Abstract
Quantitative structure–activity relationship (QSAR) was performed to analyze naphthoquinone derivatives as an inhibitor of indoleamine 2,3-dioxygenase pathogen via multivariate regression (MLR) and artificial neural network. The best descriptors were picked to construct the QSAR. Two sets of exercises and experiments were also performed using Principal Component Analysis for multiple linear regression (MLR). A quantitative model was then proposed based on these analyses and the activity of the compounds based on multivariate statistical analysis was interpreted. The study finally revealed that although the MLR model can predict the activity of the compounds to some extent, the artificial neural network (ANN) model results indicate that the predictions obtained by the neural network are much better and more efficient than other models. The neural network was also used where three coefficients of correlation were used. The results uncovered that the ANN model is statistically significant and has good stability for data validation for the validation method. Share Descriptive relationships of structure and activity were also examined.
Keywords
Artificial neural network (ANN) multiple linear regression (MLR) naphthoquinone derivatives pathogenic agent quantitative structure–activity relationship (QSAR)
Copyright
© 2021, Author(s). This open-access article is available under the Creative Commons Attribution 4.0 (CC BY 4.0) International License (https://creativecommons.org/licenses/by/4.0/), which allows for unrestricted use, distribution, and reproduction in any medium, provided that the original work is properly cited.