The invention of single-cell RNA sequencing (scRNA-seq) has led to the generation of tremendous amounts of data pertaining to populations of cells of specific interest. However, one of the major challenges associated with analysing such data includes designing efficient machine learning approaches that can cope with the noise and sparsity existing in data.

Examples of machine learning applications for scRNA-seq data include: identifying biomarkers of dementia and Alzheimer’s disease; identifying candidate drugs for numerous other neurological disorders; identifying putative cell types from scRNA-seq data of various diseases; noise filtering of low quality cells; pseudo-time reconstruction; and proposals of new clustering methods for scRNA-seq. The success behind machine learning applications depends on the development of new machine learning techniques.

This Special Issue invites not only machine learning researchers, but also researchers interested in potential applications to scRNA-seq data. Both research and review articles pertaining to new machine learning methods and applications to the interpretation of scRNA-seq data are welcomed.

Potential topics include but are not limited to the following:

• Supervised learning
• Unsupervised learning
• Semi-supervised learning
• Active learning
• Transfer and multitask learning
• Ranking
• Deep learning
• Representation learning
• Parallel and distributed learning approaches
• Distance learning
• Ensemble methods
• Dimensionality reduction methods