AUTHOR=Yang Xiaoda , Qiu Hongshun , Zhang Yuxiang , Zhang Peijian 

TITLE=Quantitative structure–activity relationship study of amide derivatives as xanthine oxidase inhibitors using machine learning

JOURNAL=Frontiers in Pharmacology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/pharmacology/articles/10.3389/fphar.2023.1227536

DOI=10.3389/fphar.2023.1227536

ISSN=1663-9812

ABSTRACT=The target of the study is to predict the inhibitory effect of amide derivatives on xanthine oxidase (XO) by building several models, which is based on the theory of quantitative structure–activity relationship (QSAR). Heuristic method (HM) was used to linearly select descriptors and build linear model. XGBoost was used to nonlinearly select descriptors and radial basis kernel function (RBF-SVR), polynomial kernel function (Poly-SVR), linear kernel function(Linear-SVR), mix-kernel function support vector regression (MIX-SVR), random forest (RF) were adopted to establish nonlinear models, in which the MIX-SVR method gives the best result.
The kernel function of MIX-SVR has strong abilities of learning and generalization of established model simultaneously, which because it is a combination of the linear kernel function, radial basis kernel function and polynomial kernel function. In order to test the robustness of the models, leave-one-out cross validation (LOOCV) was adopted. In training set, =0.97, RMSE=0.01; in test set =0.95, RMSE=0.01, and =0.96. This result is in line with experimental expectations, which indicates that the MIX-SVR modeling approach has good application in the study of the amide derivatives.