Wang Bo, He Yang, Du Xiaoxin, Zhu Lei, Wang Junqi, Wang Tongxuan
School of Computer and Control Engineering, Qiqihar University, Qiqihar 161006, China; Qiqihar University Heilongjiang Key Laboratory of Big Data Network Security Detection and Analysis, Qiqihar 161006, China.
School of Computer and Control Engineering, Qiqihar University, Qiqihar 161006, China.
Artif Intell Med. 2025 Sep;167:103198. doi: 10.1016/j.artmed.2025.103198. Epub 2025 Jun 16.
Traditional biological experimental methods typically require weeks or even months of experimentation, and the cost of each experiment can reach hundreds or even thousands of dollars, which is quite expensive and time-consuming. To address this, a model called VAE-GANMDA, which integrates variational autoencoders (VAE) and generative adversarial networks (GAN) for predicting microbe-drug associations, has been proposed. Firstly, a heterogeneous network of microbes and drugs is established to enrich the association information. Secondly, by fusing VAE and GAN, the model learns the manifold distribution of data through association features, obtaining nonlinear manifold features. Furthermore, the VAE generation module is improved by integrating the Convolutional Block Attention Module (CBAM) and Gaussian kernel function, enhancing the smooth perception of manifold features, thus endowing VAE with stronger feature extraction capabilities. Then, singular value decomposition (SVD) technique is employed to extract linear features of the data. Finally, by combining linear and nonlinear features, the k-means++ algorithm is used to select balanced and high-quality negative samples for training the MLP classifier. Through performance evaluation, the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC) of VAE-GANMDA reach 0.9724 and 0.9635 respectively, outperforming classical machine learning methods and the majority of deep learning methods. Case studies demonstrate that VAE-GANMDA accurately predicts candidate drugs related to SARS-CoV-2 and candidate microbes related to ciprofloxacin.
传统的生物学实验方法通常需要数周甚至数月的实验时间，而且每次实验的成本可达数百甚至数千美元，成本高昂且耗时。为了解决这个问题，人们提出了一种名为VAE-GANMDA的模型，该模型集成了变分自编码器（VAE）和生成对抗网络（GAN）来预测微生物-药物关联。首先，建立微生物和药物的异质网络以丰富关联信息。其次，通过融合VAE和GAN，该模型通过关联特征学习数据的流形分布，获得非线性流形特征。此外，通过集成卷积块注意力模块（CBAM）和高斯核函数对VAE生成模块进行改进，增强对流形特征的平滑感知，从而赋予VAE更强的特征提取能力。然后，采用奇异值分解（SVD）技术提取数据的线性特征。最后，通过结合线性和非线性特征，使用k均值++算法选择平衡且高质量的负样本用于训练MLP分类器。通过性能评估，VAE-GANMDA的受试者工作特征曲线下面积（AUROC）和精确率-召回率曲线下面积（AUPRC）分别达到0.9724和0.9635，优于经典机器学习方法和大多数深度学习方法。案例研究表明，VAE-GANMDA能够准确预测与SARS-CoV-2相关的候选药物以及与环丙沙星相关的候选微生物。
