{"title":"Integrating Deep Learning and Synthetic Biology: A Co-Design Approach for Enhancing Gene Expression via N-Terminal Coding Sequences","authors":"Zhanglu Yan*, Weiran Chu, Yuhua Sheng, Kaiwen Tang, Shida Wang, Yanfeng Liu* and Weng-Fai Wong, ","doi":"10.1021/acssynbio.4c0037110.1021/acssynbio.4c00371","DOIUrl":null,"url":null,"abstract":"<p >N-terminal coding sequence (NCS) influences gene expression by impacting the translation initiation rate. The NCS optimization problem is to find an NCS that maximizes gene expression. The problem is important in genetic engineering. However, current methods for NCS optimization such as rational design and statistics-guided approaches are labor-intensive yield only relatively small improvements. This paper introduces a deep learning/synthetic biology codesigned few-shot training workflow for NCS optimization. Our method utilizes <i>k</i>-nearest encoding followed by word2vec to encode the NCS, then performs feature extraction using attention mechanisms, before constructing a time-series network for predicting gene expression intensity, and finally a direct search algorithm identifies the optimal NCS with limited training data. We took green fluorescent protein (GFP) expressed by <i>Bacillus subtilis</i> as a reporting protein of NCSs, and employed the fluorescence enhancement factor as the metric of NCS optimization. Within just six iterative experiments, our model generated an NCS (MLD<sub>62</sub>) that increased average GFP expression by 5.41-fold, outperforming the state-of-the-art NCS designs. Extending our findings beyond GFP, we showed that our engineered NCS (MLD<sub>62</sub>) can effectively boost the production of N-acetylneuraminic acid by enhancing the expression of the crucial rate-limiting <i>GNA1</i> gene, demonstrating its practical utility. We have open-sourced our NCS expression database and experimental procedures for public use.</p>","PeriodicalId":26,"journal":{"name":"ACS Synthetic Biology","volume":null,"pages":null},"PeriodicalIF":3.7000,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Synthetic Biology","FirstCategoryId":"99","ListUrlMain":"https://pubs.acs.org/doi/10.1021/acssynbio.4c00371","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIOCHEMICAL RESEARCH METHODS","Score":null,"Total":0}
引用次数: 0
Abstract
N-terminal coding sequence (NCS) influences gene expression by impacting the translation initiation rate. The NCS optimization problem is to find an NCS that maximizes gene expression. The problem is important in genetic engineering. However, current methods for NCS optimization such as rational design and statistics-guided approaches are labor-intensive yield only relatively small improvements. This paper introduces a deep learning/synthetic biology codesigned few-shot training workflow for NCS optimization. Our method utilizes k-nearest encoding followed by word2vec to encode the NCS, then performs feature extraction using attention mechanisms, before constructing a time-series network for predicting gene expression intensity, and finally a direct search algorithm identifies the optimal NCS with limited training data. We took green fluorescent protein (GFP) expressed by Bacillus subtilis as a reporting protein of NCSs, and employed the fluorescence enhancement factor as the metric of NCS optimization. Within just six iterative experiments, our model generated an NCS (MLD62) that increased average GFP expression by 5.41-fold, outperforming the state-of-the-art NCS designs. Extending our findings beyond GFP, we showed that our engineered NCS (MLD62) can effectively boost the production of N-acetylneuraminic acid by enhancing the expression of the crucial rate-limiting GNA1 gene, demonstrating its practical utility. We have open-sourced our NCS expression database and experimental procedures for public use.
期刊介绍:
The journal is particularly interested in studies on the design and synthesis of new genetic circuits and gene products; computational methods in the design of systems; and integrative applied approaches to understanding disease and metabolism.
Topics may include, but are not limited to:
Design and optimization of genetic systems
Genetic circuit design and their principles for their organization into programs
Computational methods to aid the design of genetic systems
Experimental methods to quantify genetic parts, circuits, and metabolic fluxes
Genetic parts libraries: their creation, analysis, and ontological representation
Protein engineering including computational design
Metabolic engineering and cellular manufacturing, including biomass conversion
Natural product access, engineering, and production
Creative and innovative applications of cellular programming
Medical applications, tissue engineering, and the programming of therapeutic cells
Minimal cell design and construction
Genomics and genome replacement strategies
Viral engineering
Automated and robotic assembly platforms for synthetic biology
DNA synthesis methodologies
Metagenomics and synthetic metagenomic analysis
Bioinformatics applied to gene discovery, chemoinformatics, and pathway construction
Gene optimization
Methods for genome-scale measurements of transcription and metabolomics
Systems biology and methods to integrate multiple data sources
in vitro and cell-free synthetic biology and molecular programming
Nucleic acid engineering.