DeepKINET: a deep generative model for estimating single-cell RNA splicing and degradation rates

• Published in: Genome Biology Vol. 25; no. 1; p. 229
• Main Authors: Mizukoshi, Chikara, Kojima, Yasuhiro, Nomura, Satoshi, Hayashi, Shuto, Abe, Ko, Shimamura, Teppei
• Format: Journal Article
• Language: English
• Published: England BioMed Central 06.09.2024; BMC
• Subjects: Accuracy; Animals; brain; Breast cancer; breast neoplasms; Breast Neoplasms - genetics; Breast Neoplasms - metabolism; Cancer; Cell cycle; data collection; Datasets; Degradation; Female; Forebrain; Gene expression; gene expression regulation; Gene regulation; Genes; genome; Humans; Kinetics; messenger RNA; Metabolism; Methods; Neural networks; Parameter estimation; Post-transcription; Prosencephalon - metabolism; Proteins; RNA degradation; RNA Splicing; RNA Stability; RNA-binding protein; RNA-binding proteins; RNA-Binding Proteins - genetics; RNA-Binding Proteins - metabolism; Single-Cell Analysis; Single-cell RNA sequencing (scRNA-seq); Splicing factors; Splicing kinetics; Transcriptome dynamics; Velocity; Dimensionality reduction; Variational autoencoder (VAE); RNA velocity; Deep generative model; RNA degradation; RNA-binding proteins; Neural network; Cell differentiation; Transcriptome dynamics; Single-cell RNA sequencing (scRNA-seq); Splicing kinetics; Metabolic labeling; RNA splicing

Messenger RNA splicing and degradation are critical for gene expression regulation, the abnormality of which leads to diseases. Previous methods for estimating kinetic rates have limitations, assuming uniform rates across cells. DeepKINET is a deep generative model that estimates splicing and degrad...