In the current hit identification paradigm, biological screens are often tailor-made for each project and target, stretching costs and timelines. Instead, a versatile and lean hit identification approach applicable to most biological targets would provide access to hits affordably and in a timely manner; two critical attributes in drug discovery. We report in this poster the development of a new hit identification platform combining Ai-powered virtual screening with GCI-driven biophysical screening. Its application to the BRPF1b bromodomain enabled the rapid identification of 8 orthogonally validated hits from a virtual collection of nearly 25 million commercial compounds.
Combining Machine Learning with Grating-Coupled Interferometry to identify novel BRPF1B inhibitors
