Functional-Feature-Based Data Reduction Using Sparsely Connected Autoencoders

Luca Alessandri; Raffaele A Calogero

doi:10.1007/978-1-0716-2756-3_11

Functional-Feature-Based Data Reduction Using Sparsely Connected Autoencoders

Methods Mol Biol. 2023:2584:231-240. doi: 10.1007/978-1-0716-2756-3_11.

Authors

Luca Alessandri¹, Raffaele A Calogero²

Affiliations

¹ Molecular Biotechnology Center, University of Torino, Turin, Italy. l.alessandri@unito.it.
² Molecular Biotechnology Center, University of Torino, Torino, Italy.

PMID: 36495453
DOI: 10.1007/978-1-0716-2756-3_11

Abstract

Single-cell RNA sequencing (scRNA-seq) allows for the creation of large collections of individual cells transcriptome. Unsupervised clustering is an essential element for the analysis of these data, and it represents the initial step for the identification of different cell types to investigate the cell subpopulation structure of a biological sample. However, it is possible that the clustering aggregation features do not perfectly match the underlying biology since scRNA-seq data are characterized by high noise. In this chapter, we describe a functional feature-driven data reduction approach, which could provide a better link among cell clusters and their underlying cell biology.

Keywords: Data reduction; Kinase; Sparsely connected autoencoder; Transcription factor; miRNA.

MeSH terms

Algorithms
Cluster Analysis
Gene Expression Profiling*
Sequence Analysis, RNA
Single-Cell Analysis*
Transcriptome