JSNMF enables effective and accurate integrative analysis of single-cell multiomics data

Ma, Yuanyuan; Sun, Zexuan; Zeng, Pengcheng; Zhang, Wenyu; Lin, Zhixiang

doi:10.1093/bib/bbac105

Cited by 17 publications

(13 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1e). Other linear methods such as JIVE 10 , MOFA+ 12 , scAI 13 and JSNMF 14 and non-linear methods such as WNN 11 have similar qualities which learn the leading axes of variation from either modality (Extended Data Fig. 1, see Supplementary Information for more details).…”

Section: Resultsmentioning

confidence: 99%

“…Since these low-rank matrices J (1) , J (2) , A (1) , A (2) are estimated in (14) to minimize the prediction error (i.e., with additional rank constraints of the modality-specific components A (1) and A (2) not found in Consensus PCA), we deem the matrix J in JIVE as capturing the "union of information. "…”

Section: Jivementioning

confidence: 99%

“…Roughly speaking, these methods seek a low-dimensional embedding of the cells such that a distinct sub-population is distinguishable in the embedding if it is distinguishable in either modality. Methods to estimate such a joint embedding include JIVE 10 , WNN 11 , MOFA+ 12 , scAI 13 and JSNMF 14 . These methods have been useful for identification of nuanced cell types by combining information across both modalities.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Quantifying common and distinct information in single-cell multimodal data with Tilted-CCA

Lin¹,

Zhang

2022

Preprint

View full text Add to dashboard Cite

Multimodal single-cell technologies profile multiple modalities for each cell simultaneously and enable a more thorough characterization of cell populations alongside investigations into cross-modality relationships. Existing dimension-reduction methods for multimodal data focus on capturing the "union of information," producing a lower-dimensional embedding that combines the information across modalities. While these tools are useful, we develop Tilted-CCA to quantify the "intersection and difference of information," that is, a decomposition of a paired multimodal dataset into common axes of variation that is shared between both modalities and distinct axes of variation that is found only in one modality. Through examples, we show that Tilted-CCA enables meaningful visualization and quantification of the cross-modal information overlap. We also demonstrate the application of Tilted-CCA to two specific types of analyses. First, for single-cell experiments that jointly profile the transcriptome and surface antibody markers, we show how to use Tilted-CCA to design the target antibody panel to best complement the transcriptome. Second, for single-cell multiome data that jointly profiles transcriptome and chromatin accessibility, we show how to use the common embedding given by Tilted-CCA to identify development-informative genes and distinguish between transient versus terminal cell types.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Jivementioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Quantifying common and distinct information in single-cell multimodal data with Tilted-CCA

Lin¹,

Zhang

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…A more comprehensive discussion on integration of single-cell genomic data is presented in [15]. Only a few computational methods, including MOFA+ [2], scAI [20], Seurat (version 4) [18] and JSNMF [23], have been developed for integrative analysis of single-cell genomic data that are derived from the same cells.…”

Section: Introductionmentioning

confidence: 99%

scICML: Information-theoretic Co-clustering-based Multi-view Learning for the Integrative Analysis of Single-cell Multi-omics data

Zeng¹,

Lin²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Modern high-throughput sequencing technologies have enabled us to profile multiple molecular modalities from the same single cell, providing unprecedented opportunities to assay celluar heterogeneity from multiple biological layers. However, the datasets generated from these technologies tend to have high level of noise and are highly sparse, bringing challenges to data analysis. In this paper, we develop a novel information-theoretic co-clustering-based multi-view learning (scICML) method for multi-omics single-cell data integration. scICML utilizes co-clusterings to aggregate similar features for each view of data and uncover the common clustering pattern for cells. In addition, scICML automatically matches the clusters of the linked features across different data types for considering the biological dependency structure across different types of genomic features. Our experiments on four real-world datasets demonstrate that scICML improves the overall clustering performance and provides biological insights into the data analysis of peripheral blood mononuclear cells.

show abstract

“…scAI ( Jin et al , 2020 ) aggregates epigenomic data in cell subpopulations that exhibit similar gene expression and epigenomic profiles through iterative learning in an unsupervised manner. JSNMF ( Ma et al , 2022 ) is based on jointly semi-orthogonal NMF and it enables effective and accurate integrative analysis of single-cell multiomics data. (ii) Methods based on probabilistic generative models.…”

Section: Introductionmentioning

confidence: 99%

scAWMV: an adaptively weighted multi-view learning framework for the integrative analysis of parallel scRNA-seq and scATAC-seq data

Zeng

Lin

2022

Bioinformatics

Self Cite

View full text Add to dashboard Cite

Motivation Technological advances have enabled us to profile single-cell multi-omics data from the same cells, providing us with an unprecedented opportunity to understand the cellular phenotype and links to its genotype. The available protocols and multi-omics datasets (including parallel scRNA-seq and scATAC-seq data profiled from the same cell) are growing increasingly. However, such data are highly sparse and tend to have high level of noise, making data analysis challenging. The methods that integrate the multi-omics data can potentially improve the capacity of revealing the celluar heterogeneity. Results We propose an adaptively weighted multi-view learning (scAWMV) method for the integrative analysis of parallel scRNA-seq and scATAC-seq data profiled from the same cell. scAWMV considers both the difference in importance across different modalities in multi-omics data and the biological connection of the features in the scRNA-seq and scATAC-seq data. It generates biologically meaningful low-dimensional representations for the transcriptomic and epigenomic profiles via unsupervised learning. Application to four real datasets demonstrates that our framework scAWMV is an efficient method to dissect cellular heterogeneity for single-cell multi-omics data. Availability The software and datasets are available at https://github.com/pengchengzeng/scAWMV. Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

JSNMF enables effective and accurate integrative analysis of single-cell multiomics data

Cited by 17 publications

References 38 publications

Quantifying common and distinct information in single-cell multimodal data with Tilted-CCA

Quantifying common and distinct information in single-cell multimodal data with Tilted-CCA

scICML: Information-theoretic Co-clustering-based Multi-view Learning for the Integrative Analysis of Single-cell Multi-omics data

scAWMV: an adaptively weighted multi-view learning framework for the integrative analysis of parallel scRNA-seq and scATAC-seq data

Contact Info

Product

Resources

About