Paper 5: Federated Biomedical Knowledge Graphs — GRADES-NDA @ SIGMOD 2026

Title: [Demo] Federated Biomedical Knowledge Graphs: Graph-Native Storage, Planning, and AI-Agent Integration

Venue: GRADES-NDA Workshop at SIGMOD 2026, Bengaluru, India (June 5, 2026)

Status: Submitted (CMT3 Paper #23, 2026-03-16). Notification: April 13, 2026.

Authors: Madhulatha Mandarapu, Sandeep Kunkunuru

Summary

Demo paper showing three federated biomedical knowledge graphs (Pathways, Clinical Trials, Drug Interactions) queryable through a single Cypher interface. Demonstrates graph-native query planning (ADR-015), cross-KG federation via shared property bridges, and MCP tool integration for AI agent access.

Key Results

• 3 KGs federated: 7.9M nodes, 28M edges
• BiomedQA: MCP 98%, Text-to-Cypher 85%, GPT-4o standalone 75%
• Graph-native planner: up to 64 candidate plans per query, cost-based selection

Files

• LaTeX: research/arxiv/paper5_grades_nda_2026.tex
• PDF: research/arxiv/paper5_grades_nda_2026.pdf
• Author version: research/arxiv/paper5_grades_nda_2026_authors.pdf