Language:

ECNet is an evolutionary context-integrated deep learning framework for protein engineering

Nature communications, 2021-09, Vol.12 (1), p.5743-14, Article 5743 [Peer Reviewed Journal]

2021. The Author(s). ;The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;The Author(s) 2021 ;ISSN: 2041-1723 ;EISSN: 2041-1723 ;DOI: 10.1038/s41467-021-25976-8 ;PMID: 34593817

Full text available

Citations Cited by

Actions
1. Add to My Research
2. Remove from My Research
3. E-mail
4. Print
5. Permalink
6. Citation
7. EasyBib
8. EndNote
9. RefWorks
10. Delicious
11. Export RIS
12. Export BibTeX

Title:
ECNet is an evolutionary context-integrated deep learning framework for protein engineering
Author: Luo, Yunan ; Jiang, Guangde ; Yu, Tianhao ; Liu, Yang ; Vo, Lam ; Ding, Hantian ; Su, Yufeng ; Qian, Wesley Wei ; Zhao, Huimin ; Peng, Jian
Subjects: Algorithms ; Amino acid sequence ; Amino Acid Sequence - genetics ; Ampicillin ; beta-Lactam Resistance - genetics ; beta-Lactamases - genetics ; Context ; Datasets as Topic ; Deep Learning ; Engineering ; Epistasis ; Evolution ; Evolution, Molecular ; Evolutionary algorithms ; Genetic Fitness ; High-Throughput Screening Assays ; Homology ; Learning algorithms ; Machine learning ; Mutagenesis ; Mutants ; Mutation ; Neural networks ; Peptide mapping ; Protein engineering ; Protein Engineering - methods ; Proteins ; Random mutagenesis ; Residues ; Sequence Homology, Amino Acid ; β Lactamase
Is Part Of: Nature communications, 2021-09, Vol.12 (1), p.5743-14, Article 5743
Description: Machine learning has been increasingly used for protein engineering. However, because the general sequence contexts they capture are not specific to the protein being engineered, the accuracy of existing machine learning algorithms is rather limited. Here, we report ECNet (evolutionary context-integrated neural network), a deep-learning algorithm that exploits evolutionary contexts to predict functional fitness for protein engineering. This algorithm integrates local evolutionary context from homologous sequences that explicitly model residue-residue epistasis for the protein of interest with the global evolutionary context that encodes rich semantic and structural features from the enormous protein sequence universe. As such, it enables accurate mapping from sequence to function and provides generalization from low-order mutants to higher-order mutants. We show that ECNet predicts the sequence-function relationship more accurately as compared to existing machine learning algorithms by using ~50 deep mutational scanning and random mutagenesis datasets. Moreover, we used ECNet to guide the engineering of TEM-1 β-lactamase and identified variants with improved ampicillin resistance with high success rates.
Publisher: England: Nature Publishing Group
Language: English
Identifier: ISSN: 2041-1723
EISSN: 2041-1723
DOI: 10.1038/s41467-021-25976-8
PMID: 34593817
Source: DOAJ Directory of Open Access Journals
MEDLINE
PubMed Central
Coronavirus Research Database
ProQuest Central

Back to results list


INSPIRE LIBRARY - TON DUC THANG UNIVERSITY	(84-028) 37 755 057	Feedback
19 Nguyen Huu Tho St. Dist.7, HCM	thuvien@tdtu.edu.vn	Feedback

ECNet is an evolutionary context-integrated deep learning framework for protein engineering

Searching Remote Databases, Please Wait