A learnable transition from low temperature to high temperature proteins with neural machine translation

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 increased stability at high temperatures, as validated by estimators and molecular dynamics simulations. Furthermore, NOMELT achieves zero-shot predictive capabilities in ranking experimental melting and half-activation temperatures across two 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.