UIPBC: An effective clustering for scRNA-seq data analysis without user input

Chowdhury, Hussain Ahmed; Bhattacharyya, Dhruba K.; Kalita, Jugal

doi:10.1016/j.knosys.2022.108767

Cited by 2 publications

(1 citation statement)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Single-cell RNA-sequencing (scRNA-seq) techniques enable elucidating the genetic heterogeneity of individual cells, which is essential for characterizing cell types based on the transcriptome (Kolodziejczyk et al 2015), studying developmental biology (Chowdhury 2021), discovering complex diseases (Costa et al 2013), and inferring cell trajectories (Tran and Bader 2020). Therefore, accurate identification of cell types has become a key step in singlecell RNA-seq analysis (Macosko et al 2015).…”

Section: Introductionmentioning

confidence: 99%

ZINB-Based Graph Embedding Autoencoder for Single-Cell RNA-Seq Interpretations

Wang

et al. 2022

AAAI

View full text Add to dashboard Cite

Single-cell RNA sequencing (scRNA-seq) provides high-throughput information about the genome-wide gene expression levels at the single-cell resolution, bringing a precise understanding on the transcriptome of individual cells. Unfortunately, the rapidly growing scRNA-seq data and the prevalence of dropout events pose substantial challenges for cell type annotation. Here, we propose a single-cell model-based deep graph embedding clustering (scTAG) method, which simultaneously learns cell–cell topology representations and identifies cell clusters based on deep graph convolutional network. scTAG integrates the zero-inflated negative binomial (ZINB) model into a topology adaptive graph convolutional autoencoder to learn the low-dimensional latent representation and adopts Kullback–Leibler (KL) divergence for the clustering tasks. By simultaneously optimizing the clustering loss, ZINB loss, and the cell graph reconstruction loss, scTAG jointly optimizes cluster label assignment and feature learning with the topological structures preserved in an end-to-end manner. Extensive experiments on 16 single-cell RNA-seq datasets from diverse yet representative single-cell sequencing platforms demonstrate the superiority of scTAG over various state-of-the-art clustering methods.

show abstract