An incomplete multi-omics cancer subtype identification method, system, device and medium

By constructing granular feature modules and module-level skeleton representations, and combining cross-omics consensus structures and view availability masks, the problem of structural bias and missing patterns in incomplete multi-omics data is solved, improving the stability and biological consistency of cancer subtype identification.

CN122266484BActive Publication Date: 2026-07-24JIANGNAN UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
JIANGNAN UNIV
Filing Date
2026-05-27
Publication Date
2026-07-24

AI Technical Summary

Technical Problem

Existing multi-omics cancer subtype identification methods are prone to structural bias in scenarios with incomplete data, insufficient preservation of the internal structure of omics, susceptibility of cross-omics fusion to missing patterns, and limited stability of subtype results.

Method used

By constructing a granular feature module, extracting module-level skeleton representation, performing entry-level missing data recovery, and performing skeleton consensus alignment and adaptive view weighting in the cross-omics fusion stage, combined with view availability masking for sample-level mask-aware fusion, the inherent structural consistency of multi-omics data is prioritized.

Benefits of technology

This improved the robustness, stability, and biological consistency of cancer subtype identification results, enhancing their clinical application value.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122266484B_ABST
    Figure CN122266484B_ABST
Patent Text Reader

Abstract

The application discloses an incomplete multi-omics cancer subtype identification method, system, device and medium, and belongs to the technical field of bioinformatics and artificial intelligence. The method comprises the following steps: incomplete multi-omics data acquisition and preprocessing; constructing an entry-level observation mask matrix and a view availability mask matrix; constructing a feature module in the omics based on a granule division; extracting a module-level skeleton representation; recovering an entry-level missing value based on the skeleton structure; constructing a multi-expert skeleton recovery integrated result; constructing a central feature matrix of the feature module; constructing a cross-omics consensus structure space; performing a mask-aware skeleton consensus alignment; performing adaptive view weighting based on structure reliability; performing sample-level mask-aware fusion; and outputting a cancer subtype clustering result. The application provides reliable technical support for cancer typing research, patient stratification analysis, prognosis evaluation and precision medicine auxiliary decision-making.
Need to check novelty before this filing date? Find Prior Art