Single-cell multi-omics clustering method and system based on cross-omics attention fusion

By adopting a clustering method of cross-omics attention fusion in single-cell multiomics data analysis, using self-attention and cross-omics attention mechanisms, combined with deep learning gating mechanisms, the problem of insufficient exchange of omics information in the existing technology is solved, and the accuracy and robustness of cell clustering are improved.

CN119807783AActive Publication Date: 2025-04-11QUFU NORMAL UNIV
View PDF 9 Cites 2 Cited by

Patent Information

Application Number
CN202510299888.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-14
Publication Date
2025-04-11
Estimated Expiration
2045-03-14

Smart Images

  • Figure CN119807783A_ABST
    Figure CN119807783A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of single-cell multi-omics data analysis, and particularly relates to a single-cell multi-omics clustering method and system based on cross-omics attention fusion, dynamic interaction of multi-omics data is realized through a self-attention mechanism and a cross-omics attention mechanism, a deep learning gating mechanism is introduced, and multi-omics clustering is realized. Feature selection and dynamic feature fusion are adaptively adjusted, and changes of different cell types and states can be flexibly handled, so that the heterogeneity of the cells can be better revealed; fine-grained processing of cell feature representation is realized to eliminate the influence of noise, and the clustering precision is improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Multi-head attention mechanism-based cancer multi-omics data analysis method

    CN116580848A

  • Single-cell multi-omics data integration method based on variational graph auto-encoder

    CN118314946A

  • Single-cell multi-omics data integration method and system based on graph contrast learning

    CN118571328A

  • Single-cell multi-omics cell type annotation method based on pre-training

    CN119132426A

  • Method for dividing cell types based on single-cell multi-omics data

    CN119446253A

Cited By

  • Chromatin accessibility and transcription factor interaction deep learning method

    CN121862215A

  • A chromatin accessibility and transcription factor interaction deep learning method

    CN121862215B