Including optimal growth temperature during pre-training of PLMs improves prediction and design of thermostability

Summary

Including optimal growth temperature as a regression target during pretraining of protein language models improves the prediction and design of thermostability (1).

Figures

Ref (1)

See also

• PLMs are biased by uneven distribution of sequence data in datasets such as UniRef and UniProt

1.

Jiang F, Li M, Dong J, Yu Y, Sun X, Wu B, et al. A general temperature-guided language model to design proteins of enhanced stability and activity. Science Advances. 2024;10(48). Available from: https://doi.org/10.1126/sciadv.adr2641