Challenges in unsupervised clustering of single-cell RNA-seq data

1,049 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

openTSNE: a modular Python library for t-SNE dimensionality reduction and embedding (2019, methodology): “We preprocess the data using the standard single-cell analysis pipeline (Kiselev, Andrews, and Hemberg 2019) and extract the top 50 principal components.”
Fully-automated and ultra-fast cell-type identification using specific marker combinations from single-cell transcriptomic data (2022, methodology): “Identi ﬁ cation of cell populations often relies on unsupervised clustering of cells based on their transcriptomic pro ﬁ les, followed by cluster annotation using marker genes that are differentially-expressed between the clusters 14,15 .”
Identifying phenotype-associated subpopulations by integrating bulk and single-cell sequencing data (2021, neutral): “One of the advantages is that Scissor does not require any unsupervised clustering on single-cell data, which avoids subjective decisions of cell cluster numbers or clustering resolution 47 .”
Assessment of computational methods for the analysis of single-cell ATAC-seq data (2019, methodology): “Clustering results were evaluated by three commonly used metrics: adjusted random index (ARI), adjusted mutual information (AMI) and homogeneity when a gold standard solution was available (known labels for the simulation data and FACS-sorted cell populations or known tissues for the real datasets).”