College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China.
Lieber Institute, Johns Hopkins University, Baltimore, MD 21218, USA.
Biomolecules. 2024 Aug 5;14(8):946. doi: 10.3390/biom14080946.
The interaction between microbes and drugs encompasses the sourcing of pharmaceutical compounds, microbial drug degradation, the development of , and the impact of on host drug metabolism and immune modulation. These interactions significantly impact drug efficacy and the evolution of drug resistance. In this study, we propose a novel predictive model, termed GCGACNN. We first collected microbe, disease, and drug association data from multiple databases and the relevant literature to construct three association matrices and generate similarity feature matrices using Gaussian similarity functions. These association and similarity feature matrices were then input into a multi-layer Graph Neural Network for feature extraction, followed by a two-dimensional Convolutional Neural Network for feature fusion, ultimately establishing an effective predictive framework. Experimental results demonstrate that GCGACNN outperforms existing methods in predictive performance.
微生物与药物的相互作用包括药物化合物的来源、微生物对药物的降解、药物的发现以及药物对宿主药物代谢和免疫调节的影响。这些相互作用显著影响药物的疗效和耐药性的演变。在这项研究中，我们提出了一种新的预测模型，称为 GCGACNN。我们首先从多个数据库和相关文献中收集了微生物、疾病和药物的关联数据，构建了三个关联矩阵，并使用高斯相似性函数生成了相似性特征矩阵。然后，将这些关联和相似性特征矩阵输入到一个多层图神经网络中进行特征提取，接着是一个二维卷积神经网络进行特征融合，最终建立了一个有效的预测框架。实验结果表明，GCGACNN 在预测性能方面优于现有方法。
