Overexpression of EGFR has been found in many tumour types. Targeting EGFR has shown significant benefit in cancer treatment. The discovery of novel EGFR inhibitors may provide a solution to overcome drug resistance. In this work, we performed a ligand-based virtual screening (LBVS) protocol to find novel EGFR inhibitors from a 5.3 million compound library. The 3D shape-based similarity was used to obtain structurally novel EGFR inhibitors. Followed by machine learning models to screen compounds predicted to be highly active. Kinase assay validations led to the identification of 9 hits out of 18 tested compounds. Among them, three hits with novel structures had IC<sub>50</sub> values around 80 nM against EGFR. Their interaction with EGFR was further investigated by molecular dynamics simulations. Our study confirmed the validity of the hierarchical ligand-based VS cascade by combining multiple computational approaches and the ability of the DGMG model to generate novel structurally specific molecules.

Discovery of novel epidermal growth factor receptor (EGFR) inhibitors using computational screening cascade

Where thousands of chemistry professionals meet to share ideas and advance scientific and technical knowledge. Spring 2023 abstracts, posters, and presentations will launch at the end of March.

ACS Spring 2023

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