DeepBindBC: A practical deep learning method for identifying native-like protein-ligand complexes in virtual screening

doi:10.1016/j.ymeth.2022.07.009

	DeepBindBC: A practical deep learning method for identifying native-like protein-ligand complexes in virtual screening
	Zhang, Haiping 1,2; Zhang, Tingting 3; Saravanan, Konda Mani 4; Liao, Linbu 5; Wu, Hao 2; Zhang, Haishan 2; Zhang, Huiling 2; Pan, Yi 2; Wu, Xuli 3; Wei, Yanjie 1
	2022-09-01
发表期刊	METHODS
ISSN	1046-2023
卷号	205 页码:247-262
摘要	Identifying native-like protein-ligand complexes (PLCs) from an abundance of docking decoys is critical for large-scale virtual drug screening in early-stage drug discovery lead searching efforts. Providing reliable prediction is still a challenge for most current affinity predicting models because of a lack of non-binding data during model training, lost critical physical-chemical features, and difficulties in learning abstract information with limited neural layers. In this work, we proposed a deep learning model, DeepBindBC, for classifying putative ligands as binding or non-binding. Our model incorporates information on non-binding interactions, making it more suitable for real applications. ResNet model architecture and more detailed atom type representation guarantee implicit features can be learned more accurately. Here, we show that DeepBindBC outperforms Autodock Vina, Pafnucy, and DLSCORE for three DUD.E testing sets. Moreover, DeepBindBC identified a novel human pancreatic alpha-amylase binder validated by a fluorescence spectral experiment (K-a = 1.0 x 10(5) M). Furthermore, DeepBindBC can be used as a core component of a hybrid virtual screening pipeline that incorporating many other complementary methods, such as DFCNN, Autodock Vina docking, and pocket molecular dynamics simulation. Additionally, an online web server based on the model is available at http://cbblab.siat.ac. cn/DeepBindBC/index.php for the user's convenience. Our model and the web server provide alternative tools in the early steps of drug discovery by providing accurate identification of native-like PLCs.
关键词	Native like protein-ligand Drug virtual screening ResNet Deep learning Human pancreatic alpha amylase inhibitor
DOI	10.1016/j.ymeth.2022.07.009
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2018YFB0204403] ; National Science Foundation for Young Scientists of China[62106253] ; Shenzhen government[JCYJ20200109114818703] ; Key-Area Research and Development Program of Guangdong Province[2019B020213001] ; Research Funding for Innovation Project of Universities in Guangdong Province[2018KTSCX192] ; Strategic Priority CAS Project[XDB38000000] ; National Science Foundation of China[U1813203] ; Shenzhen Basic Research Fund[JCYJ20180507182818013] ; Shenzhen Basic Research Fund[JCYJ20170413 093358429] ; Shenzhen KQTD Project[KQTD20200820113106007] ; Research Funding of Shenzhen[JCYJ201803053000708] ; Research Funding of Shenzhen[JCYJ202001091 14818703]
WOS研究方向	Biochemistry & Molecular Biology
WOS类目	Biochemical Research Methods ; Biochemistry & Molecular Biology
WOS记录号	WOS:000861223100004
出版者	ACADEMIC PRESS INC ELSEVIER SCIENCE
引用统计	被引频次：11[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19813
专题	中国科学院计算技术研究所期刊论文
通讯作者	Wu, Xuli; Wei, Yanjie
作者单位	1.Chinese Acad Sci, Shenzhen Inst Synthet Biol, Shenzhen Inst Adv Technol, Shenzhen, Guangdong, Peoples R China 2.Chinese Acad Sci, Shenzhen Inst Adv Technol, Ctr High Performance Comp, Joint Engn Res Ctr Hlth Big Data Intelligent Anal, Shenzhen, Guangdong, Peoples R China 3.Shenzhen Univ, Sch Med, Shenzhen 518060, Guangdong, Peoples R China 4.Bharath Inst Higher Educ & Res, Dept Biotechnol, Chennai 600073, Tamil Nadu, India 5.Zhejiang Univ, Coll Software Technol, Ningbo 315048, Zhejiang, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Haiping,Zhang, Tingting,Saravanan, Konda Mani,et al. DeepBindBC: A practical deep learning method for identifying native-like protein-ligand complexes in virtual screening[J]. METHODS,2022,205:247-262.
APA	Zhang, Haiping.,Zhang, Tingting.,Saravanan, Konda Mani.,Liao, Linbu.,Wu, Hao.,...&Wei, Yanjie.(2022).DeepBindBC: A practical deep learning method for identifying native-like protein-ligand complexes in virtual screening.METHODS,205,247-262.
MLA	Zhang, Haiping,et al."DeepBindBC: A practical deep learning method for identifying native-like protein-ligand complexes in virtual screening".METHODS 205(2022):247-262.