摘要
验证定量-结构活性相关(QSAR)模型,是保证模型对未知样本的生物活性具有可靠预测能力的重要前提.然而,目前部分QSAR论文没有对模型进行有效验证.因此,本文详细综述QSAR模型的内部验证方法和外部验证方法.内部验证方法包括留一法(leave-one-out,LOO)交叉验证,留多法(leave-many-out,LMO)或留N法(leave-N-out,LNO)交叉验证,y随机化验证和自举法.评价模型外部预测能力的统计量包括Q2F1、Q2F2、Q2F3、一致性相关系数(concordance correlation coefficient,CCC)、r珋2m和Golbraikh-Tropsha方法.此外,从文献中总结出可接受QSAR模型对应的统计量参考数值,从而为QSAR建模者提供指导与帮助.
Validation of a quantitative structure-activity relationship （QSAR） model plays an important role lor ensuring the reliable predictive ability of activity of untested chemicals. Currently, a number of QSAR models, however, lack reliable validation. The present study reviews the internal validation and external validation methods that exist for QSAR model. The internal validations include leave-one-out （LO0） cross-validation, leave-many-out （LMO） or leave-N-out （LNO） cross-validation, y-randomization test and bootstrapping, while the external validations include the statistical parameters Q^2F1 , Q^2F2 , Q^2F3 , concordance correlation coefficient （CCC）r^-2m , and Golbraikh-Tropsha method. Furthermore, the cutoff values of the different statistical parameters for an acceptable model were recommended according to the references. The internal and external validations addressed in this study together with the recommended cutoff values of statistical parameters may help researchers to develop QSAR models.
出处
《环境化学》
CAS
CSCD
北大核心
2013年第7期1205-1211,共7页
Environmental Chemistry
基金
国家自然科学基金(21177097)资助
中国博士后科学基金(2012M520932)资助
关键词
QSAR
内部验证
外部验证
QSAR, internal validation, external validation.
