EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Combining diffusion and transformer models for enhanced promoter synthesis and strength prediction in deep learning

Xin Lei iD, Xing Wang, Guanlin Chen, Ce Liang, Quhuan Li, Huaiguang Jiang iD, Wei Xiong iD

mSystems · 22.04.2025 · 10 (4)

DOI: 10.1128/msystems.00183-25 ↗

Kurz gefasst

Fachartikel in der Zeitschrift mSystems, erschienen am 22.04.2025. Verfasst von Xin Lei und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Future Technology, South China University of Technology, Guangzhou, Guangdong, China. Hauptthemen laut MEDLINE: Deep Learning, Promoter Regions, Genetic, Synthetic Biology. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities, South China University of Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the field of synthetic biology, the engineering of synthetic promoters that outperform their natural counterparts is of paramount importance, which can optimize the expression of exogenous genes, enhance the efficiency of metabolic pathways, and possess substantial commercial value. Research indicates that some synthetic promoters have higher transcriptional activity compared to strong natural promoters. However, with the exponential increase in complexity due to the 4 n potential combinations in a promoter sequence of length n , identifying effective synthetic promoters remains a formidable challenge. Deep learning models, by adaptively learning from extensive data sets, have become instrumental in analyzing biological data. This study introduces a diffusion model-based approach for designing promoters viable in model bacteria such as Escherichia coli and cyanobacteria. This model proficiently assimilates and utilizes inherent biological features from natural promoter sequences to engineer synthetic variants. Additionally, we employed a transformer model to evaluate the efficacy of these synthetic promoters, aiming at screening those with high performance. The experimental findings suggest that the synthetic promoters by the diffusion model not only share key biological features with their natural counterparts but also demonstrate greater similarity to natural promoters than those generated by a variational autoencoder. In predicting promoter strength, the transformer model demonstrated improved performance over the convolutional neural network. Finally, we developed an integrated platform for generating promoters and predicting their strength. IMPORTANCE We demonstrated that diffusion models are superior in accomplishing the promoter synthesis task compared to other state-of-the-art deep learning models. The effectiveness of our method was validated using data sets of Escherichia coli and cyanobacteria promoters, showing more stable and prompt convergence and more natural-like promoters than the variational autoencoder model. We extracted sequence information, dimer information, and position information from promoters and combined them with a transformer model to predict promoter strength. Our prediction results were more accurate than those obtained with a convolutional neural network model. Our in silico experiments systematically introduced mutations in promoter sequences and explored their contribution to promoter strength, highlighting the depth of learning in our model.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningPromoter Regions, GeneticSynthetic BiologyEscherichia coliCyanobacteria

Stichwörter der Autor:innen

deep learningdiffusion modelsynthetic promotertransformer

Autor:innen und Institutionen

  • School of Future Technology, South China University of Technology, Guangzhou, Guangdong, China.
  • School of Biology and Biological Engineering, South China University of Technology, Guangzhou, Guangdong, China.
  • Research Projects Department, Guangdong Artificial Intelligence and Digital Economy Laboratory (Guangzhou), Guangzhou, Guangdong, China.

ORCID-Profile: Xin Lei, Huaiguang Jiang, Wei Xiong

Förderung

  • Fundamental Research Funds for the Central Universities
  • South China University of Technology

Zitieren

APA

Lei, X., Wang, X., Chen, G., Liang, C., Li, Q., Jiang, H., & Xiong, W. (2025). Combining diffusion and transformer models for enhanced promoter synthesis and strength prediction in deep learning. mSystems, 10(4). https://doi.org/10.1128/msystems.00183-25

Vancouver

Lei X, Wang X, Chen G, Liang C, Li Q, Jiang H, et al. Combining diffusion and transformer models for enhanced promoter synthesis and strength prediction in deep learning. mSystems. 2025;10(4). doi:10.1128/msystems.00183-25

BibTeX
@article{Lei2025,
  author = {Lei, Xin and Wang, Xing and Chen, Guanlin and Liang, Ce and Li, Quhuan and Jiang, Huaiguang and Xiong, Wei},
  title = {Combining diffusion and transformer models for enhanced promoter synthesis and strength prediction in deep learning},
  journal = {mSystems},
  year = {2025},
  volume = {10},
  number = {4},
  doi = {10.1128/msystems.00183-25}
}
Kostenlos starten →