Update app.py

app.py

@@ -7,27 +7,27 @@ from huggingface_hub import hf_hub_download
 from sentence_transformers import SentenceTransformer
 import os
 
-HF_TOKEN = os.environ.get(\"HF_TOKEN\")
+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.\")
+    raise ValueError("Missing Hugging Face API token. Please set HF_TOKEN as an environment variable.")
 
-EMBEDDING_MODEL = \"nomic-ai/nomic-embed-text-v1.5\"
+EMBEDDING_MODEL = "nomic-ai/nomic-embed-text-v1.5"
 embedder = SentenceTransformer(EMBEDDING_MODEL, trust_remote_code=True)
 
-db_filename = \"hpo_genes.db\"
-db_repo = \"UoS-HGIG/hpo_genes\"
+db_filename = "hpo_genes.db"
+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)
+    db_path = hf_hub_download(repo_id=db_repo, filename=db_filename, repo_type="dataset", use_auth_token=HF_TOKEN)
 
 def find_best_hpo_match(finding, region, threshold):
-    query = f\"{finding} {region}\" if region else finding
+    query = f"{finding} {region}" if region else finding
     query_embedding = embedder.encode(query)
 
     conn = sqlite3.connect(db_path)
     cursor = conn.cursor()
-    cursor.execute(\"SELECT hpo_id, hpo_name, embedding FROM hpo_embeddings\")
+    cursor.execute("SELECT hpo_id, hpo_name, embedding FROM hpo_embeddings")
 
     best_match, best_score = None, -1
 
@@ -37,7 +37,7 @@ def find_best_hpo_match(finding, region, threshold):
 
         if similarity > best_score:
             best_score = similarity
-            best_match = {\"hpo_id\": hpo_id, \"hpo_name\": hpo_name}
+            best_match = {"hpo_id": hpo_id, "hpo_name": hpo_name}
 
     conn.close()
 
@@ -46,7 +46,7 @@ def find_best_hpo_match(finding, region, threshold):
 def get_genes_for_hpo(hpo_id):
     conn = sqlite3.connect(db_path)
     cursor = conn.cursor()
-    cursor.execute(\"SELECT genes FROM hpo_gene WHERE hpo_id = ?\", (hpo_id,))
+    cursor.execute("SELECT genes FROM hpo_gene WHERE hpo_id = ?", (hpo_id,))
     result = cursor.fetchone()
     conn.close()
 
@@ -54,39 +54,40 @@ def get_genes_for_hpo(hpo_id):
 
 def hpo_mapper_ui(finding, region, threshold):
     if not finding:
-        return \"Please enter a clinical pathological finding.\", \"\", \"\"
+        return "Please enter a clinical pathological finding.", "", ""
 
     match = find_best_hpo_match(finding, region, threshold)
     if match:
         genes = get_genes_for_hpo(match['hpo_id'])
-        return match['hpo_id'], match['hpo_name'], \", \".join(genes)
+        return match['hpo_id'], match['hpo_name'], ", ".join(genes)
     else:
-        return \"\", \"No match found.\", \"\"
+        return "", "No match found.", ""
 
-image_path = \"https://huggingface.co/UoS-HGIG/MIMIC/resolve/main/images/hpo.png\"
+image_path = "https://huggingface.co/UoS-HGIG/MIMIC/resolve/main/images/hpo.png"
 
 demo = gr.Interface(
     fn=hpo_mapper_ui,
     inputs=[
-        gr.Textbox(label=\"Clinical Pathological Finding\"),
-        gr.Textbox(label=\"Anatomical Region (optional)\"),
-        gr.Slider(0.5, 1.0, 0.01, value=0.74, label=\"Similarity Threshold\")
+        gr.Textbox(label="Clinical Pathological Finding"),
+        gr.Textbox(label="Anatomical Region (optional)"),
+        gr.Slider(0.5, 1.0, 0.01, value=0.74, label="Similarity Threshold")
     ],
     outputs=[
-        gr.Textbox(label=\"HPO ID\"),
-        gr.Textbox(label=\"HPO Term\"),
-        gr.Textbox(label=\"Associated Genes\")
+        gr.Textbox(label="HPO ID"),
+        gr.Textbox(label="HPO Term"),
+        gr.Textbox(label="Associated Genes")
     ],
-    title=\"Human Phenotype Ontology (HPO) Mapper\",
+    title="Human Phenotype Ontology (HPO) Mapper",
     description=(
-        f\"![]({image_path})\\n\\n\"
-        \"## HPO to gene mappings obtained from [https://hpo.jax.org/data/annotations](https://hpo.jax.org/data/annotations)\\n\"
-        \"Enter a clinical pathological finding and optionally a region to map it to the closest Human Phenotype Ontology (HPO) term and retrieve associated genes.\\n\\n\"
-        \"**Reference:**\\n\"
-        \"Application of Generative Artificial Intelligence to Utilise Unstructured Clinical Data for Acceleration of Inflammatory Bowel Disease Research\\n\"
-        \"Alex Z Kadhim et al., [doi:10.1101/2025.03.07.25323569](https://doi.org/10.1101/2025.03.07.25323569)\"
+        f"![Workflow](https://huggingface.co/UoS-HGIG/MIMIC/blob/main/images/hpo.png)\n\n"
+        "## HPO to gene mappings obtained from [jax](https://hpo.jax.org/data/annotations)\n"
+        "Enter a clinical pathological finding and optionally a region to map it to the closest Human Phenotype Ontology (HPO) term and retrieve associated genes.\n\n"
+        "**Reference:**\n"
+        "Application of Generative Artificial Intelligence to Utilise Unstructured Clinical Data for Acceleration of Inflammatory Bowel Disease Research\n"
+        "Alex Z Kadhim, Zachary Green, Iman Nazari, Jonathan Baker, Michael George, Ashley Heinson, Matt Stammers, Christopher M Kipps, R Mark Beattie, James J Ashton, Sarah Ennis\n"
+        "medRxiv 2025.03.07.25323569; doi: [https://doi.org/10.1101/2025.03.07.25323569](https://doi.org/10.1101/2025.03.07.25323569)"
     )
 )
 
-if __name__ == \"__main__\":
-    demo.launch()
+if __name__ == "__main__":
+    demo.launch()