Biomarker for predicting severe condition of COVID-19 patient and application of biomarker

Abstract

The invention discloses a biomarker for predicting severe treatment of a COVID-19 patient and application of the biomarker, and relates to the technical field of biomedicine. According to the invention, a COVID-19 patient severity prediction or auxiliary prediction model which is obtained by constructing biomarkers including Gemelia haemolsos, Streptococcus sp.A12, Fusobacterium pseudoperiodontium, Gemelia mollissima, Villonella atypical, Villonella rogosa and Prevotella melaninogena is found, the model is used for predicting and evaluating the severity of the COVID-19 patient, the sensitivity is high, and the specificity is good. The invention further discloses a method for predicting and evaluating the severity of the COVID-19 patient severity, and the method has the advantages that the method can be used for predicting and evaluating the severity of the COVID-19 patient severity;

Description

Technical Field

[0001] This invention relates to the field of biomedical technology, and in particular to a biomarker for predicting the severity of COVID-19 in patients and its application. Background Technology

[0002] Coronavirus disease 2019 (COVID-19) is an infection caused by the novel coronavirus (SARS-CoV-2, hereinafter referred to as "COVID-19"). It has a certain rate of severe illness, and severe COVID-19 infection is highly dangerous, not only incurring significant medical needs and costs, but also potentially leading to prolonged illness, complications, and even death. Therefore, providing a biomarker that can predict the severity of COVID-19 in patients is of great significance. Summary of the Invention

[0003] This invention aims to at least solve one of the technical problems existing in the prior art. To this end, this invention proposes a biomarker for predicting or assisting in the prediction of severe illness in COVID-19 patients. The COVID-19 patient severe illness prediction model constructed from it is used for the prediction and assessment of severe illness in COVID-19 patients, and has high sensitivity and good specificity.

[0004] The present invention also provides a reagent kit.

[0005] The present invention also provides the use of the above-mentioned biomarkers or substances for detecting the abundance of the above-mentioned biomarkers in the preparation of products for predicting or assisting in the prediction of the severity of COVID-19 patients.

[0006] The present invention also provides a method for constructing a predictive or auxiliary predictive model for the progression of COVID-19 patients to severe illness.

[0007] The present invention also provides a predictive or auxiliary predictive model for the progression of COVID-19 patients to severe illness.

[0008] The present invention also provides a system for predicting or assisting in the prediction of severe illness in COVID-19 patients.

[0009] The present invention also provides a computer-readable storage medium.

[0010] According to a first aspect of the present invention, a biomarker for predicting or assisting in predicting the severity of COVID-19 in patients includes Gemella haemolysans, Streptococcus sp. A12, Fusobacteriumpseudoperiodonticum, Gemella morbillorum, Veillonella atypica, Veillonellarogosae, and Prevotella melaninogenica.

[0011] A kit according to a second aspect of the present invention includes a substance for detecting the abundance of the biomarkers described in the first aspect of the present invention.

[0012] According to some embodiments of the present invention, the substance includes reagents for detecting the abundance of the biomarker by metatranscriptomics or metagenomic sequencing.

[0013] The application of the biomarkers described in the first aspect of the present invention, according to a third aspect of the present invention, in the preparation of products for predicting or assisting in predicting the severity of COVID-19 in patients.

[0014] According to some embodiments of the present invention, the products include, but are not limited to, reagent kits, chips, or prediction systems.

[0015] According to some embodiments of the present invention, the method of using the product includes the following steps:

[0016] S1. Obtain the abundance data of the biomarkers described in the first aspect of the present invention from pharyngeal swabs of patients with severe COVID-19 and patients without severe COVID-19; construct a predictive or auxiliary predictive model for the severity of COVID-19 patients using machine learning methods;

[0017] S2. Collect abundance data of the biomarkers described in the first aspect of the present invention from samples of COVID-19 patients in a progressive state to be predicted;

[0018] S3. Input the abundance data collected in step S2 into the COVID-19 patient severe illness prediction or auxiliary prediction model constructed in step S1 to assess or assist in assessing the risk of the COVID-19 patient in the progressive stage developing severe illness.

[0019] According to some embodiments of the present invention, assessing or assisting in assessing the risk of a COVID-19 patient developing severe illness includes: using a COVID-19 patient severe illness prediction model to predict the probability of the COVID-19 patient developing severe illness; the higher the probability, the greater the risk of the COVID-19 patient developing severe illness.

