Towards deep learning sequence-structure co-generation for protein design

TL;DR

This paper reviews recent advances in deep generative models that simultaneously generate protein sequences and structures, aiming to improve accuracy and controllability in protein design.

Contribution

It provides a comprehensive overview of current sequence-structure co-generation methods and discusses future opportunities for development in this area.

Findings

Emerging co-generation methods enhance protein design accuracy.

Recent models enable controllable protein generation.

The review highlights key methodological principles.

Abstract

Deep generative models that learn from the distribution of natural protein sequences and structures may enable the design of new proteins with valuable functions. While the majority of today's models focus on generating either sequences or structures, emerging co-generation methods promise more accurate and controllable protein design, ideally achieved by modeling both modalities simultaneously. Here we review recent advances in deep generative models for protein design, with a particular focus on sequence-structure co-generation methods. We describe the key methodological and evaluation principles underlying these methods, highlight recent advances from the literature, and discuss opportunities for continued development of sequence-structure co-generation approaches.