Simple yet accurate prediction method for sublimation enthalpies of organic contaminants using their molecular structure

摘要

The objective of this study is to provide a simple yet accurate theoretical strategy for the prediction of the sublimation enthalpy of wide range organic contaminants only from their 3D molecular structure. Therefore, by integrating the gene expression programming (GEP) and quantitative structure-property relationship (QSPR) modeling resulted in promising statistics of R ~2 = 0.931, QLOO2=0.930 and RMSE = 9.87 kJ/mol for the entire dataset. By using this extended dataset including 1586 organic contaminants from 73 diverse material classes the accuracy and generalizability of the work is benefited. In order to demonstrate the proposed modeling capabilities, these results were compared with those obtained by an optimized support vector regression.