From dd2b36c5a3427c58df0cee332bd4661a3ceb0b4d Mon Sep 17 00:00:00 2001
From: Frederick Muriuki Muriithi
Date: Wed, 9 Apr 2025 17:02:57 -0500
Subject: Convert PubMed_ID value from file to int

---
 scripts/phenotypes_bulk_edit.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'scripts')

diff --git a/scripts/phenotypes_bulk_edit.py b/scripts/phenotypes_bulk_edit.py
index 395b1bb..07104a5 100644
--- a/scripts/phenotypes_bulk_edit.py
+++ b/scripts/phenotypes_bulk_edit.py
@@ -168,7 +168,7 @@ def __fetch_new_pubmed_ids__(pubmed_ids):
         return tuple()
 
     logger.info("Fetching publications data for the following PubMed IDs: %s",
-                ", ".join(pubmed_ids))
+                ", ".join((str(pid) for pid in pubmed_ids)))
 
     # Should we, perhaps, pass this in from a config variable?
     uri = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi"
@@ -343,6 +343,9 @@ def read_file(filepath: Path) -> Iterator[str]:
             _pheno, _xref = _dict.pop("UniqueIdentifier").split("::")
             _dict["phenotype_id"] = int(_pheno.split(":")[1])
             _dict["xref_id"] = int(_xref.split(":")[1])
+            if _dict["PubMed_ID"] is not None:
+                _dict["PubMed_ID"] = int(_dict["PubMed_ID"])
+
             yield _dict
             count = count + 1
 
-- 
cgit v1.2.3