Single cell atlas of developing mouse dental germs reveals populations of CD24+ and Plac8+ odontogenic cells.

The spatiotemporal relationships in high-resolution during odontogenesis remain poorly understood. We report a cell lineage and atlas of developing mouse teeth. We performed a large-scale (92,688 cells) single cell RNA sequencing, tracing the cell trajectories during odontogenesis from embryonic days 10.5 to 16.5. Combined with an assay for transposase-accessible chromatin with high-throughput sequencing, our results suggest that mesenchymal cells show the specific transcriptome profiles to distinguish the tooth types. Subsequently, we identified key gene regulatory networks in teeth and bone formation and uncovered spatiotemporal patterns of odontogenic mesenchymal cells. CD24+ and Plac8+ cells from the mesenchyme at the bell stage were distributed in the upper half and preodontoblast layer of the dental papilla, respectively, which could individually induce nonodontogenic epithelia to form tooth-like structures. Specifically, the Plac8+ tissue we discovered is the smallest piece with the most homogenous cells that could induce tooth regeneration to date. Our work reveals previously unknown heterogeneity and spatiotemporal patterns of tooth germs that may lead to tooth regeneration for regenerative dentistry.

EXPERT: transfer learning-enabled context-aware microbial community classification.

Microbial community classification enables identification of putative type and source of the microbial community, thus facilitating a better understanding of how the taxonomic and functional structure were developed and maintained. However, previous classification models required a trade-off between speed and accuracy, and faced difficulties to be customized for a variety of contexts, especially less studied contexts. Here, we introduced EXPERT based on transfer learning that enabled the classification model to be adaptable in multiple contexts, with both high efficiency and accuracy. More importantly, we demonstrated that transfer learning can facilitate microbial community classification in diverse contexts, such as classification of microbial communities for multiple diseases with limited number of samples, as well as prediction of the changes in gut microbiome across successive stages of colorectal cancer. Broadly, EXPERT enables accurate and context-aware customized microbial community classification, and potentiates novel microbial knowledge discovery.