Augmenting generative models with biomedical knowledge graphs improves targeted drug discovery

• URL: http://arxiv.org/abs/2510.09914v1
• Date: Fri, 10 Oct 2025 23:18:20 GMT
• Title: Augmenting generative models with biomedical knowledge graphs improves targeted drug discovery
• Authors: Aditya Malusare, Vineet Punyamoorty, Vaneet Aggarwal,
• Abstract summary: K-DREAM (Knowledge-Driven Embedding-Augmented Model) is a novel framework that leverages knowledge graphs to augment diffusion-based generative models for drug discovery.<n>By embedding structured information from large-scale knowledge graphs, K-DREAM directs molecular generation toward candidates with higher biological relevance and therapeutic suitability.<n>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.
• Score: 41.64418624570687
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• Diffusion Models for Molecules: A Survey of Methods and Tasks [56.44565051667812]
  Generative tasks about molecules are crucial for drug discovery and material design.<n>Diffusion models have emerged as an impressive class of deep generative models.<n>This paper conducts a comprehensive survey of diffusion model-based molecular generative methods.
  arXiv  Detail & Related papers  (2025-02-13T17:22:50Z)
• Large Language Models in Drug Discovery and Development: From Disease Mechanisms to Clinical Trials [49.19897427783105]
  The integration of Large Language Models (LLMs) into the drug discovery and development field marks a significant paradigm shift. We investigate how these advanced computational models can uncover target-disease linkage, interpret complex biomedical data, enhance drug molecule design, predict drug efficacy and safety profiles, and facilitate clinical trial processes.
  arXiv  Detail & Related papers  (2024-09-06T02:03:38Z)
• Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization [147.7899503829411]
  AliDiff is a novel framework to align pretrained target diffusion models with preferred functional properties. It can generate molecules with state-of-the-art binding energies with up to -7.07 Avg. Vina Score.
  arXiv  Detail & Related papers  (2024-07-01T06:10:29Z)
• Discovering intrinsic multi-compartment pharmacometric models using Physics Informed Neural Networks [0.0]
  We introduce PKINNs, a novel purely data-driven neural network model. PKINNs efficiently discovers and models intrinsic multi-compartment-based pharmacometric structures. The resulting models are both interpretable and explainable through Symbolic Regression methods.
  arXiv  Detail & Related papers  (2024-04-30T19:31:31Z)
• Latent Chemical Space Searching for Plug-in Multi-objective Molecule Generation [9.442146563809953]
  We develop a versatile 'plug-in' molecular generation model that incorporates objectives related to target affinity, drug-likeness, and synthesizability. We identify PSO-ENP as the optimal variant for multi-objective molecular generation and optimization.
  arXiv  Detail & Related papers  (2024-04-10T02:37:24Z)
• Improving Molecule Generation and Drug Discovery with a Knowledge-enhanced Generative Model [33.38582292895673]
  We develop a framework for knowledge-enhanced generative models called KARL. We extend the functionality of knowledge graphs while preserving semantic integrity, and incorporate this contextual information into a generative framework. KARL outperforms state-of-the-art generative models on both unconditional and targeted generation tasks.
  arXiv  Detail & Related papers  (2024-02-13T20:58:36Z)
• Tertiary Lymphoid Structures Generation through Graph-based Diffusion [54.37503714313661]
  In this work, we leverage state-of-the-art graph-based diffusion models to generate biologically meaningful cell-graphs. We show that the adopted graph diffusion model is able to accurately learn the distribution of cells in terms of their tertiary lymphoid structures (TLS) content.
  arXiv  Detail & Related papers  (2023-10-10T14:37:17Z)
• Energy-based Generative Models for Target-specific Drug Discovery [7.509129971169722]
  We develop an energy-based probabilistic model for computational target-specific drug discovery. Results show that our proposed TagMol can generate molecules with similar binding affinity scores as real molecules.
  arXiv  Detail & Related papers  (2022-12-05T16:41:36Z)
• Retrieval-based Controllable Molecule Generation [63.44583084888342]
  We propose a new retrieval-based framework for controllable molecule generation. We use a small set of molecules to steer the pre-trained generative model towards synthesizing molecules that satisfy the given design criteria. Our approach is agnostic to the choice of generative models and requires no task-specific fine-tuning.
  arXiv  Detail & Related papers  (2022-08-23T17:01:16Z)
• Visualizing Deep Graph Generative Models for Drug Discovery [16.78530326723672]
  We propose a visualization framework to visualize molecules generated during the encoding and decoding process of deep graph generative models. Our work tries to empower black box AI driven drug discovery models with some visual interpretabilities.
  arXiv  Detail & Related papers  (2020-07-20T18:49:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.