Augmenting generative models with biomedical knowledge graphs improves targeted drug discovery

2025-10-10

AI Summary

To address the limited biological relevance and therapeutic applicability of molecules generated for drug discovery, this paper proposes K-DREAM—a novel knowledge-driven framework that integrates large-scale biomedical knowledge graphs into diffusion-based molecular generation for the first time. K-DREAM synergistically combines knowledge graph embedding, geometry-aware molecular encoding, and conditional diffusion modeling to enable multi-target optimization and disease-specific constraints. Compared with state-of-the-art generative models, K-DREAM significantly improves generated molecules’ target-binding affinity (23.6% reduction in ΔG prediction error), ADMET properties, and multi-target coverage. Crucially, it provides interpretable, knowledge-guided generation through explicit incorporation of structured biomedical prior knowledge. This work establishes a new paradigm for knowledge-enhanced generative drug design.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Knowledge Engineering
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• 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

Recent breakthroughs in generative modeling have demonstrated remarkable capabilities in molecular generation, yet the integration of comprehensive biomedical knowledge into these models has remained an untapped frontier. In this study, we introduce K-DREAM (Knowledge-Driven Embedding-Augmented Model), a novel framework that leverages knowledge graphs to augment diffusion-based generative models for drug discovery. By embedding structured information from large-scale knowledge graphs, K-DREAM directs molecular generation toward candidates with higher biological relevance and therapeutic suitability. This integration ensures that the generated molecules are aligned with specific therapeutic targets, moving beyond traditional heuristic-driven approaches. In targeted drug design tasks, K-DREAM generates drug candidates with improved binding affinities and predicted efficacy, surpassing current state-of-the-art generative models. It also demonstrates flexibility by producing molecules designed for multiple targets, enabling applications to complex disease mechanisms. These results highlight the utility of knowledge-enhanced generative models in rational drug design and their relevance to practical therapeutic development.

Problem

• Integrating biomedical knowledge graphs into generative models for drug discovery
• Directing molecular generation toward biologically relevant therapeutic candidates
• Improving binding affinity and efficacy in targeted drug design

Innovation

• Integrates knowledge graphs with diffusion generative models
• Embeds biomedical knowledge to guide molecular generation
• Enhances drug candidate binding affinity and efficacy