Effective Preprocessing of Single-Cell RNA-Seq for Unravelling Alzheimer's Disease Signatures

The development in the field of biomedical technology has brought significant progress in the diagnosis and prediction of many complex diseases. Part of this development is the single-cell RNA sequencing analysis, which allows the study of a complex disease in great depth at the cellular level. Such analyses can decipher the mechanisms that cause complex diseases, such as Alzheimer's disease (AD). However, the increasing depth in the collection of single-cell RNA sequencing data implies, in addition to greater challenges, the production of a large amount of information, which needs careful analysis. Toward this direction, we examine the approach to single-cell RNA sequencing data through the development of an exploratory data analysis methodology. For this purpose, a combination of various tools is presented for their effective and efficient processing. At the same time, reference is made to the relevant biological concepts, the goals and challenges of the studies, and the workflows of sequencing, preprocessing, and analysis of the data. Our framework is applied to Alzheimer's disease data providing evidence that such data are quite complex while the appropriate preprocess step can boost the machine learning processes for identifying AD signatures.