Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database

TL;DR

This paper presents the construction, federation, and AI agent access methods for large-scale open biomedical knowledge graphs built on the Samyama graph database, enabling efficient cross-source querying and high-accuracy LLM-based question answering.

Contribution

It introduces a reproducible ETL pattern for large-scale biomedical KGs, demonstrates cross-KG federation, and develops schema-driven MCP server tools for LLM access with high accuracy.

Findings

Federated graph loads in ~3 minutes on commodity hardware.

Single-KG queries complete in 80-100ms.

Cross-KG federation joins take 1-4 seconds.

Abstract

Biomedical knowledge is fragmented across siloed databases -- Reactome for pathways, STRING for protein interactions, ClinicalTrials.gov for study registries, DrugBank for drug vocabularies, DGIdb for drug-gene interactions, SIDER for side effects. We present three open-source biomedical knowledge graphs -- Pathways KG (118,686 nodes, 834,785 edges from 5 sources), Clinical Trials KG (7,774,446 nodes, 26,973,997 edges from 5 sources), and Drug Interactions KG (32,726 nodes, 191,970 edges from 3 sources) -- built on Samyama, a high-performance graph database written in Rust. Our contributions are threefold. First, we describe a reproducible ETL pattern for constructing large-scale KGs from heterogeneous public data sources, with cross-source deduplication, batch loading (Python Cypher and Rust native loaders), and portable snapshot export. Second, we demonstrate cross-KG federation: loading all three snapshots into a single graph tenant enables property-based joins across datasets. Third, we introduce schema-driven MCP server generation for LLM agent access, evaluated on a new BiomedQA benchmark (40 pharmacology questions): domain-specific MCP tools achieve 98% accuracy vs. 85% for schema-aware text-to-Cypher and 75% for standalone GPT-4o, with zero schema errors. All data sources are open-license. The combined federated graph (7.9M nodes, 28M edges) loads in approximately 3 minutes on commodity cloud hardware, with single-KG queries completing in 80-100ms and cross-KG federation joins in 1-4s