ScRNA-seq data clustering method, system and device based on ZINB distribution and graph attention

Through the ZINB autoencoder and graph attention autoencoder combined with the self-optimized deep clustering model, the sparsity and nonlinear relationship modeling problems in single-cell RNA sequencing data are solved, and high-precision and robust clustering effect are achieved, and clustering performance is improved.

CN120432017APending Publication Date: 2025-08-05NANJING UNIV
0 Cites 3 Cited by

Patent Information

Application Number
CN202510524450.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-04-24
Publication Date
2025-08-05

AI Technical Summary

Technical Problem

The prior art has data sparsity caused by high shedding rates, insufficient modeling of nonlinear relationships between cells, and problems of embedding and clustering separation in single-cell RNA sequencing data, which affect clustering accuracy and robustness.

Method used

The scRNA-seq data clustering method based on ZINB distribution and graph attention was adopted, and the sparsity and shedding events were captured through the ZINB autoencoder, and the cell relationship graph was constructed using the Pearson correlation coefficient, and the neighborhood weights were dynamically learned through the residual graph attention autoencoder, and end-to-end optimization was performed by combining the self-optimized deep clustering model.

Benefits of technology

The clustering accuracy is improved, and the NMI and ARI indicators are improved by 15%-25%. The clustering accuracy (CA) is significantly better than the existing methods. UMAP visualization shows tighter intra-cluster distances and farther inter-cluster distances, and the contour coefficient is increased by 30%-50%.

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

Abstract

The invention provides an scRNA-seq data clustering method, system and device based on ZINB distribution and graph attention. The scRNA-seq data clustering system mainly comprises three core modules: a ZINB auto-encoder, which is used for modeling scRNA-seq data based on zero-expansion negative binomial distribution, generating robust potential representation through a denoising auto-encoder, and accurately capturing sparsity, excessive discreteness and shedding events of gene expression; the residual image attention auto-encoder is used for constructing a cell relation graph by using a Pearson correlation coefficient, dynamically learning a neighborhood weight in combination with a multi-head attention mechanism, retaining original features through residual connection, and relieving the excessive smoothness problem of image convolution; and a deep clustering model is self-optimized: target distribution and soft label distribution are minimized through KL divergence, and end-to-end joint optimization of embedded learning and clustering is realized.
Need to check novelty before this filing date? Find Prior Art