Single-cell RNA-seq data clustering method based on deep noise reduction auto-encoder

Abstract

The invention discloses a single-cell RNA-seq data clustering method based on a deep noise reduction auto-encoder. The method comprises the following steps: firstly, adjusting the batch effect of single-cell RNA-seq data and standardizing the data so as to reduce adverse effects caused by technical noise; secondly, using a deep noise reduction self-encoder based on zero-expansion negative binomial distribution for effectively excavating feature information of the single-cell RNA-seq data; carrying out dimensionality reduction on single-cell RNA-seq data by using a rapid independent component analysis method to improve the calculation efficiency of a method model; and finally, carrying out more accurate clustering on the cells through a Gaussian mixture model based on expectation maximization, and visualizing a final single-cell RNA-seq data clustering result by using a T distribution random neighbor embedding method. According to the method, the interference of the characteristics of high dimension, large noise and the like of the single-cell RNA-seq data on data clustering can be effectively reduced, the gene expression information of the single-cell RNA-seq data is accurately learned so as to cluster cells, and help is provided for gene network construction, cell type discovery and early cancer discovery and treatment.

Description

technical field [0001] The invention belongs to the technical field of single-cell RNA-seq data analysis in bioinformatics, and in particular relates to a single-cell RNA-seq (RiboNucleicAcid-sequencing) data clustering method based on a deep noise reduction autoencoder. Background technique [0002] With the rapid development of sequencing technology, researchers have obtained a large amount of single-cell RNA-seq data. Unsupervised clustering plays an important role in the analysis of single-cell RNA-seq data. Clustering methods for single-cell RNA-seq data can not only identify unknown cell types, but also reveal cell heterogeneity. Through the research on the clustering method of single-cell RNA-seq data, researchers can more accurately identify the cell state, build the network structure between cells, and deeply understand the differentiation process of cancer cells, etc., laying the foundation for the early detection and treatment of cancer in the future. Base. At p...

AI Technical Summary

Problems solved by technology

At present, traditional clustering methods such as hierarchical clustering, spectral clustering, and density-based clustering methods with noise have been widely used. However, single-cell RNA-seq data has its unique characteristics, which make traditional clustering methods It is not possible to efficiently cluster these data

Images