Generative artificial intelligence for de novo protein design

TL;DR

Recent advances in artificial intelligence, including generative models like language models and diffusion processes, have significantly improved de novo protein design, enabling the creation of novel proteins with desirable functions and near 20% experimental success.

Contribution

This review synthesizes current AI-driven methods for de novo protein design and offers a framework to understand their integration and challenges in the field.

Findings

Generative AI models can produce realistic, functional proteins.

Experimental success rates of AI-designed proteins are approaching 20%.

Incorporating biochemical knowledge enhances design performance and interpretability.

Abstract

Engineering new molecules with desirable functions and properties has the potential to extend our ability to engineer proteins beyond what nature has so far evolved. Advances in the so-called "de novo" design problem have recently been brought forward by developments in artificial intelligence. Generative architectures, such as language models and diffusion processes, seem adept at generating novel, yet realistic proteins that display desirable properties and perform specified functions. State-of-the-art design protocols now achieve experimental success rates nearing 20%, thus widening the access to de novo designed proteins. Despite extensive progress, there are clear field-wide challenges, for example in determining the best in silico metrics to prioritise designs for experimental testing, and in designing proteins that can undergo large conformational changes or be regulated by post-translational modifications and other cellular processes. With an increase in the number of models being developed, this review provides a framework to understand how these tools fit into the overall process of de novo protein design. Throughout, we highlight the power of incorporating biochemical knowledge to improve performance and interpretability.