Author:
Feng Yifan,Ai Yutong,Jiang Hao
Abstract
AbstractThe single-cell RNA sequencing (scRNA-seq) technique allows single cell level of gene expression measurements, but the scRNA-seq data often contain missing values, with a large proportion caused by technical defects failing to detect gene expressions, which is called dropout event. The dropout issue poses a great challenge for scRNA-seq data analysis. In this chapter, we introduce a method based on KNN-smoothing: LLE-KNN-smoothing to impute the dropout values in scRNA-seq data and show that the LLE-KNN-smoothing greatly improves the recovery of gene expression in cells and shows better performance than state-of-the-art imputation methods on a number of scRNA-seq data sets.
Publisher
Springer Nature Singapore
Reference30 articles.
1. Aittokallio, T. (2010). Dealing with missing values in large-scale studies: Microarray data imputation and beyond. Briefings in Bioinformatics, 11(2), 253–264.
2. Arisdakessian, C., Poirion, O., Yunits, B., Zhu, X., & Garmire, L. X. (2018). Deepimpute: An accurate, fast and scalable deep neural network method to impute single-cell RNA-seq data. Genome Biology.
3. Chen, M. J., & Zhou, X. (2018). Viper: Variability-preserving imputation for accurate gene expression recovery in single-cell RNA sequencing studies. Genome Biology.
4. Darmanis, S., Sloan, S. A., Zhang, Y., Enge, M., Caneda, C., Shuer, L. M., et al. (2015). A survey of human brain transcriptome diversity at the single cell level. Proceedings of the National Academy of Sciences, 112(23), 7285–7290.
5. Dijk, D. V., Nainys, J., Sharma, R., Kathail, P., Carr, A. J., Moon, K. R., Mazutis, L., Wolf, G., Krishnaswamy, S., & Pe’Er, D.: Magic: A diffusion-based imputation method reveals gene-gene interactions in single-cell RNA-sequencing data. BioRxiv.