Structure-aware protein self-supervised learning
Bioinformatics · 03.04.2023 · 39 (4)
DOI: 10.1093/bioinformatics/btad189 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 13.04.2023. Verfasst von Can Sam Chen und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, McGill University, 845 Rue Sherbrooke O, Montreal, Quebec H3A 0G4, Canada. Hauptthemen laut MEDLINE: Membrane Proteins, Language. Die Arbeit wurde bisher 57-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Motivation Protein representation learning methods have shown great potential to many downstream tasks in biological applications. A few recent studies have demonstrated that the self-supervised learning is a promising solution to addressing insufficient labels of proteins, which is a major obstacle to effective protein representation learning. However, existing protein representation learning is usually pretrained on protein sequences without considering the important protein structural information. Results In this work, we propose a novel structure-aware protein self-supervised learning method to effectively capture structural information of proteins. In particular, a graph neural network model is pretrained to preserve the protein structural information with self-supervised tasks from a pairwise residue distance perspective and a dihedral angle perspective, respectively. Furthermore, we propose to leverage the available protein language model pretrained on protein sequences to enhance the self-supervised learning. Specifically, we identify the relation between the sequential information in the protein language model and the structural information in the specially designed graph neural network model via a novel pseudo bi-level optimization scheme. We conduct experiments on three downstream tasks: the binary classification into membrane/non-membrane proteins, the location classification into 10 cellular compartments, and the enzyme-catalyzed reaction classification into 384 EC numbers, and these experiments verify the effectiveness of our proposed method. Availability and implementation The Alphafold2 database is available in https://alphafold.ebi.ac.uk/. The PDB files are available in https://www.rcsb.org/. The downstream tasks are available in https://github.com/phermosilla/IEConv\_proteins/tree/master/Datasets. The code of the proposed method is available in https://github.com/GGchen1997/STEPS_Bioinformatics.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Computer Science, McGill University, 845 Rue Sherbrooke O, Montreal, Quebec H3A 0G4, Canada.
- MILA-Quebec AI Institute, 6666 Rue Saint-Urbain, Montreal, Quebec H2S 3H1, Canada.
- Baidu Research, Xibeiwang East Road, Haidian District, Beijing 100193, China.
- Baidu Inc., Xuefu Road East, Nanshan District, Shenzhen 518000, China.
- BCG X, Level 22, West Tower, Genesis Beijing 8 Xinyuan South Road, Chaoyang District, Beijing 100027, China.
ORCID-Profile: Can Sam Chen, Jingbo Zhou
Zitieren
APA
Chen, C. S., Zhou, J., Wang, F., Liu, X., & Dou, D. (2023). Structure-aware protein self-supervised learning. Bioinformatics, 39(4). https://doi.org/10.1093/bioinformatics/btad189
Vancouver
Chen CS, Zhou J, Wang F, Liu X, Dou D. Structure-aware protein self-supervised learning. Bioinformatics. 2023;39(4). doi:10.1093/bioinformatics/btad189
BibTeX
@article{Chen2023,
author = {Chen, Can Sam and Zhou, Jingbo and Wang, Fan and Liu, Xue and Dou, Dejing},
title = {Structure-aware protein self-supervised learning},
journal = {Bioinformatics},
year = {2023},
volume = {39},
number = {4},
doi = {10.1093/bioinformatics/btad189}
}
EUVIMED