2022
DOI: 10.7554/elife.77007
|View full text |Cite
|
Sign up to set email alerts
|

Robotic search for optimal cell culture in regenerative medicine

Abstract: Induced differentiation is one of the most experience- and skill-dependent experimental processes in regenerative medicine, and establishing optimal conditions often takes years. We developed a robotic AI system with a batch Bayesian optimization algorithm that autonomously induces the differentiation of induced pluripotent stem cell-derived retinal pigment epithelial (iPSC-RPE) cells. From 200 million possible parameter combinations, the system performed cell culture in 143 different conditions in 111 days, r… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
15
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 42 publications
(15 citation statements)
references
References 37 publications
0
15
0
Order By: Relevance
“…By utilizing GSCAS find common ancestor strains and MTM to minimize total manipulations, the proposed method can effectively reduce the working load of large‐scale parallel strain construction in biofoundry. The methods presented in this paper are in the upstream and complimentary to existing relative down‐stream algorithms, such as equipment scheduling [ 20 ] and Bayesian/machine learning algorithms for fine‐tuning promoter/RBS strength [ 6 ] and optimizing culture medium, [ 21 ] We believe that integrating GSCAS/MTM and other methods in biofoundry practice can significantly reduce cost, time and man‐power involved in large scale strain developments, thereby contributing to the acceleration of the DBTL cycle for strain development.…”
Section: Discussionmentioning
confidence: 99%
“…By utilizing GSCAS find common ancestor strains and MTM to minimize total manipulations, the proposed method can effectively reduce the working load of large‐scale parallel strain construction in biofoundry. The methods presented in this paper are in the upstream and complimentary to existing relative down‐stream algorithms, such as equipment scheduling [ 20 ] and Bayesian/machine learning algorithms for fine‐tuning promoter/RBS strength [ 6 ] and optimizing culture medium, [ 21 ] We believe that integrating GSCAS/MTM and other methods in biofoundry practice can significantly reduce cost, time and man‐power involved in large scale strain developments, thereby contributing to the acceleration of the DBTL cycle for strain development.…”
Section: Discussionmentioning
confidence: 99%
“…While the transfection efficiency of 10 to 15% allows us to visually isolate a single cell and observe its entire structure without being overlapped by other surrounding cells, it also means that a limited number of cells can be observed per experiment, resulting in low throughput. However, this limitation can be overcome by incorporating laboratory automation, which is becoming increasingly available, into our analysis system ( 41 , 42 ). By automating the analysis and observing more cells, we believe that the difference between without and with stretch will become more visible even in single-cell analysis and that the distribution will eventually converge to a histogram similar to the one obtained from the multicell-scale analysis (Fig.…”
Section: Discussionmentioning
confidence: 99%
“…Exciting examples in biology include autonomous experimentation for genome engineering, [172][173][174] and optimal growth of cell cultures. 175 Si et al 173 and HamediRad et al 174 utilize iBioFab, a delocalized biofoundry which is similar to the concept of delocalized experimentation with cloud labs. iBioFab can produce one gene sequence for <3 USD, so it is inexpensive from the user's perspective.…”
Section: Frugal Twins In Biologymentioning
confidence: 99%