Prioritization of new molecule design using QSAR models - 2D- and 3D-QSAR studies on SARS-CoV-2 Mpro inhibitors

Robust and predictive Quantitative Structure Activity Relationships (QSAR) models can be used to both explain observed activity and to inform new molecule design.

Using a dataset of 76 compounds with known experimental activity against Mpro of SARS-CoV-2, Cresset Discovery scientists built both predictive machine learning (ML) models and Cresset Field 3D-QSAR methods, to elucidate binding activity.

We demonstrate how the models show statistical performance aligned with experimental results, and how the results from the Field 3D-QSAR highlight the regions driving activity. We discuss how these insights can be used to inform further modeling to improve the recognition, binding and subsequently the activity of the tested molecule.

To learn more, read the case study.