Single-cell RNA sequencing clustering method based on adversarial autoencoder

Abstract

One or more embodiments of the present specification provide a single-cell RNA sequencing clustering method based on an adversarial autoencoder, integrating the advantages of specific bionoise modeling, variation inference, and deep clustering modeling. The model restrains a data structure, and clustering analysis is carried out through an AAE module. Experiments performed on three real scRNA-seqdata sets show that the clustering performance of the method is much better than that of the latest technology in clustering accuracy, standardized mutual information and Rand index adjustment.

Description

technical field [0001] One or more embodiments of this specification relate to the technical field of RNA sequencing, and in particular to a single-cell RNA sequencing clustering method based on an anti-autoencoder. Background technique [0002] Advances in single-cell RNA-sequencing (scRNA-seq) technology have revolutionized transcriptomics research by providing resolution of individual cell differences in the transcriptome at higher resolution than commonly used bulk RNA-sequencing. This technique enables researchers to systematically study cellular heterogeneity, cell developmental trajectories, and classification of tumor subpopulations across large numbers of cells, and unsupervised clustering is an important step in analyzing scRNA-seq to achieve the above tasks. Only after clustering can cell types be identified, after which researchers can further delineate cellular functional states and infer underlying cellular dynamics. [0003] Although clustering is one of the ...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the purpose of one or more embodiments of this specification is to propose a single-cell RNA sequencing clustering method based on an adversarial autoencoder to solve the problem of poor clustering performance

Images