Joint Analysis of Single-Cell and Bulk RNA Data via Matrix Factorization
To improve the analysis of single-cell RNA-sequencing data by using matrix factorization methods to jointly analyze RNA-sequencing data along with bulk RNA data.
Results & Resources
This project resulted in multiple publications supporting the biomedical application of single-cell RNA-sequencing, including a publication quantifying the cell states of the mammary gland throughout developmental states using single-cell RNA-sequencing data. With this data, the team has defined and optimized a new method for single-cell dataset alignment. They also reported a new method for supervised principal component analysis (PCA) that simultaneously optimizes PCA and supervised learning objects, leading to performance improvements when compared to previously reported methods.