Kang Yanlei, Xia Qiwei, Jiang Yunliang, Li Zhong
Zhejiang Province Key Laboratory of Smart Management & Application of Modern Agricultural Re-sources, School of Information Engineering, Huzhou University, Huzhou 313000, Zhejiang Province,China.
School of Computer Science and Technology, Zhejiang Normal University, Jinhua 321004, Zhejiang Province, China.
ACS Omega. 2024 Oct 30;9(45):45159-45168. doi: 10.1021/acsomega.4c06224. eCollection 2024 Nov 12.
PI3K (phosphatidylinositol 3-kinase) is an intracellular phosphatidylinositol kinase composed of a regulatory subunit, p85, and a catalytic subunit, p110. Based on the different structures of the p110 catalytic subunit, PI3K can be divided into four isoforms: PI3Kα, PI3Kβ, PI3Kγ, and PI3Kδ. As molecularly targeted drugs, PI3K inhibitors have demonstrated antiproliferative effects on tumor cells and can also induce cancer cell death. In this study, a multiview deep learning framework (MVGNet) is proposed, which integrates fragment-based pharmacophore information and utilizes multitask learning to capture correlation information between subtasks. This framework predicts the inhibitory activity of molecules against the four PI3K isoforms (PI3Kα, PI3Kβ, PI3Kγ, and PI3Kδ). Compared to baseline prediction models based on three traditional machine learning methods (RF, SVM, and XGBoost) and four deep learning algorithms (GAT, D-MPNN, CMPNN, and KANO), our model demonstrates superior performance. The evaluation results show that our model achieves the highest average AUC-ROC and AUC-PR values on the test set, which are 0.927 ± 0.006 and 0.980 ± 0.002, respectively. This study provides a reference for exploring the structure-activity relationship of PI3K inhibitors.
磷脂酰肌醇3-激酶（PI3K）是一种细胞内磷脂酰肌醇激酶，由一个调节亚基p85和一个催化亚基p110组成。根据p110催化亚基的不同结构，PI3K可分为四种亚型：PI3Kα、PI3Kβ、PI3Kγ和PI3Kδ。作为分子靶向药物，PI3K抑制剂已显示出对肿瘤细胞的抗增殖作用，还可诱导癌细胞死亡。在本研究中，提出了一种多视图深度学习框架（MVGNet），该框架整合了基于片段的药效团信息，并利用多任务学习来捕获子任务之间的相关信息。该框架预测分子对四种PI3K亚型（PI3Kα、PI3Kβ、PI3Kγ和PI3Kδ）的抑制活性。与基于三种传统机器学习方法（随机森林、支持向量机和极端梯度提升）和四种深度学习算法（图注意力网络、深度消息传递神经网络、比较消息传递神经网络和卡诺网络）的基线预测模型相比，我们的模型表现出更优的性能。评估结果表明，我们的模型在测试集上实现了最高的平均AUC-ROC和AUC-PR值，分别为0.927±0.006和0.980±0.002。本研究为探索PI3K抑制剂的构效关系提供了参考。
