Allostery is a fundamental process in biology to regulate proteins' activity. Allosteric drug development holds promise since they are more selective, less toxic and have fewer side effects. The discovery, design and development of allosteric drugs demand for better identification of allosteric sites. In this study, we used automated machine learning to develop a computational model for allosteric site prediction. The developed model has superior performance, high ranking power, and capability of predicting allosteric sites for other allosteric proteins. The model has been integrated with the Protein Allosteric Sites Server (https://passer.smu.edu) available to the public to facilitate allosteric drug discovery.

Identifying protein allosteric sites through automated machine learning

ACS Spring 2022

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.