QSPR modeling of decomposition temperature of energetic cocrystals using artificial neural network

• Published in: Journal of thermal analysis and calorimetry Vol. 133; no. 3; pp. 1663 - 1672
• Main Authors: Fathollahi, M., Sajady, H.
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.09.2018; Springer; Springer Nature B.V
• Subjects: Analysis; Analytical Chemistry; Artificial neural networks; Chemistry; Chemistry and Materials Science; Correlation coefficients; Decomposition; Inorganic Chemistry; Mathematical models; Measurement Science and Instrumentation; Neural networks; Physical Chemistry; Polymer Sciences; Predictions; Regression analysis; Reliability analysis; Molecular descriptors; Decomposition temperature; QSPR; Artificial neural network; Energetic cocrystals
• ISSN: 1388-6150; 1588-2926
• DOI: 10.1007/s10973-018-7173-3

The quantitative structure–property relationship for the decomposition temperature ( T d ) of energetic cocrystals was investigated. The artificial neural network (ANN) model was employed to predict the T d of cocrystals by using molecular descriptors achieved from Dragon software as input variables. The complete set of 30 cocrystals was randomly divided into a training set of 19, a test set of 6, and a validation set of 5 compounds. Average absolute relative deviations and correlation coefficient ( R 2 ) of the ANN model (for the whole dataset) were 1.94% and 0.9784, respectively, indicating satisfactory predictive ability and reliability of the model. Moreover, these data were analyzed by multiple linear regression (MLR) method which showed R 2  = 0.7438. The result of MLR proves the necessity of applying ANN models for the prediction of the T d of cocrystals.