Recently, a research team from the University of Science and Technology of China adopted a data-driven strategy to establish a new route for protein de novo design. This method breaks through the limitation of only splicing natural fragments to generate new backbone structures, and can even design novel structures that are different from known natural proteins, laying an important foundation for the design of functional proteins such as industrial enzymes and biological materials.
Huang, B., Xu, Y., Hu, X. et al. A backbone-centred energy function of neural networks for protein design. Nature (2022). https://doi.org/10.1038/s41586-021-04...