Sequence perplexity and TM-score are negatively correlated when predicting structure using protein language models

Summary

Sequence perplexity and TM-score are negatively correlated when predicting protein structure using protein language models (1).** This was observed with ESMFold and ESM3.

Figures

Ref (1)

1.

Bushuiev A, Bushuiev R, Pimenova O, Zadorozhny N, Samusevich R, Manaskova E, et al. One protein is all you need. 2024; Available from: https://arxiv.org/abs/2411.02109