Large Language Models Meet Biomedical Knowledge Graphs for Mechanistically Grounded Therapeutic Prioritization

2026-04-17

AI Summary

This study addresses the limitation of existing drug repositioning approaches, which often struggle to distinguish biologically plausible candidates due to their reliance on historical associations. To overcome this, the authors propose DrugKLM, a novel hybrid framework that uniquely integrates the structural knowledge from knowledge graphs with the mechanistic reasoning capabilities of large language models. By combining knowledge graph embeddings, transcriptomic phenotype alignment, and expert-informed clinical context, DrugKLM generates interpretable and clinically relevant therapeutic hypotheses. The method consistently outperforms approaches based solely on knowledge graphs or language models across multiple benchmarks. Its confidence scores show significant concordance with survival-associated transcriptional signatures across 12 TCGA cancer types, and expert evaluation confirms that DrugKLM prioritizes mechanistically sound and clinically promising candidate drugs in five distinct cancers.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Knowledge Representation and Reasoning: Knowledge Representation Languages

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Drug repurposing is often framed as a candidate identification task, but existing approaches provide limited guidance for distinguishing biologically plausible candidates from historically well-connected ones. Here we introduce DrugKLM, a hybrid framework that integrates biomedical knowledge graph structure with large language model-based mechanistic reasoning to enable mechanistically grounded therapeutic prioritization. Across benchmark datasets, DrugKLM outperforms knowledge graph-only and language model-only baselines, including TxGNN. Beyond improved recall, DrugKLM confidence scores exhibit functional alignment with molecular phenotypes: higher scores are associated with transcriptional signatures linked to improved survival across 12 TCGA cancers. The scoring framework preferentially captures biologically perturbational signals rather than historical indication patterns. Expert curation across five cancers further reveals systematic differences in prioritization behavior, with DrugKLM elevating candidates supported by coherent mechanistic rationale and disease-specific clinical context. Together, these results establish DrugKLM as an evidence-integrative framework that translates heterogeneous biomedical data into mechanistically interpretable and clinically grounded therapeutic hypotheses.

Problem

• drug repurposing
• biomedical knowledge graphs
• mechanistic reasoning
• therapeutic prioritization
• biological plausibility

Innovation

• Drug Repurposing
• Knowledge Graph
• Large Language Model
• Mechanistic Reasoning
• Therapeutic Prioritization