AI-Designed Universal Coronavirus Vaccine Candidate pEVAC-PS Clears Phase I Human Trial

AI-Designed Universal Coronavirus Vaccine Candidate pEVAC-PS Clears Phase I Human Trial

In June 2026, researchers from the University of Cambridge and biotech spinout DIOSynVax (DVX) Ltd published the first human clinical trial results for a universal coronavirus vaccine designed entirely by artificial intelligence. The study, published in the Journal of Infection, showed that the pan-sarbecovirus vaccine candidate pEVAC-PS was safe, well-tolerated, and capable of directing the immune system toward conserved features of the coronavirus family.

The DIOSynVax platform (Digitally Immune Optimised Synthetic Vaccines) uses machine learning algorithms to analyze global animal surveillance genetic sequences of the Sarbecovirus subgenus—which includes SARS-CoV-1, SARS-CoV-2, and hundreds of bat coronaviruses. Instead of targeting hyper-mutable regions like traditional vaccines, the AI identified highly conserved structural features across all strains to design a synthetic "super-antigen" composite protein.¹

Key findings from the Phase I trial, which enrolled 39 healthy volunteers between December 2021 and September 2023, include:

• Delivery and Format: pEVAC-PS was formulated as a highly thermostable DNA plasmid vaccine and delivered needle-free using the high-pressure PharmaJet Tropis intradermal microfluidic jet device.
• Safety Profile: No serious adverse events (SAEs) were recorded across any of the four escalating dose levels (0.2 mg to 1.2 mg), establishing a clean safety record.
• Immunogenicity: The vaccine triggered cross-reactive immune responses, directing antibody binding to highly conserved receptor-binding domain (RBD) epitopes shared across the Sarbecovirus family. This included related bat coronaviruses that have not yet spilled over into humans.
• Methodological Limitations: Researchers characterized the overall immune response as "modest and variable." Because the trial occurred during active Omicron waves and booster campaigns, most participants entered the study with high pre-existing background immunity, which likely obscured the vaccine's specific contribution. Additionally, DNA vaccines historically show weaker immunogenicity in humans than in animal models.

A Phase II clinical trial enrolling approximately 200 participants is currently underway to evaluate the vaccine's efficacy in a larger, more diverse population. The DIOSynVax team is also adapting its AI platform to develop broad-spectrum vaccines for influenza and Ebola-family viruses.

Verbatim Quotes

• Tech Times: "For the first time in history, a vaccine whose active ingredient was designed entirely by artificial intelligence has cleared human safety testing — and its target is not a single coronavirus strain, but an entire viral family spanning hundreds of known pathogens..."
• Prof. Saul Faust, Chief Investigator (via Tech Times): "If we can develop and clinically advance this new class of vaccines before a virus outbreak begins, millions of lives could be saved, lockdowns avoided and the economy preserved."
• Marc Boubnovski, Senior AI Scientist at Novo Nordisk (via Tech Times): "The trial 'did not yet show the strong, broad immune response you would want before calling it a protective universal coronavirus vaccine,' while acknowledging it showed evidence of directing immunity toward conserved sarbecovirus regions."