Zhao Yanpeng, Xing Yuting, Zhang Yixin, Wang Yifei, Wan Mengxuan, Yi Duoyun, Wu Chengkun, Li Shangze, Xu Huiyan, Zhang Hongyang, Liu Ziyi, Zhou Guowei, Li Mengfan, Wang Xuanze, Chen Zhengshan, Li Ruijiang, Wu Lianlian, Zhao Dongsheng, Zan Peng, He Song, Bo Xiaochen
Academy of Military Medical Sciences, Beijing, China.
School of Medicine, Shanghai University, Shanghai, China.
Nat Commun. 2025 Jul 26;16(1):6915. doi: 10.1038/s41467-025-62235-6.
Drug-target interaction (DTI) prediction is a crucial component of drug discovery. Recent deep learning methods show great potential in this field but also encounter substantial challenges. These include generating reliable confidence estimates for predictions, enhancing robustness when handling novel, unseen DTIs, and mitigating the tendency toward overconfident and incorrect predictions. To solve these problems, we propose EviDTI, a novel approach utilizing evidential deep learning (EDL) for uncertainty quantification in neural network-based DTI prediction. EviDTI integrates multiple data dimensions, including drug 2D topological graphs and 3D spatial structures, and target sequence features. Through EDL, EviDTI provides uncertainty estimates for its predictions. Experimental results on three benchmark datasets demonstrate the competitiveness of EviDTI against 11 baseline models. In addition, our study shows that EviDTI can calibrate prediction errors. More importantly, well-calibrated uncertainty information enhances the efficiency of drug discovery by prioritizing DTIs with higher confident predictions for experimental validation. In a case study focused on tyrosine kinase modulators, uncertainty-guided predictions identify novel potential modulators targeting tyrosine kinase FAK and FLT3. These results underscore the potential of evidential deep learning as a robust tool for uncertainty quantification in DTI prediction and its broader implications for accelerating drug discovery.
药物-靶点相互作用(DTI)预测是药物发现的关键组成部分。最近的深度学习方法在该领域显示出巨大潜力,但也面临着重大挑战。这些挑战包括为预测生成可靠的置信度估计、在处理新的、未见的DTI时增强鲁棒性,以及减轻过度自信和错误预测的倾向。为了解决这些问题,我们提出了EviDTI,这是一种利用证据深度学习(EDL)在基于神经网络的DTI预测中进行不确定性量化的新方法。EviDTI整合了多个数据维度,包括药物二维拓扑图和三维空间结构以及靶点序列特征。通过EDL,EviDTI为其预测提供不确定性估计。在三个基准数据集上的实验结果证明了EviDTI相对于11个基线模型的竞争力。此外,我们的研究表明EviDTI可以校准预测误差。更重要的是,经过良好校准的不确定性信息通过优先选择具有更高置信度预测的DTI进行实验验证,提高了药物发现的效率。在一项针对酪氨酸激酶调节剂的案例研究中,不确定性引导的预测识别出了针对酪氨酸激酶FAK和FLT3的新型潜在调节剂。这些结果强调了证据深度学习作为DTI预测中不确定性量化的强大工具的潜力及其对加速药物发现的更广泛意义。