Quantum-AI Hybrid Designs Novel Vaccine Peptides
Get the Tech newsletter
Daily tech — startups, AI labs, chips, the launches that shape the next decade. Free.
- Technical University of Denmark team combined its generative AI protein-prediction model with a printer-sized quantum computer built by British startup ORCA Computing, linking quantum machines with traditional processors to generate novel peptides capable of binding to specific proteins—a key step in vaccine development.
- Lab testing confirmed the quantum-enhanced model produced more successful peptides than its classical counterpart, with the strongest improvements in cases where training data was rare.
- Timothy Patrick Jenkins, the DTU professor who led the project, said the team worked weekends and pooled unspent money from other projects because "most innovative science is too scary for foundations"; the team is broadly funded by the Novo Nordisk Foundation.
- The approach is intended to accelerate personalized immunotherapies and vaccines, and improve drug efficacy in understudied populations like those in Asia and Africa, where most genomic research data is concentrated on Western populations.
- Researchers acknowledged the technique won't revolutionize research yet—quantum computers are still too small to run full-scale cutting-edge AI models, and the peptides produced are smaller than the normal-sized antibodies the team usually works with.
- Jenkins said he was initially a "huge quantum skeptic" and plans to apply the workflow to more cutting-edge models, larger proteins, and synthetic antidotes for snakebite venom.
- ORCA Computing CEO Richard Murray called the study a rare near-term commercial application for quantum, noting the technology "has not ever had really clear near-term examples of usefulness."
Why it matters: DTU's self-funded project—backed broadly by the Novo Nordisk Foundation—offers quantum computing one of its first clear near-term commercial applications in drug discovery. If the workflow scales to larger proteins and more cutting-edge AI models, it could expand vaccine and immunotherapy pipelines to understudied populations whose genetic data is largely absent from Western-focused research.
