Overall Area: How can we develop deep learning methods for cell annotation in scRNA-seq data, with a focus on macrophages?
Motivation: Single-cell RNA sequencing data is providing insight into the transcriptomes of cells at unprecedented resolution. Determining the relationship between genotype and phenotype is one of the central question of genomics. In the context of scRNA-seq, this involves determining the cell type solely from gene expression values (clustering and cell annotation). This allows us to characterize cell types and subtypes and generate maps of different tissues. These efforts can provide in insight into how cell types develop their identity and allow for the creation of cell type atlases for the whole human body. Given the high dimensionality and noise in the data, state-of-the-art computational methods are required.
First Goal: Develop a baseline neural network to identify macrophages in single-cell data