AI-Assisted Probe Used to Engineer Stem Cells

Researchers at Northwestern University in Chicago have developed a tool that uses artificial intelligence (AI) to enable efficient engineering of stem cells and could significantly advance personalized disease diagnostics and therapeutics, as well as basic research.

Led by Professor Horacio Espinosa, the research team developed a new version of its Nanofountain Probe Electroporation (NFP-E), a tool used to deliver molecules into single-cells using electricity. The enhanced method uses AI to execute cell engineering tasks such as cell nuclei localization and probe detection. Probe motion, probe-to-cell contact detection, and electroporation-mediated delivery of foreign cargo into single cells are also automated, minimizing user intervention.

Probe-based, microfluidic methods, like NFP-E, use hollow nanopipettes or atomic-force microscopy tips to deliver materials into cells. NFP-E also allows researchers to selectively manipulate cells of interest, work with very small starting samples, and deliver both proteins and plasmids in a variety of animal and human cell types with dosage control. 

Other cell engineering methods such as bulk electroporation require millions of cells and lead to significant cell losses.  And other probe methods require manual operation and produce low throughputs, making them unsuitable for common cell engineering workflows.

“Selective cell manipulation at sufficient throughput is challenging,” Espinosa said. “Most methods either provide high throughput at the expense of individual cell control or sacrifice throughput for single cell selectivity and control.”

The automated NFP-E enables selective cell engineering at higher-throughputs than manual probe-based methods while also reducing experimental variability and enabling more efficient engineering of human induced pluripotent stem cells (hiPSCs). Using the automated NFP-E, Espinosa and his colleagues delivered clustered regularly interspaced short palindromic repeats (CRISPR) RNP to hiPSCs for efficient knockout of genes in a variety of culture formats: culture plates, micro-patterns, and micro-wells arrays.

Automated engineering of cells in micro-arrays using NFP-E has potential applications such as isogenic cell line generation from single cells and studying dynamic cellular processes such as intracellular signaling cascades and cell-cell communication.

Doctors could also tailor treatments to individuals, leading to safer and more effective care.  “Genetic manipulation of hiPSCs by introducing exogenous cargo has a wide range of applications in disease diagnostics, therapeutic discovery, and regenerative medicine,” says Prithvijit Mukherjee, a PhD student in Espinosa’s lab.  

The group will next work to automate NFP-E’s entire workflow, which includes steps such as automated cell imaging, cell tracking, switching probes, and media exchange for cell culture.

“The idea is to establish a fully automated cell line generation workflow using the combination of the NFP-E and the micro-well arrays,” Espinosa said. “The AI can be further trained to recognize and target specific cell types in multi-cell co-cultures. This can be useful in understanding dynamics such as disease progression or cell communication.”

The updated tool is described in a recent issue of the journal Small.