The First Attempt at Non-Linear in Silico Prediction of Sampling Rates for Polar Organic Chemical Integrative Samplers (POCIS)

详细信息    查看全文

• 作者：Thomas H. Miller ; Jose A. Baz-Lomba ; Christopher Harman ; Malcolm J. Reid ; Stewart F. Owen ; Nicolas R. Bury ; Kevin V. Thomas ; Leon P. Barron
• 刊名：Environmental Science & Technology
• 出版年：2016
• 出版时间：August 2, 2016
• 年：2016
• 卷：50
• 期：15
• 页码：7973-7981
• 全文大小：472K
• 年卷期：0
• ISSN：1520-5851

文摘

Modeling and prediction of polar organic chemical integrative sampler (POCIS) sampling rates (R_s) for 73 compounds using artificial neural networks (ANNs) is presented for the first time. Two models were constructed: the first was developed ab initio using a genetic algorithm (GSD-model) to shortlist 24 descriptors covering constitutional, topological, geometrical and physicochemical properties and the second model was adapted for R_s prediction from a previous chromatographic retention model (RTD-model). Mechanistic evaluation of descriptors showed that models did not require comprehensive a priori information to predict R_s. Average predicted errors for the verification and blind test sets were 0.03 ± 0.02 L d^–1 (RTD-model) and 0.03 ± 0.03 L d^–1 (GSD-model) relative to experimentally determined R_s. Prediction variability in replicated models was the same or less than for measured R_s. Networks were externally validated using a measured R_s data set of six benzodiazepines. The RTD-model performed best in comparison to the GSD-model for these compounds (average absolute errors of 0.0145 ± 0.008 L d^–1 and 0.0437 ± 0.02 L d^–1, respectively). Improvements to generalizability of modeling approaches will be reliant on the need for standardized guidelines for R_s measurement. The use of in silico tools for R_s determination represents a more economical approach than laboratory calibrations.