Lightweight Equivariant Graph Representation Learning for Protein EngineeringDownload PDF

Published: 01 Feb 2023, Last Modified: 13 Feb 2023Submitted to ICLR 2023Readers: Everyone
Keywords: graph neural networks
TL;DR: We design a lightweight pre-training model for multi-task protein representation learning from its 3D structure and sequence.
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.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability )
Supplementary Material: zip
13 Replies