ProRefiner: an entropy-based refining strategy for inverse protein folding with global graph attention
Open Access
- 16 November 2023
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-12
Abstract
Inverse Protein Folding (IPF) is an important task of protein design, which aims to design sequences compatible with a given backbone structure. Despite the prosperous development of algorithms for this task, existing methods tend to rely on noisy predicted residues located in the local neighborhood when generating sequences. To address this limitation, we propose an entropy-based residue selection method to remove noise in the input residue context. Additionally, we introduce ProRefiner, a memory-efficient global graph attention model to fully utilize the denoised context. Our proposed method achieves state-of-the-art performance on multiple sequence design benchmarks in different design settings. Furthermore, we demonstrate the applicability of ProRefiner in redesigning Transposon-associated transposase B, where six out of the 20 variants we propose exhibit improved gene editing activity.Keywords
Funding Information
- National Natural Science Foundation of China (62006219)
- Natural Science Foundation of Guangdong Province (2022A1515011579)
- National Natural Science Foundation of China (62376254)
- National Key R&D Program of China
- National Natural Science Foundation of China (22007082)
- Natural Science Foundation of Zhejiang Province (LQ21B030013)
- National Key R&D Program of China
- Hong Kong Innovation and Technology Fund
This publication has 40 references indexed in Scilit:
- Direct prediction of profiles of sequences compatible with a protein structure by neural networks with fragment-based local and energy-based nonlocal profilesProteins: Structure, Function, and Bioinformatics, 2014
- Automating human intuition for protein designProteins: Structure, Function, and Bioinformatics, 2013
- RosettaBackrub--a web server for flexible backbone protein structure modeling and designNucleic Acids Research, 2010
- De Novo Computational Design of Retro-Aldol EnzymesScience, 2008
- Scoring function for automated assessment of protein structure template qualityProteins: Structure, Function, and Bioinformatics, 2004
- Protein Structure Prediction Using Rosetta2004
- Computational design of a water‐soluble analog of phospholambanProtein Science, 2003
- Three-dimensional profiles from residue-pair preferences: identification of sequences with beta/alpha-barrel fold.Proceedings of the National Academy of Sciences, 1993
- Amino acid substitution matrices from protein blocks.Proceedings of the National Academy of Sciences, 1992
- Molecular technology: Designing proteins and peptidesNature, 1983