基于泛基因组图谱的结构变异识别方法及系统
By dynamically expanding the pan-genome map and using deep learning models to evaluate structural variations, the problems of insufficient coverage of unknown or individual-specific variations and map fragmentation in existing technologies have been solved, achieving high-precision identification and analysis of structural variations.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XIANGYA HOSPITAL CENT SOUTH UNIV
- Filing Date
- 2026-03-18
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for identifying structural variations based on pan-genome maps rely on existing variation information, making it difficult to cover unknown or individual-specific structural variations. Furthermore, map construction and sample analysis are disconnected, and traditional filtering strategies lack adaptability, making it difficult to meet the needs of high-precision structural variation analysis.
The pan-genome map is dynamically expanded using third-generation sequencing data. A deep learning model is used to assess the credibility and classify candidate structural variants. The pan-genome map serves as a unified reference framework to reduce reference bias, improve identification accuracy and sensitivity, and incorporate users' own high-quality third-generation sequencing data for personalized analysis.
It improves the sensitivity and accuracy of structural variation identification, enhances the ability to capture complex and individual-specific variations, and achieves high reliability and consistency of structural variation results, making it suitable for large-scale sample analysis and various application scenarios.
Smart Images
Figure CN121884945B_ABST