AlphaDesign: A graph protein design method and benchmark on AlphaFoldDB

TL;DR

This paper introduces AlphaDesign, a new benchmark for protein design based on AlphaFoldDB, and proposes ADesign, a graph-based method that improves accuracy and efficiency in predicting protein sequences from structures.

Contribution

The paper establishes a large-scale standardized benchmark for protein design and introduces ADesign, a novel graph transformer-based method with enhanced features and efficiency.

Findings

ADesign outperforms previous models in accuracy by 8%

ADesign achieves over 40 times faster inference speed

The benchmark facilitates standardized comparisons in protein design

Abstract

While DeepMind has tentatively solved protein folding, its inverse problem -- protein design which predicts protein sequences from their 3D structures -- still faces significant challenges. Particularly, the lack of large-scale standardized benchmark and poor accuray hinder the research progress. In order to standardize comparisons and draw more research interest, we use AlphaFold DB, one of the world's largest protein structure databases, to establish a new graph-based benchmark -- AlphaDesign. Based on AlphaDesign, we propose a new method called ADesign to improve accuracy by introducing protein angles as new features, using a simplified graph transformer encoder (SGT), and proposing a confidence-aware protein decoder (CPD). Meanwhile, SGT and CPD also improve model efficiency by simplifying the training and testing procedures. Experiments show that ADesign significantly outperforms previous graph models, e.g., the average accuracy is improved by 8\%, and the inference speed is 40+ times faster than before.