AlphaFold distillation for inverse protein design

TL;DR

This paper introduces a faster method for designing protein sequences that fold into specific 3D structures by using knowledge distillation from AlphaFold.

Contribution

The novelty is using knowledge distillation on AlphaFold confidence metrics to create a fast, differentiable model for inverse protein design.

Findings

The method improves sequence recovery by up to 3% compared to non-regularized baselines.

It increases protein diversity by up to 45% while maintaining structural consistency.

The approach is versatile and applicable to other design tasks like protein infilling.

Abstract

Inverse protein folding, the process of designing sequences that fold into a specific 3D structure, is crucial in bio-engineering and drug discovery. Traditional methods rely on experimentally resolved structures, but these cover only a small fraction of protein sequences. Forward folding models like AlphaFold offer a potential solution by accurately predicting structures from sequences. However, these models are too slow for integration into the optimization loop of inverse folding models during training. To address this, we propose using knowledge distillation on folding model confidence metrics, such as pTM or pLDDT scores, to create a faster and end-to-end differentiable distilled model. This model can then be used as a structure consistency regularizer in training the inverse folding model. Our technique is versatile and can be applied to other design tasks, such as sequence-based protein infilling. Experimental results show that our method outperforms non-regularized baselines, yielding up to 3% improvement in sequence recovery and up to 45% improvement in protein diversity while maintaining structural consistency in generated sequences.

Figures