3D-QSAR and SVM Prediction of BRAF-V600E and HIV Integrase Inhibitors: A Comparative Study and Characterization of Performance with a New Expected Prediction Performance Metric

Abstract

Abstract:The results of directly comparing the prediction accuracy of optimized 3D Quantitative Structure-Activity Relationship (3D-QSAR) models and linear Support Vector Machine (SVM) classifiers to identify small molecule inhibitors of the BRAF-V600E and HIV Integrase targets are reported. Performance comparisons were carried out using 303 compounds (68 active) against BRAF-V600E and 204 compounds (159 active) against HIV Integrase. A SVM prediction accuracy of 95% (BRAF-V600E) and 100% (HIV Integrase) and 3D-QSAR prediction accuracy of 76% (BRAFV600E) and 82% (HIV Integrase) was observed. To help explain the better performance of SVM in the comparison reported here and to help assess the degree to which a SVM or 3D-QSAR model is likely to perform best for other targetligands of interest a new EPP (Expected Predictive Performance) metric is introduced. How EPP can be used to help predict future performance of SVM and 3D-QSAR models by quantifying the degree of similarity between candidate compounds and training data is also demonstrated. Results show that the EPP metric is capable of predicting future prediction accuracy of SVM and 3D-QSAr models within 7% of actual performance.

StackBRAF: A Large-Scale Stacking Ensemble Learning for BRAF Affinity Prediction

“…In comparison, our StackBRAF has 11–100 times larger training and 6–77 times larger test datasets than those of previous studies. The StackBRAF demonstrated the highest goodness of fit in the CV test ( Q 2 CV ) compared to the four previous studies. − StackBRAF also exhibits better predictability ( Q 2 Ext ) than the three previous studies of the 3D-QSAR model. − Overall, our StackBRAF model offers improved predictability, robustness, and applicability across a wide range of chemical molecules.…”

“… − Most of them utilized 3D descriptors calculated from comparative molecular force field and comparative molecular similarity indices analysis models. They also applied the PLS as a regression model with steric, electrostatic, hydrophobic, and hydrogen bonding between the drug and target as molecular descriptors. − The training datasets of previous studies included 27–243 compounds, while the test datasets comprised 15–189 compounds. In comparison, our StackBRAF has 11–100 times larger training and 6–77 times larger test datasets than those of previous studies.…”

“…Previous studies have constructed the validated QSAR models for designing new drugs against the BRAF protein (Table ). − Most of them utilized 3D descriptors calculated from comparative molecular force field and comparative molecular similarity indices analysis models. They also applied the PLS as a regression model with steric, electrostatic, hydrophobic, and hydrogen bonding between the drug and target as molecular descriptors. − The training datasets of previous studies included 27–243 compounds, while the test datasets comprised 15–189 compounds.…”

“…Recently, Gaussian field-based 3D-QSAR and molecular simulation studies were performed to design a potent pyrimidine–sulfonamide, also using the PLS model . Two studies also built 3D-QSAR models using the PLS algorithm to predict BRAF inhibitors. , Additionally, one study applied a deep learning (DL) generative model for designing BRAF inhibitors . In total, four previous studies used 3D-QSAR and PLS models, and one study applied DL for predicting BRAF inhibitors.…”

Evaluation of the performance of various machine learning methods on the discrimination of the active compounds

“…By introduction of large datasets, the more sophisticated methods were employed to make predictive QSAR models: SVM, RF, and ANN with different architectures including DL. One of the successful applications of the SVM is the prediction of the activity of HIV integrase inhibitors (Leonard et al, 2016). Sometimes RF and usually DL outperform other methods in the model development for large datasets.…”