DrugReason: Dynamic Multi-View Reasoning over Knowledge Graph and Language Evidence for Drug Repurposing

Researchers proposed DrugReason, a multi-view reasoning framework that integrates knowledge graph-based reasoning with LLM-generated mechanistic inference for drug repurposing, according to an arXiv paper (arXiv:2609.06779v1). DrugReason adaptively routes reasoning paths to specialized experts based on query context and uses a cross-expert distillation objective to share knowledge while preserving expert specialization. Experiments on PharmaDB, DDInter, and DrugBank showed DrugReason improved average performance over strong single-view reasoning baselines and achieved competitive or superior results versus graph-based alternatives while providing interpretable routing-based predictions.

arXiv:2609.06779v1 Announce Type: cross Abstract: Drug repurposing aims to identify new therapeutic uses for existing compounds and, compared with de novo drug discovery, offers a faster and more cost-effective path to clinical translation. However, the space of candidate drug-disease pairs is enormous and their underlying relationships often depend on complex multi-hop biological mechanisms, making it difficult to reliably predict which pairs represent true therapeutic relationships. Existing approaches tackle this from two directions: knowledge graph-based methods organize curated biomedical evidence into structured relational networks for grounded multi-hop reasoning, while LLM-based methods leverage pretrained knowledge to generate flexible mechanistic rationales. Yet neither is sufficient alone - KGs are confined to observed graph structure while LLMs lack factual grounding and risk hallucination. To address this gap, we propose DrugReason, a multi-view reasoning framework that integrates grounded KG reasoning with LLM-generated mechanistic inference for drug repurposing. DrugReason adaptively routes diverse reasoning paths to specialized experts conditioned on the query context, while a cross-expert distillation objective enables knowledge sharing without sacrificing expert specialization. Experiments on PharmaDB, DDInter, and DrugBank show that DrugReason improves average performance over strong single-view reasoning baselines and achieves competitive or superior results compared with graph-based alternatives, while providing interpretable routing-based predictions.