2023
DOI: 10.1021/acssynbio.3c00203
|View full text |Cite
|
Sign up to set email alerts
|

Deep Neural Networks for Predicting Single-Cell Responses and Probability Landscapes

Abstract: Engineering biology relies on the accurate prediction of cell responses. However, making these predictions is challenging for a variety of reasons, including the stochasticity of biochemical reactions, variability between cells, and incomplete information about underlying biological processes. Machine learning methods, which can model diverse input–output relationships without requiring a priori mechanistic knowledge, are an ideal tool for this task. For example, such approaches can be used to predict gene exp… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
1

Relationship

1
0

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 67 publications
(110 reference statements)
0
1
0
Order By: Relevance
“…Another direction to explore regarding aging would be to re-train prediction models on-the-fly, as data is acquired during control experiments, to see if the controller can adapt to changes in system behavior. Yet another limitation is that our predictive model also does not provide any information about prediction uncertainty or noise, which could help improve control accuracy, and may be critical for the control of multistable genetic systems 49,50 . Finally, our use of a model predictive control framework requires that hundreds or thousands of model inferences are made per cell and timepoint.…”
Section: Discussionmentioning
confidence: 99%
“…Another direction to explore regarding aging would be to re-train prediction models on-the-fly, as data is acquired during control experiments, to see if the controller can adapt to changes in system behavior. Yet another limitation is that our predictive model also does not provide any information about prediction uncertainty or noise, which could help improve control accuracy, and may be critical for the control of multistable genetic systems 49,50 . Finally, our use of a model predictive control framework requires that hundreds or thousands of model inferences are made per cell and timepoint.…”
Section: Discussionmentioning
confidence: 99%