Department of Computer Science, Hong Kong Baptist University, Kowloon, 999077, Hong Kong.
Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong (Shenzhen), 518172, China.
Bioinformatics. 2024 May 2;40(5). doi: 10.1093/bioinformatics/btae308.
Enhanced by contemporary computational advances, the prediction of drug-target interactions (DTIs) has become crucial in developing de novo and effective drugs. Existing deep learning approaches to DTI prediction are frequently beleaguered by a tendency to overfit specific molecular representations, which significantly impedes their predictive reliability and utility in novel drug discovery contexts. Furthermore, existing DTI networks often disregard the molecular size variance between macro molecules (targets) and micro molecules (drugs) by treating them at an equivalent scale that undermines the accurate elucidation of their interaction.
We propose a novel DTI network with a differential-scale scheme to model the binding site for enhancing DTI prediction, which is named as BindingSiteDTI. It explicitly extracts multiscale substructures from targets with different scales of molecular size and fixed-scale substructures from drugs, facilitating the identification of structurally similar substructural tokens, and models the concealed relationships at the substructural level to construct interaction feature. Experiments conducted on popular benchmarks, including DUD-E, human, and BindingDB, shown that BindingSiteDTI contains significant improvements compared with recent DTI prediction methods.
The source code of BindingSiteDTI can be accessed at https://github.com/MagicPF/BindingSiteDTI.
受当代计算技术进步的推动，药物-靶标相互作用（DTI）的预测在开发全新有效药物方面变得至关重要。现有的深度学习方法在预测 DTI 时经常受到特定分子表示过度拟合的倾向的困扰，这极大地阻碍了它们在新的药物发现环境中的预测可靠性和实用性。此外，现有的 DTI 网络经常忽略宏观分子（靶标）和微观分子（药物）之间的分子大小差异，将它们以相同的尺度处理，从而破坏了对它们相互作用的准确阐明。
我们提出了一种新的 DTI 网络，具有差分尺度方案，用于建模结合位点，以增强 DTI 预测，该网络名为 BindingSiteDTI。它从具有不同分子大小尺度的靶标中显式地提取多尺度子结构，并从药物中提取固定尺度子结构，有助于识别结构相似的子结构标记，并在子结构水平上建模隐藏的关系，以构建相互作用特征。在流行的基准上进行的实验，包括 DUD-E、人类和 BindingDB，表明与最近的 DTI 预测方法相比，BindingSiteDTI 有显著的改进。
BindingSiteDTI 的源代码可以在 https://github.com/MagicPF/BindingSiteDTI 上获得。
