ProteinGuide: On-the-fly property guidance for protein sequence generative models

TL;DR

ProteinGuide introduces a versatile on-the-fly conditioning framework for various protein sequence generative models, enabling targeted protein design based on specific properties without retraining the models.

Contribution

It provides a unifying statistical framework for on-the-fly conditioning of diverse protein generative models, demonstrated through in silico and in vivo experiments.

Findings

Successfully designed proteins with desired properties such as stability and activity.

Optimized multiple properties simultaneously in protein design.

Enhanced base editing efficiency in vivo with a single round of guidance.

Abstract

Sequence generative models are transforming protein engineering. However, no principled framework exists for conditioning these models on auxiliary information, such as experimental data, without additional training of a generative model. Herein, we present ProteinGuide, a method for such "on-the-fly" conditioning, amenable to a broad class of protein generative models including Masked Language Models (e.g. ESM3), any-order auto-regressive models (e.g. ProteinMPNN) as well as diffusion and flow matching models (e.g. MultiFlow). ProteinGuide stems from our unifying view of these model classes under a single statistical framework. As proof of principle, we perform several in silico experiments. We first guide pre-trained generative models to design proteins with user-specified properties, such as higher stability or activity. Next, we design for optimizing two desired properties that are in tension with each other. Finally, we apply our method in the wet lab, using ProteinGuide to increase the editing activity of an adenine base editor in vivo with data from only a single pooled library of 2,000 variants. We find that a single round of ProteinGuide achieves a higher editing efficiency than was previously achieved using seven rounds of directed evolution.