Clustering and classification methods for single-cell RNA-sequencing data

Qi, Ren; Ma, Anjun; Ma, Qin; Zou, Quan

doi:10.1093/bib/bbz062

Cited by 129 publications

(53 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The frequently used methods include Seurat 67 , pcaReduce 68 , SC3 69 , BackSPIN 70 , and SNN-cliq 71 . The detailed algorithms and applications of these and other methods have been extensively reviewed [72][73][74] . Second, another set of methods infer the regulatory networks delineating regulatory relationships among marker genes (e.g., transcription factors and their targets) showing coexpression across different cells in a cell population.…”

Section: Integrative Analysis Of Transcriptome and Proteome Datamentioning

confidence: 99%

Single-cell multiomics: technologies and data analysis methods

2020

View full text Add to dashboard Cite

Advances in single-cell isolation and barcoding technologies offer unprecedented opportunities to profile DNA, mRNA, and proteins at a single-cell resolution. Recently, bulk multiomics analyses, such as multidimensional genomic and proteogenomic analyses, have proven beneficial for obtaining a comprehensive understanding of cellular events. This benefit has facilitated the development of single-cell multiomics analysis, which enables cell type-specific gene regulation to be examined. The cardinal features of single-cell multiomics analysis include (1) technologies for single-cell isolation, barcoding, and sequencing to measure multiple types of molecules from individual cells and (2) the integrative analysis of molecules to characterize cell types and their functions regarding pathophysiological processes based on molecular signatures. Here, we summarize the technologies for single-cell multiomics analyses (mRNA-genome, mRNA-DNA methylation, mRNA-chromatin accessibility, and mRNA-protein) as well as the methods for the integrative analysis of single-cell multiomics data.

show abstract

Section: Integrative Analysis Of Transcriptome and Proteome Datamentioning

confidence: 99%

Single-cell multiomics: technologies and data analysis methods

2020

View full text Add to dashboard Cite

show abstract

“…Recently, Skinnider et al ( 14 ) evaluated the multiple existing methods to assess gene-to-gene similarity and cell-to-cell similarity and their performance to cluster cells, reconstruct cell networks or link gene expression to diseases in different conditions. A review of the clustering methods has been done by Qi et al ( 15 ).…”

Section: Introductionmentioning

confidence: 99%

Bayesian correlation is a robust gene similarity measure for single-cell RNA-seq data

Sánchez-Taltavull

Perkins

Dommann

et al. 2020

NAR Genomics and Bioinformatics

View full text Add to dashboard Cite

Assessing similarity is highly important for bioinformatics algorithms to determine correlations between biological information. A common problem is that similarity can appear by chance, particularly for low expressed entities. This is especially relevant in single-cell RNA-seq (scRNA-seq) data because read counts are much lower compared to bulk RNA-seq. Recently, a Bayesian correlation scheme that assigns low similarity to genes that have low confidence expression estimates has been proposed to assess similarity for bulk RNA-seq. Our goal is to extend the properties of the Bayesian correlation in scRNA-seq data by considering three ways to compute similarity. First, we compute the similarity of pairs of genes over all cells. Second, we identify specific cell populations and compute the correlation in those populations. Third, we compute the similarity of pairs of genes over all clusters, by considering the total mRNA expression. We demonstrate that Bayesian correlations are more reproducible than Pearson correlations. Compared to Pearson correlations, Bayesian correlations have a smaller dependence on the number of input cells. We show that the Bayesian correlation algorithm assigns high similarity values to genes with a biological relevance in a specific population. We conclude that Bayesian correlation is a robust similarity measure in scRNA-seq data.

show abstract

“…Supervised machine learning is often applied to classify new unlabeled samples [20][21][22][23][24]. Unsupervised learning, such as autoencoder [25,26], manifold approximation [27,28], and various clustering methods [29], have been applied to the dimensionality…”

Section: Introductionmentioning

confidence: 99%

Building patient‐specific models for receptor tyrosine kinase signaling networks

et al. 2021

View full text Add to dashboard Cite

Cancer progresses due to changes in the dynamic interactions of multidimensional factors associated with gene mutations. Cancer research has actively adopted computational methods, including data-and mathematical model-driven approaches, to identify causative factors and regulatory rules that can explain the complexity and diversity of cancers. A data-driven, statistics-based approach revealed correlations between gene alterations and clinical outcomes in many types of cancers. A model-driven mathematical approach has elucidated the dynamic features of cancer networks and identified the mechanisms of drug efficacy and resistance. More recently, machine learning methods have emerged that can be used for mining omics data and classifying patient. However, as the strengths and weaknesses of each method becoming apparent, new analytical tools are emerging to combine and improve the methodologies and maximize their predictive power for classifying cancer subtypes and prognosis. Here, we introduce recent advances in cancer systems biology aimed at personalized medicine, with focus on the receptor tyrosine kinase signaling network.

show abstract

Clustering and classification methods for single-cell RNA-sequencing data

Cited by 129 publications

References 69 publications

Single-cell multiomics: technologies and data analysis methods

Single-cell multiomics: technologies and data analysis methods

Bayesian correlation is a robust gene similarity measure for single-cell RNA-seq data

Building patient‐specific models for receptor tyrosine kinase signaling networks

Contact Info

Product

Resources

About