Cross contamination prediction method and related product

By using the pre-trained contamination ratio prediction model and the variable allelic frequency VAF of SNP sites in liquid biopsy, the problems of long calculation time and low sensitivity of cross-contamination detection in the prior art are solved, and efficient and accurate cross-contamination prediction is achieved.

CN119724337APending Publication Date: 2025-03-28GUANGZHOU BURNING ROCK DX CO LTD
0 Cites 1 Cited by

Patent Information

Application Number
CN202411700289.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-25
Publication Date
2025-03-28

AI Technical Summary

Technical Problem

The existing cross-contamination detection methods have problems such as long calculation time, difficulty in detecting contamination between blood samples of cfDNA of the same species, limited local contamination sensitivity, and abnormal genomic interference in the field of liquid biopsy, making it difficult to achieve high sensitivity and specific cross-contamination prediction.

Method used

By obtaining the variable allelic frequency VAF of the sample to be tested at at least one detected SNP site, the pollution ratio prediction model is used to predict the pollution ratio to generate the predicted pollution ratio set of detected SNP sites. Based on the proportional relationship between the number of detected SNP sites with contamination and the number of detected SNP sites, the predicted pollution score of the sample to be tested is determined, and cross-contamination prediction information is generated based on the score.

Benefits of technology

实现了快速、简便的交叉污染预测,提高了检测的敏感性和特异性,能够准确捕捉早期肿瘤的信号,减少了基因组异常的干扰。

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

Abstract

The invention provides a cross contamination prediction method and a related product. According to a specific implementation mode of the method, VAF of a sample to be detected at each detected SNP site is input into a pre-trained pollution proportion prediction model corresponding to the detected SNP site for pollution proportion prediction, and a detected SNP site predicted pollution proportion set containing predicted pollution proportions of the sample to be detected at each detected SNP site is obtained; determining a predicted pollution score of the to-be-detected sample on the basis of a proportional relation between the number of the detected SNP sites with pollution and the number of the detected SNP sites; and finally, according to a comparison result of the predicted pollution score of the to-be-detected sample and a preset sample pollution score threshold, generating cross pollution prediction information of the to-be-detected sample. Therefore, the cross contamination prediction information of the to-be-detected sample can be generated only by obtaining the VAF of the to-be-detected sample at the at least one detected SNP site, the calculation speed is high, and the sensitivity and specificity of contamination prediction are high.
Need to check novelty before this filing date? Find Prior Art