Mycobacterium tuberculosis drug resistance phenotype prediction method and device and computer equipment

CN119541635AActive Publication Date: 2025-02-28SANSURE BIOTECH INC +2
View PDF 4 Cites 1 Cited by

Patent Information

Application Number
CN202411596869.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-08
Publication Date
2025-02-28
Estimated Expiration
2044-11-08

AI Technical Summary

Technical Problem

The prior art takes a long time to detect the drug-resistant phenotype of Mycobacterium tuberculosis or cannot judge the drug-resistant phenotype of unknown mutations, resulting in poor detection effect.

Method used

The mutation sites to be predicted are determined through gene sequencing data, converted into protein structure change data, and the drug resistance phenotype prediction model is input to predict drug resistance phenotype, and the final drug resistance phenotype prediction results are determined in combination with the mutation phenotype annotation database.

Benefits of technology

It improves the efficiency of predicting drug resistance phenotype of Mycobacterium tuberculosis, can effectively judge whether unknown new mutation sites lead to drug resistance, and improves the speed and accuracy of detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119541635A_ABST
    Figure CN119541635A_ABST
Patent Text Reader

Abstract

The invention relates to a mycobacterium tuberculosis drug resistance phenotype prediction method and device and computer equipment. The method comprises the following steps: determining a to-be-predicted mutation site which does not exist in a mutation phenotype annotation database from at least one mutation site of a target gene segment of the to-be-processed mycobacterium tuberculosis according to gene sequencing data of the to-be-processed mycobacterium tuberculosis; according to the protein structure data corresponding to the to-be-predicted mutation site, performing conversion to obtain protein structure change data of the to-be-predicted mutation site; inputting the protein structure change data of the to-be-predicted mutation site into the drug resistance phenotype prediction model to obtain a predicted drug resistance phenotype of the to-be-predicted mutation site; based on the predicted drug-resistant phenotype of the mutation site to be predicted and drug-resistant phenotypes of mutation sites except the mutation site to be predicted in the at least one mutation site, determining a drug-resistant phenotype prediction result of the mycobacterium tuberculosis to be treated. By adopting the method, the prediction efficiency of the drug-resistant phenotype of the mycobacterium tuberculosis can be effectively improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Tubercle bacillus drug resistance detection method and device, computer device and storage medium

    CN110706755A

  • Mycobacterium tuberculosis drug resistance prediction method and device based on hierarchical attention neural network

    CN114582429A

  • Use of computationally derived protein structures of genetic polymorphisms in pharmacogenomics for drug design and clinical applications

    US20030158672A1

  • Method for rapid identification of drug targets and drug mechanisms of action in human cells

    WO2012122017A2

Cited By

  • Cell mechanical phenotype analysis method and equipment based on deep learning

    CN119993284A