整合五大生物医学数据库，构建可快速查询的开放知识图谱。
Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database
- 用统一流程从多个公开数据源抽取、去重并加载到图数据库中。
- 三张知识图谱共790万节点2800万边，跨图关联查询仅需1-4秒。
- 支持大模型智能问答，准确率达98%，零错误且无需人工标注schema。
生物医学知识分散在多个孤立数据库中：Reactome（通路）、STRING（蛋白互作）、ClinicalTrials.gov（临床试验注册）、DrugBank（药物术语）、DGIdb（药物-基因互作）、SIDER（不良反应）。我们基于Rust编写的高性能图数据库Samyama，构建了三个开源生物医学知识图谱：通路知识图谱（118,686个节点，834,785条边，来自5个来源）、临床试验知识图谱（7,774,446个节点，26,973,997条边，来自5个来源）、药物互作知识图谱（32,726个节点，191,970条边，来自3个来源）。贡献有三：第一，提出可复现的ETL流程，实现异构数据源的跨源去重、批处理加载（Python Cypher与Rust原生加载器）及可移植快照导出；第二，实现跨知识图谱联邦：将三个快照加载至同一图租户，支持属性级跨数据集连接；第三，引入基于模式的MCP服务器生成，用于大模型代理访问，在新提出的BiomedQA基准（40道药理学问题）上，领域专用MCP工具准确率达98%，高于模式感知文本转Cypher的85%和独立GPT-4o的75%，且无模式错误。所有数据源均为开源许可。合并后的联邦图谱（约790万节点，2800万边）在普通云硬件上约3分钟完成加载，单图查询耗时80-100毫秒，跨图联接查询耗时1-4秒。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。