丹麦科技大学的研究团队利用业余时间和剩余资金，成功证明量子电脑能提升生成式人工智慧在药物探索模型上的准确度与范围。他们将预测蛋白质的AI模型与英国新创公司Orca Computing打造的量子电脑结合，透过这种混合技术生成能与体内特定蛋白质结合的新型胜肽，这对于疫苗的开发至关重要。

实验结果显示，相较于传统的运算方法，这套结合量子计算的模型能产生更多成功的胜肽，尤其在训练数据稀缺的情况下改善最为显著。这项突破不仅有望加速个人化免疫疗法与疫苗的发展，也能够提高药物在亚洲与非洲等缺乏研究数据之族群中的功效。

虽然这项研究展示了量子计算在近期的商业应用潜力，但由于现今的量子电脑规模仍小，尚无法运行完整的尖端AI模型。研究团队未来将尝试把此工作流程应用于更先进的模型与更大的蛋白质，并计划利用量子电脑来增强其设计蛇毒合成解毒剂的生成式AI方法。

A research team from the Technical University of Denmark used their spare time and leftover funds to successfully demonstrate that quantum computers can improve the accuracy and reach of generative AI in drug discovery models. By combining their protein-predicting AI model with a quantum computer built by the British startup Orca Computing, they utilized a hybrid technique to generate novel peptides capable of binding to specific proteins in the body, which is a crucial step in vaccine development.

Experimental results showed that, compared to classical computing methods, this quantum-enhanced model produced more successful peptides, with the most significant improvements occurring where training data was scarce. This breakthrough has the potential to accelerate the development of personalized immunotherapies and vaccines, as well as improve drug efficacy for understudied populations, such as those in Asia and Africa.

Although this study demonstrates near-term commercial application potential for quantum computing, current quantum computers are still too small to run full-scale, cutting-edge AI models. The research team plans to apply this workflow to more advanced models and larger proteins in the future, and is even planning to use quantum computers to enhance their generative AI methods for designing synthetic antidotes for snakebite venom.