Scientists at the Technical University of Denmark combined quantum computing with generative AI to improve drug discovery models. The hybrid approach, using a printer-sized quantum computer from ORCA Computing, enabled the creation of novel peptides capable of binding to specific proteins. This is a critical step in vaccine development, as the team demonstrated that the model produced more successful peptides than classical counterparts, especially when training data was limited.
The researchers worked weekends and pooled leftover funds from other projects, as most foundations are hesitant to fund innovative science. DTU professor Timothy Patrick Jenkins explained that the team needed to prove their predictions connect to real-world outcomes. Quantum computing remains a developing field, facing challenges in building machines and applying them effectively to solve complex problems.
The study highlights the potential of quantum computing in accelerating personalized immunotherapies and improving drug efficacy for understudied populations. However, the technology is still too small to run full-scale AI models, limiting its current impact. DTU PhD student Jonathan Funk noted that quantum computers lack the power to handle the complexity of typical antibodies, and generating a peptide that binds to a specific gene is just one step in vaccine development.
Source: wired
