In Silico Estimation of Chemical Carcinogenicity with Binary and Ternary Classification Methods

doi:10.1002/minf.201400127

CORC > 上海药物研究所 > 中国科学院上海药物研究所 > 药理学第三研究室

	In Silico Estimation of Chemical Carcinogenicity with Binary and Ternary Classification Methods
	Li, Xiao 2,3; Du, Zheng 2; Wang, Jie 2; Wu, Zengrui 2; Li, Weihua 2; Liu, Guixia 2; Shen, Xu3 ; Tang, Yun 1,2
刊名	MOLECULAR INFORMATICS
	2015-04
卷号	34 期号:4 页码:228-235
关键词	Binary classification Ternary classification Chemical carcinogenicity Machine learning methods Tobacco smoke
ISSN号	1868-1743
DOI	10.1002/minf.201400127
文献子类	Article
英文摘要	Carcinogenicity is one of the most concerned properties of chemicals to human health, thus it is important to identify chemical carcinogenicity as early as possible. In this study, 829 diverse compounds with rat carcinogenicity were collected from Carcinogenic Potency Database (CPDB). Using six types of fingerprints to represent the molecules, 30 binary and ternary classification models were generated to predict chemical carcinogenicity by five machine learning methods. The models were evaluated by an external validation set containing 87 chemicals from ISSCAN database. The best binary model was developed by MACCS keys and kNN algorithm with predictive accuracy at 83.91 %, while the best ternary model was also generated by MACCS keys and kNN algorithm with overall accuracy at 80.46 %. Furthermore, the best binary and ternary classification models were used to estimate carcinogenicity of tobacco smoke components containing 2251 compounds. 981 ones were predicted as carcinogens by binary classification model, while 110 compounds were predicted as strong carcinogens and 807 ones as weak carcinogens by ternary classification model. The results indicated that our models would be helpful for prediction of chemical carcinogenicity.
资助项目	National Natural Science Foundation of China[81373329] ; 863 Project[2012AA020308] ; Shanghai Tobacco Group Co. Ltd. Research Fund[K2013-1-044P] ; Fundamental Research Funds for the Central Universities[WY1113007]
WOS关键词	SUPPORT VECTOR MACHINES ; RODENT CARCINOGENICITY ; PREDICTION ; INHIBITORS ; MODELS
WOS研究方向	Pharmacology & Pharmacy ; Computer Science ; Mathematical & Computational Biology
语种	英语
出版者	WILEY-V C H VERLAG GMBH
WOS记录号	WOS:000352620100004
内容类型	期刊论文
源URL	[http://119.78.100.183/handle/2S10ELR8/276586]
专题	药理学第三研究室
通讯作者	Tang, Yun
作者单位	1.Shanghai Tobacco Grp Co Ltd, Ctr Tech, Key Lab Cigarette Smoke, Shanghai 200082, Peoples R China; 2.E China Univ Sci & Technol, Sch Pharm, Shanghai Key Lab New Drug Design, Shanghai 200237, Peoples R China; 3.Chinese Acad Sci, Shanghai Inst Mat Med, Shanghai 201203, Peoples R China
推荐引用方式 GB/T 7714	Li, Xiao,Du, Zheng,Wang, Jie,et al. In Silico Estimation of Chemical Carcinogenicity with Binary and Ternary Classification Methods[J]. MOLECULAR INFORMATICS,2015,34(4):228-235.
APA	Li, Xiao.,Du, Zheng.,Wang, Jie.,Wu, Zengrui.,Li, Weihua.,...&Tang, Yun.(2015).In Silico Estimation of Chemical Carcinogenicity with Binary and Ternary Classification Methods.MOLECULAR INFORMATICS,34(4),228-235.
MLA	Li, Xiao,et al."In Silico Estimation of Chemical Carcinogenicity with Binary and Ternary Classification Methods".MOLECULAR INFORMATICS 34.4(2015):228-235.