European Conference on Mathematical and Theoretical Biology (ECMTB 2026)

Deep learning for the Analysis and Reconstruction of Transcriptional dynamics from live-cell imaging data

MS160-06

14 Jul 2026, 17:40

20m

11.01 - HS (University of Graz)

Minisymposium Talk Systems Biology and Biochemical Networks Stochastic Modelling for Inference with Gene Expression data: Methods and Applications

Speaker

Muhan Ma (University of Edinburgh)

Description

Quantifying transcriptional bursting from live-cell imaging data is critical for understanding stochastic gene regulation. Here, we present DART (Deep learning for the Analysis and Reconstruction of Transcriptional dynamics) \cite{m}, a deep learning framework that infers promoter-state trajectories from fluorescence intensity traces, enabling the estimation of activation and inactivation rates and the selection of the most appropriate promoter-switching model. Using extensive synthetic datasets spanning a wide range of transcriptional bursting levels, we demonstrate that DART outperforms current binarization methods, including conventional and augmented hidden Markov models, in both accuracy and robustness. Furthermore, a reanalysis of published experimental data using DART reveals a strong linear coupling between activation and inactivation rates, contradicting previous claims of independence. By integrating machine learning with stochastic modelling, DART provides a powerful and generalizable tool for quantitative analysis of transcriptional kinetics from live-cell imaging data.

Bibliography

@article{m,
title={DART: Deep learning for the Analysis and Reconstruction of Transcriptional dynamics from live-cell imaging data},
author={Ma, Muhan and Grima, Ramon},
journal={bioRxiv},
pages={2025--09},
year={2025},
publisher={Cold Spring Harbor Laboratory}
}