Paper List
-
Translating Measures onto Mechanisms: The Cognitive Relevance of Higher-Order Information
This review addresses the core challenge of translating abstract higher-order information theory metrics (e.g., synergy, redundancy) into defensible, ...
-
Emergent Bayesian Behaviour and Optimal Cue Combination in LLMs
This paper addresses the critical gap in understanding whether LLMs spontaneously develop human-like Bayesian strategies for processing uncertain info...
-
Vessel Network Topology in Molecular Communication: Insights from Experiments and Theory
This work addresses the critical lack of experimentally validated channel models for molecular communication within complex vessel networks, which is ...
-
Modulation of DNA rheology by a transcription factor that forms aging microgels
This work addresses the fundamental question of how the transcription factor NANOG, essential for embryonic stem cell pluripotency, physically regulat...
-
Imperfect molecular detection renormalizes apparent kinetic rates in stochastic gene regulatory networks
This paper addresses the core challenge of distinguishing genuine stochastic dynamics of gene regulatory networks from artifacts introduced by imperfe...
-
PanFoMa: A Lightweight Foundation Model and Benchmark for Pan-Cancer
This paper addresses the dual challenge of achieving computational efficiency without sacrificing accuracy in whole-transcriptome single-cell represen...
-
Beyond Bayesian Inference: The Correlation Integral Likelihood Framework and Gradient Flow Methods for Deterministic Sampling
This paper addresses the core challenge of calibrating complex biological models (e.g., PDEs, agent-based models) with incomplete, noisy, or heterogen...
-
Contrastive Deep Learning for Variant Detection in Wastewater Genomic Sequencing
This paper addresses the core challenge of detecting viral variants in wastewater sequencing data without reference genomes or labeled annotations, ov...
Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database
VaidhyaMegha Private Limited, India
30秒速读
IN SHORT: This paper addresses the core pain point of fragmented biomedical data by constructing and federating large-scale, open knowledge graphs to enable seamless cross-domain queries and natural language access via AI agents.
核心创新
- Methodology A reproducible ETL pattern for constructing large-scale biomedical KGs from heterogeneous public sources, featuring cross-source deduplication, batch loading, and portable snapshot export.
- Methodology Demonstration of cross-KG federation via property-based joins, enabling queries that traverse multiple independent knowledge graphs (e.g., from clinical trials to biological pathways).
- Methodology Schema-driven MCP server generation that automatically exposes typed tools for LLM agents, achieving 98% accuracy on a new BiomedQA benchmark, significantly outperforming text-to-Cypher (0%) and standalone GPT-4o (75%).
主要结论
- The federated graph (7.9M nodes, 28M edges) loads in approximately 3 minutes on commodity hardware (AWS g4dn.4xlarge, 62 GB RAM), with cross-KG queries completing in 80 ms–4 s.
- Schema-driven MCP tools achieve 98% accuracy (39/40) on the BiomedQA benchmark, dramatically outperforming text-to-Cypher (0%) and standalone GPT-4o (75%).
- A Rust native loader constructs the Drug Interactions KG (32,726 nodes, 191,970 edges) in under 1 second, demonstrating orders-of-magnitude performance improvement over Python HTTP-based ETL.
摘要: Biomedical knowledge is fragmented across siloed databases—Reactome for pathways, STRING for protein interactions, Gene Ontology for functional annotations, ClinicalTrials.gov for study registries, DrugBank for drug vocabularies, DGIdb for drug–gene interactions, SIDER for side effects, and dozens more. Researchers routinely download flat files from each source and write bespoke scripts to cross-reference them, a process that is slow, error-prone, and not reproducible. 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 (both 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, answering questions like “For drugs indicated for diabetes, what are their gene targets and which biological pathways do those targets participate in?”—a query that no single KG can answer alone. Third, we introduce schema-driven MCP server generation: each KG automatically exposes typed tools for LLM agents via the Model Context Protocol, enabling natural-language access to graph queries. We evaluate domain-specific MCP tools against text-to-Cypher and standalone GPT-4o on a new BiomedQA benchmark (40 pharmacology questions), achieving 98% accuracy vs. 0% for text-to-Cypher and 75% for standalone GPT-4o. All data sources are open-license (CC BY 4.0, CC0, OBO, public domain). Snapshots, ETL code, and MCP configurations are publicly available. The combined federated graph (7.9M nodes, 28M edges) loads in approximately 3 minutes from portable snapshots on commodity cloud hardware (AWS g4dn.4xlarge, 62 GB RAM), and cross-KG queries complete in 80 ms–4 s.