...
首页> 外文期刊>Environmental Science & Technology: ES&T >Applicability Domain of Polyparameter Linear Free EnergyRelationship Models Evaluated by Leverage and Prediction IntervalCalculation
【24h】

Applicability Domain of Polyparameter Linear Free EnergyRelationship Models Evaluated by Leverage and Prediction IntervalCalculation

机译:Applicability Domain of Polyparameter Linear Free EnergyRelationship Models Evaluated by Leverage and Prediction IntervalCalculation

获取原文
获取原文并翻译 | 示例
           

摘要

Polyparameter linear free energy relationships (PP-LFERs) areaccurate and robust models employed to predict equilibrium partitioncoefficients (K) of organic chemicals. The accuracy of predictions by a PP-LFER depends on the composition of the respective calibration data set.Generally, extrapolation outside the domain defined by the calibration data islikely to be less accurate than interpolation. In this study, the applicabilitydomain (AD) of PP-LFERs was systematically evaluated by calculating theleverage (h) and prediction interval (PI). Repeated simulations withexperimental data showed that the root mean squared error of predictionsincreased withh. However, the analysis also showed that PP-LFERscalibrated with a large number (e.g., 100) of training data were highly robust against extrapolation error. For such PP-LFERs,the common definition of extrapolation (h>3hmean, wherehmeanis the meanhof all training compounds) may be excessively strict.Alternatively, the PI is proposed as a metric to define the AD of PP-LFERs, as it provides a concrete estimate of the error range thatagrees well with the observed errors, even for extreme extrapolations. Additionally, published PP-LFERs were evaluated in terms oftheir AD using the new concept of AD probes, which indicated the varying predictive performance of PP-LFERs in the existingliterature for environmentally relevant compounds.

著录项

获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号