1. Cheetah: A Computational Toolkit for Cybergenetic Control
- Author
-
Thomas E. Gorochowski, Nigel J. Savery, Antonella La Regina, Claire S. Grierson, Lorena Postiglione, Elisa Pedone, Irene de Cesare, Lucia Marucci, Mario di Bernardo, David Haener, Criseida Zamora, Barbara Shannon, Pedone, E., De Cesare, I., Zamora-Chimal, C. G., Haener, D., Postiglione, L., La Regina, A., Shannon, B., Savery, N. J., Grierson, C. S., Di Bernardo, M., Gorochowski, T. E., and Marucci, L.
- Subjects
0106 biological sciences ,Computer science ,01 natural sciences ,Convolutional neural network ,Protein expression ,Computer System ,Synthetic biology ,Mice ,0302 clinical medicine ,cybergenetic ,Mammalian cell ,Lab-On-A-Chip Devices ,Image Processing, Computer-Assisted ,Segmentation ,Control (linguistics) ,0303 health sciences ,Microscopy ,Mouse Embryonic Stem Cells ,General Medicine ,Thresholding ,U-Net ,Data Accuracy ,Synthetic Biology ,Microfluidics ,Biomedical Engineering ,Reproducibility of Result ,Optogenetics ,Biochemistry, Genetics and Molecular Biology (miscellaneous) ,Cell Line ,03 medical and health sciences ,Computer Systems ,010608 biotechnology ,Escherichia coli ,Animals ,Bespoke ,030304 developmental biology ,business.industry ,Animal ,Deep learning ,Reproducibility of Results ,deep learning ,Mouse Embryonic Stem Cell ,Image segmentation ,Computer architecture ,Lab-On-A-Chip Device ,Artificial intelligence ,business ,image analysi ,030217 neurology & neurosurgery ,Software - Abstract
Advances in microscopy, microfluidics and optogenetics enable single-cell monitoring and environmental regulation and offer the means to control cellular phenotypes. The development of such systems is challenging and often results in bespoke setups that hinder reproducibility. To address this, we introduce Cheetah – a flexible computational toolkit that simplifies the integration of real-time microscopy analysis with algorithms for cellular control. Central to the platform is an image segmentation system based on the versatile U-Net convolutional neural network. This is supplemented with functionality to robustly count, characterise and control cells over time. We demonstrate Cheetah’s core capabilities by analysing long-term bacterial and mammalian cell growth and by dynamically controlling protein expression in mammalian cells. In all cases, Cheetah’s segmentation accuracy exceeds that of a commonly used thresholding-based method, allowing for more accurate control signals to be generated. Availability of this easy-to-use platform will make control engineering techniques more accessible and offer new ways to probe and manipulate living cells.
- Published
- 2021