09-25
+39047988	0	irrelevant_other		0009-0009-5240-7463	2024-09-25
+39115390	0	irrelevant_other		0009-0009-5240-7463	2024-09-26
+39095357	0	irrelevant_other		0009-0009-5240-7463	2024-09-26
+39084442	0	not_identifiers_resource		0009-0009-5240-7463	2024-09-27
+38991851	1	unclear	"identifiers for sharing, retrieving, and validating sample metadata. Unclear if this should be curated as a prefix, provider or a separate registry"	0009-0009-5240-7463	2024-09-28
+38991828	0	irrelevant_other		0009-0009-5240-7463	2024-09-28
+39049520	0	not_identifiers_resource		0009-0009-5240-7463	2024-09-30
+39104826	1	existing	Already present in the bioregistry as a provider for mesh prefix	0009-0009-5240-7463	2024-10-01
+39050757	0	irrelevant_other		0009-0009-5240-7463	2024-10-01
+39064021	0	irrelevant_other		0009-0009-5240-7463	2024-10-01
+39028894	0	not_identifiers_resource		0009-0009-5240-7463	2024-10-04
+39044201	0	not_identifiers_resource	Potential resource for rare diseases identifiers, but not identifier information	0009-0009-5240-7463	2024-10-04
+39088253	0	irrelevant_other		0009-0009-5240-7463	2024-10-05
+39119155	0	irrelevant_other		0009-0009-5240-7463	2024-10-05
+39005357	0	irrelevant_other		0009-0009-5240-7463	2024-10-05
+39044130	0	irrelevant_other		0009-0009-5240-7463	2024-10-05
+39010878	0	irrelevant_other		0009-0009-5240-7463	2024-10-05

tests/test_curated_papers.py

@@ -0,0 +1,61 @@
+# -*- coding: utf-8 -*-
+
+"""Test for checking the integrity of the curated_papers TSV file."""
+
+import csv
+import re
+import unittest
+from datetime import datetime
+
+from bioregistry.constants import (
+    CURATED_PAPERS_PATH,
+    CURATED_PAPERS_RELEVANCY_VOCAB,
+    ORCID_PATTERN,
+)
+
+
+class TestTSV(unittest.TestCase):
+    """Tests for curated_papers tsv file."""
+
+    def setUp(self):
+        """Set up the test case."""
+        self.tsv_file_path = CURATED_PAPERS_PATH
+        self.relevancy_vocab = CURATED_PAPERS_RELEVANCY_VOCAB
+        self.orcid_pattern = re.compile(ORCID_PATTERN)
+
+    def validate_row(self, row):
+        """Validate a single row from the TSV file."""
+        # Validate required fields
+        required_fields = ["pmid", "relevant", "relevancy_type", "orcid", "date_curated"]
+        for field in required_fields:
+            self.assertIn(field, row)
+
+        # Validate pmid is an integer
+        self.assertTrue(row["pmid"].isdigit())
+
+        # Validate relevant is 0 or 1
+        self.assertIn(row["relevant"], ["0", "1"])
+
+        # Validate relevancy_type is in relevancy_vocab
+        self.assertIn(row["relevancy_type"], self.relevancy_vocab)
+
+        # Validate orcid against oricd_pattern
+        self.assertTrue(self.orcid_pattern.match(row["orcid"]))
+
+        # Validate date_curated format
+        try:
+            datetime.strptime(row["date_curated"], "%Y-%m-%d")
+        except ValueError:
+            self.fail("Date_curated should follow format YYYY-MM-DD")
+
+    def test_tsv_file(self):
+        """Tests all rows in TSV file are valid."""
+        with open(self.tsv_file_path, mode="r") as tsv_file:
+            tsv_reader = csv.DictReader(tsv_file, delimiter="\t")
+            for row in tsv_reader:
+                with self.subTest(row=row):
+                    self.validate_row(row)
+
+
+if __name__ == "__main__":
+    unittest.main()