Sun Lu, Yin Zhixiang, Lu Lin
School of Mathematics, Physics and Statistics, Institute for Frontier Medical Technology, Center of Intelligent Computing and Applied Statistics, Shanghai University of Engineering Science, Shanghai, China.
Shanghai Xinhao Information Technology Co., Ltd., Shanghai, China.
PLoS One. 2025 Jan 30;20(1):e0302281. doi: 10.1371/journal.pone.0302281. eCollection 2025.
Machine learning techniques and computer-aided methods are now widely used in the pre-discovery tasks of drug discovery, effectively improving the efficiency of drug development and reducing the workload and cost. In this study, we used multi-source heterogeneous network information to build a network model, learn the network topology through multiple network diffusion algorithms, and obtain compressed low-dimensional feature vectors for predicting drug-target interactions (DTIs). We applied the metropolis-hasting random walk (MHRW) algorithm to improve the performance of the random walk with restart (RWR) algorithm, forming the basis by which the self-loop probability of the current node is removed. Additionally, the propagation efficiency of the MHRW was improved using the improved metropolis-hasting random walk (IMRWR) algorithm, facilitating network deep sampling. Finally, we proposed a correction of the transfer probability of the entire network after increasing the self-loop rate of isolated nodes to form the ISLRWR algorithm. Notably, the ISLRWR algorithm improved the area under the receiver operating characteristic curve (AUROC) by 7.53 and 5.72%, and the area under the precision-recall curve (AUPRC) by 5.95 and 4.19% compared to the RWR and MHRW algorithms, respectively, in predicting DTIs performance. Moreover, after excluding the interference of homologous proteins (popular drugs or targets may lead to inflated prediction results), the ISLRWR algorithm still showed a significant performance improvement.
机器学习技术和计算机辅助方法目前广泛应用于药物发现的前期探索任务中，有效提高了药物开发的效率，降低了工作量和成本。在本研究中，我们利用多源异构网络信息构建网络模型，通过多种网络扩散算法学习网络拓扑结构，并获得用于预测药物-靶点相互作用（DTIs）的压缩低维特征向量。我们应用 metropolis-hasting 随机游走（MHRW）算法来提高重启随机游走（RWR）算法的性能，形成去除当前节点自环概率的基础。此外，使用改进的 metropolis-hasting 随机游走（IMRWR）算法提高了 MHRW 的传播效率，促进了网络深度采样。最后，我们提出在提高孤立节点的自环率后对整个网络的转移概率进行校正，形成 ISLRWR 算法。值得注意的是，在预测 DTIs 性能方面，与 RWR 和 MHRW 算法相比，ISLRWR 算法分别将接收器操作特征曲线下面积（AUROC）提高了 7.53%和 5.72%，将精确召回率曲线下面积（AUPRC）提高了 5.95%和 4.19%。此外，在排除同源蛋白的干扰后（热门药物或靶点可能导致预测结果虚高），ISLRWR 算法仍表现出显著的性能提升。
