Researchers Use Quantum Computer to Improve AI Peptide Generation
7 reported2 unconfirmed
A team from the Technical University of Denmark has demonstrated that a quantum computer can improve the accuracy and reach of generative artificial intelligence models used in drug discovery. The researchers, led by DTU professor Timothy Patrick Jenkins, worked on weekends and used leftover money from other projects to run their generative AI model for predicting proteins in conjunction with a printer-sized quantum computer built by British startup ORCA Computing. The hybrid technique was used to generate novel peptides, which are short chains of amino acids capable of binding to specific proteins in the body, a crucial step in vaccine development. Laboratory testing showed the model produced more successful peptides than its classical counterpart, with the strongest improvements occurring where training data was scarce. The team believes the machine could accelerate the development of personalized immunotherapies and vaccines, as well as improve drug efficacy in understudied groups. However, the process will not revolutionize research yet, as quantum computers remain too small to run full-scale, cutting-edge AI models.
What’s reported
The Technical University of Denmark team used a generative AI model with a quantum computer built by ORCA Computing.
The hybrid technique generated novel peptides capable of binding to specific proteins in the body.
The researchers worked weekends and pooled unspent money from other projects to fund the work.
Laboratory testing showed the model produced more successful peptides than its classical counterpart, especially where training data was rare.
The team believes the machine could accelerate personalized immunotherapies and vaccines, and improve drug efficacy in understudied groups.
Quantum computers are still too small to run full-scale, cutting-edge AI models, so better results could be achieved on a classical computer.
Finding a peptide that can bind to a specific gene is just one step in vaccine development and would not alone yield successful drugs.
Open questions
Whether the workflow can be successfully applied to larger proteins and more cutting-edge models.
Whether the process will lead to practical commercial applications beyond this study.
Key figures
Timothy Patrick Jenkins: DTU professor who led the project.
Jonathan Funk: DTU PhD student.
Richard Murray: CEO of ORCA Computing.
Sources: Wired
