Abstract
BackgroundWith single-cell RNA sequencing (scRNA-seq) methods, gene expression patterns at the single-cell resolution can be revealed. But as impacted by current technical defects, dropout events in scRNA-seq lead to missing data and noise in the gene-cell expression matrix and adversely affect downstream analyses. Accordingly, the true gene expression level should be recovered before the downstream analysis is carried out.ResultsIn this paper, a novel low-rank tensor completion-based method, termed as scLRTC, is proposed to impute the dropout entries of a given scRNA-seq expression. It initially exploits the similarity of single cells to build a third-order low-rank tensor and employs the tensor decomposition to denoise the data. Subsequently, it reconstructs the cell expression by adopting the low-rank tensor completion algorithm, which can restore the gene-to-gene and cell-to-cell correlations. ScLRTC is compared with other state-of-the-art methods on simulated datasets and real scRNA-seq datasets with different data sizes. Specific to simulated datasets, scLRTC outperforms other methods in imputing the dropouts closest to the original expression values, which is assessed by both the sum of squared error (SSE) and Pearson correlation coefficient (PCC). In terms of real datasets, scLRTC achieves the most accurate cell classification results in spite of the choice of different clustering methods (e.g., SC3 or t-SNE followed by K-means), which is evaluated by using adjusted rand index (ARI) and normalized mutual information (NMI). Lastly, scLRTC is demonstrated to be also effective in cell visualization and in inferring cell lineage trajectories.Conclusionsa novel low-rank tensor completion-based method scLRTC gave imputation results better than the state-of-the-art tools. Source code of scLRTC can be accessed at https://github.com/jianghuaijie/scLRTC.
Highlights
With single-cell RNA sequencing methods, gene expression patterns at the single-cell resolution can be revealed
As impacted by the picogram level of RNAs in a single cell, RNA transcripts may be missed during the reverse transcription and amplification step, so the transcripts are not detected in the following sequencing, which is termed as the dropout problem [1]
The proposed imputation method is employed for nine published scRNA-seq datasets (i.e., Pollen [20], Usoskin [21], Yan [22], Zeisel [23], Mouse [24], PBMC [25], Chen [26], Loh [27] and Petropoulos [28]) and four simulation datasets generated from Splatter package [29], and it is compared with some popular methods (e.g., SAVER [7], MAGIC [8], scImpute [9], DrImpute [10], CMF-Impute [11], PBLR [15], WEDGE [18] and scGNN [19])
Summary
With single-cell RNA sequencing (scRNA-seq) methods, gene expression patterns at the single-cell resolution can be revealed. As impacted by current technical defects, dropout events in scRNA-seq lead to missing data and noise in the gene-cell expression matrix and adversely affect downstream analyses. Due to the influence of the training set and the existence of over-fitting problem, these methods may generate the false-positive results in differential expression analyses [6]. Another type for single-cell imputation methods complies with the statistical algorithm. CMF-Impute [11] drew upon the similarity of cells and genes to build a collaborative matrix factorization-based model for imputing the dropout entries of a given scRNA-seq expression. Experimental comparisons show that these methods are more accurate and robust than other heuristic approaches (Tucker, Parafac and SVD), which can propagate the data structure to fill large missing regions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
