Scientists have achieved It has been shown that a quantum computer can improve the accuracy and scope of drug discovery models with generative artificial intelligence. And they did it taking advantage of their free time and the money they had left over from other projects.

The team at the Technical University of Denmark ran their generative AI model to predict proteins alongside a printer-sized quantum computer built by British startup ORCA Computing, which accelerated AI by linking quantum machines with traditional processors. The researchers used the hybrid technique to generate new peptides (short chains of amino acids) capable of binding to specific proteins in the body. Doing so is a crucial step in vaccine development.

The team of researchers worked on weekends and raised unspent money from other projects because “cutting-edge science is too scary for foundations,” according to DTU professor Timothy Patrick Jenkins, who led the project.

Making the peptides in the lab and testing whether they would bind to particular proteins showed that the model produced more successful peptides than its classical counterpart, with the strongest improvements where training data was sparse.

The team believes the machine could accelerate the development of personalized immunotherapies and vaccines, as well as improve the effectiveness of drugs in understudied groups.

“We needed to really prove it to convince skeptics that our predictions connect to the real world,” Patrick Jenkins tells WIRED. Quantum computing remains a nascent field and faces intense scrutiny due to the technical challenges involved in building these machines and successfully applying them to solve problems.

Even Patrick Jenkins was initially reluctant to explore the technology: “I was a big quantum skeptic,” he says with a laugh, believing that any application to his work would be “decades away.”

He and his team use big data and artificial intelligence to discover proteins that could unlock new, cheaper and faster immunotherapies, often funded by the Novo Nordisk Foundation. While most biological modellers are desperate for more data, a particular challenge for his team has been the lack of data on the full range of genetic information across the human race, as most medical research has focused on Western populations. This may make it difficult to develop peptides that work in understudied populations, such as those in Asia and Africa, he says.

His team hypothesized that incorporating a quantum computer into their workflow could cause it to generate a more diverse set of peptides, especially for targets where they had less data, after learning that the machines had a similar effect when generating images.

The newly discovered process will not revolutionize research yet, as quantum computers are still too small to run cutting-edge AI models on a large scale, meaning better results could be achieved on a classical computer.

“Quantum technology is not very powerful yet, so the level of complexity we were able to encode was not a normal-sized antibody, which is what we typically work with,” says DTU PhD student Jonathan Funk. Furthermore, finding a peptide that can bind to a specific gene is only one step in the development of a vaccine and would not alone produce successful drugs.

“I think it’s not surprising that many industrial companies think quantum technology is confusing and distant,” ORCA Computing CEO Richard Murray tells WIRED, in part because the technology “has never had really clear examples of near-term utility.”

He says this study is novel because it shows a near-term commercial application of quantum technology. His company is also applying the technology through projects with oil company BP in chemicals and automaker Toyota to make its design process more efficient.

The DTU team will now see if they can use the workflow with more advanced models and larger proteins. “We needed this as an easy way to validate that we now really have an opportunity to make substantial change,” says Patrick Jenkins, noting that generative AI workflows are particularly valuable in neglected diseases that receive little research money. It is also considering using a quantum computer to improve its generative artificial intelligence method for designing synthetic antidotes to snakebite venom.