ForceGen: End-to-end de novo protein generation based on nonlinear mechanical unfolding responses using a protein language diffusion model

TL;DR

ForceGen is an innovative deep learning model that designs novel proteins with specific nonlinear mechanical properties, validated through molecular simulations, advancing the discovery of superior mechanobiological materials.

Contribution

The paper introduces a novel generative model that predicts protein sequences meeting complex mechanical property objectives using a protein language diffusion approach.

Findings

Designed proteins meet targeted mechanical properties

Validated by molecular simulations showing novel, functional proteins

Enables rapid exploration of protein sequence space for mechanical features

Abstract

Through evolution, nature has presented a set of remarkable protein materials, including elastins, silks, keratins and collagens with superior mechanical performances that play crucial roles in mechanobiology. However, going beyond natural designs to discover proteins that meet specified mechanical properties remains challenging. Here we report a generative model that predicts protein designs to meet complex nonlinear mechanical property-design objectives. Our model leverages deep knowledge on protein sequences from a pre-trained protein language model and maps mechanical unfolding responses to create novel proteins. Via full-atom molecular simulations for direct validation, we demonstrate that the designed proteins are novel, and fulfill the targeted mechanical properties, including unfolding energy and mechanical strength, as well as the detailed unfolding force-separation curves. Our model offers rapid pathways to explore the enormous mechanobiological protein sequence space unconstrained by biological synthesis, using mechanical features as target to enable the discovery of protein materials with superior mechanical properties.