School of Mathematics and Physics, Wuhan Institute of Technology, 430205 Wuhan, China.
Comput Math Methods Med. 2021 Oct 4;2021:6842752. doi: 10.1155/2021/6842752. eCollection 2021.
Clustering analysis is one of the most important technologies for single-cell data mining. It is widely used in the division of different gene sequences, the identification of functional genes, and the detection of new cell types. Although the traditional unsupervised clustering method does not require label data, the distribution of the original data, the setting of hyperparameters, and other factors all affect the effectiveness of the clustering algorithm. While in some cases the type of some cells is known, it is hoped to achieve high accuracy if the prior information about those cells is utilized sufficiently. In this study, we propose SCMAG (a semisupervised single-cell clustering method based on a matrix aggregation graph convolutional neural network) that takes into full consideration the prior information for single-cell data. To evaluate the performance of the proposed semisupervised clustering method, we test on different single-cell datasets and compare with the current semisupervised clustering algorithm in recognizing cell types on various real scRNA-seq data; the results show that it is a more accurate and significant model.
聚类分析是单细胞数据挖掘中最重要的技术之一。它广泛应用于不同基因序列的划分、功能基因的鉴定和新细胞类型的检测。虽然传统的无监督聚类方法不需要标签数据，但原始数据的分布、超参数的设置等因素都会影响聚类算法的有效性。而在某些情况下，已知某些细胞的类型，如果能够充分利用这些细胞的先验信息，则有望实现高精度。在这项研究中，我们提出了 SCMAG（一种基于矩阵聚合图卷积神经网络的半监督单细胞聚类方法），它充分考虑了单细胞数据的先验信息。为了评估所提出的半监督聚类方法的性能，我们在不同的单细胞数据集上进行了测试，并在识别各种真实 scRNA-seq 数据上的细胞类型方面与当前的半监督聚类算法进行了比较；结果表明，该方法是一个更准确、更显著的模型。
