Woods, V.; Umansky, T.; Russell, S. M.; McGovern, B. L.; Rosales, R.; Rodriguez, M. L.; van Bakel, H.; Sordillo, E. M.; Simon, V.; Garcia-Sastre, A.; White, K. M.; Smith, D. M.; Haders, D.

The death toll and financial stress posed by the recent COVID-19 pandemic have highlighted the pressing need to develop safe and effective, broad-spectrum inhibitors to treat viral infections. To accelerate the antiviral drug discovery process, we developed GALILEOTM, a computational platform that interfaces with a customizable bioinformatics pipeline with a geometric deep learning algorithm we named ChemPrintTM for in silico drug screening. Combining these algorithms with a large chemical repositioning library, we discovered MDL-001, which interacts with the Thumb pocket 1 subdomain of multiple single-stranded RNA viruses. For MDL-001, we demonstrate potent in vitro activity against a broad spectrum of pathogenic viruses, and we demonstrate potent in vivo efficacy in a mouse model of SARS-CoV-2 infection. In clinical trials, orally administered MDL-001 has been shown to be safe and well tolerated. These data underline both the effectiveness of the GALILEO platform for drug discovery and the promise of MDL-001 as a novel broad-spectrum antiviral clinical candidate.