Researchers at the Technical University of Denmark (DTU) and UK-based ORCA Computing have demonstrated that a quantum computer can improve the accuracy and reach of AI-driven peptide design, opening a potential path to cheaper, faster development of drugs for rare diseases and underserved populations.
Peptides, short chains of amino acids that act as signalling molecules in the body, are promising therapeutic candidates for a wide range of conditions, from metabolic disorders to infectious diseases. But designing effective peptide drugs has traditionally required extensive computational resources and experimental iteration, limiting the range of targets that pharmaceutical companies are willing to pursue.
The team cobbled together funding and time to show how ORCA Computing’s photonic quantum processor, combined with classical AI models, could generate novel peptide sequences with properties tailored to specific biological targets. The quantum-enhanced approach was able to explore a wider range of molecular configurations than classical computing alone, producing candidate peptides that might otherwise have been missed.
“This is a proof of concept that quantum computing can add real value to generative AI in drug discovery,” the researchers said. The work focused on peptide targets relevant to diseases that lack sufficient market incentives for traditional pharmaceutical development, precisely the kind of “orphan” indications that rarely attract large-scale R&D investment.
ORCA Computing’s PT-2 photonic quantum system, which operates at room temperature using standard telecommunications components, was used to generate richer probability distributions for the AI model’s training process. The company’s technology is based on a patented quantum memory that traps and releases single photons on demand, enabling hybrid quantum-classical machine learning workflows.
The demonstration comes as the broader drug discovery industry wrestles with the cost and complexity of bringing new therapies to market. Generative AI models have already shown they can design novel proteins and small molecules, but the addition of quantum computing could unlock more chemically complex targets that classical AI struggles with.
ORCA Computing has previously announced partnerships with institutions including the UK’s National Quantum Computing Centre and Poznan Supercomputing and Networking Center in Poland to develop quantum-enhanced machine learning for applications ranging from chemical formulation to biological imaging.
Sources: Scientists’ Side Hustle? Using AI and Quantum Computing to Generate New Peptides (Wired, July 12, 2026)