Mouse blood cells types and aging prediction using penalized Latent Dirichlet Allocation

Aging is a complex, heterogeneous process that has multiple causes. Knowledge on genomic, epigenomic and transcriptomic changes during the aging process shed light on understanding the aging mechanism. A recent breakthrough in biotechnology, single cell RNAseq, is revolutionizing aging study by providing gene expression profile of the entire transcriptome of individual cells. Many interesting information could be inferred from this new type of data with the help of novel computational methods.

In this manuscript a novel statistical method, penalized Latent Dirichlet Allocation (pLDA), is applied to an aging mouse blood scRNA-seq data set. A pipeline is built for cell type and aging prediction. The sequence of models in the pipeline take scRNA-seq expression counts as input, preprocess the data using pLDA and predict the cell type and aging status.

pLDA learns a dimension reduced representation of the expression profile. This representation allows identification of cell types and has predictability of the age of cells.