Augmenting generative models with biomedical knowledge graphs improves targeted drug discovery
This work addresses the challenge of generating biologically relevant drug candidates for targeted therapeutic development, representing a novel integration of knowledge graphs into generative models.
The study tackled the problem of integrating biomedical knowledge into generative models for drug discovery by introducing K-DREAM, a framework that uses knowledge graphs to direct molecular generation, resulting in improved binding affinities and predicted efficacy compared to state-of-the-art models.
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.