ifDEEPre: large protein language-based deep learning enables interpretable and fast predictions of enzyme commission numbers
Briefings in Bioinformatics · 23.05.2024 · 25 (4)
DOI: 10.1093/bib/bbae225 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 28.06.2024. Verfasst von Qingxiong Tan und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China. Hauptthemen laut MEDLINE: Deep Learning, Enzymes. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Accurate understanding of the biological functions of enzymes is vital for various tasks in both pathologies and industrial biotechnology. However, the existing methods are usually not fast enough and lack explanations on the prediction results, which severely limits their real-world applications. Following our previous work, DEEPre, we propose a new interpretable and fast version (ifDEEPre) by designing novel self-guided attention and incorporating biological knowledge learned via large protein language models to accurately predict the commission numbers of enzymes and confirm their functions. Novel self-guided attention is designed to optimize the unique contributions of representations, automatically detecting key protein motifs to provide meaningful interpretations. Representations learned from raw protein sequences are strictly screened to improve the running speed of the framework, 50 times faster than DEEPre while requiring 12.89 times smaller storage space. Large language modules are incorporated to learn physical properties from hundreds of millions of proteins, extending biological knowledge of the whole network. Extensive experiments indicate that ifDEEPre outperforms all the current methods, achieving more than 14.22% larger F1-score on the NEW dataset. Furthermore, the trained ifDEEPre models accurately capture multi-level protein biological patterns and infer evolutionary trends of enzymes by taking only raw sequences without label information. Meanwhile, ifDEEPre predicts the evolutionary relationships between different yeast sub-species, which are highly consistent with the ground truth. Case studies indicate that ifDEEPre can detect key amino acid motifs, which have important implications for designing novel enzymes. A web server running ifDEEPre is available at https://proj.cse.cuhk.edu.hk/aihlab/ifdeepre/ to provide convenient services to the public. Meanwhile, ifDEEPre is freely available on GitHub at https://github.com/ml4bio/ifDEEPre/.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China.
- Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China.
- Department of Computer Science, University of Rochester, Rochester, New York State, USA.
- School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China.
- School of Software, Shandong University, Jinan, China.
- The CUHK Shenzhen Research Institute, Nanshan, Shenzhen, China.
Zitieren
APA
Tan, Q., Xiao, J., Chen, J., Wang, Y., Zhang, Z., Zhao, T., & Li, Y. (2024). ifDEEPre: large protein language-based deep learning enables interpretable and fast predictions of enzyme commission numbers. Briefings in Bioinformatics, 25(4). https://doi.org/10.1093/bib/bbae225
Vancouver
Tan Q, Xiao J, Chen J, Wang Y, Zhang Z, Zhao T, et al. ifDEEPre: large protein language-based deep learning enables interpretable and fast predictions of enzyme commission numbers. Briefings in Bioinformatics. 2024;25(4). doi:10.1093/bib/bbae225
BibTeX
@article{Tan2024,
author = {Tan, Qingxiong and Xiao, Jin and Chen, Jiayang and Wang, Yixuan and Zhang, Zeliang and Zhao, Tiancheng and Li, Yu},
title = {ifDEEPre: large protein language-based deep learning enables interpretable and fast predictions of enzyme commission numbers},
journal = {Briefings in Bioinformatics},
year = {2024},
volume = {25},
number = {4},
doi = {10.1093/bib/bbae225}
}
EUVIMED