Korea University Uses AI to Find Potential Antiviral Compounds

Korea University researchers used AI and laboratory testing to identify potential inhibitors of a human enzyme involved in viral replication, the university said in a press release. The study was published online in the Journal of Cheminformatics on August 5, 2026.

The team benchmarked 13 machine learning models and 10 molecular generation methods using deoxyhypusine synthase, or DHPS, as the target. DHPS supports a cellular process used in the replication of several viruses.

Researchers selected six AI generated molecular fragments for laboratory tests, including three predicted to be active and three predicted to be inactive. All three predicted active fragments inhibited DHPS, while the other three did not. Two active fragments had measurable IC50 values of 31.2 and 49.1 μM, and an X ray co crystal structure showed one compound binding near the enzyme's substrate and NAD binding pocket. The researchers described the compounds as early stage hits rather than drug candidates.