Format

Send to

Choose Destination
Cell Syst. 2019 Nov 27;9(5):483-495.e10. doi: 10.1016/j.cels.2019.10.008. Epub 2019 Nov 20.

Automated Design of Pluripotent Stem Cell Self-Organization.

Author information

1
Developmental and Stem Cell Biology PhD Program, University of California, San Francisco, San Francisco, CA, USA; Gladstone Institute of Cardiovascular Disease, Gladstone Institutes, San Francisco, CA, USA.
2
Boston University Bioinformatics Program, Boston, MA, USA.
3
Systems Engineering Department at Boston University, Boston, MA, USA.
4
Gladstone Institute of Cardiovascular Disease, Gladstone Institutes, San Francisco, CA, USA; UC Berkeley-UC San Francisco Bioengineering Graduate Program, San Francisco, CA, USA.
5
Gladstone Institute of Cardiovascular Disease, Gladstone Institutes, San Francisco, CA, USA; Departments of Medicine, Pharmacology, and Ophthalmology, University of California, San Francisco, San Francisco, CA, USA.
6
Systems Engineering Department at Boston University, Boston, MA, USA. Electronic address: cbelta@bu.edu.
7
Gladstone Institute of Cardiovascular Disease, Gladstone Institutes, San Francisco, CA, USA; Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, San Francisco, CA, USA. Electronic address: todd.mcdevitt@gladstone.ucsf.edu.

Abstract

Human pluripotent stem cells (hPSCs) have the intrinsic ability to self-organize into complex multicellular organoids that recapitulate many aspects of tissue development. However, robustly directing morphogenesis of hPSC-derived organoids requires novel approaches to accurately control self-directed pattern formation. Here, we combined genetic engineering with computational modeling, machine learning, and mathematical pattern optimization to create a data-driven approach to control hPSC self-organization by knock down of genes previously shown to affect stem cell colony organization, CDH1 and ROCK1. Computational replication of the in vitro system in silico using an extended cellular Potts model enabled machine learning-driven optimization of parameters that yielded emergence of desired patterns. Furthermore, in vitro the predicted experimental parameters quantitatively recapitulated the in silico patterns. These results demonstrate that morphogenic dynamics can be accurately predicted through model-driven exploration of hPSC behaviors via machine learning, thereby enabling spatial control of multicellular patterning to engineer human organoids and tissues. A record of this paper's Transparent Peer Review process is included in the Supplemental Information.

KEYWORDS:

bioengineering; control theory; machine learning; mathematical optimization; multicellular patterning; stem cell biology

PMID:
31759947
DOI:
10.1016/j.cels.2019.10.008

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center