updated node titles to contain node name instead of id

visualize_kg.py

@@ -1,5 +1,7 @@
 from pyvis.network import Network
 import os
+import json
+import gzip
 
 NODE_TYPE_COLORS = {
  'Disease': '#079dbb',
@@ -48,6 +50,40 @@ GO_CATEGORY_MAPPING = {
     'Cellular Component': 'GO_term_C'
 }
 
+def get_node_url(node_type, node_id):
+    """Get the URL for a node based on its type and ID"""
+    if node_type.startswith('GO_term'):
+        return f"https://www.ebi.ac.uk/QuickGO/term/{node_id}"
+    elif node_type == 'Protein':
+        return f"https://www.uniprot.org/uniprotkb/{node_id}/entry"
+    elif node_type == 'Disease':
+        if ':' in node_id:
+            ontology = node_id.split(':')[0]
+            if ontology == 'EFO':
+                return f"http://www.ebi.ac.uk/efo/EFO_{node_id.split(':')[1]}"
+            elif ontology == 'MONDO':
+                return f'http://purl.obolibrary.org/obo/MONDO_{node_id.split(":")[1]}'
+            elif ontology == 'Orphanet':
+                return f"http://www.orpha.net/ORDO/Orphanet_{node_id.split(':')[1]}"
+        else:
+            return f"https://www.genome.jp/entry/{node_id}"
+    elif node_type == 'HPO':
+        return f"https://hpo.jax.org/browse/term/{node_id}"
+    elif node_type == 'Drug':
+        return f"https://go.drugbank.com/drugs/{node_id}"
+    elif node_type == 'Compound':
+        return f"https://www.ebi.ac.uk/chembl/explore/compound/{node_id}"
+    elif node_type == 'Domain':
+        return f"https://www.ebi.ac.uk/interpro/entry/InterPro/{node_id}"
+    elif node_type == 'Pathway':
+        return f"https://reactome.org/content/detail/{node_id}"
+    elif node_type == 'kegg_Pathway':
+        return f"https://www.genome.jp/pathway/{node_id}"
+    elif node_type == 'EC_number':
+        return f"https://enzyme.expasy.org/EC/{node_id}"
+    else:
+        return None
+
 def _gather_protein_edges(data, protein_id):
 
     protein_idx = data['Protein']['id_mapping'][protein_id]
@@ -134,6 +170,10 @@ def _filter_edges(protein_id, protein_edges, prediction_df, limit=10):
 
 
 def visualize_protein_subgraph(data, protein_id, prediction_df, limit=10):
+
+    with gzip.open('data/name_info.json.gz', 'rt', encoding='utf-8') as file:
+        name_info = json.load(file)
+
     protein_edges = _gather_protein_edges(data, protein_id)
     visualized_edges = _filter_edges(protein_id, protein_edges, prediction_df, limit)
     print(f'Edges to be visualized: {visualized_edges}')
@@ -148,7 +188,6 @@ def visualize_protein_subgraph(data, protein_id, prediction_df, limit=10):
             }
 
     # Convert groups_config to a JSON-compatible string
-    import json
     groups_json = json.dumps(groups_config)
 
     # Configure physics options with settings for better clustering
@@ -196,8 +235,15 @@ def visualize_protein_subgraph(data, protein_id, prediction_df, limit=10):
         "groups": """ + groups_json + "}")
 
     # Add the main protein node
+    query_node_url = get_node_url('Protein', protein_id)
+    node_name = name_info['Protein'][protein_id]
+    query_node_title = f"{node_name} (Query Protein)"
+    if query_node_url:
+        query_node_title = f'<a href="{query_node_url}" target="_blank">{query_node_title}</a>'
+
     net.add_node(protein_id, 
-                 label=f"{protein_id} (Protein)", 
+                 label=protein_id, 
+                 title=query_node_title,
                  color={'background': 'white', 'border': '#c1121f'},
                  borderWidth=4,
                  shape="dot", 
@@ -226,11 +272,19 @@ def visualize_protein_subgraph(data, protein_id, prediction_df, limit=10):
 
             # Add source node if not present
             if source_str not in added_nodes:
+                if not source_type.startswith('GO_term'):
+                    node_name = name_info[source_type][source_str]
+                else:
+                    node_name = name_info['GO_term'][source_str]
+                url = get_node_url(source_type, source_str)
+                title = f"{node_name} ({NODE_LABEL_TRANSLATION[source_type] if source_type in NODE_LABEL_TRANSLATION else source_type})"
+                if url:
+                    title = f'<a href="{url}" target="_blank">{title}</a>'
                 net.add_node(source_str, 
-                           label= source_str,
+                           label=source_str,
                            shape="dot", 
                            font={'color': '#000000', 'size': 12},
-                           title=f"{source_str} ({NODE_LABEL_TRANSLATION[source_type] if source_type in NODE_LABEL_TRANSLATION else source_type})",
+                           title=title,
                            group=source_type,
                            size=15,
                            mass=1.5)
@@ -238,16 +292,23 @@ def visualize_protein_subgraph(data, protein_id, prediction_df, limit=10):
 
             # Add target node if not present
             if target_str not in added_nodes:
+                if not target_type.startswith('GO_term'):
+                    node_name = name_info[target_type][target_str]
+                else:
+                    node_name = name_info['GO_term'][target_str]
+                url = get_node_url(target_type, target_str)
+                title = f"{node_name} ({NODE_LABEL_TRANSLATION[target_type] if target_type in NODE_LABEL_TRANSLATION else target_type})"
+                if url:
+                    title = f'<a href="{url}" target="_blank">{title}</a>'
                 net.add_node(target_str, 
-                           label= target_str,
+                           label=target_str,
                            shape="dot", 
                            font={'color': '#000000', 'size': 12},
-                           title=f"{target_str} ({NODE_LABEL_TRANSLATION[target_type] if target_type in NODE_LABEL_TRANSLATION else target_type})",
+                           title=title,
                            group=target_type,
                            size=15,
                            mass=1.5)
                 added_nodes.add(target_str)
-
             # Add edge with relationship type and probability as label
             edge_label = f"{relation_type}"
             if probability is not None: