Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
Scientists have succeeded A appears As much as a computer The accuracy and range of generation can be improved Artificial intelligence drug discovery models. They did this using their free time and money left over from other projects.
The Technical University of Denmark team ran a generative AI model for protein prediction in conjunction with a printer-sized quantum computer built by British startup ORCA Computing, which accelerated AI by linking quantum machines to classical processors. The researchers used the hybrid technology to generate new peptides – short chains of amino acids – capable of binding to specific proteins in the body. Doing so is a critical step in vaccine development.
The team of researchers worked on weekends and pooled unspent funds from other projects because “most innovative science is too scary for institutions,” according to DTU Professor Timothy Patrick Jenkins, who led the project.
Making peptides in the lab and testing whether they would bind to specific proteins showed that the model produced more successful peptides than its classical counterpart, with the strongest improvements where training data was scarce.
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 prove this to convince skeptics that our predictions were relevant to the real world,” Patrick Jenkins tells WIRED. Quantum computing remains a Emerging field It faces intense scrutiny due to the technical challenges of building these machines and Successfully applied to solve problems.
Even Patrick Jenkins was initially reluctant to explore the technology: “I was a huge quantum skeptic, thinking any application of his work would only be decades away,” he says with a laugh.
He and his team use big data and artificial intelligence to discover proteins that could unlock new immunotherapies that are cheaper and faster, often funded by the Novo Nordisk Foundation. While most biological modellers are desperate for more data, a particular challenge facing his team is the lack of data on the full range of genetic information across the human race, since most medical research has focused on Western populations. This could make it difficult to develop peptides that will work in understudied populations, such as those in Asia and Africa, he says.
His team hypothesized that incorporating a quantum computer into the workflow could make it generate a more diverse set of peptides, especially for targets for which they have less data, after learning that machines have a similar effect in generating images.
The newly discovered process won’t revolutionize research yet, as quantum computers are still too small to run large-scale, sophisticated AI models, meaning better results could be achieved on a classical computer.
“Quantum is still not very powerful, so the level of complexity we were able to encode was not a normal-sized antibody, which is what we normally work with,” says Jonathan Funk, a PhD student at DTU. Moreover, finding a peptide that can bind to a specific gene is just one step in vaccine development, and will not alone lead to successful drugs.
“I think it’s not surprising that a lot of industrial companies think quantum is nebulous and distant,” Richard Murray, CEO of computing company ORCA, tells WIRED, in part because the technology has “never provided clear examples of near-term benefit.”
He says this study is novel because it shows a near-term commercial application for the quantum. His company is also applying the technology through projects with oil major BP in chemistry and automaker Toyota to make the design process more efficient.
The DTU team will now see if it can use the workflow with more sophisticated models and larger proteins. “We needed this as an easy way to verify that now we actually have an opportunity to move the needle significantly,” says Patrick Jenkins, noting that generative AI workflows are especially valuable in neglected diseases that receive little research money. He’s also considering using a quantum computer to enhance the generative AI approach to design Synthetic antidote to snakebite venom.
