Codon optimization with deep learning to enhance protein expression
Abstract Heterologous expression is the main approach for recombinant protein production ingenetic synthesis, for which codon optimization is necessary. The existing optimization methods are based on biological indexes. In this paper, we propose a novel codon optimization method based on deep learni...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2020-10-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-020-74091-z |
id |
doaj-099d6ae85f104ec1a497335bc64d5ae2 |
---|---|
record_format |
Article |
spelling |
doaj-099d6ae85f104ec1a497335bc64d5ae22020-12-08T10:40:02ZengNature Publishing GroupScientific Reports2045-23222020-10-011011910.1038/s41598-020-74091-zCodon optimization with deep learning to enhance protein expressionHongguang Fu0Yanbing Liang1Xiuqin Zhong2ZhiLing Pan3Lei Huang4HaiLin Zhang5Yang Xu6Wei Zhou7Zhong Liu8University of Electronic Science and Technology of ChinaUniversity of Electronic Science and Technology of ChinaUniversity of Electronic Science and Technology of ChinaState Key Laboratory of Biotherapy, West China Hospital, Sichuan UniversityUniversity of Electronic Science and Technology of ChinaState Key Laboratory of Biotherapy, West China Hospital, Sichuan UniversityUniversity of Electronic Science and Technology of ChinaUniversity of Electronic Science and Technology of ChinaChengdu Institute of Computer Applications, Chinese Academy of SciencesAbstract Heterologous expression is the main approach for recombinant protein production ingenetic synthesis, for which codon optimization is necessary. The existing optimization methods are based on biological indexes. In this paper, we propose a novel codon optimization method based on deep learning. First, we introduce the concept of codon boxes, via which DNA sequences can be recoded into codon box sequences while ignoring the order of bases. Then, the problem of codon optimization can be converted to sequence annotation of corresponding amino acids with codon boxes. The codon optimization models for Escherichia Coli were trained by the Bidirectional Long-Short-Term Memory Conditional Random Field. Theoretically, deep learning is a good method to obtain the distribution characteristics of DNA. In addition to the comparison of the codon adaptation index, protein expression experiments for plasmodium falciparum candidate vaccine and polymerase acidic protein were implemented for comparison with the original sequences and the optimized sequences from Genewiz and ThermoFisher. The results show that our method for enhancing protein expression is efficient and competitive.https://doi.org/10.1038/s41598-020-74091-z |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hongguang Fu Yanbing Liang Xiuqin Zhong ZhiLing Pan Lei Huang HaiLin Zhang Yang Xu Wei Zhou Zhong Liu |
spellingShingle |
Hongguang Fu Yanbing Liang Xiuqin Zhong ZhiLing Pan Lei Huang HaiLin Zhang Yang Xu Wei Zhou Zhong Liu Codon optimization with deep learning to enhance protein expression Scientific Reports |
author_facet |
Hongguang Fu Yanbing Liang Xiuqin Zhong ZhiLing Pan Lei Huang HaiLin Zhang Yang Xu Wei Zhou Zhong Liu |
author_sort |
Hongguang Fu |
title |
Codon optimization with deep learning to enhance protein expression |
title_short |
Codon optimization with deep learning to enhance protein expression |
title_full |
Codon optimization with deep learning to enhance protein expression |
title_fullStr |
Codon optimization with deep learning to enhance protein expression |
title_full_unstemmed |
Codon optimization with deep learning to enhance protein expression |
title_sort |
codon optimization with deep learning to enhance protein expression |
publisher |
Nature Publishing Group |
series |
Scientific Reports |
issn |
2045-2322 |
publishDate |
2020-10-01 |
description |
Abstract Heterologous expression is the main approach for recombinant protein production ingenetic synthesis, for which codon optimization is necessary. The existing optimization methods are based on biological indexes. In this paper, we propose a novel codon optimization method based on deep learning. First, we introduce the concept of codon boxes, via which DNA sequences can be recoded into codon box sequences while ignoring the order of bases. Then, the problem of codon optimization can be converted to sequence annotation of corresponding amino acids with codon boxes. The codon optimization models for Escherichia Coli were trained by the Bidirectional Long-Short-Term Memory Conditional Random Field. Theoretically, deep learning is a good method to obtain the distribution characteristics of DNA. In addition to the comparison of the codon adaptation index, protein expression experiments for plasmodium falciparum candidate vaccine and polymerase acidic protein were implemented for comparison with the original sequences and the optimized sequences from Genewiz and ThermoFisher. The results show that our method for enhancing protein expression is efficient and competitive. |
url |
https://doi.org/10.1038/s41598-020-74091-z |
work_keys_str_mv |
AT hongguangfu codonoptimizationwithdeeplearningtoenhanceproteinexpression AT yanbingliang codonoptimizationwithdeeplearningtoenhanceproteinexpression AT xiuqinzhong codonoptimizationwithdeeplearningtoenhanceproteinexpression AT zhilingpan codonoptimizationwithdeeplearningtoenhanceproteinexpression AT leihuang codonoptimizationwithdeeplearningtoenhanceproteinexpression AT hailinzhang codonoptimizationwithdeeplearningtoenhanceproteinexpression AT yangxu codonoptimizationwithdeeplearningtoenhanceproteinexpression AT weizhou codonoptimizationwithdeeplearningtoenhanceproteinexpression AT zhongliu codonoptimizationwithdeeplearningtoenhanceproteinexpression |
_version_ |
1715005112148033536 |