A bstract The creation of induced pluripotent stem cells (iPSCs) has enabled scientists to explore the derivation of many types of cells. While there are diverse general approaches for cell-fate engineering, one of the fastest and most efficient approaches is transcription factor (TF) over-expression. However, finding the right combination of TFs to over-express to differentiate iPSCs directly into other cell-types is a difficult task. Here were describe a machine-learning (ML) pipeline, called CellCartographer , for using chromatin accessibility data to design multiplex TF pooled-screens for cell type conversions. We validate this method by differentiating iPSCs into twelve diverse cell types at low efficiency in preliminary screens and then iteratively refining our TF combinations to achieve high efficiency differentiation for six of these cell types in &lt; 6 days. Finally, we functionally characterized engineered iPSC-derived cytotoxic T-cells (iCytoT), regulatory T-cells (iTReg), type II astrocytes (iAstII), and hepatocytes (iHep) to validate functionally accurate differentiation.

Machine-guided cell-fate engineering