[0020] A method for constructing a predictive or auxiliary predictive model for the progression of COVID-19 patients to severe illness, according to a fourth aspect of the present invention, includes the following steps:

[0021] Abundance data of the biomarkers described in the first aspect of this invention were obtained from pharyngeal swabs of patients with severe COVID-19 and patients without severe COVID-19; a predictive model for the severity of COVID-19 patients was constructed using machine learning methods.

[0022] According to some embodiments of the present invention, the COVID-19 severe illness patient refers to a COVID-19 patient who progresses from a progressive state to a severe state;

[0023] The progressive state refers to the period when the symptoms of upper respiratory tract infection are increasing;

[0024] The critical condition refers to COVID-19 patients who have been admitted to the ICU and require mechanical ventilation, and who have ground-glass opacities / nodular lung imaging features.

[0025] According to some embodiments of the present invention, the COVID-19 non-severe patients refer to COVID-19 patients who have progressed from a progressive state to a moderate symptom state;

[0026] The progressive state refers to the period when the symptoms of upper respiratory tract infection are increasing;

[0027] The term "intermediate symptom state" refers to COVID-19 patients who only require intermittent oxygen therapy and have only mild inflammatory symptoms.

[0028] According to some embodiments of the present invention, the symptoms of upper respiratory tract infection include at least one of nasal congestion, runny nose, sneezing, sore throat, difficulty swallowing, fever, and cough.

[0029] According to some embodiments of the present invention, the abundance data is obtained by analyzing bacterial metatranscriptome or metagenomic sequencing data.

[0030] According to some embodiments of the present invention, the machine learning method includes, but is not limited to, random forest classifiers.

[0031] A COVID-19 patient severe illness prediction or auxiliary prediction model according to a fifth aspect embodiment of the present invention is constructed by the construction method described in the fourth aspect embodiment of the present invention.

[0032] A COVID-19 patient severe illness prediction or auxiliary prediction system according to a sixth aspect embodiment of the present invention includes:

[0033] A data collection module for collecting abundance data of the biomarkers described in the first aspect of the present invention in samples from COVID-19 patients in a progressive stage;

[0034] The prediction module inputs the abundance data into the COVID-19 patient severe illness prediction or auxiliary prediction model described in the fifth aspect embodiment of the present invention to assess the risk of the COVID-19 patient developing severe illness.

[0035] According to some embodiments of the present invention, the progressive state refers to the period in which the clinical symptoms and inflammatory symptoms of COVID-19 are increasing.

[0036] According to some embodiments of the present invention, assessing the risk of the COVID-19 patient developing severe illness includes:

[0037] The COVID-19 patient severity prediction model is used to predict the probability of a COVID-19 patient developing severe illness; the higher the probability, the greater the risk of the COVID-19 patient developing severe illness.

[0038] According to some embodiments of the present invention, the sample is a throat swab.

[0039] According to a seventh aspect of the present invention, a computer-readable storage medium stores a computer program that, when executed by a processor, can perform the functions of a construction method as described in a fourth aspect of the present invention or a COVID-19 patient severe illness prediction or auxiliary prediction system as described in a sixth aspect of the present invention.

[0040] The present invention has at least the following beneficial effects:

[0041] The biomarkers described in this embodiment can be used to construct predictive or auxiliary predictive models for the progression of COVID-19 patients to severe illness. They have demonstrated good predictive ability, high sensitivity, and good specificity in the prediction and assessment of the progression of COVID-19 patients to severe illness. Moreover, the biomarker data are derived from throat swabs, making the samples readily available.

[0042] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. Attached Figure Description

[0043] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0044] Figure 1 This is a schematic diagram illustrating the status of 33 hospitalized patients infected with the novel coronavirus in Example 1 during their hospitalization. An asterisk indicates the time of pharyngeal swab sampling; gray areas indicate patients in a progressive state; red areas indicate patients in a severe state; orange areas indicate patients in a moderate symptom state; and green areas indicate patients in a recovery state.

[0045] Figure 2 The classification model ranks the importance of the 10 bacterial species selected through screening.

[0046] Figure 3 The receiver operating characteristic (ROC) curves are obtained by analyzing the seven bacterial species in Example 1 as classification markers.

