We have constructed a drug design platform by integrating deep learning, quantum mechanical calculations, and in vivo screening to produce a lead compound that inhibits CB1 (cannabinoid receptor 1) target protein for the treatment of obesity. The first part of our research was to establish a protocol in which deep learning is trained with binding poses that are close to the native cocrystal structures so that it can predict “good enough” binding poses without detailed scoring. These binding poses will be subjected to QM/MM calculations to obtain QM-derived atomic charges on ligands, which, in turn, will be used for further docking. Our protocol displayed an excellent performance on GPCR targets and thus we proceeded further to combine it with in vivo screening and tested it on CB1 target. By targeting CB1, we aimed to discover a lead compound for the treatment of obesity, which is a condition easily checked with mouse models. I will discuss our results and findings for further improvement.

Development of CB1 inhibitor as obesity treatment by combining AI, quantum mechanical calculations, and in vivo screening

Fall 2022 abstracts, posters, and presentations will launch in mid-September.

ACS Fall 2022

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