Neural network conditioned to produce thermophilic protein sequences can increase thermal stability

TL;DR

A new method called NOMELT uses neural networks to design proteins that are more stable at high temperatures, successfully increasing the melting temperature of a fruit fly protein by 15.5 K.

Contribution

NOMELT introduces a novel neural machine translation approach specifically trained to enhance thermal stability in proteins.

Findings

NOMELT increases the melting temperature of a Drosophila melanogaster protein by 15.5 K.

The model ranks melting and half-activation temperatures across protein families without needing extensive homology data.

NOMELT learns thermophilicity rather than general natural variation, enabling zero-shot predictions.

Abstract

This work presents Neural Optimization for Melting-temperature Enabled by Leveraging Translation (NOMELT), a novel approach for designing and ranking high-temperature stable proteins using neural machine translation. The model, trained on over 4 million protein homologous pairs from organisms adapted to different temperatures, demonstrates promising capability in targeting thermal stability. A designed variant of the Drosophila melanogaster Engrailed Homeodomain shows a melting temperature increase of 15.5 K. Furthermore, NOMELT achieves zero-shot predictive capabilities in ranking experimental melting and half-activation temperatures across a number of protein families. It achieves this without requiring extensive homology data or massive training datasets as do existing zero-shot predictors by specifically learning thermophilicity, as opposed to all natural variation. These findings underscore the potential of leveraging organismal growth temperatures in context-dependent design of proteins for enhanced thermal stability.

Figures