Automated machine learning robots unlock new possibilities for genetics research

Researchers at the University of Minnesota, Twin Cities have built a robot that uses machine learning to fully automate the complex microinjection process used in genetic research.

In experiments, researchers were able to use the automated robot to manipulate the genetics of multicellular organisms, including fruit fly and zebrafish embryos. This technology allows laboratories to save time and money while making it easier to conduct new large-scale genetic experiments that were previously not possible using manual techniques.

The study, titled “High-throughput genetic manipulation of multicellular organisms using machine vision-guided embryonic microinjection robots,” is featured on the cover of the magazine's April 2024 issue. genetics, an open access journal. The research was co-led by University of Minnesota mechanical engineering graduate students Andrew Alegria and Amy Joshi. The team is also working to commercialize the technology and make it widely available through Objective Biotechnology, a University of Minnesota startup.

Microinjection is a method of introducing cells, genetic material, or other drugs directly into an embryo, cell, or tissue using a very thin pipette. The researchers trained the robot to detect embryos that are 100 times smaller than a grain of rice. After detection, the machine can calculate the path and automate the injection process.

“This new process is more robust and reproducible than manual injection,” said Suhasa Kodandaramaiah, associate professor of mechanical engineering at the University of Minnesota and senior author of the study. “This model allows individual laboratories to come up with new experiments that would not be possible without this type of technology.”

Typically, this type of research requires highly skilled technicians to perform the microinjections, which many laboratories do not have. This new technology has the potential to expand the ability to perform large-scale experiments in the laboratory while reducing time and cost.

“This is very exciting for the world of genetics. Writing and reading DNA has improved significantly in recent years, and this technology will improve our ability to perform large-scale genetic experiments in a wide range of organisms.” said Darryl Gall. He is a co-author of the study, a group leader in the Innovation Lab at the University of Minnesota Genomics Center, and a research assistant professor in the Department of Genetics, Cell Biology, and Development.

Not only can this technology be used for genetic experiments, but it can also help preserve endangered species through cryopreservation, a preservation technique that takes place at extremely low temperatures.

“Using this robot to inject nanoparticles into cells and tissues will help in the process of cryopreservation and subsequent rewarming,” Kodandaramaiah explained.

Other team members highlighted other applications of the technology that could have even greater impact.

“We hope that this technology will eventually be used for in vitro fertilization to detect eggs at the microscale level,” said co-first author of the paper and director of the University of Minnesota's Department of Biosensing. said Andrew Alegria, a mechanical engineering graduate research assistant. and the Biorobotics Institute.

In addition to Kodandaramaiah, Gohl, Alegria, and Joshi, the team included several researchers from the University of Minnesota College of Science and Engineering and the Innovation Lab at the University of Minnesota Genomics Center. The team recently won the university's “Walleye Tank” life science competition. This life sciences pitch competition provides educational and promotional opportunities for emerging and established medical and life sciences companies.

This research was completed in collaboration with the Advanced Technology Engineering Research Center for the Preservation of Biological Systems (ATP-Bio) and the University of Minnesota Zebrafish Core.