Scholarlink

Background: <p>Single-cell RNA sequencing (scRNA-Seq) technology reveals biological processes and molecular-level genomic information among individual cells. Numerous computational methods, including methods based on graph neural networks (GNNs), have been developed to enhance scRNA-Seq data analysis. However, existing GNNs-based methods usually construct fixed graphs by applying the k-nearest neighbors algorithm, which may result in information loss.</p> Methods: <p>To address this problem, we propose scE2EGAE, which learns cell graphs during the training processes. Firstly, the scRNA-Seq data is fed into a deep count autoencoder (DCA). Secondly, the hidden representations of DCA are extracted and then used to generate cell-to-cell graph edges through a straight-through estimator (STE) based on top-<i>k</i> sampling and Gumbel-Softmax. Finally, the generated cell-to-cell graph and scRNA-Seq data are fed into the GNNs-based downstream tasks. In this paper, we design a graph autoencoder which performs denoising on scRNA-Seq data as the downstream task.</p> Results: <p>We evaluate scE2EGAE on eight public scRNA-Seq datasets and compare its performance with seven existing scRNA-Seq data denoising methods. In this paper, extensive experiments are conducted, encompassing: 1) the evaluation of denoising performance, with metrics including mean absolute error, Pearson correlation coefficient, and cosine similarity; 2) the assessment of clustering performance of the denoised results, utilizing adjusted rand index, normalized mutual information and silhouette score; and 3) the evaluation of the cell trajectory inference performance of the denoised results, measured by the pseudo-temporal ordering score. The results show that, on the scRNA-Seq data denoising task, scE2EGAE outperforms most of the methods, proving that it can learn cell-to-cell graphs containing real information of cell-to-cell relationships.</p> Conclusions: <p>In this paper, we validate the proposed scE2EGAE method through its application to the denoising task of scRNA-Seq data. This method demonstrates its capability to learn inter-cellular relationships and construct cell-to-cell graphs, thereby enhancing the downstream analysis of scRNA-Seq data. Our approach can serve as an inspiration for future research on scRNA-Seq analysis methods based on GNNs, holding broad application prospects.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

scE2EGAE: enhancing single-cell RNA-Seq data analysis through an end-to-end cell-graph-learnable graph autoencoder with differentiable edge sampling

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月27日

查看全文
  • Shuo Wang,
  • Yuanning Liu,
  • Hao Zhang,
  • Zhen Liu

摘要

Background:

Single-cell RNA sequencing (scRNA-Seq) technology reveals biological processes and molecular-level genomic information among individual cells. Numerous computational methods, including methods based on graph neural networks (GNNs), have been developed to enhance scRNA-Seq data analysis. However, existing GNNs-based methods usually construct fixed graphs by applying the k-nearest neighbors algorithm, which may result in information loss.

Methods:

To address this problem, we propose scE2EGAE, which learns cell graphs during the training processes. Firstly, the scRNA-Seq data is fed into a deep count autoencoder (DCA). Secondly, the hidden representations of DCA are extracted and then used to generate cell-to-cell graph edges through a straight-through estimator (STE) based on top-k sampling and Gumbel-Softmax. Finally, the generated cell-to-cell graph and scRNA-Seq data are fed into the GNNs-based downstream tasks. In this paper, we design a graph autoencoder which performs denoising on scRNA-Seq data as the downstream task.

Results:

We evaluate scE2EGAE on eight public scRNA-Seq datasets and compare its performance with seven existing scRNA-Seq data denoising methods. In this paper, extensive experiments are conducted, encompassing: 1) the evaluation of denoising performance, with metrics including mean absolute error, Pearson correlation coefficient, and cosine similarity; 2) the assessment of clustering performance of the denoised results, utilizing adjusted rand index, normalized mutual information and silhouette score; and 3) the evaluation of the cell trajectory inference performance of the denoised results, measured by the pseudo-temporal ordering score. The results show that, on the scRNA-Seq data denoising task, scE2EGAE outperforms most of the methods, proving that it can learn cell-to-cell graphs containing real information of cell-to-cell relationships.

Conclusions:

In this paper, we validate the proposed scE2EGAE method through its application to the denoising task of scRNA-Seq data. This method demonstrates its capability to learn inter-cellular relationships and construct cell-to-cell graphs, thereby enhancing the downstream analysis of scRNA-Seq data. Our approach can serve as an inspiration for future research on scRNA-Seq analysis methods based on GNNs, holding broad application prospects.