PHILADELPHIA – Artificial intelligence algorithms have now been combined with traditional laboratory methods to uncover promising drug leads against human enterovirus 71 (EV71), the pathogen behind most cases of hand, foot and mouth disease. The study, published today in Cell Reports Physical Science by researchers at the Perelman School of Medicine at the University of Pennsylvania, showed that reliable antiviral predictions can be made even when only a modest amount of experimental data are available.
"We see this as a template for rapid antiviral discovery," said César de la Fuente, PhD, a Presidential Associate Professor of Psychiatry, Microbiology, Bioengineering, Chemical and Biomolecular Engineering, and Chemistry. "Whether the next threat is another enterovirus, an emergent respiratory pathogen or a reemerging virus like polio, AI driven methods can help us stay ahead."
AI streamlines the research process
Using an initial panel of 36 small molecules, the investigators trained a machine learning model to spot certain shapes and chemical features that help stop viruses, scoring each compound's likelihood of blocking EV71. The authors put their AI-chosen shortlist to the test: out of eight compounds, five successfully slowed the virus in cell experiments—about ten times more hits than traditional screening methods usually deliver.
"We are collapsing what used to be months of trial‑and‑error into days," said César de la Fuente, PhD, a Presidential Associate Professor of Psychiatry, Microbiology, Bioengineering, Chemical and Biomolecular Engineering, and Chemistry. "The approach is especially powerful when time, budget or other constraints limit the amount of data you can generate up front."
EV71 infections can escalate from mild rash and fever to severe neurological complications, particularly in children under seven and immunocompromised adults. No FDA-approved antivirals currently target the virus.
All five confirmed results were tested using computer simulations, which showed that they stuck to certain spots on the virus, findings which could help future researchers stop the virus from changing shape and entering cells.
"We see this as a template for rapid antiviral discovery," added postdoctoral researcher Angela Cesaro, PhD, a study co-author. "Whether the next threat is another enterovirus, an emergent respiratory pathogen or a reemerging virus like polio, our AI-driven method shows that, even with limited data, machine learning can accelerate the development of effective solutions and drive a swift response to future outbreaks."
The work included collaboration with Procter & Gamble and Cornell University. Research reported in this publication was supported by the Langer Prize (AIChE Foundation), the NIH R35GM138201, DTRA HDTRA1-21-1-0014, and NIAID NIH R01AI149487. Figures created with BioRender.com are attributed as such. Molecules were rendered using the PyMOL Molecular Graphics System, Version 3.1.1 Schrödinger, LLC.
Cesar de la Fuente-Nunez is a co-founder of, and scientific advisor, to Peptaris, Inc., provides consulting services to Invaio Sciences, and is a member of the Scientific Advisory Boards of Nowture S.L., Peptidus, European Biotech Venture Builder, the Peptide Drug Hunting Consortium (PDHC), ePhective Therapeutics, Inc., and Phare Bio. The de la Fuente Lab has received research funding or in-kind donations from United Therapeutics, Strata Manufacturing PJSC, and Procter & Gamble; however, only support from Procter & Gamble was used in this work. An invention disclosure associated with this work has been filed.
