Researchers were able to apply a machine-learning computational model to arrange stem cells into different shapes.
The holy grail of medical advancements is being able to create organs out of one’s own cells. But to do that researchers have to organize stem cells into predictable patterns, which has been quite a struggle.
3-D printing is one approach researchers are taking to create organs in the desired shapes but another new one relies on computational modeling and may just be able to overcome the past challenges.
Machine-learning can help grow organs outside of the Petri dish
Scientists from Gladstone Institutes and Boston University create a computational model to get stem cells to form into the shapes they want. The technique could someday be used to create organs. Their work was published in journal Cell Systems.
Researchers around the world have been using induced pluripotent stem cells or IPS, which are similar to the stem cells found in an embryo, to develop organs in Petri dishes. These stems can be shaped and molded to become hearts and even brains. They are already being used in transplants and to model diseases. But they aren’t the same as creating an organ that is three dimensional and functioning.
“Despite the importance of organization for functioning tissues, we as scientists have had difficulty creating tissues in a dish with stem cells,” said Ashley Libby, a graduate student in the UC San Francisco Developmental & Stem Cell Biology Program and co-first author of the new paper, who worked on the project with David Joy, a graduate student in the joint Graduate Program in Bioengineering from UC Berkeley and UC San Francisco (BioE). “Instead of an organized tissue, we often get a disorganized mix of different cell types.”
Researchers rely on CRISPR/Cas9 gene-editing system
That got researchers wondering if they could predict the exact arrangement of cells applying their understanding that blocking the expression of two different genes changes the layout of iPS cells in a Petri dish. But testing every combination would take too much time so the researches teamed up with Belta Lab to create a computation model.
The researchers used a CRISPR/Cas9 gene-editing system and carried out different experiments. The data was then inputted into a machine learning program designed to pinpoint patterns within the data.
“The power of this model is that it can generate thousands of data points simulating things that it could take months for me to do in a lab,” said Libby. The simulations spit back a set of conditions that could lead to the arrangement of cells they were desiring. After testing the arrangements they found the machine learning system was correct.
“I was just blown away when I first saw the results,” said Bruce Conklin, MD, a Gladstone senior investigator who also worked on the new study. “Modeling cell behavior is the Holy Grail of biology and this paper takes an important step forward in doing that.”