Zhong Huayu, Wang Juanji, Liu Xiaoxiao, Wei Xiaoyun, Zhou Chengcheng, Zou Taiyan, Han Xin, Mo Lingyun, Qin Wenling, Zhang Yonghong
College of Pharmacy, Chongqing Medical University, No. 1 Yixueyuan Road, Yuzhong District, Chongqing 400016, P. R. China.
Chongqing Engineering Research Center for Clinical Big Data and Drug Evaluation, Chongqing Medical University, No. 1 Yixueyuan Road, Yuzhong District, Chongqing 401331, P. R. China.
Brief Bioinform. 2025 Aug 31;26(5). doi: 10.1093/bib/bbaf456.
Drug-induced hepatotoxicity (DIH), characterized by diverse phenotypes and complex mechanisms, remains a critical challenge in drug discovery. To systematically decode this diversity and complexity, we propose a multi-dimensional computational framework integrating molecular structure analysis with disease pathogenesis exploration, focusing on drug-induced intrahepatic cholestasis (DIIC) as a representative DIH subtype. First, a graph-based modularity maximization algorithm identified DIIC risk genes, forming a DIIC module and eight disease pathogenesis clusters. Network proximity values between drug targets and DIIC clusters were calculated to define drug-disease relationships. Subsequently, a random forest model combining Mordred molecular descriptors, structural alerts (SAs), and network proximity achieved robust DIIC prediction: Accuracy(ACC) = 0.740 ± 0.014 and area under the curve (AUC) = 0.828 ± 0.008 (ntraining = 342, nvalidation = 114, nexternal test = 295, randomly modeling 100 times). Notably, a K-nearest neighbors-graph convolutional network classified drugs into 8 clusters, with the Cluster 3 model demonstrating superior performance (ACC = 0.810 ± 0.024; AUC = 0.890 ± 0.014; ntraining = 186, nvalidation = 63, nexternal test = 172). Mechanistic analysis linked critical SAs to DIIC pathogenesis: (i) Furan (SA3) perturbed cytochrome P450-mediated metabolism and regulation of lipid metabolism by PPARα; (ii) Nitrogen-sulfur heteroatom chains (SA7) disrupted metabolism of steroids; (iii) Phenylthio groups (SA12) and their CYP450 metabolites induced cholestasis. This multi-dimensional framework bridges molecular features and disease mechanisms, offering a generalizable strategy for toxicity prediction and pathway-centric drug safety evaluation, especial for complex disease.
药物性肝毒性（DIH）具有多种表型和复杂机制，仍然是药物研发中的一项严峻挑战。为了系统地解读这种多样性和复杂性，我们提出了一个多维计算框架，将分子结构分析与疾病发病机制探索相结合，重点关注药物性肝内胆汁淤积（DIIC）这一代表性的DIH亚型。首先，基于图的模块最大化算法识别出DIIC风险基因，形成一个DIIC模块和八个疾病发病机制簇。计算药物靶点与DIIC簇之间的网络接近值，以定义药物与疾病的关系。随后，结合Mordred分子描述符、结构警报（SA）和网络接近度的随机森林模型实现了可靠的DIIC预测：准确率（ACC）=0.740±0.014，曲线下面积（AUC）=0.828±0.008（训练集n=342，验证集n=114，外部测试集n=295，随机建模100次）。值得注意的是，一个K近邻-图卷积网络将药物分为8个簇，其中簇3模型表现出卓越的性能（ACC=0.810±0.024；AUC=0.890±0.014；训练集n=186，验证集n=63，外部测试集n=172）。机制分析将关键的SA与DIIC发病机制联系起来：（i）呋喃（SA3）扰乱细胞色素P450介导的代谢以及PPARα对脂质代谢的调节；（ii）氮-硫杂原子链（SA7）破坏类固醇的代谢；（iii）苯硫基（SA12）及其CYP450代谢产物诱导胆汁淤积。这个多维框架架起了分子特征与疾病机制之间的桥梁，为毒性预测和以通路为中心的药物安全性评估提供了一种可推广的策略，尤其适用于复杂疾病。
