He Mingxiu, Shi Yiyang, Han Fangfang, Cai Yongming
College of Medical Information and Engineering, Guangdong Pharmaceutical University, Guangzhou, China.
Department of Information, Guangdong Provincial Key Laboratory of Major Obstetric Diseases, Guangdong Provincial Clinical Research Center for Obstetrics and Gynecology, The Third Affiliated Hospital, Guangzhou Medical University, Guangzhou, China.
Front Pharmacol. 2025 Mar 10;16:1448106. doi: 10.3389/fphar.2025.1448106. eCollection 2025.
Adverse Drug Reactions (ADRs), a widespread phenomenon in clinical drug treatment, are often associated with a high risk of morbidity and even death. Drugs and changes in gene expression are the two important factors that affect whether and how adverse reactions occur. Notably, pharmacogenomics data have recently become more available and could be used to predict ADR occurrence. However, there is a challenge in effectively analyzing the massive data lacking guidance on mutual relationship for ADRs prediction.
We constructed separate similarity features for drugs and ADRs using pharmacogenomics data from the Comparative Toxicogenomics Database [CTD, including Chemical-Gene Interactions (CGIs) and Gene-Disease Associations (GDAs)]. We proposed a novel deep learning architecture, DGANet, based on the constructed features for ADR prediction. The algorithm uses Convolutional Neural Networks (CNN) and cross-features to learn the latent drug-gene-ADR associations for ADRs prediction.
The performance of DGANet was compared to three state-of-the-art algorithms with different genomic features. According to the results, GDANet outperformed the benchmark algorithms (AUROC = 92.76%, AUPRC = 92.49%), demonstrating a 3.36% AUROC and 4.05% accuracy improvement over the cutting-edge algorithms. We further proposed new genomic features that improved DGANet's predictive capability. Moreover, case studies on top-ranked candidates confirmed DGANet's ability to predict new ADRs.
药物不良反应（ADR）是临床药物治疗中普遍存在的现象，通常与高发病率甚至死亡风险相关。药物和基因表达变化是影响不良反应是否发生以及如何发生的两个重要因素。值得注意的是，药物基因组学数据最近变得更加容易获取，可用于预测ADR的发生。然而，在有效分析大量缺乏ADR预测相互关系指导的数据方面存在挑战。
我们利用来自比较毒理基因组学数据库[CTD，包括化学-基因相互作用（CGI）和基因-疾病关联（GDA）]的药物基因组学数据，为药物和ADR构建了单独的相似性特征。我们基于构建的特征提出了一种用于ADR预测的新型深度学习架构DGANet。该算法使用卷积神经网络（CNN）和交叉特征来学习潜在的药物-基因-ADR关联以进行ADR预测。
将DGANet的性能与三种具有不同基因组特征的先进算法进行了比较。结果显示，DGANet优于基准算法（AUROC = 92.76%，AUPRC = 92.49%），与前沿算法相比，AUROC提高了3.36%，准确率提高了4.05%。我们进一步提出了新的基因组特征，提高了DGANet的预测能力。此外，对排名靠前的候选药物的案例研究证实了DGANet预测新ADR的能力。
