Quantitative structure–activity relationship study of influenza virus neuraminidase A/PR/8/34 (H1N1) inhibitors by genetic algorithm feature selection and support vector regression

• We explored the Machine Learning (ML) methods for predicting H1N1 inhibitors.
• Two coupled GA-PLS and GA-SVM methods were employed to construct QSAR models.
• GA-PLS method was applied for extracting a set of the most appropriate descriptors.
• SVM gives more accurate predicted values for H1N1 inhibitory activity than PLS.
• It is shown that SVM is useful for facilitating the discovery of H1N1 inhibitors.

The quantitative structure–activity relationship (QSAR) for the prediction of the activity of two different scaffolds of 108 influenza neuraminidase A/PR/8/34 (H1N1) inhibitors was investigated. A feature selection method, which combines Genetic Algorithm with Partial Least Square (GA–PLS), was applied to select proper descriptor subset for QSAR modeling in a linear model. Then Genetic Algorithm-Support Vector Machine coupled approach (GA–SVM) was first used to build the nonlinear models with nine GA–PLS selected descriptors. With the SVM regression model, the corresponding correlation coefficients (R) of 0.9189 for the training set, 0.9415 for the testing set and 0.9254 for the whole data set were achieved respectively. The two proposed models gained satisfactory prediction results and can be extended to other QSAR studies.

The Genetic Algorithm combining respectively with Partial Least Square (GA–PLS) and Support Vector Machine (GA–SVM) were used to study the quantitative structure–activity relationship on influenza neuraminidase A/PR/8/34 (H1N1) inhibitors.Figure optionsDownload as PowerPoint slide