Saved in:
Bibliographic Details
Main Authors: Lin, Chen, Zhu, Zhengwen, Wang, Xinglong, Wang, Yonghua
Format: Artículo científico
Language:en
Published: Synthetic and systems biotechnology 2026
Online Access:https://pubmed.ncbi.nlm.nih.gov/42212299/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1868266041757401090
author Lin, Chen
Zhu, Zhengwen
Wang, Xinglong
Wang, Yonghua
author_facet Lin, Chen
Zhu, Zhengwen
Wang, Xinglong
Wang, Yonghua
Lin, Chen
Zhu, Zhengwen
Wang, Xinglong
Wang, Yonghua
collection PubMed - marine biology
contents Unconditional generation and functional validation of synthetic promoters with a diffusion model. Lin, Chen Zhu, Zhengwen Wang, Xinglong Wang, Yonghua Generative neural networks enable design of synthetic genetic elements. Here, we present DiPro, an unconditional diffusion model that learns promoter features to generate novel sequences without conditional input. DiPro directly generates 50-bp promoter sequences from Gaussian noise using a time-conditioned Transformer denoiser, without auxiliary discriminators or recognizers. DiPro accurately recapitulates natural promoter statistics, including sequence motifs, k-mer spectra, conserved -35/-10 spacing (16-18 bp). Over 90% of generated sequences were classified as real promoters by an independent recognizer, indicating high structural fidelity. To design stationary-phase-specific promoters, generation was guided by inpainting randomly masked regions (three non-overlapping 6-mers, 18 bp) within sigma38-associated (σ) seed sequences, yielding 5000 candidates while preserving global promoter architecture. Bayesian classification resolved these sequences into three distinct clusters with divergent -35/-10 composition and motif conservation. Experimentally, 81.6% of tested promoters exhibited stationary-phase activity, with the strongest variant reaching 79.6% of the activity of the constitutive promoter J23119. Promoters displayed distinct activation timing, reflecting heterogeneous stress responses. As a proof-of-concept, selected promoters were used to drive a lysis protein, achieving phase-specific and tunable cell lysis that matched promoter activation timing, with early-phase promoters reducing culture density to an optical density at 600 nm of approximately 1.5-2.0. Together, these results establish DiPro as a generative framework for creating functional bacterial promoters with programmable temporal dynamics, offering a new tool for synthetic biology and metabolic engineering.
format Artículo científico
id pubmed_42212299
institution PubMed
language en
publishDate 2026
publisher Synthetic and systems biotechnology
record_format pubmed
spellingShingle Unconditional generation and functional validation of synthetic promoters with a diffusion model.
Lin, Chen
Zhu, Zhengwen
Wang, Xinglong
Wang, Yonghua
Unconditional generation and functional validation of synthetic promoters with a diffusion model. Lin, Chen Zhu, Zhengwen Wang, Xinglong Wang, Yonghua Generative neural networks enable design of synthetic genetic elements. Here, we present DiPro, an unconditional diffusion model that learns promoter features to generate novel sequences without conditional input. DiPro directly generates 50-bp promoter sequences from Gaussian noise using a time-conditioned Transformer denoiser, without auxiliary discriminators or recognizers. DiPro accurately recapitulates natural promoter statistics, including sequence motifs, k-mer spectra, conserved -35/-10 spacing (16-18 bp). Over 90% of generated sequences were classified as real promoters by an independent recognizer, indicating high structural fidelity. To design stationary-phase-specific promoters, generation was guided by inpainting randomly masked regions (three non-overlapping 6-mers, 18 bp) within sigma38-associated (σ) seed sequences, yielding 5000 candidates while preserving global promoter architecture. Bayesian classification resolved these sequences into three distinct clusters with divergent -35/-10 composition and motif conservation. Experimentally, 81.6% of tested promoters exhibited stationary-phase activity, with the strongest variant reaching 79.6% of the activity of the constitutive promoter J23119. Promoters displayed distinct activation timing, reflecting heterogeneous stress responses. As a proof-of-concept, selected promoters were used to drive a lysis protein, achieving phase-specific and tunable cell lysis that matched promoter activation timing, with early-phase promoters reducing culture density to an optical density at 600 nm of approximately 1.5-2.0. Together, these results establish DiPro as a generative framework for creating functional bacterial promoters with programmable temporal dynamics, offering a new tool for synthetic biology and metabolic engineering.
title Unconditional generation and functional validation of synthetic promoters with a diffusion model.
url https://pubmed.ncbi.nlm.nih.gov/42212299/