# Unifying biomedical knowledge in a modern multimodal graph

arXiv: https://arxiv.org/abs/2604.27269 · HTML: https://mlsanity.com/paper/2604.27269/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 93 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Builds on (most cited first, 19 of 19)

- [GraphGPT: Graph Instruction Tuning for Large Language Models](https://mlsanity.com/paper/2310.13023/) (2023)
- [Language agents achieve superhuman synthesis of scientific knowledge](https://mlsanity.com/paper/2409.13740/) (2024)
- [Learning to Drop: Robust Graph Neural Network via Topological Denoising](https://mlsanity.com/paper/2011.07057/) (2020)
- [Graph Neural Prompting with Large Language Models](https://mlsanity.com/paper/2309.15427/) (2023)
- [LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings](https://mlsanity.com/paper/2408.14512/) (2024)
- [Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning](https://mlsanity.com/paper/2410.14211/) (2024)
- [Can Graph Learning Improve Planning in LLM-based Agents?](https://mlsanity.com/paper/2405.19119/) (2024)
- [Building a PubMed knowledge graph](https://mlsanity.com/paper/2005.04308/) (2020)
- [A Review of Biomedical Datasets Relating to Drug Discovery: A Knowledge Graph Perspective](https://mlsanity.com/paper/2102.10062/) (2021)
- [COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation](https://mlsanity.com/paper/2007.00576/) (2020)
- [OpenBioLink: A benchmarking framework for large-scale biomedical link prediction](https://mlsanity.com/paper/1912.04616/) (2019)
- [Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing](https://mlsanity.com/paper/2007.10261/) (2020)
- [KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA](https://mlsanity.com/paper/2410.04660/) (2024)
- [Biolink Model: A Universal Schema for Knowledge Graphs in Clinical, Biomedical, and Translational Science](https://mlsanity.com/paper/2203.13906/) (2022)
- [Mining On Alzheimer's Diseases Related Knowledge Graph to Identity Potential AD-related Semantic Triples for Drug Repurposing](https://mlsanity.com/paper/2202.08712/) (2022)
- [CancerKG.ORG A Web-scale, Interactive, Verifiable Knowledge Graph-LLM Hybrid for Assisting with Optimal Cancer Treatment and Care](https://mlsanity.com/paper/2501.00223/) (2024)
- [RNA-KG: An ontology-based knowledge graph for representing interactions involving RNA molecules](https://mlsanity.com/paper/2312.00183/) (2023)
- [RNA-KG v2.0: An RNA-centered Knowledge Graph with Properties](https://mlsanity.com/paper/2508.07427/) (2025)
- [Reproducible Domain-Specific Knowledge Graphs in the Life Sciences: a Systematic Literature Review](https://mlsanity.com/paper/2309.08754/) (2023)

## Built on by (most cited first, 1 of 1)

- [Plausibility-Driven Prioritization of Candidate Biomedical Annotations](https://mlsanity.com/paper/2607.20163/) (2026)

## Abstract (arXiv)

Biomedical knowledge graphs (KGs) are widely used in the life sciences, yet many are derived from unstructured documents and therefore lack schema-level constraints, whereas graphs assembled from structured resources are difficult to harmonize into a unified representation. We present OptimusKG, a multimodal biomedical labeled property graph (LPG) built from structured and semi-structured resources to preserve factual, type-specific metadata across molecular, anatomical, clinical, and environmental domains. OptimusKG contains 190,939 nodes across 10 entity types, 21,818,752 edges across 27 edge types, and 67,070,490 property instances encoding 109,665,797 values across 145 distinct property keys, derived from 18 ontologies and controlled vocabularies. The graph enforces a top-level schema for nodes and edges and retains granular, type-specific properties, cross-references, and provenance. We assessed the validity of OptimusKG by evaluating whether graph relationships are supported by evidence from the scientific literature using a multimodal agent, PaperQA3. PaperQA3 identified supporting evidence for 70.0% of sampled edges, whereas 83.4% of sampled false edges received no supporting evidence. Edges without literature support were concentrated in associations derived from experimental and functional genomics resources, suggesting that OptimusKG captures biomedical knowledge that may precede synthesis in the scientific literature. OptimusKG is distributed as Apache Parquet files, providing a standardized resource for graph-based machine learning, knowledge-grounded retrieval with large language models, and biomedical discovery use cases such as hypothesis generation.