Molecular Sparse Representation by a 3D Ellipsoid Radial Basis Function Neural Network via L1 Regularization

doi:10.1021/acs.jcim.0c00585

CSpace

	Molecular Sparse Representation by a 3D Ellipsoid Radial Basis Function Neural Network via L1 Regularization
	Gui, Sheng 1,2,3; Chen, Zhaodi 3; Lu, Benzhuo 1,2; Chen, Minxin 3
	2020-12-28
发表期刊	JOURNAL OF CHEMICAL INFORMATION AND MODELING
ISSN	1549-9596
卷号	60 期号:12 页码:6054-6064
摘要	The three-dimensional structures and shapes of biomolecules provide essential information about their interactions and functions. Unfortunately, the computational cost of bio-molecular shape representation is an active challenge which increases rapidly as the number of atoms increase. Recent developments in sparse representation and deep learning have shown significant improvements in terms of time and space. A sparse representation of molecular shape is also useful in various other applications, such as molecular structure alignment, docking, and coarse-grained molecular modeling. We have developed an ellipsoid radial basis function neural network (ERBFNN) and an algorithm for sparsely representing molecular shape. To evaluate a sparse representation model of molecular shape, the Gaussian density map of the molecule is approximated using ERBFNN with a relatively small number of neurons. The deep learning models were trained by optimizing a nonlinear loss function with L1 regularization. Experimental results reveal that our algorithm can represent the original molecular shape with a relatively higher accuracy and fewer scale of ERBFNN. Our network in principle is applicable to the multiresolution sparse representation of molecular shape and coarse-grained molecular modeling. Executable files are available at https://github.com/SGUI-LSEC/SparseGaussianMolecule. The program was implemented in PyTorch and was run on Linux.
DOI	10.1021/acs.jcim.0c00585
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2016YF-B0201304] ; China NSF (NSFC)[11771435] ; China NSF (NSFC)[21573274]
WOS研究方向	Pharmacology & Pharmacy ; Chemistry ; Computer Science
WOS类目	Chemistry, Medicinal ; Chemistry, Multidisciplinary ; Computer Science, Information Systems ; Computer Science, Interdisciplinary Applications
WOS记录号	WOS:000608875100046
出版者	AMER CHEMICAL SOC
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/58035
专题	中国科学院数学与系统科学研究院
通讯作者	Lu, Benzhuo; Chen, Minxin
作者单位	1.Chinese Acad Sci, Acad Math & Syst Sci, Natl Ctr Math & Interdisciplinary Sci, State Key Lab Sci & Engn Comp, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Math Sci, Beijing 100049, Peoples R China 3.Soochow Univ, Dept Math, Suzhou 215006, Peoples R China
推荐引用方式 GB/T 7714	Gui, Sheng,Chen, Zhaodi,Lu, Benzhuo,et al. Molecular Sparse Representation by a 3D Ellipsoid Radial Basis Function Neural Network via L1 Regularization[J]. JOURNAL OF CHEMICAL INFORMATION AND MODELING,2020,60(12):6054-6064.
APA	Gui, Sheng,Chen, Zhaodi,Lu, Benzhuo,&Chen, Minxin.(2020).Molecular Sparse Representation by a 3D Ellipsoid Radial Basis Function Neural Network via L1 Regularization.JOURNAL OF CHEMICAL INFORMATION AND MODELING,60(12),6054-6064.
MLA	Gui, Sheng,et al."Molecular Sparse Representation by a 3D Ellipsoid Radial Basis Function Neural Network via L1 Regularization".JOURNAL OF CHEMICAL INFORMATION AND MODELING 60.12(2020):6054-6064.