Machine learning-assisted decoding of temporal transcriptional dynamics via fluorescent timer

Abstract Investigating the temporal dynamics of gene expression is crucial for understanding gene regulation across various biological processes. Using the Fluorescent Timer protein, the Timer-of-cell-kinetics-and-activity system enables analysis of transcriptional dynamics at the single-cell level....

Full description

Saved in:
Bibliographic Details
Main Authors: Nobuko Irie, Naoki Takeda, Yorifumi Satou, Kimi Araki, Masahiro Ono
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-61279-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849768598158966784
author Nobuko Irie
Naoki Takeda
Yorifumi Satou
Kimi Araki
Masahiro Ono
author_facet Nobuko Irie
Naoki Takeda
Yorifumi Satou
Kimi Araki
Masahiro Ono
author_sort Nobuko Irie
collection DOAJ
description Abstract Investigating the temporal dynamics of gene expression is crucial for understanding gene regulation across various biological processes. Using the Fluorescent Timer protein, the Timer-of-cell-kinetics-and-activity system enables analysis of transcriptional dynamics at the single-cell level. However, the complexity of Timer fluorescence data has limited its broader application. Here, we introduce an integrative approach combining molecular biology and machine learning to elucidate Foxp3 transcriptional dynamics through flow cytometric Timer analysis. We have developed a convolutional neural network-based method that incorporates image conversion and class-specific feature visualisation for class-specific feature identification at the single-cell level. Biologically, we developed a novel CRISPR mutant of Foxp3 fluorescent Timer reporter mice lacking the enhancer Conserved Non-coding Sequence 2, which revealed new roles of this enhancer in regulating Foxp3 transcription frequency under specific conditions. Furthermore, analysis of wild-type Foxp3 fluorescent Timer reporter mice at different ages uncovered distinct patterns of Foxp3 expression from neonatal to aged mice, highlighting prominent thymus-like features of neonatal splenic Foxp3 + T cells. In conclusion, our study uncovers previously unrecognised Foxp3 transcriptional dynamics, establishing a proof-of-concept for integrating CRISPR, single-cell dynamics analysis, and machine learning methods as advanced techniques to understand transcriptional dynamics in vivo.
format Article
id doaj-art-5c8d715ff3c044359dca54c7ef66e7a9
institution DOAJ
issn 2041-1723
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-5c8d715ff3c044359dca54c7ef66e7a92025-08-20T03:03:44ZengNature PortfolioNature Communications2041-17232025-07-0116112110.1038/s41467-025-61279-yMachine learning-assisted decoding of temporal transcriptional dynamics via fluorescent timerNobuko Irie0Naoki Takeda1Yorifumi Satou2Kimi Araki3Masahiro Ono4The Joint Research Center for Human Retrovirus Infection, Kumamoto UniversityInstitute of Resource Development and Analysis, Kumamoto UniversityThe Joint Research Center for Human Retrovirus Infection, Kumamoto UniversityInstitute of Resource Development and Analysis, Kumamoto UniversityThe Joint Research Center for Human Retrovirus Infection, Kumamoto UniversityAbstract Investigating the temporal dynamics of gene expression is crucial for understanding gene regulation across various biological processes. Using the Fluorescent Timer protein, the Timer-of-cell-kinetics-and-activity system enables analysis of transcriptional dynamics at the single-cell level. However, the complexity of Timer fluorescence data has limited its broader application. Here, we introduce an integrative approach combining molecular biology and machine learning to elucidate Foxp3 transcriptional dynamics through flow cytometric Timer analysis. We have developed a convolutional neural network-based method that incorporates image conversion and class-specific feature visualisation for class-specific feature identification at the single-cell level. Biologically, we developed a novel CRISPR mutant of Foxp3 fluorescent Timer reporter mice lacking the enhancer Conserved Non-coding Sequence 2, which revealed new roles of this enhancer in regulating Foxp3 transcription frequency under specific conditions. Furthermore, analysis of wild-type Foxp3 fluorescent Timer reporter mice at different ages uncovered distinct patterns of Foxp3 expression from neonatal to aged mice, highlighting prominent thymus-like features of neonatal splenic Foxp3 + T cells. In conclusion, our study uncovers previously unrecognised Foxp3 transcriptional dynamics, establishing a proof-of-concept for integrating CRISPR, single-cell dynamics analysis, and machine learning methods as advanced techniques to understand transcriptional dynamics in vivo.https://doi.org/10.1038/s41467-025-61279-y
spellingShingle Nobuko Irie
Naoki Takeda
Yorifumi Satou
Kimi Araki
Masahiro Ono
Machine learning-assisted decoding of temporal transcriptional dynamics via fluorescent timer
Nature Communications
title Machine learning-assisted decoding of temporal transcriptional dynamics via fluorescent timer
title_full Machine learning-assisted decoding of temporal transcriptional dynamics via fluorescent timer
title_fullStr Machine learning-assisted decoding of temporal transcriptional dynamics via fluorescent timer
title_full_unstemmed Machine learning-assisted decoding of temporal transcriptional dynamics via fluorescent timer
title_short Machine learning-assisted decoding of temporal transcriptional dynamics via fluorescent timer
title_sort machine learning assisted decoding of temporal transcriptional dynamics via fluorescent timer
url https://doi.org/10.1038/s41467-025-61279-y
work_keys_str_mv AT nobukoirie machinelearningassisteddecodingoftemporaltranscriptionaldynamicsviafluorescenttimer
AT naokitakeda machinelearningassisteddecodingoftemporaltranscriptionaldynamicsviafluorescenttimer
AT yorifumisatou machinelearningassisteddecodingoftemporaltranscriptionaldynamicsviafluorescenttimer
AT kimiaraki machinelearningassisteddecodingoftemporaltranscriptionaldynamicsviafluorescenttimer
AT masahiroono machinelearningassisteddecodingoftemporaltranscriptionaldynamicsviafluorescenttimer