Quantum Computing Meets AI: Scientists Generate Novel Peptides for Drug Discovery

Researchers at the Technical University of Denmark (DTU) have demonstrated that a quantum computer can enhance the accuracy and scope of generative artificial intelligence models used in drug discovery. Working on weekends and pooling leftover funding from other projects, the team showed that quantum-enhanced AI could generate novel peptides capable of binding to specific proteins in the human body—a critical step in vaccine development.

A Side Project Born from Scientific Curiosity

The DTU team, led by professor Timothy Patrick Jenkins, ran their generative AI model for protein prediction alongside a printer-sized quantum computer built by British startup ORCA Computing. The hybrid approach connected quantum machines with traditional processors to accelerate the AI's performance.

The researchers dedicated their own spare time and redirected unspent money from existing grants because, as Jenkins explained, "most innovative science is too scary for foundations." The team's work is typically funded by the Novo Nordisk Foundation and focuses on using big data and AI to discover proteins that could unlock new immunotherapies more cheaply and quickly.

Jenkins himself was initially doubtful about the technology's relevance to his field. "I was a huge quantum skeptic," he said, believing any practical application to his research would be "decades away." The team's hypothesis emerged after learning that quantum computers had shown similar diversity-boosting effects in image generation tasks.

Quantum Advantage in Data-Scarce Scenarios

After generating peptides computationally, the team manufactured them in the laboratory and tested whether they would bind to the target proteins. The results showed that the quantum-enhanced model produced more successful peptides than its purely classical counterpart, with the strongest improvements occurring in cases where training data was limited.

This finding is particularly significant given one of the team's core challenges: the lack of genetic data covering the full diversity of the human population. Most medical research has historically focused on Western populations, making it difficult to develop peptides that work effectively for understudied groups in regions such as Asia and Africa. The researchers hypothesized that embedding a quantum computer into their workflow could help generate a more diverse set of peptides, particularly for targets where available data was sparse.

"We needed to really prove it to convince skeptics that our predictions connect to the real world," Jenkins said. The successful laboratory validation of the model's peptide designs marks an important step toward establishing quantum computing's practical relevance in biomedical research.

Limitations and the Road Ahead

Despite the promising results, the breakthrough does not yet signal a revolution in pharmaceutical research. Current quantum computers remain too small to run full-scale, state-of-the-art AI models, meaning that better results could still be achieved on classical computers for certain tasks.

"Quantum is still not very powerful, so the level of complexity that we could encode wasn't a normal-sized antibody, which is what we usually work with," explained Jonathan Funk, a PhD student at DTU. Additionally, identifying a peptide that binds to a specific gene represents just one step in vaccine development and would not alone produce a successful drug.

The team believes the approach could eventually accelerate the development of personalized immunotherapies and vaccines, as well as improve drug efficacy for understudied populations. Jenkins noted that generative AI workflows are especially valuable for neglected diseases that receive little research funding. He is also exploring whether quantum computing can enhance his generative AI methods for designing synthetic antidotes to snakebite venom.

A Near-Term Win for Quantum Computing

ORCA Computing CEO Richard Murray acknowledged that skepticism toward quantum technology persists in industry, partly because the field "has not ever had really clear near-term examples of usefulness." He described the DTU study as notable for demonstrating a concrete near-term commercial application for quantum computing.

ORCA Computing is also applying the technology through partnerships with oil major BP on chemistry problems and with automaker Toyota to improve its design process efficiency. The DTU team plans to test their workflow with more advanced models and larger proteins in future experiments.

"We needed this as an easy way to validate that now we actually have a shot at moving the needle substantially," Jenkins said of the project's significance. As quantum hardware continues to develop, the intersection of quantum computing and generative AI may open new pathways for addressing some of medicine's most persistent challenges.

Could quantum-enhanced AI reshape the future of drug discovery? Share this article with your network and join the conversation about how emerging technologies are transforming biomedical research.

Source: Wired