Deep Generative Modeling for Protein Design

TL;DR

This paper reviews how deep generative models are transforming protein design by enabling rapid creation of novel proteins with desired properties, surpassing traditional methods in efficiency and effectiveness.

Contribution

It provides a comprehensive overview of five successful classes of deep generative models for proteins and a framework for model-guided protein design.

Findings

Generative models can produce millions of novel proteins resembling native ones.

Models learn informative protein representations surpassing hand-engineered features.

Guided design with discriminative oracles improves candidate selection.

Abstract

Deep learning approaches have produced substantial breakthroughs in fields such as image classification and natural language processing and are making rapid inroads in the area of protein design. Many generative models of proteins have been developed that encompass all known protein sequences, model specific protein families, or extrapolate the dynamics of individual proteins. Those generative models can learn protein representations that are often more informative of protein structure and function than hand-engineered features. Furthermore, they can be used to quickly propose millions of novel proteins that resemble the native counterparts in terms of expression level, stability, or other attributes. The protein design process can further be guided by discriminative oracles to select candidates with the highest probability of having the desired properties. In this review, we discuss five classes of generative models that have been most successful at modeling proteins and provide a framework for model guided protein design.