Lightweight Equivariant Graph Representation Learning for Protein Engineering

Bingxin Zhou, Outongyi Lv, Kai Yi, Xinye Xiong, Pan Tan, Liang Hong, Yu Guang WangICLR 2023 · OpenReview

Abstract

This work tackles the issue of directed evolution in computational protein design that makes accurate predictions of the function of a protein mutant. We design a lightweight pre-training graph neural network model for multi-task protein representation learning from its 3D structure. Rather than reconstructing and optimizing the protein structure, the trained model recovers the amino acid types and key properties of the central residues from a given noisy three-dimensional local environment. On the prediction task for the higher-order mutants, where many amino acid sites of the protein are mutated, the proposed training strategy achieves remarkably higher performance by 20% improvement at the cost of requiring less than 1% of computational resources that are required by popular transformer-based state-of-the-art deep learning models for protein design.
BibTeX
@inproceedings{zhou2023lightweight,
  author = {Bingxin Zhou and Outongyi Lv and Kai Yi and Xinye Xiong and Pan Tan and Liang Hong and Yu Guang Wang},
  title = {{Lightweight Equivariant Graph Representation Learning for Protein Engineering}},
  booktitle = {International Conference on Learning Representations},
  year = {2023},
  url = {https://openreview.net/forum?id=IWoHx6bY4Zm},
}

Loading related content...

Figure