Weekend Science: A Quantum Computer Just Helped Invent New Drug Candidates

Key points

• Researchers at the Technical University of Denmark used a quantum-assisted AI model in 2024 to generate novel peptides, short protein-like chains used in drug development.
• Lab tests confirmed the quantum-assisted model produced more successful peptides than the standard software equivalent, with the biggest gains where training data was scarce.
• The team funded the work by pooling unspent money from other projects and working weekends, because no grant body would back it.
• Quantum computers are still too small to run full-scale drug-discovery models, so this result is a proof of concept, not a finished product.
• ORCA Computing, the British startup that built the quantum machine, says the study is one of the first clear near-term commercial uses of the technology.

A small team at the Technical University of Denmark (DTU) has shown that plugging a quantum computer into an AI drug-discovery pipeline can produce better medicine candidates than using a regular computer alone. They published the results after running the experiment on weekends, paying for it with leftover budget from other grants.

The AI model in question is a generative model, software that creates new outputs rather than just classifying existing ones, similar in spirit to the technology behind image generators. Here, it was generating peptides: tiny chains of amino acids, the building blocks of proteins, that can latch onto specific targets inside the body. Finding peptides that bind reliably to a target protein is a critical early step in designing vaccines and other medicines.

The quantum machine they used was built by British startup ORCA Computing and is roughly the size of a desktop printer. It is not a standalone replacement for a normal computer. Instead, it works alongside one, a setup researchers call a hybrid system. The quantum component handles a specific part of the calculation where quantum physics gives it an edge in exploring varied possibilities.

Lab tests mattered here. The team actually synthesised the peptides the model suggested and tested whether they physically stuck to their target proteins. They did, and at a higher success rate than peptides generated by the classical, non-quantum version of the same model. The improvement was sharpest for proteins where the training data, the historical examples the AI learns from, was limited.

That last point is significant. Most medical research has focused on Western populations, leaving less genetic data for people in Asia, Africa, and other understudied groups. DTU professor Timothy Patrick Jenkins, who led the project, told Wired that the quantum step appeared to help the model generate a more diverse set of candidates even with thin data, which could eventually help produce medicines that work across a wider range of patients.

Does this mean quantum computers will change medicine soon?

Not yet. The quantum machines available today are too small to run a full-sized antibody model, the kind researchers normally work with. A standard high-end computer would still outperform them on most real drug-discovery tasks. ORCA Computing chief executive Richard Murray acknowledged the technology has long suffered from a lack of clear near-term uses. This study, he says, is one of the first concrete examples that it can do something useful in a commercial setting today.

Jenkins is already planning the next step: testing the workflow on larger proteins and more advanced AI models. He is also exploring whether the same quantum approach could help design synthetic antidotes for snakebite venom, a neglected area that attracts little research funding.

For patients and the public, the practical impact is years away. What this study does is give researchers a small but real reason to keep exploring the combination.