deepMc: deep Matrix Completion for imputation of single cell RNA-seq data

Mongia, Aanchal; Sengupta, Debarka; Majumdar, Angshul

doi:10.1101/387621

Cited by 11 publications

(10 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with the DeepImpute method, Mongia et al proposed an attribution technology based on deep matrix factorization deepMc 33 . The deepMc method does not assume any gene expression distribution.…”

Section: Discussionmentioning

confidence: 99%

“…Mongia et al proved that the deepMc method is better than the DeepImpute attribution technology under most experimental conditions (Figure 4). We all know that one of the most important applications of scRNA‐seq is to cluster scRNA‐seq data to discover different cell types from heterogeneous cell populations, so the two can be compared from the clustering accuracy obtained after imputation The advantages of the algorithm, as shown in Figure 4A, the Adjusted Rand Index value obtained after applying k‐means clustering after various interpolation techniques, deepMc has a much higher accuracy than DeepImpute 33 . Second, they also compared the two methods by evaluating the accuracy of DE analysis.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Potential applications of deep learning in single-cell RNA sequencing analysis for cell therapy and regenerative medicine

et al. 2021

View full text Add to dashboard Cite

When used in cell therapy and regenerative medicine strategies, stem cells have potential to treat many previously incurable diseases. However, current application methods using stem cells are underdeveloped, as these cells are used directly regardless of their culture medium and subgroup. For example, when using mesenchymal stem cells (MSCs) in cell therapy, researchers do not consider their source and culture method nor their application angle and function (soft tissue regeneration, hard tissue regeneration, suppression of immune function, or promotion of immune function). By combining machine learning methods (such as deep learning) with data sets obtained through single-cell RNA sequencing (scRNA-seq) technology, we can discover the hidden structure of these cells, predict their effects more accurately, and effectively use subpopulations with differentiation potential for stem cell therapy. scRNA-seq technology has changed the study of transcription, because it can express single-cell genes with single-cell anatomical resolution. However, this powerful technology is sensitive to biological and technical noise. The subsequent data analysis can be computationally difficult for a variety of reasons, such as denoising single cell data, reducing dimensionality, imputing missing values, and accounting for the zero-inflated nature. In this review, we discussed how deep learning methods combined with scRNA-seq data for research, how to interpret scRNA-seq data in more depth, improve the follow-up analysis of stem cells, identify potential subgroups, and promote the implementation of cell therapy and regenerative medicine measures.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Potential applications of deep learning in single-cell RNA sequencing analysis for cell therapy and regenerative medicine

et al. 2021

View full text Add to dashboard Cite

show abstract

“…McImpute applies soft thresholding iteratively on singular values without making any assumption about the expression data distribution. Deep learning‐based pipeline, deepMc, imputes missing values in gene expression data using a deep matrix factorization‐based method (Mongia, Sengupta, & Majumdar, 2020). SAVER is a model‐based method that models UMI counts using a negative binomial distribution (Huang et al, 2018).…”

Section: Data Analytics Best‐practices In Single‐cell Transcriptomics: a Surveymentioning

confidence: 99%

Big data analytics in single‐cell transcriptomics: Five grand opportunities

Bhattacharya

Nelson

Ahuja

et al. 2021

WIREs Data Min & Knowl

Self Cite

View full text Add to dashboard Cite

Single‐cell omics technologies provide biologists with a new dimension for systematically dissecting the underlying complexities within biological systems. These powerful technologies have triggered a wave of rapid development and deployment of new computational tools capable of teasing out critical insights by analysis of large volumes of omics data at single‐cell resolution. Some of the key advancements include identifying molecular signatures imparting cellular identities, their evolutionary relationships, identifying novel and rare cell‐types, and establishing a direct link between cellular genotypes and phenotypes. With the sharp increase in the throughput of single‐cell platforms, the demand for efficient computational algorithms has become prominent. As such, devising novel computational strategies is critical to ensure optimal use of this wealth of molecular data for gaining newer insights into cellular biology. Here we discuss some of the grand opportunities of computational breakthroughs which would accelerate single‐cell research. These are: predicting cellular identity, single‐cell guided in silico drug screening for precision medicine, transfer learning methods to handle sparsity and heterogeneity of expression data, establishing genotype–phenotype relationships at single‐cell resolution, and developing computational platforms for handling big data. This article is categorized under: Algorithmic Development > Biological Data Mining Fundamental Concepts of Data and Knowledge > Big Data Mining Technologies > Machine Learning

show abstract

“…The setting of the size of the latent factors U and V allow to impose rank constraints on their product. Motivated by the success of deep learning in numerous fields [64,67,61,53], the shallow (two factor) models have been extended to deeper versions. The general factorization problem when the matrix is completely observed have been proposed in [41,71].…”

Section: Matrix Completionmentioning

confidence: 99%

“…The general factorization problem when the matrix is completely observed have been proposed in [41,71]. The solution to matrix completion via deep factorization has been proposed very recently, in [53]. This can be formally expressed as follows, in the 2-layers case:…”

Section: Matrix Completionmentioning

confidence: 99%

DeepVir - Graphical Deep Matrix Factorization for In Silico Antiviral Repositioning: Application to COVID-19

Majumdar¹,

Mongia²,

Chouzenoux³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

This work formulates antiviral repositioning as a matrix completion problem where the antiviral drugs are along the rows and the viruses along the columns. The input matrix is partially filled, with ones in positions where the antiviral has been known to be effective against a virus. The curated metadata for antivirals (chemical structure and pathways) and viruses (genomic structure and symptoms) is encoded into our matrix completion framework as graph Laplacian regularization. We then frame the resulting multiple graph regularized matrix completion problem as deep matrix factorization. This is solved by using a novel optimization method called HyPALM (Hybrid Proximal Alternating Linearized Minimization). Results on our curated RNA drug virus association (DVA) dataset shows that the proposed approach excels over state-of-the-art graph regularized matrix completion techniques. When applied to in silico prediction of antivirals for COVID-19, our approach returns antivirals that are either used for treating patients or are under for trials for the same.<br>

show abstract

deepMc: deep Matrix Completion for imputation of single cell RNA-seq data

Cited by 11 publications

References 37 publications

Potential applications of deep learning in single-cell RNA sequencing analysis for cell therapy and regenerative medicine

Potential applications of deep learning in single-cell RNA sequencing analysis for cell therapy and regenerative medicine

Big data analytics in single‐cell transcriptomics: Five grand opportunities

DeepVir - Graphical Deep Matrix Factorization for In Silico Antiviral Repositioning: Application to COVID-19

Contact Info

Product

Resources

About