Multimodal Data Visualization and Denoising with Integrated Diffusion

Kuchroo, Manik; Godavarthi, Abhinav; Tong, Alexander; Wolf, Guy; Krishnaswamy, Smita

doi:10.1109/mlsp52302.2021.9596214

Cited by 18 publications

(22 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Features specified through the integration strategy are used to infer trajectories, predict response to drug treatment, and classify patient cells. (B) Overview of data integration strategies (unintegrated, concatenation, sum, CellRank [17], Grassmann joint embedding [26], integrated diffusion [24], SNF [25], and PRECISE [47]).…”

Section: Resultsmentioning

confidence: 99%

“…Integrated Diffusion: Integrated diffusion [24] combines data modalities by computing a joint data diffusion operator. First, individual modalities are locally denoised by performing a truncated singular value decomposition (SVD) on local neighborhoods determined through spectral clustering.…”

Section: Problem Formulationmentioning

confidence: 99%

“…Here, integration methods aim to merge individual layers of single-cell data (e.g. transcriptomic, proteomic, epigenomic) * Correspondence to Natalie Stanley, email: natalies@cs.unc.edu and Jeremy Purvis, email: purvisj@email.unc.edu into a unified consensus representation, such as an integrated graph [25] or a joint-embedding [24,26]. To do so, computational approaches have leveraged techniques, including kernel learning [27,28], matrix factorization [29,30,31,32,33], or deep learning [34].…”

Section: Introductionmentioning

confidence: 99%

“…Single-cell multi-omics data integration methods have had great success in fusing different molecular data types, or modalities for disease subtyping, predicting biomarkers, or uncovering cross-modality correlations [23, 24]. Here, integration methods aim to merge individual layers of single-cell data (e.g.…”

Section: Introductionmentioning

confidence: 99%

“…Integrated diffusion: Integrated diffusion[24] merges data modalities by first computing a diffusion operator for each denoised data type. Next, individual operators are merged by computing a joint diffusion operator.8.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Integrating temporal single-cell gene expression modalities for trajectory inference and disease prediction

Ranek

Stanley

Purvis

2022

Preprint

View full text Add to dashboard Cite

Current methods for analyzing single-cell datasets have relied primarily on static gene expression measurements to characterize the molecular state of individual cells. However, capturing temporal changes in cell state is crucial for the interpretation of dynamic phenotypes such as the cell cycle, development, or disease progression. RNA velocity infers the direction and speed of transcriptional changes in individual cells, yet it is unclear how these temporal gene expression modalities may be leveraged for predictive modeling of cellular dynamics. Here, we present the first task-oriented benchmarking study that investigates integration of temporal sequencing modalities for dynamic cell state prediction. We benchmark eight integration approaches on eight datasets spanning different biological contexts, sequencing technologies, and species. We find that integrated data more accurately infers biological trajectories and achieves increased performance on classifying cells according to perturbation and disease states. Furthermore, we show that simple concatenation of spliced and unspliced molecules performs consistently well on classification tasks and can be used over more memory intensive and computationally expensive methods. This work provides users with practical recommendations for task-specific integration of single-cell gene expression modalities.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Problem Formulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Integrating temporal single-cell gene expression modalities for trajectory inference and disease prediction

Ranek

Stanley

Purvis

2022

Preprint

View full text Add to dashboard Cite

show abstract

Diffusion Transport Alignment

Duque¹,

Wolf²,

Moon³

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Computational Methods for Single-Cell Multi-Omics Integration and Alignment

Stanojevic

Ristivojevic

et al. 2022

Genomics, Proteomics &Amp; Bioinformatics

View full text Add to dashboard Cite

Recently developed technologies to generate single-cell genomic data have made a revolutionary impact in the field of biology. Multi-omics assays offer even greater opportunities to understand cellular states and biological processes. The problem of integrating different omics data with very different dimensionality and statistical properties remains, however, quite challenging. A growing body of computational tools is being developed for this task, leveraging ideas ranging from machine translation to the theory of networks, and represents another frontier on the interface of biology and data science. Our goal in this review is to provide a comprehensive, up-to-date survey of computational techniques for the integration of single-cell multi-omics data, while making the concepts behind each algorithm approachable to a non-expert audience.

show abstract

Multimodal Data Visualization and Denoising with Integrated Diffusion

Cited by 18 publications

References 10 publications

Integrating temporal single-cell gene expression modalities for trajectory inference and disease prediction

Integrating temporal single-cell gene expression modalities for trajectory inference and disease prediction

Diffusion Transport Alignment

Computational Methods for Single-Cell Multi-Omics Integration and Alignment

Contact Info

Product

Resources

About