AutoImpute: Autoencoder based imputation of single-cell RNA-seq data

Talwar, Divyanshu; Mongia, Aanchal; Sengupta, Debarka; Majumdar, Angshul

doi:10.1038/s41598-018-34688-x

Cited by 152 publications

(101 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…variation mirrored those of real datasets. To overcome the limitations of previously described simulation approaches 15,16,[18][19][20]24 (Supplementary Note 1), we used the output of a denoising method as the ground truth, and then simulated realistic efficiency and sampling noise (Methods). We applied this approach to simulate data based on a renal cell carcinoma biopsy sample 25 , which contained a heterogeneous set of populations from the tumor microenvironment ( Fig.…”

Section: Resultsmentioning

confidence: 99%

“…However, these methods do not generate denoised gene expression values, and thus cannot be used to perform genelevel analyses, for example with scatter plots or heatmaps 15 . To overcome this limitation, a diverse array of methods have been proposed to computationally remove noise by sharing information across cells and genes 10,[15][16][17][18][19][20][21] . The general lack of an experimental ground truth has made it difficult to establish and compare the accuracies of these approaches, and it is currently unclear what levels of theoretical and algorithmic complexity are necessary or appropriate to address the denoising problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Accurate denoising of single-cell RNA-Seq data using unbiased principal component analysis

Wagner¹,

Barkley²,

Yanai³

2019

Preprint

View full text Add to dashboard Cite

Single-cell RNA-Seq measurements are commonly affected by high levels of technical noise, posing challenges for data analysis and visualization. A diverse array of methods has been proposed to computationally remove noise by sharing information across similar cells or genes, however their respective accuracies have been difficult to establish. Here, we propose a simple denoising strategy based on principal component analysis (PCA). We show that while PCA performed on raw data is biased towards highly expressed genes, this bias can be mitigated with a cell aggregation step, allowing the recovery of denoised expression values for both highly and lowly expressed genes. We benchmark our resulting ENHANCE algorithm and three previously described methods on simulated data that closely mimic real datasets, showing that ENHANCE provides the best overall denoising accuracy, recovering modules of co-expressed genes and cell subpopulations. Implementations of our algorithm are available at https://github.com/yanailab/enhance.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Accurate denoising of single-cell RNA-Seq data using unbiased principal component analysis

Wagner¹,

Barkley²,

Yanai³

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Autoencoder was also used to discover two liver cancer sub-types that had distinguishable chances of survival [58]. Moreover, some recent successful data imputation methods have been developed based on autoencoders [59][60][61]. Autoimpute [59] can be an example which imputes single cell RNA-seq gene expression.…”

Section: Autoencoder (Ae)mentioning

confidence: 99%

“…Moreover, some recent successful data imputation methods have been developed based on autoencoders [59][60][61]. Autoimpute [59] can be an example which imputes single cell RNA-seq gene expression. Autoencoder-based methods such as [60] and [61] have surpassed older machine learning techniques on various real life datasets.…”

Section: Autoencoder (Ae)mentioning

confidence: 99%

Machine learning based imputation techniques for estimating phylogenetic trees from incomplete distance matrices

Bhattacharjee

Bayzid

2019

Preprint

View full text Add to dashboard Cite

Background: Due to the recent advances in sequencing technologies and species tree estimation methods capable of taking gene tree discordance into account, notable progress has been achieved in constructing large scale phylogenetic trees from genome wide data. However, substantial challenges remain in leveraging this huge amount of molecular data. One of the foremost among these challenges is the need for efficient tools that can handle missing data. Popular distance-based methods such as neighbor joining and UPGMA require that the input distance matrix does not contain any missing values.Results: We introduce two highly accurate machine learning based distance imputation techniques. One of our approaches is based on matrix factorization, and the other one is an autoencoder based deep learning technique. We evaluate these two techniques on a collection of simulated and biological datasets, and show that our techniques match or improve upon the best alternate techniques for distance imputation. Moreover, our proposed techniques can handle substantial amount of missing data, to the extent where the best alternate methods fail.Conclusions: This study shows for the first time the power and feasibility of applying deep learning techniques for imputing distance matrices. The autoencoder based deep learning technique is highly accurate and scalable to large dataset. We have made these techniques freely available as a cross-platform software (available at https://github.com/Ananya-Bhattacharjee/ImputeDistances).

show abstract

“…Recently, a group of methods were proposed to target that problem inspired from the emerging success of generative models. Among these methods are AutoImpute [18], scVI [13] and DCA [4]. scVI uses stochastic optimization and learns cell-specific embeddings using deep neural networks that best explains the observed data, whereas both AutoImpute and DCA uses autoencoders as their interior models.…”

Section: Introductionmentioning

confidence: 99%

scGAIN: Single Cell RNA-seq Data Imputation using Generative Adversarial Networks

Gunady

Kancherla

Bravo

et al. 2019

Preprint

View full text Add to dashboard Cite

Single cell RNA sequencing (scRNA-seq) provides a rich view into the heterogeneity underlying a cell population. However single-cell data are usually noisy and very sparse due to the presence of dropout genes. In this work we propose an approach to impute missing gene expressions in single cell data using generative adversarial networks (GANs). By learning an approximate distribution of the data, our approach, scGAIN, can impute dropouts in simulated and real single cell data. The work in this paper discusses how to adopt GAIN training model into the domain of imputing single cell data. Experiments show that scGAIN gives competitive results compared to the state-of-the-art approaches while showing superiority in various aspects in simulation and real data. Imputation by scGAIN successfully recovers the underlying clustering of different subpopulations, provides sharp estimates around true mean expressions and increase the correspondence with matched bulk RNAseq experiments.

show abstract

AutoImpute: Autoencoder based imputation of single-cell RNA-seq data

Cited by 152 publications

References 45 publications

Accurate denoising of single-cell RNA-Seq data using unbiased principal component analysis

Accurate denoising of single-cell RNA-Seq data using unbiased principal component analysis

Machine learning based imputation techniques for estimating phylogenetic trees from incomplete distance matrices

scGAIN: Single Cell RNA-seq Data Imputation using Generative Adversarial Networks

Contact Info

Product

Resources

About