Versatile in silico modeling of XAD-air partition coefficients for POPs based on abraham descriptor and temperature

The concentration of persistent organic pollutants (POPs) makes remarkable difference to environmental fate. In the field of passive sampling, the partition coefficients between polystyrene-divinylbenzene resin (XAD) and air (i.e., KXAD-A) are indispensable to obtain POPs concentration, and the KXAD-A is generally thought to be governed by temperature and molecular structure of POPs. However, experimental determination of KXAD-A is unrealistic for countless and novel chemicals. Herein, the Abraham solute descriptors of poly parameter linear free energy relationship (pp-LFER) and temperature were utilized to develop models, namely pp-LFER-T, for predicting KXAD-A values. Two linear (MLR and LASSO) and four nonlinear (ANN, SVM, kNN and RF) machine learning algorithms were employed to develop models based on a data set of 307 sample points. For the aforementioned six models, R(adj)(2 )and Q(ext)(2) were both beyond 0.90, indicating distinguished goodness-of-fit and robust generalization ability. By comparing the established models, the best model was observed as the RF model with R-adj(2) = 0.991, Q(ext)(2) = 0.935, RMSEtra = 0.271 and RMSEext = 0.868. The mechanism interpretation revealed that the temperature, size of molecules and dipole-type interactions were the predominant factors affecting KXAD-A values. Concurrently, the developed models with the broad applicability domain provide available tools to fill the experimental data gap for untested chemicals. In addition, the developed models were helpful to preliminarily evaluate the environmental ecological risk and understand the adsorption behavior of POPs between XAD membrane and air.

Automated summary

The study developed models for predicting the partition coefficients of persistent organic pollutants (POPs) between XAD resin and air using poly parameter linear free energy relationship (pp-LFER) and temperature. Machine learning algorithms showed good fitting and generalization abilities, with the random forest (RF) model performing the best. The models provide a useful tool for filling experimental data gaps and evaluating the environmental ecological risk of untested chemicals.