4.6 Article

A Comparison for Dimensionality Reduction Methods of Single-Cell RNA-seq Data

期刊

FRONTIERS IN GENETICS
卷 12, 期 -, 页码 -

出版社

FRONTIERS MEDIA SA
DOI: 10.3389/fgene.2021.646936

关键词

single-cell RNA-seq; dimension reduction; benchmark; sequences analysis; deep learning

资金

  1. Heilongjiang Postdoctoral Research Startup Foundation [LBH-Q19116, LBH-Q19118]
  2. Heilongjiang Natural Science Fund Project [LH2019C087]
  3. National Natural Science Foundation of China [31871336, 61573122, 31701159]
  4. Wu Lien-Teh Youth Science fund project of Harbin Medical University [WLD-QN1407]
  5. Health Department Science Foundation of Heilongjiang Province [2013128]
  6. Education Department Science Foundation of Heilongjiang Province [12541415]
  7. Postdoctoral project of Heilongjiang Province [LBH-Z14130]

向作者/读者索取更多资源

The study compared the performance of different dimensionality reduction methods in scRNA-seq data analysis. t-SNE showed the best accuracy and computing cost, while UMAP demonstrated high stability and preserved the cohesion and separation of cell populations.
Single-cell RNA sequencing (scRNA-seq) is a high-throughput sequencing technology performed at the level of an individual cell, which can have a potential to understand cellular heterogeneity. However, scRNA-seq data are high-dimensional, noisy, and sparse data. Dimension reduction is an important step in downstream analysis of scRNA-seq. Therefore, several dimension reduction methods have been developed. We developed a strategy to evaluate the stability, accuracy, and computing cost of 10 dimensionality reduction methods using 30 simulation datasets and five real datasets. Additionally, we investigated the sensitivity of all the methods to hyperparameter tuning and gave users appropriate suggestions. We found that t-distributed stochastic neighbor embedding (t-SNE) yielded the best overall performance with the highest accuracy and computing cost. Meanwhile, uniform manifold approximation and projection (UMAP) exhibited the highest stability, as well as moderate accuracy and the second highest computing cost. UMAP well preserves the original cohesion and separation of cell populations. In addition, it is worth noting that users need to set the hyperparameters according to the specific situation before using the dimensionality reduction methods based on non-linear model and neural network.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据