A single-cell rare cell type identification method and system based on divide-and-conquer strategy

By optimizing single-cell data using variational autoencoders and divide-and-conquer strategies, the problem of identifying and clustering rare cell types was solved, achieving high-precision cell type identification and biological interpretation, and providing reliable cell annotation capabilities.

CN115910219BActive Publication Date: 2026-06-26SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
2 Cites 0 Cited by

Patent Information

Application Number
CN202211542385.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-12-02
Publication Date
2026-06-26
Estimated Expiration
2042-12-02

AI Technical Summary

Technical Problem

Existing technologies struggle to accurately identify and analyze rare cell types, leading to misclassification or difficulty in identification, and lack reliability assessment of clustering results.

Method used

A variational autoencoder is used to encode single-cell transcriptome data into Gaussian distributed latent variables. The cluster loss is optimized by spectral clustering and divide-and-conquer strategies. Combined with Bayesian neural networks and MC-dropout, the identification and clustering of rare cell types are achieved.

Benefits of technology

It improves the accuracy of rare cell type identification and clustering precision, provides reliable biological interpretation and knowledge-driven cell annotation capabilities, and enhances the reliability and biological significance of single-cell data analysis.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application provides a single-cell rare cell type identification method and system based on a divide-and-conquer strategy, comprising the following steps: S1, using a variational autoencoder to encode single-cell transcriptome data into Gaussian distribution hidden variables; S2, performing spectral clustering on the Gaussian distribution hidden variables to obtain a single-cell coarse-grained clustering result; and S3, optimizing the single-cell coarse-grained clustering result based on intra-class cluster loss and inter-class cluster loss until the intra-class cluster loss and the inter-class cluster loss are minimized to obtain a single-cell clustering result containing rare cell types. The application can overcome the deficiency that previous single-cell clustering and identification methods do not optimize rare cell types, leading to misclassification or difficulty in identifying rare cell types.
Need to check novelty before this filing date? Find Prior Art