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

TL;DR

DrugKLM is a hybrid framework combining biomedical knowledge graphs and large language models to improve therapeutic candidate prioritization with mechanistic insights and clinical relevance.

Contribution

It introduces DrugKLM, a novel approach that integrates knowledge graph structure with language model reasoning for biologically grounded drug repurposing.

Findings

DrugKLM outperforms knowledge graph-only and language model-only baselines.

Higher confidence scores correlate with transcriptional signatures linked to better survival.

The framework captures biologically perturbational signals rather than just historical indication patterns.

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.