New-to-nature PHA synthase design using deep learning

Abstract

Polyhydroxyalkanaoate (PHA) synthases are a group of complex, dimeric enzymes which catalyse polymerization of Rhydroxyacids into PHAs. PHA properties depend on their monomer composition but enzymes found in nature have narrow specificities to certain R-hydroxyacids. In this study, a conditional variational autoencoder was used for the first time to design new-to-nature PHA synthases. The model was trained with natural protein sequences obtained from Uniprot and was used for the creation of approximately 10 000 new PHA synthase enzymes. Out of these, 16 sequences were selected for in vivo validation. The selection criteria included the presence of conserved residues such as catalytic amino acids and amino acids in the dimer interface and structural features like the number of -helixes in the N-terminal part of the enzyme. Two of the new-to-nature PHA synthases that had substantial numbers of amino acid substitutions (87 and 98) with respect to the most similar native enzymes were confirmed active and produced poly(hydroxybutyrate) (PHB) when expressed in yeast S. cerevisiae. PHA including PHB have high potential as biodegradable and biocompatible materials. Ultimately the model-designed new-to-nature PHA synthases, could expand the PHA material properties to suit new application areas.