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

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

doi:10.1016/j.isci.2021.102393

Cited by 60 publications

(40 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the superior results, GraphCS can be improved in several aspects. Firstly, our model ignores the relations between genes, which has been shown to improve the imputation of scRNA-seq data [27]. Secondly, the performance of our model is influenced by the constructed cell graph, and a high-quality graph can improve performance.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Robust and Scalable Graph Neural Network for Accurate Single Cell Classification

Zeng

Zhou

Pan

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Single-cell RNA sequencing (scRNA-seq) techniques provide high-resolution data on cellular heterogeneity in diverse tissues, and a critical step for the data analysis is cell type identification. Traditional methods usually cluster the cells and manually identify cell clusters through marker genes, which is time-consuming and subjective. With the launch of several large-scale single-cell projects, millions of sequenced cells have been annotated and it is promising to transfer labels from the annotated datasets to newly generated datasets. One powerful way for the transferring is to learn cell relations through the graph neural network (GNN), while vanilla GNN is difficult to process millions of cells due to the expensive costs of the message-passing procedure at each training epoch. Here, we have developed a robust and scalable GNN-based method for accurate single cell classification (GraphCS), where the graph is constructed to connect similar cells within and between labelled and unlabelled scRNA-seq datasets for propagation of shared information. To overcome the slow information propagation of GNN at each training epoch, the diffused information is pre-calculated via the approximate Generalized PageRank algorithm, enabling sublinear complexity for a high speed and scalability on millions of cells. Compared with existing methods, GraphCS demonstrates better performance on simulated, cross-platform, and cross-species scRNA-seq datasets. More importantly, our model can achieve superior performance on a large dataset with one million cells within 50 minutes.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In fact, the high-order representation and topological relations could been naturally learned by the graph neural network (GNN), and GNN have been proven with improved performance in scRNA-seq data analyses such as imputation and clustering [27–29]. ScGCN[30] is currently the only graph neural network method for annotating cells.…”

Section: Introductionmentioning

confidence: 99%

A Robust and Scalable Graph Neural Network for Accurate Single Cell Classification

Zeng

Zhou

Pan

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Single-cell RNA sequencing technology provides gene expression data for a single cell. GNNs can infer the interaction between cells ( Jiahua et al, 2020 ; Zeng et al, 2020 ; Wang et al, 2021 ) and simulate cell differentiation ( Bica et al, 2020 ) and disease state prediction ( Ravindra et al, 2020 ). Precise gene–disease association prediction can help researchers reveal the function of disease-causing genes and provide evidence for disease prevention.…”

Section: Typical Application Of Gnns In Bioinformaticsmentioning

confidence: 99%

Graph Neural Networks and Their Current Applications in Bioinformatics

et al. 2021

View full text Add to dashboard Cite

Graph neural networks (GNNs), as a branch of deep learning in non-Euclidean space, perform particularly well in various tasks that process graph structure data. With the rapid accumulation of biological network data, GNNs have also become an important tool in bioinformatics. In this research, a systematic survey of GNNs and their advances in bioinformatics is presented from multiple perspectives. We first introduce some commonly used GNN models and their basic principles. Then, three representative tasks are proposed based on the three levels of structural information that can be learned by GNNs: node classification, link prediction, and graph generation. Meanwhile, according to the specific applications for various omics data, we categorize and discuss the related studies in three aspects: disease prediction, drug discovery, and biomedical imaging. Based on the analysis, we provide an outlook on the shortcomings of current studies and point out their developing prospect. Although GNNs have achieved excellent results in many biological tasks at present, they still face challenges in terms of low-quality data processing, methodology, and interpretability and have a long road ahead. We believe that GNNs are potentially an excellent method that solves various biological problems in bioinformatics research.

show abstract

“…To utilize the similarity information between cell-to-cell as well as gene-to-gene relationships, Rao et al. ( 37 ) proposed a graph convolution network called GraphSCI that uses the relationship information between genes to construct a graph neural network, and learns the data distribution for imputation. Most recently, Wang et al.…”

Section: Introductionmentioning

confidence: 99%

scIMC: a platform for benchmarking comparison and visualization analysis of scRNA-seq data imputation methods

Dai

Jiang

Yin

et al. 2022

Nucleic Acids Research

View full text Add to dashboard Cite

With the advent of single-cell RNA sequencing (scRNA-seq), one major challenging is the so-called ‘dropout’ events that distort gene expression and remarkably influence downstream analysis in single-cell transcriptome. To address this issue, much effort has been done and several scRNA-seq imputation methods were developed with two categories: model-based and deep learning-based. However, comprehensively and systematically comparing existing methods are still lacking. In this work, we use six simulated and two real scRNA-seq datasets to comprehensively evaluate and compare a total of 12 available imputation methods from the following four aspects: (i) gene expression recovering, (ii) cell clustering, (iii) gene differential expression, and (iv) cellular trajectory reconstruction. We demonstrate that deep learning-based approaches generally exhibit better overall performance than model-based approaches under major benchmarking comparison, indicating the power of deep learning for imputation. Importantly, we built scIMC (single-cell Imputation Methods Comparison platform), the first online platform that integrates all available state-of-the-art imputation methods for benchmarking comparison and visualization analysis, which is expected to be a convenient and useful tool for researchers of interest. It is now freely accessible via https://server.wei-group.net/scIMC/.

show abstract

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

Cited by 60 publications

References 29 publications

A Robust and Scalable Graph Neural Network for Accurate Single Cell Classification

A Robust and Scalable Graph Neural Network for Accurate Single Cell Classification

Graph Neural Networks and Their Current Applications in Bioinformatics

scIMC: a platform for benchmarking comparison and visualization analysis of scRNA-seq data imputation methods

Contact Info

Product

Resources

About