Protein backbones designed by diffusion, but not by language models, have more secondary structure

Summary

Designed protein backbones have more secondary structure content than naturally occurring proteins (1). Natural proteins redesigned for improved expression have also had their loops removed (2). In contrast, language model-designed proteins tend to have more sheets and loops.

Figures

Ref (1)

Ref (2)

Ref (3)

See also

• Protein backbones designed using diffusion, but not sequence-based models, have fewer beta sheets

1.

Chu AE, Lu T, Huang P-S. Sparks of function by de novo protein design. Nature Biotechnology. 2024;42(2):203–15. Available from: https://doi.org/10.1038/s41587-024-02133-2

2.

Sumida KH, Núñez-Franco R, Kalvet I, Pellock SJ, Wicky BIM, Milles LF, et al. Improving Protein Expression, Stability, and Function with ProteinMPNN. Journal of the American Chemical Society. 2024;146(3):2054–61. Available from: https://doi.org/10.1021/jacs.3c10941

3.

Alamdari S, Thakkar N, van den Berg R, Tenenholtz N, Strome R, Moses AM, et al. Protein generation with evolutionary diffusion: sequence is all you need. openRxiv; 2023. Available from: https://doi.org/10.1101/2023.09.11.556673