利用深度迁移学习靶向GPCRs的配体活性预测  

Predicting Bioactivities of Ligands Acting with G Protein-Coupled Receptors via Deep Transfer Learning

作　　者：汤丽华[1] 卢宁 兰闯闯 陈荣华[3] 吴建盛[1] TANG Lihua;LU Ning;LAN Chuangchuang;CHEN Ronghua;WU Jiansheng(School of Geographic and Biological Information,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;School of Telecommunications and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Department of Neurosurgery,the First People’s Hospital of Changzhou,Changzhou,Jiangsu 213003,China)

机构地区：[1]南京邮电大学地理与生物信息学院,南京210023 [2]南京邮电大学通信与信息工程学院,南京210023 [3]常州市第一人民医院神经外科,江苏常州213003

出　　处：《计算机工程与应用》2023年第13期120-128,共9页Computer Engineering and Applications

基　　金：国家自然科学基金(61872198,61971216,81771478,81973512);江苏省科技厅基础研究计划(自然科学基金)面上项目(BK20201378)。

摘　　要：G蛋白偶联受体(GPCRs)是最重要的药物靶标之一,约占市场上药物靶标的34%。药物发现过程中,配体生物活性的准确建模和解释对于筛选苗头化合物至关重要。研究表明,同源的G蛋白偶联受体能提升配体分子生物活性的预测性能和可解释性。提出了一种新的方法GLEM,用多任务下的深度迁移学习来预测配体的生物活性,并通过组稀疏来识别相关的关键子结构。GLEM方法在9组30个具有代表性的人类GPCR数据集上进行了实验,这些GPCRs涵盖了大部分人类GPCRs的子家族,每个GPCR数据集都包含60~3000个配体。实验结果表明,GLEM方法在绝大多数数据集中都获得了最好的性能。与单任务学习方法相比,GLEM方法在r2上平均提升了31.72%;与深度学习方法相比,GLEM方法在r2上平均提升了22.45%。此外,还评估了不同数量的训练样本对模型性能的影响,实验发现GLEM方法在小样本情况下表现最好。G protein coupled receptors(GPCRs)are among the most important drug targets,accounting for approximately 34%of drug targets on the market.Accurate modelling and interpretation of bioactivities of ligands are essential for screening hit compounds for GPCR targets in modern drug discovery.Previous studies demonstrate that homologous G protein-coupled receptors can boost the modelling and interpretation of bioactivities of ligand molecules.A new method called GLEM is proposed to model bioactivities of ligands via multi-task deep transfer learning and identify key substructures via group sparse learning by relied homologous information.The GLEM method is tested on 9 groups with 30 representative GPCR datasets which cover most subfamilies of human GPCRs,each with 60~3000 ligand associations.The results show that the GLEM method performs best on most datasets,where it obtains an average improvement of 31.72%on r2 over single-task learning methods,and an average improvement of 22.45%on r2 against deep learning methods.In addition,the influence of the size of training samples on model performance is evaluated and shows that the GLEM method performs best in most small-sized datasets.

关 键 词：G蛋白偶联受体(GPCRs) 扩展连通性指纹 配体活性 多任务学习 深度迁移学习 

分 类 号：TP315.69[自动化与计算机技术—计算机软件与理论]