Administrative Supplement: Enhancing cell-type-specific inference with millions of snRNA-seq and deep learning methods

Univ Of North Carolina Chapel Hill, Chapel Hill NC

Investigators

Linked publications & trials

Abstract

Abstract The proposed Diversity Supplement will extend the original parent R01 in two aspects. First, innovative deep learning models will be employed to perform aggressive deconvolution to complement the empirical Bayesian method proposed in the parent R01. Second, the Supplement will leverage additional single cell omics data that became available after the funding of the parent R01. Specifically, we anticipate much enhanced deconvolution using as reference newly published single nuclei RNA- sequencing data, containing ~2.3 million nuclei from 427 donors.