Machine Learning and Mathematical Models for Single-Cell Data Analysis

Advances in single-cell isolation and sequencing technologies enable assaying DNA, mRNA, and protein abundances at a single-cell resolution. Single-cell omics data, including genomics, transcriptomics, epige-nomics, metabolomics and proteomics data, have offered us new opportunities to study cell type identity, cellular heterogeneity, cellular dynamics process (e.g., cell cycle, cell differentiation and cell activation), cell-cell interactions, etc. However, processing single-cell data of high dimensionality and scale is inher-ently difficult, especially considering the degree of noise, sparsity, batch effects and heterogeneity in the data. Thus, there is an urgent need for developing computational models which can handle the size, di-mensionality, and various characteristics of single-cell data. Recently, the developments of single-cell mul-ti-omics technologies have enabled the simultaneous profiling of multiple types of molecule within a single cell. Single-cell multi-omics data has the potential to enable a more systematic study of the inner workings of biological systems, and allows us to uncover the underlying mechanisms for cellular functions and bio-logical processes such as cell differentiation and disease development. Integrative analysis methods for integrating multi-omics data may need to address more computational issues and are hence more difficult to upscale, but promise exploit the full potential of single-cell multi-omics technologies.

In this Research Topic, we aim at collecting research articles covering recent advancements in single-cell data analysis with a special focus on using machine learning and mathematical models in service of the analysis of single-cell omics data. Specifically, we welcome both methodological papers, proposing novel techniques for single-cell analysis, and application papers, showing techniques for solving real-world prob-lems.

Areas of interest to this Research Topic include, but are not limited to:
Machine learning and mathematical models for:
- Single-cell multi-omics integration
- Tumor heterogeneity and tumor microenvironment analysis at single cell resolution
- Network modeling of single-cell omics data