Imputing single-cell RNA-seq data by combining graph convolution and autoencoder neural networks

Jiahua Rao; Xiang Zhou; Yutong Lu; Huiying Zhao; Yuedong Yang

doi:10.1016/j.isci.2021.102393

Imputing single-cell RNA-seq data by combining graph convolution and autoencoder neural networks

iScience. 2021 Apr 2;24(5):102393. doi: 10.1016/j.isci.2021.102393. eCollection 2021 May 21.

Authors

Jiahua Rao¹, Xiang Zhou¹, Yutong Lu¹, Huiying Zhao², Yuedong Yang^{1

3}

Affiliations

¹ School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510000, China.
² Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou 510000, China.
³ Key Laboratory of Machine Intelligence and Advanced Computing (Sun Yat-sen University), Ministry of Education, Guangzhou 510000, China.

Abstract

Single-cell RNA sequencing technology promotes the profiling of single-cell transcriptomes at an unprecedented throughput and resolution. However, in scRNA-seq studies, only a low amount of sequenced mRNA in each cell leads to missing detection for a portion of mRNA molecules, i.e. the dropout problem which hinders various downstream analyses. Therefore, it is necessary to develop robust and effective imputation methods for the increasing scRNA-seq data. In this study, we have developed an imputation method (GraphSCI) to impute the dropout events in scRNA-seq data based on the graph convolution networks. Extensive experiments demonstrated that GraphSCI outperforms other state-of-the-art methods for imputation on both simulated and real scRNA-seq data. Meanwhile, GraphSCI is able to accurately infer gene-to-gene relationships and the inferred gene-to-gene relationships could also provide powerful assistance for imputation dynamically during the training process, which is a key promotion of GraphSCI compared with other imputation algorithms.

Keywords: Artificial Intelligence; Bioinformatics; Data Acquisition in Bioinformatics; Genomics.