Background:
HIV-1 protease inhibitor (PIs) is a good choice of ADIS patients. Nevertheless, for PIs, there are several bugs in clinical application, like drug resistance, the large dose, the high costs and so on, among which, the poor pharmacokinetics property is one of the important reasons that leads to the failure of its clinical application.
Objective:
We aimed to build computational models for studying the relationship between PIs structure and its pharmacological activities.
Method:
We collected experimental values of koff/Ki and structures of 50 PIs through a careful literature and database search. Quantitative structure activity/pharmacokinetics relationship (QSAR/QSPR) models were constructed by support vector machine (SVM), partial-least squares regression (PLSR) and back-propagation neural network (BPNN).
Results:
For QSAR models, SVM, PLSR and BPNN all generated reliable prediction models with the r2 of 0.688, 0.768 and 0.787, respectively, and "r" _"pred" ^"2" of 0.748, 0.696 and 0.640, respectively. For QSPR models, the optimum models of SVM, PLSR and BPNN got the r2 of 0.952, 0.869 and 0.960, respectively, and the "r" _"pred" ^"2" of 0.852, 0.628 and 0.814, respectively.
Conclusion:
Among these three modelling methods, SVM showed superior ability to PLSR and BPNN both in QSAR/QSPR modelling of PIs, thus, we suspected that SVM was more suitable for predicting activities of PIs. In addition, 3D-MoRSE descriptors may have a tight relationship with the Ki values of PIs, and the GETAWAY descriptors have significant influence for both koff and Ki in PLSR equations.
Cancer Risk Prediction Models: A Workshop on Development, Evaluation, and Application