DTF-diffusion: A 3D equivariant diffusion generation model based on ligand-target information fusion.
Journal:
Computational biology and chemistry
Published Date:
Feb 22, 2025
Abstract
The goal of drug discovery based on deep learning is to generate drug molecules that bind to a given target protein. Recently, the use of three-dimensional molecular structures has shown superior performance over other two-dimensional structural models. However, most of the current depth generation models are based on ligands, and in the process of molecular generation, the models only learn the independent information of ligands or targets, without considering the complex interaction information of them. In addition, chemical knowledge was not considered in the process of molecular formation, which led to generation unreasonable drug molecular structure. In order to solve above problems, this paper proposes DTF-diffusion, a 3D equivariant diffusion generation model based on ligand-target information fusion. Firstly based on the diffusion model, DTF-diffusion uses multimodal feature fusion module proposed in this paper to fuse the three-dimensional position feature information of ligand molecules and targets, and extract advanced hidden features from ligand atom information and target sequence information. Secondly, this paper designs a chemical rule discrimination module, and learns the real ligand molecular structure and the characteristic information of the generated ligand molecules through the discriminator, and then capture the chemical rules in the drug molecular structure, which effectively improve the rationality of the ligand structure generated by the model. This paper evaluates the generation performance of DTF-diffusion and other baseline methods from multiple perspectives based on the CrossDocket2020 dataset. In the quantitative estimate of drug-likeness index, DTF-diffusion is 3.85 % higher than the existing optimal model, the drug validity index increased by 4.34 %. More generation experiments have proved that DTF-diffusion has excellent performance, indicating that it has a good application prospect in the field of drug molecule generation.
Authors
Keywords
No keywords available for this article.
