Prediction of the heat capacity for compounds based on the conjugate gradient and support vector machine methods

Abstract

A quantitative structure–property relationship model for prediction of the heat capacity was developed from molecular structures. By using DRAGON 2.1, various kinds of molecular structure descriptors were calculated to represent the molecular structures of compounds, which contain 18 categories of descriptors in total. The novel variable selection method of ant colony optimization (ACO) algorithm was employed to select an optimal subset of descriptors that have significant contribution to the property from a large pool of calculated descriptors. As a result, five descriptors were screened out as input parameters. With the same five descriptors, ACO coupled with the conjugate gradient (CG) method and support vector machine (SVM) method was employed to construct the linear model (ACO‐CG) and the nonlinear model (ACO‐SVM), respectively. The results showed robust models and small prediction error, and the built models were very satisfying. In addition, the fitting and predicting performances of the ACO‐SVM model (squared correlation coefficient, bold-italicRboldtrainbold2=0.9607, bold-italicRboldtestbold2=0.9398) are both better than that of the ACO‐CG model (bold-italicRboldtrainbold2=0.9404, bold-italicRboldtestbold2=0.9281). The traditional validation parameters of Qloo2 (internal validation) and Qext2(external validation) have been supplemented with two novel parameters rm2 and cbold-italicRbold-italicpbold2 for a stricter test of validation. The developed models could achieve the required values for the novel parameters rm2 (rm2true¯>0.5, Δbold-italicrbold-italicmbold2<0.2) and cbold-italicRbold-italicpbold2 (cbold-italicRbold-italicpbold2>0.5). From the preceding analysis, it can be concluded that the proposed methods can be successfully used to predict the heat capacity with preselected theoretical descriptors, which can be directly calculated solely from the molecular structure. The applicability domain of the model was assessed by the Williams plot. Copyright © 2013 John Wiley & Sons, Ltd.

Estimation of Heat Capacity of Ionic Liquids Using Sσ-profile Molecular Descriptors

“…10 However, in fact, the new or required certain compounds' heat capacity sometimes can not be detected from the manual and databank of chemical thermodynamics, and due to the different experimental conditions and apparatuses, there are unavoidably some uncertainties in measurements. 11 In addition, because of the tunable properties of ILs, there are numerous potential combinations of cations and anions from a current chemical database to create useful ILs; thus, measuring the heat capacity of various ILs under a wide range of conditions through experimental techniques is impractical and costly. Accordingly, it is necessary to develop computational approaches to predict the heat capacity of ILs.…”

“…Usually, the heat capacity can be measured by various experimental methods such as the differential scanning calorimetry (DSC), adiabatic calorimetry, hot-wire method, and temperature oscillation calorimetry . However, in fact, the new or required certain compounds’ heat capacity sometimes can not be detected from the manual and databank of chemical thermodynamics, and due to the different experimental conditions and apparatuses, there are unavoidably some uncertainties in measurements . In addition, because of the tunable properties of ILs, there are numerous potential combinations of cations and anions from a current chemical database to create useful ILs; thus, measuring the heat capacity of various ILs under a wide range of conditions through experimental techniques is impractical and costly.…”

Prediction on the Auto-ignition Temperature Using Substructural Molecular Fragments

“…The internal validation for the model is necessary for robustness and possible high predictive power. In this research, we have applied the leave-one-out (LOO) for the internal validation, which is calculated according to the formula [11].…”

Prediction of Heat Capacity of Ionic Liquids Based on COSMO-RS Sσ-profile

“…All these characteristics make ILs promising options for the use in the chemical processes including catalytic synthesis, extraction separation, electrochemistry, etc . In addition, the different experimental conditions and equipment are also resulted in the uncertainty of measurement (Shi et al, 2013). Therefore, it was essential to develop new model to predict the properties of ILs.…”