diff --git a/chebai/preprocessing/datasets/base.py b/chebai/preprocessing/datasets/base.py
index 24655b0d..d5cd5653 100644
--- a/chebai/preprocessing/datasets/base.py
+++ b/chebai/preprocessing/datasets/base.py
@@ -1111,6 +1111,7 @@ def _retrieve_splits_from_csv(self) -> None:
         filename = self.processed_file_names_dict["data"]
         data = self.load_processed_data_from_file(filename)
         df_data = pd.DataFrame(data)
+        df_data["ident"] = df_data["ident"].astype(str)
 
         if self.apply_id_filter:
             print(f"Applying ID filter from {self.apply_id_filter}...")