DeepPFP: a multi-task-aware architecture for protein function prediction
Briefings in Bioinformatics · 2024
DOI: 10.1093/bib/bbae579 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2024. Verfasst von Han Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Science and Technology, Beijing University of Chemical Technology, No. 15 North Third Ring East Road, Chaoyang District, Beiji…. Hauptthemen laut MEDLINE: Proteins, Deep Learning, Computational Biology. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Technology of the People's Republic of China.
Abstract (Originalsprache)
Deriving protein function from protein sequences poses a significant challenge due to the intricate relationship between sequence and function. Deep learning has made remarkable strides in predicting sequence-function relationships. However, models tailored for specific tasks or protein types encounter difficulties when using transfer learning across domains. This is attributed to the fact that protein function relies heavily on structural characteristics rather than mere sequence information. Consequently, there is a pressing need for a model capable of capturing shared features among diverse sequence-function mapping tasks to address the generalization issue. In this study, we explore the potential of Model-Agnostic Meta-Learning combined with a protein language model called Evolutionary Scale Modeling to tackle this challenge. Our approach involves training the architecture on five out-domain deep mutational scanning (DMS) datasets and evaluating its performance across four key dimensions. Our findings demonstrate that the proposed architecture exhibits satisfactory performance in terms of generalization and employs an effective few-shot learning strategy. To explain further, Compared to the best results, the Pearson’s correlation coefficient (PCC) in the final stage increased by ~0.31%. Furthermore, we leverage the trained architecture to predict binding affinity scores of the DMS dataset of SARS-CoV-2 using transfer learning. Notably, training on a subset of the Ube4b dataset with 500 samples resulted in a notable improvement of 0.11 in the PCC. These results underscore the potential of our conceptual architecture as a promising methodology for multi-task protein function prediction.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- College of Information Science and Technology, Beijing University of Chemical Technology, No. 15 North Third Ring East Road, Chaoyang District, Beijing 100029, China.
- Changchun Veterinary Research Institute, Chinese Academy of Agricultural Sciences, State Key Laboratory of Pathogen and Biosecurity, Key Laboratory of Jilin Province for Zoonosis Prevention and Control, Changchun 130122…
- School of Information Science and Technology, Northeast Normal University, Changchun 130117, China.
- Advanced & Interdisciplinary Biotechnology, Academy of Military Medical Sciences, No. 27 Taiping Road, Haidian District, Beijing 100850, China.
ORCID-Profile: Han Wang, Zilin Ren, Xiaochen Bo
Förderung
- Ministry of Science and Technology of the People's Republic of China
Zitieren
APA
Wang, H., Ren, Z., Sun, J., Chen, Y., Bo, X., Xue, J., Gao, J., & Ni, M. (2024). DeepPFP: a multi-task-aware architecture for protein function prediction. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae579
Vancouver
Wang H, Ren Z, Sun J, Chen Y, Bo X, Xue J, et al. DeepPFP: a multi-task-aware architecture for protein function prediction. Briefings in Bioinformatics. 2024. doi:10.1093/bib/bbae579
BibTeX
@article{Wang2024,
author = {Wang, Han and Ren, Zilin and Sun, Jinghong and Chen, Yongbing and Bo, Xiaochen and Xue, JiGuo and Gao, Jingyang and Ni, Ming},
title = {DeepPFP: a multi-task-aware architecture for protein function prediction},
journal = {Briefings in Bioinformatics},
year = {2024},
doi = {10.1093/bib/bbae579}
}
EUVIMED