Predicting network of drug-enzyme interaction based on machine learning method

doi:10.1016/j.bbapap.2013.07.008

CORC > 上海药物研究所 > 中国科学院上海药物研究所 > 药物发现与设计中心

	Predicting network of drug-enzyme interaction based on machine learning method
	Niu, Bing 1; Zhang, Yuchao 2,3; Ding, Juan 4; Lu, Yin 5; Wang, Miao 6; Lu, Wencong 7; Yuan, Xiaochen 8; Yin, Jinyuan 8
刊名	BIOCHIMICA ET BIOPHYSICA ACTA-PROTEINS AND PROTEOMICS
	2014-01
卷号	1844 期号:1 页码:214-223
关键词	Drug-enzyme interaction CfsSubset Machine learning Random Forest Pseudo amino acid composition Molecular descriptor
ISSN号	1570-9639
DOI	10.1016/j.bbapap.2013.07.008
文献子类	Article
英文摘要	It is important to correctly and efficiently map drugs and enzymes to their possible interaction network in modern drug research. In this work, a novel approach was introduced to encode drug and enzyme molecules with physicochemical molecular descriptors and pseudo amino acid composition, respectively. Based on this encoding method, Random Forest was adopted to build the drug-enzyme interaction network. After selecting the optimal features that are able to represent the main factors of drug-enzyme interaction in our prediction, a total of 129 features were attained which can be clustered into nine categories: Elemental Analysis, Geometry, Chemistry, Amino Acid Composition, Secondary Structure, Polarity, Molecular Volume, Codon Diversity and Electrostatic Charge. It is further found that Geometry features were the most important of all the features. As a result, our predicting model achieved an MCC of 0.915 and a sensitivity of 87.9% at the specificity level of 99.8% for 10-fold cross-validation test, and achieved an MCC of 0.895 and a sensitivity of 95.7% at the specificity level of 95.4% for independent set test. This article is part of a Special Issue entitled: Computational Proteomics, Systems Biology & Clinical Implications. Guest Editor: Yudong Cai. (C) 2013 Elsevier B.V. All rights reserved.
资助项目	National Natural Science Foundation of China[20973108] ; Shanghai Key Laboratory of Bioenergy Crops[13DZ2272100] ; Science Foundation of Shanghai for Excellent Young Teachers[SHU10022]
WOS关键词	AMINO-ACID-COMPOSITION ; SUPPORT VECTOR MACHINES ; PROTEIN SUBCELLULAR LOCATION ; TARGET INTERACTION NETWORKS ; ESTROGEN RECEPTOR LIGANDS ; RANDOM FOREST APPROACH ; PHYSICOCHEMICAL PROPERTIES ; STRUCTURAL CLASS ; CONOTOXIN SUPERFAMILY ; PHARMACOPHORE MODEL
WOS研究方向	Biochemistry & Molecular Biology ; Biophysics
语种	英语
出版者	ELSEVIER SCIENCE BV
WOS记录号	WOS:000330911500008
内容类型	期刊论文
源URL	[http://119.78.100.183/handle/2S10ELR8/277307]
专题	药物发现与设计中心
通讯作者	Lu, Wencong
作者单位	1.Shanghai Univ, Coll Life Sci, Shanghai 200072, Peoples R China; 2.Chinese Acad Sci, Inst Hlth Sci, Shanghai Inst Biol Sci, Mol Genet Lab, Shanghai, Peoples R China; 3.Shanghai Jiao Tong Univ, Sch Med, Shanghai 200025, Peoples R China; 4.Harvard Univ, Sch Med, Schepens Eye Res Inst, Boston, MA 02114 USA; 5.Shanghai Inst Mat Med, DDDC, Shanghai, Peoples R China; 6.Shanghai Int Studies Univ, Shanghai, Peoples R China; 7.Shanghai Univ, Coll Sci, Dept Chem, Shanghai 200444, Peoples R China; 8.Shanghai Univ, Coll Comp Sci, Shanghai 200072, Peoples R China
推荐引用方式 GB/T 7714	Niu, Bing,Zhang, Yuchao,Ding, Juan,et al. Predicting network of drug-enzyme interaction based on machine learning method[J]. BIOCHIMICA ET BIOPHYSICA ACTA-PROTEINS AND PROTEOMICS,2014,1844(1):214-223.
APA	Niu, Bing.,Zhang, Yuchao.,Ding, Juan.,Lu, Yin.,Wang, Miao.,...&Yin, Jinyuan.(2014).Predicting network of drug-enzyme interaction based on machine learning method.BIOCHIMICA ET BIOPHYSICA ACTA-PROTEINS AND PROTEOMICS,1844(1),214-223.
MLA	Niu, Bing,et al."Predicting network of drug-enzyme interaction based on machine learning method".BIOCHIMICA ET BIOPHYSICA ACTA-PROTEINS AND PROTEOMICS 1844.1(2014):214-223.