Deep model predictive control of gene expression in thousands of single cells
Problem
Researchers could only passively observe natural gene expression dynamics in cells; they needed a way to actively impose specific, cell-specific expression dynamics in individual live cells.
Why it matters
Controlling gene expression dynamics in single cells allows study of noisy, elusive cellular events that passive observation cannot reveal.
What the AI did
A deep neural network was trained to accurately predict the response of an optogenetic system in E. coli, then used in a deep model predictive control framework to impose arbitrary, cell-specific gene expression dynamics on thousands of single cells in real time.
Results
Imposed arbitrary and cell-specific gene expression dynamics on thousands of single cells in real time and generated complex time-varying patterns
Impact
The framework enables active control of expression dynamics and linking expression patterns to dynamic functional outcomes.
Record
| Venue | Nature Communications |
|---|---|
| Published | 2024 |
| Work type | article |
| Authors | Jean‐Baptiste Lugagne, Caroline M. Blassick, Mary J. Dunlop |
| Citations | 38 (OpenAlex, at import time) |
| References | 57 |
| Model or method | deep neural network in a deep model predictive control framework |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s41467-024-46361-1 |
| Open access | gold |
| Keywords | deep learning, model predictive control, optogenetics, gene expression, E. coli, single cells |
Importance rating
significant — thousands to millions affected
Genuinely new capability: actively imposing arbitrary, cell-specific gene expression dynamics on thousands of single cells in real time, enabling study of noisy events passive observation cannot reveal.