摘要
蛋白质-配体的结合亲和力预测是药物重定位回归中具有挑战性的任务。深度学习方法可以有效预测蛋白质与配体相互作用的结合亲和力,减少药物发现的时间和成本。由此,基于长短期记忆模块(LSTM)和注意力机制模块(attention)提出了一种深度卷积神经网络模型(DLLSA)。模型由嵌入LSTM和空间注意力模块(spatial-attention)的卷积网络并行模块构建,其中LSTM模块针对蛋白质-配体接触特征的长序列信息,spatial-attention注意力模块聚集接触特征局部信息。采用PDBbind(v.2020)数据集进行训练,CASF-2013和CASF-2016数据集进行验证,模型的皮尔逊相关系数相比于PLEC模型分别提高了0.6%和3%,实验结果显著优于其他相关方法。
Protein-ligand binding affinity prediction is a challenging task in drug repositioning regression.Deep learning methods can effectively predict the binding affinity of protein-ligand interactions,reducing the time and cost of drug discovery.This study proposes a deep convolutional neural network model(DLLSA)based on long short-term memory module(LSTM)and attention mechanism module.The model is constructed using a convolutional network parallel pattern embedded with LSTM and spatial attention module.The LSTM module focuses on the long sequence information of protein ligand contact features,while the spatial attention module aggregates local information of contact features.PDBbind(v.2020)dataset was used for training,and CASF-2013 and CASF-2016 datasets were used for validating.Pearson correlation coefficients of the model were improved by 0.6%and 3%compared to the PLEC model,and the experimental results were significantly better than the current correlation methods.
作者
王伟
吴世玉
刘栋
梁慧茹
史进玲
周运
张红军
王鲜芳
WANG Wei;WU Shiyu;LIU Dong;LIANG Huiru;SHI Jinling;ZHOU Yun;ZHANG Hongjun;WANG Xianfang(College of Computer and Information Engineering,Henan Normal University,Xinxiang 453007,Henan,China;Key Laboratory of Artificial Intelligence and Personalized Learning in Education of Henan Province,Xinxiang 453007,Henan,China;International School of Education,Xuchang University,Xuchang 461000,Henan,China;Hebi Instiute of Engineering and Technology,Henan Polytechnic University,Hebi 458030,Henan,China;College of Computer Science and Technology Engineering,Henan Institute of Technology,Xinxiang 453000,Henan,China)
出处
《陕西师范大学学报(自然科学版)》
CAS
CSCD
北大核心
2024年第3期76-84,共9页
Journal of Shaanxi Normal University:Natural Science Edition
基金
国家自然科学基金(62072157)
河南省科技攻关项目(242102211045,242102210001)
河南师范大学高性能计算中心项目。
关键词
结合亲和力
卷积神经网络
注意力机制
评分功能
机器学习
binding affinity
convolution neural network
attention mechanism
scoring function
machine learning