Driving cell response through deep learning, a study in simulated 3D cell cultures

Computational simulations are becoming increasingly relevant in biomedical research, providing strategies to reproduce experimental results, improve the resolution of in-vitro experiments, and predict the system’s behavior in untested conditions.
The study of how each simulated variable influences measurable outcomes, however, has received little attention. To bridge this gap, we here propose a deep learning framework capable of reliably classify simulated time series data and identify class-defining features. This information will be shown to be useful for the determination of which changes in the experimental conditions elicit a desired cellular response.
This analysis pipeline will be initially tested on a synthetic dataset created ad-hoc to identify its accuracy in identifying the most relevant portion of the signals. Successively this method will be applied to simulations describing the behaviors of populations of cancer cells treated with either one or two drugs in different concentrations.
The proposed method will be shown to be effective in identifying which changes in the treatment protocol leads to a more extensive response to treatment. While lacking direct experimental validation, this result holds great potential for the integration of in-silico and in-vitro analyses and the effective optimization of experimental conditions in complex experimental set-ups.