EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Deep learning guided programmable design of Escherichia coli core promoters from sequence architecture to strength control

Xuan Zhou, Renxu Feng, Nana Ding, Wenyan Cao, Yang Liu, Shenghu Zhou iD, Yu Deng iD

Nucleic Acids Research · 2025

DOI: 10.1093/nar/gkaf863 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Nucleic Acids Research, 2025. Verfasst von Xuan Zhou und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Biotechnology and Key Laboratory of Industrial Biotechnology of Ministry of Education, Jiangnan University, Wuxi 214122, China. Hauptthemen laut MEDLINE: Promoter Regions, Genetic, Escherichia coli, Deep Learning. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Key R&D Program of China, Distinguished Young Scholars of Jiangsu Province, Key R&D Project of Jiangsu Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Core promoters are essential regulatory elements that control transcription initiation, but accurately predicting and designing their strength remains challenging due to complex sequence-function relationships and the limited generalizability of existing AI-based approaches. To address this, we developed a modular platform integrating rational library design, predictive modelling, and generative optimization into a closed-loop workflow for end-to-end core promoter engineering. Conserved and spacer region of core promoters exert distinct effects on transcriptional strength, with the former driving large-scale variation and the latter enabling finer gradation. Based on this insight, Mutation-Barcoding-Reverse Sequencing approach was used and constructed a synthetic promoter library comprising 112 955 variants with minimal redundancy and a 16 226-fold expression range. A Transformer-based model trained on this dataset achieved a Pearson correlation of 0.87 with experimentally measured promoter strengths. When combined with a conditional diffusion model, the system enabled de novo generation of promoter sequences with defined strengths, achieving a design-to-measurement correlation of 0.95 and maintaining high accuracy (R = 0.93) across varied sequence contexts. The designed promoters consistently preserved their intended strength gradients, demonstrating robust plug-and-play functionality. This work establishes a scalable and extensible platform (www.yudenglab.com) for deep learning-guided programmable design of Escherichia coli core promoters, enabling precise transcriptional control.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Promoter Regions, GeneticEscherichia coliDeep LearningGene Expression Regulation, BacterialGene Library

Autor:innen und Institutionen

  • School of Biotechnology and Key Laboratory of Industrial Biotechnology of Ministry of Education, Jiangnan University, Wuxi 214122, China.
  • School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China.
  • Key Lab of Broadband Wireless Communication and Sensor Network Technology, Nanjing University of Posts and Telecommunications, Ministry of Education, Nanjing 210023, China.

ORCID-Profile: Shenghu Zhou, Yu Deng

Förderung

  • National Key R&D Program of China
  • Distinguished Young Scholars of Jiangsu Province
  • Key R&D Project of Jiangsu Province
  • National Natural Science Foundation of China
  • "Pilot Plan" Internet of Things Special Project
  • “Pilot Plan” Internet of Things Special Project

Zitieren

APA

Zhou, X., Feng, R., Ding, N., Cao, W., Liu, Y., Zhou, S., & Deng, Y. (2025). Deep learning guided programmable design of Escherichia coli core promoters from sequence architecture to strength control. Nucleic Acids Research. https://doi.org/10.1093/nar/gkaf863

Vancouver

Zhou X, Feng R, Ding N, Cao W, Liu Y, Zhou S, et al. Deep learning guided programmable design of Escherichia coli core promoters from sequence architecture to strength control. Nucleic Acids Research. 2025. doi:10.1093/nar/gkaf863

BibTeX
@article{Zhou2025,
  author = {Zhou, Xuan and Feng, Renxu and Ding, Nana and Cao, Wenyan and Liu, Yang and Zhou, Shenghu and Deng, Yu},
  title = {Deep learning guided programmable design of Escherichia coli core promoters from sequence architecture to strength control},
  journal = {Nucleic Acids Research},
  year = {2025},
  doi = {10.1093/nar/gkaf863}
}
Kostenlos starten →