In a groundbreaking move for pandemic preparedness, a recent international endeavor showcased the potential and boundaries of artificial intelligence in expediting drug discovery for coronaviruses. The recently unveiled outcomes of the ASAP-Polaris-OpenADMET Challenge, a blind community competition, are detailed in a preprint by the Open Molecular Software Foundation (OMSF) and collaborators. This initiative, supported by the NIH’s Antiviral Drug Discovery (AViDD) program, called upon researchers worldwide to utilize machine learning models on novel drug discovery data aimed at the main proteases (Mpro) of SARS-CoV-2 and MERS-CoV—key enzymes crucial for coronavirus replication. Co-organized by the AI-driven Structure-enabled Antiviral Platform (ASAP), the Polaris benchmarking platform, and the OpenADMET project (backed by ARPA-H), the challenge attracted 66 teams from academia, industry, and government.
Read more from globalbiodefense.com