Update app.py

app.py

@@ -6,11 +6,24 @@ from numpy.linalg import norm
 from huggingface_hub import hf_hub_download
 from sentence_transformers import SentenceTransformer
 import os
+import logging
+
+# Create a logs directory if it does not exist
+log_dir = "logs"
+if not os.path.exists(log_dir):
+    os.makedirs(log_dir)
+
+# Configure logging
+log_file = os.path.join(log_dir, "hpo_mapper.log")
+logging.basicConfig(filename=log_file, level=logging.INFO, 
+                    format="%(asctime)s - %(levelname)s - %(message)s")
 
 # Get Hugging Face Token from Environment Variables
 HF_TOKEN = os.environ.get("HF_TOKEN")
 if not HF_TOKEN:
-    raise ValueError("Missing Hugging Face API token. Please set HF_TOKEN as an environment variable in Hugging Face Secrets.")
+    error_msg = "Missing Hugging Face API token. Please set HF_TOKEN as an environment variable in Hugging Face Secrets."
+    logging.error(error_msg)
+    raise ValueError(error_msg)
 
 # Load the Nomic-Embed Model from Hugging Face
 EMBEDDING_MODEL = "nomic-ai/nomic-embed-text-v1.5"
@@ -22,8 +35,12 @@ db_repo = "UoS-HGIG/hpo_genes"
 db_path = os.path.join(os.getcwd(), db_filename)
 
 if not os.path.exists(db_path):
-    db_path = hf_hub_download(repo_id=db_repo, filename=db_filename, repo_type="dataset", use_auth_token=HF_TOKEN)
-
+    try:
+        db_path = hf_hub_download(repo_id=db_repo, filename=db_filename, repo_type="dataset", use_auth_token=HF_TOKEN)
+        logging.info("Database successfully downloaded from Hugging Face.")
+    except Exception as e:
+        logging.error(f"Failed to download database: {e}")
+        raise
 
 def find_best_hpo_match(finding, region, threshold):
     query_text = f"{finding} in {region}" if region else finding
@@ -44,8 +61,13 @@ def find_best_hpo_match(finding, region, threshold):
             best_match = {"hpo_id": hpo_id, "hpo_term": hpo_name}
 
     conn.close()
-    return best_match if best_score >= threshold else None
 
+    if best_score >= threshold:
+        logging.info(f"Match found: {best_match['hpo_id']} - {best_match['hpo_term']} with score {best_score}")
+        return best_match
+    else:
+        logging.info(f"No suitable match found for query '{query_text}' with threshold {threshold}.")
+        return None
 
 def get_genes_for_hpo(hpo_id):
     conn = sqlite3.connect(db_path)
@@ -53,11 +75,17 @@ def get_genes_for_hpo(hpo_id):
     cursor.execute("SELECT genes FROM hpo_gene WHERE hpo_id = ?", (hpo_id,))
     result = cursor.fetchone()
     conn.close()
-    return result[0].split(", ") if result else []
 
+    genes = result[0].split(", ") if result else []
+    logging.info(f"Genes retrieved for HPO ID {hpo_id}: {genes}")
+    return genes
 
 def hpo_mapper_ui(finding, region, threshold):
+    logging.info(f"User input: Finding='{finding}', Region='{region}', Threshold={threshold}")
+
     if not finding:
+        error_msg = "No pathological finding entered."
+        logging.warning(error_msg)
         return "Please enter a pathological finding.", "", ""
 
     match = find_best_hpo_match(finding, region, threshold)
@@ -68,7 +96,6 @@ def hpo_mapper_ui(finding, region, threshold):
 
     return "No match found.", "", ""
 
-
 demo = gr.Interface(
     fn=hpo_mapper_ui,
     inputs=[
@@ -98,4 +125,5 @@ demo = gr.Interface(
 )
 
 if __name__ == "__main__":
-    demo.launch()
+    logging.info("Launching Gradio app.")
+    demo.launch()