Quantifying the fidelity of in vitro human cell culture systems using a biomedical foundation model.

Primary cell culture is fast becoming a dominant method for discovery work regarding human disease. Currently, there are no methods to quantitatively benchmark these systems. Here, we apply a uniform in vitro culture system of human intestinal epithelial cells (IECs) to achieve this goal. We previously established methods for long-term two-dimensional (2D) cultivation of mouse IECs using an air-liquid interface (ALI) technique. Here, we further refined these methods for long-term 2D cultivation of human IECs, with histological and molecular features of differentiated intestinal epithelia. Leveraging the power and scalability of a biomedical foundation model (BMFM) trained on single-cell RNA sequencing data (BMFM-RNA), we performed classification tasks to identify cell types across sample sources and to quantitatively benchmark our in vitro differentiated cells against cells collected from patient biopsies. We observed a striking concordance between our in vitro differentiated cells and the corresponding cell types in vivo for multiple differentiated secretory cell types. This approach using BMFM-RNA holds promise to expand our understanding of the regulatory mechanisms, including gene-gene regulation underlying homeostasis and regeneration, as well as the functions of rare and poorly understood lineages within the human intestinal epithelia. Moreover, these methods may be applicable to other organs, model systems, and experimental modalities. We propose that the framework used here can be deployed as a standard benchmarking methodology, ultimately improving the fidelity of primary human culture systems.