Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Marker for predicting attack and severity of hereditary angioedema and application thereof

A severity, heritability technique used in microbiomics and bioinformatics to achieve short measurement cycles, reduced morbidity, and easy access

Pending Publication Date: 2022-03-18
PEKING UNION MEDICAL COLLEGE HOSPITAL CHINESE ACAD OF MEDICAL SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] So far, there are no relevant research reports on the condition of HAE and pharyngeal flora at home and abroad

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Marker for predicting attack and severity of hereditary angioedema and application thereof
  • Marker for predicting attack and severity of hereditary angioedema and application thereof
  • Marker for predicting attack and severity of hereditary angioedema and application thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] The establishment and screening of embodiment 1 model algorithm

[0076] The present invention finds the most suitable model and specific species of bacteria as microbial markers through preliminary screening operations, optimizes the parameters of the model according to the data with class labels, improves the accuracy and sensitivity of the model, and predicts through the output risk value, and can Indicate the balance of pharyngeal microorganisms, guide the adjustment of individualized pharyngeal flora, and reduce the risk of HAE attacks.

[0077] The present invention selects and incorporates the random forest model of 20 kinds of fungus genera as the optimal model basis through the screening and matching of a large amount of information, and the specific method is as follows:

[0078] 1. The 16S rRNA gene sequencing data of the pharyngeal flora of 21 patients with acute attack and 20 patients without attack in the past 1 month were obtained from HAE patients in Pek...

Embodiment 2

[0091] The bacterium of embodiment 2 specific species is selected

[0092] 1. The random forest model of the medium-batch bacterial population obtains the feature-importance score of the variable feature. According to the high and low ranking of the score, the number of bacterial variables is gradually increased to obtain the variables required for the optimal ROC-AUC. The results show that, The ROC-AUC value is the largest when inputting the bacterial abundance of 20 specific species as the characteristic variable.

[0093] 2. Test the model, split the data into a training set and a test set, input the bacterial abundance of 20 specific species in the sample, input the random forest model, and optimize the parameters of the model according to GridsearchCV, train with the training set, and test with the test set .

[0094] 3. The storage model is used for the prediction of disease risk of subsequent measurement data.

[0095] The number and combination of input variables wil...

Embodiment 3

[0099] Example 3 Practical application of the assessment model of hereditary angioedema attack severity

[0100] The present invention is based on a generalized linear model, and uses the relative abundance of Bacteroidetes as a biomarker to measure the severity of the acute onset of hereditary angioedema. At the same time, taking into account factors such as the patient's age, gender, whether to receive hereditary angioedema treatment drugs, etc., the severity of the patient's acute attack is comprehensively predicted. The specific method is as follows:

[0101] (1) Detect the relative abundance of Bacteroidetes in throat swab samples of patients with hereditary angioedema during the attack period;

[0102] (2) Collect information on the patient's age, gender, and whether or not to receive hereditary angioedema treatment drugs (such as danazol);

[0103] (3) Input the abundance data obtained in step (1) and the information in step (2) into the generalized linear model, optim...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a marker for predicting attack and severity of hereditary angioedema (HAE) and application of the marker. The marker for predicting the HAE attack is the relative abundance of 20 bacterial genus of the throat of a patient, after the relative abundance data of the 20 bacterial genus are input into the random forest model, the obtained score is greater than or equal to 0.5, the HAE attack risk is high, and the obtained score is lt; and the attack risk of the HAE is low. The marker for predicting the severity of the HAE attack is the relative abundance of Bacteroides bacteria in the throat of a patient. The invention finds that the throat flora is closely related to the attack and severity of the HAE for the first time, establishes a set of marker and risk early warning model for the acute attack of the HAE based on the throat flora and an evaluation system for the severity of the attack, can assist in clinically predicting the acute attack of the HAE in advance, provides a marker for future flora transplantation of a patient, and has a good application prospect. The important significance is realized on reducing the occurrence rate of the HAE acute edema and improving the treatment rate.

Description

technical field [0001] The present invention relates to microbiome and bioinformatics, in particular, to a marker for predicting the onset and severity of hereditary angioedema and its application. Background technique [0002] Hereditary angioedema (HAE) is a rare, life-threatening genetic disease with an incidence of about 1 / 10000-1 / 50000, characterized by acute and recurrent subcutaneous and / or submucosal tissue edema It is characterized by non-depressing, self-limiting, localized, and unpredictable features. Commonly affected sites include the face, extremities, trunk, reproductive tract, upper respiratory tract, and gastrointestinal tract. The symptoms exhibited by HAE patients have obvious clinical heterogeneity, specifically in the age of onset, frequency, predilection site, and severity. It only manifests as mild acral edema, which does not affect normal daily life. In severe cases, if the gastrointestinal tract is involved, unbearable abdominal pain, nausea, vomiti...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): C12Q1/06C12Q1/10C12Q1/689G06F30/20
CPCC12Q1/06C12Q1/10C12Q1/689G06F30/20G01N2800/32G01N2800/52G06F2119/02
Inventor 支玉香王雪曹阳
Owner PEKING UNION MEDICAL COLLEGE HOSPITAL CHINESE ACAD OF MEDICAL SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com