CN-121992092-A - Biomarker for predicting severe patients of COVID-19 and application thereof

Abstract

The invention discloses a biomarker for predicting the criticality of COVID-19 patients and application thereof, and relates to the technical field of biomedicine. The invention discovers that the COVID-19 patient severe prediction or auxiliary prediction model constructed by the Gemella haemolysans, Streptococcus sp.A12, Fusobacterium pseudoperiodonticum, Gemella morbillorum, Veillonella atypica, Veillonella rogosae, Prevotella melaninogenica biomarker is used for predicting and evaluating the severe of COVID-19 patients, and has high sensitivity and good specificity.

Inventors

• MOU XIANGYU
• ZHAO WENJING
• FAN PEIZHI

Assignees

• 中山大学·深圳
• 中山大学

Dates

Publication Date

20260508

Application Date

20241105

Claims (10)

1. 1. A biomarker for predicting or aiding in predicting the criticality of a COVID-19 patient, comprising Gemella haemolysans、Streptococcus sp.A12、Fusobacterium pseudoperiodonticum、Gemella morbillorum、Veillonella atypica、Veillonella rogosae、Prevotella melaninogenica.
2. 2. A kit comprising a substance for detecting the abundance of a biomarker of claim 1.
3. 3. The kit of claim 2, wherein the substance comprises reagents for detecting the abundance of the biomarker by macro-transcriptome or macro-genome sequencing.
4. 4. Use of a biomarker as claimed in claim 1 or a substance for detecting the abundance of a biomarker as claimed in claim 1 in the manufacture of a product for predicting or aiding in predicting the criticality of a COVID-19 patient.
5. 5. The use according to claim 4, wherein the product is selected from a kit, a chip or a predictive system; and/or the method of using the product comprises the steps of: S1, acquiring abundance data of the biomarker of claim 1 in throat swabs of COVID-19 critically ill patients and COVID-19 non-critically ill patients, and constructing a COVID-19 critically ill prediction or auxiliary prediction model by using a machine learning method; s2, collecting abundance data of the biomarker of claim 1 in samples of COVID-19 patients in a progressive state to be predicted; s3, inputting the abundance data collected in the step S2 into the COVID-19 patient severe prediction or auxiliary prediction model constructed in the step S1, and evaluating or assisting in evaluating the risk of severe occurrence of the COVID-19 patient in the progressive state to be predicted.
6. 6. The construction method of COVID-19 patient severe prediction or auxiliary prediction model is characterized by comprising the following steps: Obtaining abundance data of the biomarker of claim 1 in a pharynx swab of COVID-19 critically ill patients, COVID-19 non-critically ill patients, and constructing the COVID-19 critically ill prediction or auxiliary prediction model by using a machine learning method.
7. 7. The method of claim 6, wherein the abundance data is analyzed from strain macro-transcriptome or metagenome sequencing data; And/or the method of machine learning includes a random forest classifier.
8. 8. A model for the prediction or auxiliary prediction of the severity of a patient COVID-19, which is constructed by the construction method according to claim 6 or 7.
9. 9. A COVID-19 patient intensive care or auxiliary prediction system, comprising: A data collection module for collecting abundance data of the biomarker of claim 1 in a sample of COVID-19 patients in a progressive state; A prediction module that inputs the abundance data into the COVID-19 patient severity prediction or auxiliary prediction model of claim 8, assessing the risk of developing severity in the COVID-19 patient.
10. 10. A computer-readable storage medium, characterized in that it stores a computer program, which, when executed by a processor, implements the functions of the construction method of any one of claims 6 to 7 or of the COVID-19 patient intensive care prediction or auxiliary prediction system of claim 9.

Description

Biomarker for predicting severe patients of COVID-19 and application thereof Technical Field The invention relates to the technical field of biomedicine, in particular to a biomarker for predicting the severe of COVID-19 patients and application thereof. Background The novel coronavirus infection (Corona Virus Disease 2019, covd-19) is an infection caused by a novel coronavirus (SARS-CoV-2, hereinafter referred to as "novel coronavirus") with a certain severe rate, and the novel coronavirus infection has serious hazard, can generate more medical demands and expenses, and has a certain probability of causing long and new crowns, complications and even death. Therefore, it is significant to provide a marker that can predict the severity of a COVID-19 patient. Disclosure of Invention The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the invention provides a biomarker for predicting or assisting in predicting the criticality of COVID-19 patients, and the constructed model for predicting the criticality of COVID-19 patients is used for predicting and evaluating the criticality of COVID-19 patients, and has high sensitivity and good specificity. The invention also provides a kit. The invention also provides application of the biomarker or a substance for detecting the abundance of the biomarker in preparing a product for predicting or assisting in predicting the criticality of COVID-19 patients. The invention also provides a construction method of the COVID-19 patient severe prediction or auxiliary prediction model. The invention also provides a COVID-19 patient severe prediction or auxiliary prediction model. The invention also provides a COVID-19 patient severe prediction or auxiliary prediction system. The invention also provides a computer readable storage medium. According to an embodiment of the first aspect of the invention, a biomarker for predicting or aiding in predicting COVID-19 patient criticality comprises Gemella haemolysans、Streptococcus sp.A12、Fusobacterium pseudoperiodonticum、Gemella morbillorum、Veillonella atypica、Veillonella rogosae、Prevotella melaninogenica. A kit according to an embodiment of the second aspect of the invention comprises a substance for detecting the abundance of a biomarker as described in the embodiment of the first aspect of the invention. According to some embodiments of the invention, the substance comprises an agent that detects the abundance of the biomarker by macro-transcriptome or metagenomic sequencing. Use of a biomarker as described in an embodiment of the first aspect of the present invention according to an embodiment of the third aspect of the present invention for the preparation of a product for predicting or aiding in predicting COVID-19 patients' critically ill. According to some embodiments of the invention, the product includes, but is not limited to, a kit, a chip, or a predictive system. According to some embodiments of the invention, the method of using the product comprises the steps of: S1, acquiring abundance data of the biomarker in the embodiment of the first aspect of the invention in throat swabs of COVID-19 critically ill patients and COVID-19 non-critically ill patients, and constructing a COVID-19 critically ill prediction or auxiliary prediction model by using a machine learning method; S2, collecting abundance data of the biomarker in the embodiment of the first aspect of the invention in samples of COVID-19 patients in a progressive state to be predicted; s3, inputting the abundance data collected in the step S2 into the COVID-19 patient severe prediction or auxiliary prediction model constructed in the step S1, and evaluating or assisting in evaluating the risk of severe occurrence of the COVID-19 patient in the progressive state to be predicted. According to some embodiments of the invention, assessing or aiding in assessing the risk of developing a criticality of the COVID-19 patient includes predicting the probability of developing a criticality of the COVID-19 patient using the COVID-19 patient criticality prediction model, the higher the probability the greater the risk of developing a criticality of the COVID-19 patient. According to a fourth aspect of the present invention, a method for constructing a COVID-19 patient critical prediction or auxiliary prediction model includes the steps of: Obtaining abundance data of the biomarker described in the embodiment of the first aspect of the invention in a pharynx swab of COVID-19 critically ill patients and COVID-19 non-critically ill patients, and constructing the COVID-19 patient critically ill prediction model by using a machine learning method. According to some embodiments of the invention, the COVID-19 critically ill patient refers to a COVID-19 patient that enters a critically ill state from a progressive state; the progressive state refers to a period in which symptoms of upper respiratory tract infection are in an i