Exploring Alternative Strategies for the Identification of Potent Compounds Using Support Vector Machine and Regression Modeling

Abstract

Support vector regression (SVR) is a premier approach for the prediction of compound potency. Given the conceptual link between support vector machine (SVM) and SVR modeling, SVR is capable of accounting for continuous and discontinuous structure−activity relationships (SARs) in potency prediction, which further extends the classical quantitative SAR (QSAR) paradigm. In the context of virtual compound screening, compound potency prediction can be applied to identify the most potent compounds that are available or enrich database selection sets with potent compounds. To these ends, we have evaluated new potency prediction strategies. Conventional (direct) potency prediction using SVR was compared to two-stage SVM-SVR modeling and potency prediction using SVR models trained in the presence of active and inactive compounds, a previously unconsidered approach. The latter models were found to maximize the recall of potent compounds but were least accurate in predicting high potency values. For this purpose, direct SVR predictions were preferred. However, the best balance between accurate potency predictions and enrichment of potent compounds in database selection sets was achieved by combined SVM-SVR modeling. Taken together, our findings further extend current approaches for compound potency prediction in virtual compound screening.

Ligand- and Structure-Based Analysis of Deep Learning-Generated Potential α2a Adrenoceptor Agonists

“…SVMs have demonstrated value as QSAR models. , The training and comparison of several baseline machine learning models including logistic regression, decision trees, and Gaussian Bayes demonstrated significantly superior performance of the SVM for both classes in accuracy, precision, recall, and f1 score (Figures S3 and S4A). We therefore proceeded with parameter tuning of the SVM to achieve a final agonist classification model for the α 2A -AR molecular library.…”

Iterative Screening Methods for Identification of Chemical Compounds with Specific Values of Various Properties

“…Five sets of active compounds with highly confident potency data and ZINC decoy compounds were taken from a previous study on virtual screening. 25 The target activity sets, originally used for activity cliff analysis, 26 were extracted from the ChEMBL database (version 23) 27 and showed large potency variation. Compound potency was specified in the form of equilibrium constants (K i ).…”

Application and assessment of deep learning for the generation of potential NMDA receptor antagonists

“…95 Although developed fairly recently, support vector machines (SVM) have demonstrated significant value as activity prediction models. [96][97] The SVM model for PCP site activity prediction achieved a ten-fold cross-validated accuracy of 0.95, with a weighted average precision of 0.98, recall of 0.97, and f1 of 0.97 on the test set (Figure S2). We built the initial classification models using a training set comprised of samples from only the library actives and inactives, which resulted in worse than desired performance due to the scarcity of inactives (N=X).…”