Integrating Deep Learning and Synthetic Biology: A Co-Design Approach for Enhancing Gene Expression via N-Terminal Coding Sequences.

Yan, Zhanglu; Chu, Weiran; Sheng, Yuhua; Tang, Kaiwen; Wang, Shida; Liu, Yanfeng; Wong, Weng-Fai

Yan, Zhanglu; Chu, Weiran; Sheng, Yuhua; Tang, Kaiwen; Wang, Shida; Liu, Yanfeng; Wong, Weng-Fai.

Afiliación

Yan Z; School of Computing, National University of Singapore, Singapore 117417, Singapore.
Chu W; Science Center for Future Foods, Jiangnan University, Wuxi 214122, PR China.
Sheng Y; Science Center for Future Foods, Jiangnan University, Wuxi 214122, PR China.
Tang K; School of Computing, National University of Singapore, Singapore 117417, Singapore.
Wang S; Department of Mathematics, National University of Singapore, Singapore 119077, Singapore.
Liu Y; Science Center for Future Foods, Jiangnan University, Wuxi 214122, PR China.
Wong WF; School of Computing, National University of Singapore, Singapore 117417, Singapore.

ACS Synth Biol ; 13(9): 2960-2968, 2024 Sep 20.

Article en En | MEDLINE | ID: mdl-39229974

ABSTRACT

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.

Asunto(s)

Bacillus subtilis; Aprendizaje Profundo; Proteínas Fluorescentes Verdes; Biología Sintética; Biología Sintética/métodos; Proteínas Fluorescentes Verdes/genética; Proteínas Fluorescentes Verdes/metabolismo; Bacillus subtilis/genética; Bacillus subtilis/metabolismo; Expresión Génica/genética; Algoritmos; Ingeniería Genética/métodos

Palabras clave

Bacillus subtilis; N-acetylneuraminic acid; N-terminal coding sequence; deep learning; few-shot learning; gene expression regulation

Texto completo

Añadir a Mi BVS

Imprimir

XML

PubMed Links

Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Bacillus subtilis / Proteínas Fluorescentes Verdes / Biología Sintética / Aprendizaje Profundo Idioma: En Revista: ACS Synth Biol Año: 2024 Tipo del documento: Article País de afiliación: Singapur Pais de publicación: Estados Unidos

Texto completo

Añadir a Mi BVS

Imprimir

XML

PubMed Links

Buscar en Google