Create app.py

app.py

@@ -0,0 +1,83 @@
+import gradio as gr
+import ollama
+import sqlite3
+import json
+import numpy as np
+from numpy.linalg import norm
+from huggingface_hub import hf_hub_download
+import os
+
+# Download database from Hugging Face if not exists
+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)
+
+def find_best_hpo_match(finding, region):
+    """Finds the best HPO match using semantic similarity."""
+    query_text = f"{finding} in {region}"
+    query_embedding = np.array(ollama.embeddings(model='nomic-embed-text', prompt=query_text)["embedding"])
+
+    conn = sqlite3.connect(db_path)
+    cursor = conn.cursor()
+    cursor.execute("SELECT hpo_id, hpo_name, embedding FROM hpo_embeddings")
+    
+    best_match, best_score = None, -1
+    
+    for hpo_id, hpo_name, embedding_str in cursor.fetchall():
+        hpo_embedding = np.array(json.loads(embedding_str))
+        similarity = np.dot(query_embedding, hpo_embedding) / (norm(query_embedding) * norm(hpo_embedding))
+        
+        if similarity > best_score:
+            best_score = similarity
+            best_match = {"hpo_id": hpo_id, "hpo_term": hpo_name}
+    
+    conn.close()
+    return best_match if best_score > 0.74 else None  # Adjust threshold as needed
+
+
+def get_genes_for_hpo(hpo_id):
+    """Retrieves associated genes for a given HPO ID."""
+    conn = sqlite3.connect(db_path)
+    cursor = conn.cursor()
+    cursor.execute("SELECT genes FROM hpo_gene WHERE hpo_id = ?", (hpo_id,))
+    result = cursor.fetchone()
+    conn.close()
+    return result[0].split(", ") if result else []
+
+
+def get_hpo_for_finding(finding, region):
+    """Finds the best HPO term and retrieves associated genes."""
+    hpo_match = find_best_hpo_match(finding, region)
+    if hpo_match:
+        hpo_match["genes"] = get_genes_for_hpo(hpo_match["hpo_id"])
+    else:
+        hpo_match = {"hpo_id": "NA", "hpo_term": "NA", "genes": []}
+    return hpo_match
+
+
+def hpo_mapper_ui(finding, region):
+    """Function for Gradio UI to get HPO mappings."""
+    if not finding or not region:
+        return "Please enter both finding and region.", "", ""
+    
+    result = get_hpo_for_finding(finding, region)
+    return result["hpo_id"], result["hpo_term"], ", ".join(result["genes"])
+
+# Create Gradio UI
+demo = gr.Interface(
+    fn=hpo_mapper_ui,
+    inputs=[gr.Textbox(label="Finding"), gr.Textbox(label="Region")],
+    outputs=[
+        gr.Textbox(label="HPO ID"),
+        gr.Textbox(label="HPO Term"),
+        gr.Textbox(label="Associated Genes")
+    ],
+    title="HPO Mapper",
+    description="Enter a clinical finding and anatomical region to get the best-matching HPO term and associated genes."
+)
+
+if __name__ == "__main__":
+    demo.launch()