Joint Design of Protein Sequence and Structure based on Motifs

TL;DR

GeoPro is a novel method for jointly designing protein sequences and structures, leveraging 3D geometry to produce diverse, functional proteins that outperform existing methods and discover new biologically stable proteins.

Contribution

It introduces GeoPro, a joint design approach using equivariant encoding and geometry-guided decoding for protein backbone and sequence, enabling the discovery of novel functional proteins.

Findings

Outperforms strong baselines on metalloprotein datasets.

Discovers novel stable β-lactamases and myoglobins.

Produced proteins with natural-like folding and active sites.

Abstract

Designing novel proteins with desired functions is crucial in biology and chemistry. However, most existing work focus on protein sequence design, leaving protein sequence and structure co-design underexplored. In this paper, we propose GeoPro, a method to design protein backbone structure and sequence jointly. Our motivation is that protein sequence and its backbone structure constrain each other, and thus joint design of both can not only avoid nonfolding and misfolding but also produce more diverse candidates with desired functions. To this end, GeoPro is powered by an equivariant encoder for three-dimensional (3D) backbone structure and a protein sequence decoder guided by 3D geometry. Experimental results on two biologically significant metalloprotein datasets, including $\beta$-lactamases and myoglobins, show that our proposed GeoPro outperforms several strong baselines on most metrics. Remarkably, our method discovers novel $\beta$-lactamases and myoglobins which are not present in protein data bank (PDB) and UniProt. These proteins exhibit stable folding and active site environments reminiscent of those of natural proteins, demonstrating their excellent potential to be biologically functional.