癌变·畸变·突变Issue(5)：399-403,5.DOI:10.3969/j.issn.1004-616x.2015.05.015
应用PLS-QSAR模型预测纳米金属氧化物的毒性
The application of PLS-QSAR model to predict the toxicity of nanometer metal oxide
摘要
Abstract
OBJECTIVE:To explore the application of partial least squares-quantities structure activity relationship (PLS-QSAR) model to predict the bacterial toxicity of nanometer metal oxide,in order to provide methodological support for toxicology research.METHODS:We built 12 models through 3 ways to determine principal components and 4 ways of variables selection from published data of nanometer metal oxide (EC50) and chose the best model based on internal and external validations.RESULTS:We chose the best model obtained using forward selection of variables combining variable importance in projection(VIP) and cross validation,and CVtest principle components 222determination. The model had the better fitness(R=0.974),stability (QCV=0.951) and prediction (QEXT=0.775). CONCLUSION:PLS-QSAR can be applied to predict the bacterial toxicity of nanometer metal oxide as an alternative method and it may b e w orthwhile to explore variable selections and determine number of principle component.关键词
偏最小二乘法/定量构效关系/纳米金属氧化物/毒性Key words
partial least squares/quantities structure activity relationship/nanometer metal oxide/toxicity分类
医药卫生引用本文复制引用
邓景景,王萌,唐萌,刘冉,闵捷,余小金..应用PLS-QSAR模型预测纳米金属氧化物的毒性[J].癌变·畸变·突变,2015,(5):399-403,5.基金项目
国家重大科学研究计划项目(2011CB933404) （2011CB933404）
