一种基于染色体互作的基因组结构变异检测方法和系统
By employing multimodal information fusion and a two-stage detection framework, the problems of insufficient information utilization and high false positive rate in chromosome structural variation detection are solved, achieving efficient and accurate variation detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XI AN JIAOTONG UNIV
- Filing Date
- 2025-12-08
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for detecting chromosomal structural variations suffer from several problems: insufficient information utilization due to a single data source; high false positive rates due to improper handling of unbalanced categories; and complex and inefficient detection procedures.
Multimodal information fusion technology is used to deeply integrate the spatial interaction patterns of the Hi-C interaction matrix with the sequencing coverage information of the BAM file. By using RGB three-channel image encoding and combining it with a ResNet-based classification network, a two-stage detection framework is used to screen candidate regions and identify variant types.
It improves detection accuracy, reduces false positive rate, and enhances computational efficiency, achieving efficient and accurate detection of chromosomal structural variations.
Smart Images
Figure CN121506240B_ABST