Korea University Study Uses Artificial Intelligence to Design Potential Antiviral Compounds

New study combines AI-guided molecular design with experimental validation to identify potential inhibitors of a host enzyme involved in viral replication

SEOUL, South Korea, Oct. 19, 2026 /PRNewswire/ -- Viral infections can be difficult to treat as viruses evolve rapidly, allowing them to develop resistance to drugs designed to attack viral proteins directly. One alternative is host-directed therapy (HDT), an emerging medical approach that treats infections by targeting the host's own biological pathways and associated proteins rather than attacking the pathogen directly.

Against this backdrop, researchers at Korea University, led by Professor Kwang Yeon Hwang of the College of Life Sciences and Biotechnology and Associate Professor Hong-Rae Kim of the College of Medicine, have developed an artificial intelligence (AI)-guided strategy to discover molecules that inhibit deoxyhypusine synthase (DHPS), a human enzyme involved in eIF5A hypusination, a process that supports the replication of a broad range of viruses. Unlike many AI drug-discovery approaches evaluated only computationally, the researchers experimentally tested AI-generated molecules. The study was published online in the Journal of Cheminformatics on August 05, 2026.

"DHPS is involved in activating eukaryotic translation initiation factor 5A or eIF5A through a unique modification called hypusination. This process is important for the replication of a broad range of viruses, including HIV-1 and SARS-CoV-2, making DHPS a potential target for host-directed antiviral drug discovery," explained Prof. Hwang.

The researchers systematically benchmarked 13 machine-learning models for predicting molecular binding scores and 10 methods for generating new molecules, using DHPS as a common target. Out-of-Fold Stacking (OOF-Stacking) achieved the strongest overall performance among the prediction models tested, while RL-Design achieved the highest predicted hit rate of 92.02% among the generation methods tested, and 98.0% of its top-ranked molecules passed a standard drug-likeness threshold.

To experimentally assess the AI-generated molecules, six fragments, small compounds of 140 to 190 daltons, were selected: three predicted-active and three predicted-inactive. All three predicted-active fragments inhibited DHPS and none of the predicted-inactive ones did, a complete agreement between computational predictions and experimental results. Two of the active fragments gave measurable IC₅₀ values of 31.2 and 49.1 μM, the range in which fragment hits typically begin.

An X-ray co-crystal structure also provided structural evidence for the binding of one AI-generated compound at the entrance of the DHPS substrate and NAD-binding pocket.

"The best-known DHPS inhibitor closely mimics a natural cellular molecule, which brings a risk of off-target activity. Our hits are fragments built on scaffolds unrelated to the known inhibitor. In fragment-based discovery this is exactly where you want to start: they are small and bind efficiently for their size, which leaves considerable room to grow them into more potent compounds. However, these molecules are early-stage hits rather than drug candidates," noted Prof. Kim. "Further studies will be needed to establish their inhibition mechanisms, selectivity, cellular activity, toxicity and performance in animal models." Nevertheless, the work demonstrates a reproducible route from AI-based molecular design to experimental validation.

Beyond DHPS, the freely available pipeline could be applied to other disease targets. Its modest computing requirements may also make experimentally grounded AI-assisted drug discovery more accessible to laboratories with limited computational resources.

Overall, the study provides an early proof of concept for AI-guided, host-directed antiviral drug discovery and shows how computational predictions can be systematically benchmarked and then combined with molecular generation and laboratory experimentation to identify and validate early-stage inhibitor hits.

Reference
Title of original paper: AI-guided De Novo design of DHPS inhibitors
Journal: Journal of Cheminformatics
DOI: 10.1186/s13321-026-01277-4

About Korea University College of Medicine
Website: https://medicine.korea.ac.kr/en/index.do

Media Contact
Soo-Jin Jeon
+82 2 3407 4040
[email protected]

SOURCE Korea University College of Medicine