[0047] Figure 4 The ROC curves are obtained from the analysis of five bacterial genera as taxonomic markers in Example 1. Detailed Implementation

[0048] The following will describe the concept and technical effects of the present invention clearly and completely with reference to embodiments, so as to fully understand the purpose, features and effects of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are all within the scope of protection of the present invention.

[0049] Unless otherwise specified in the examples, the procedures should be performed under standard conditions or conditions recommended by the manufacturer. Reagents or instruments whose manufacturers are not specified are all commercially available products.

[0050] "And / or" is used to indicate that one or both of the described situations may occur, for example, A and / or B includes (A and B) and (A or B).

[0051] Example 1

[0052] Pharyngeal swab samples were collected from 33 hospitalized patients infected with COVID-19 (samples were obtained from multiple clinical research centers). Based on the patients' medical indicators, their daily status was categorized into four states: State 1, incremental state, characterized by increasing upper respiratory tract infection symptoms (such as nasal congestion, runny nose, sneezing, sore throat, dysphagia, fever, cough, etc.); State 2, critical state, characterized by admission to the ICU, requiring mechanical ventilation, and exhibiting ground-glass opacities / nodular lung imaging features; State 3, moderate state, characterized by intermittent oxygen requirements and mild inflammatory symptoms; and State 4, recovery state, characterized by the absence of oxygen and inflammatory symptoms. State 1 was referred to as the "early stage of illness." Patients who progressed from State 1 to State 2 were defined as "critically ill patients," and those who progressed from State 1 to State 3 were defined as "non-critically ill patients."

[0053] The daily condition of the 33 patients during their hospitalization was as follows Figure 1 As shown.

[0054] like Figure 1 The data shows that all pharyngeal swab sampling occurred before the patients entered state 2 (i.e., the critical state), and the number of days prior is shown in Table 1. The average number of days prior to the critical state of pharyngeal swab sampling was approximately 6.8 days.

[0055] Table 1

[0056]

[0057] Nucleic acid was extracted from the patient's pharyngeal swab samples and subjected to deep metatranscriptomic sequencing. Subsequently, MetaPhlAn 3 was used for bacterial species annotation, resulting in an abundance table of 187 bacterial species. In the R environment (https: / / www.r-project.org / ), the mainstream machine learning algorithm of Random Forest classifier (randomForest package; https: / / www.rdocumentation.org / packages / randomForest / versions / 4.7-1.1 / topics / randomForest) was applied to search for classifiable markers among the 187 bacterial species. The specific process is as follows:

[0058] Using 187 bacterial species as input data, data preprocessing was performed, including variable label replacement. Then, cross-validation and feature selection were conducted: the queue data was randomly divided into 10 parts, with 9 parts used to train the classification model and the remaining part used to test the model's predictions. This process was repeated 10 times, using different test data each time. The average error rate of the 10 results was used as an estimate of the algorithm's accuracy. The 10-fold cross-validation method was repeated 5 times, and the average error rate of the 5 10-fold cross-validations was used as an estimate of the algorithm's accuracy, selecting the optimal number of bacterial species as 10. The importance parameter of the randomForest() function was used to evaluate feature importance, and the importance results were visualized using the ggplot2 package (https: / / ggplot2.tidyverse.org / ). The importance ranking results of the classification model for the selected 10 bacterial species are shown below. Figure 2 As shown.

[0059] Seven bacterial species (Gemella haemolysans, Streptococcus sp. A12, Fusobacterium pseudoperiodonticum, Gemella morbillorum, Veillonella atypica, Veillonella rogosae, and Prevotella melaninogenica) were selected as taxonomic markers, and their classification performance was tested using 33 sample data. ROC curves were plotted using the pROC package in R. The results are as follows. Figure 3 As shown, the area under the ROC curve (AUC) is 0.85. This indicates that the above seven bacterial species, as a combination of biomarkers, have good classification ability.

[0060] Five genera—Gemella, Veillonella, Fusobacterium, Prevotella, and Streptococcus—containing the aforementioned seven bacterial species, were used as taxonomic markers, and their taxonomic performance was tested using data from 33 samples. The resulting ROC curves are shown below. Figure 4 As shown, the AUC value was 0.59, indicating that its classification performance was significantly worse than the seven bacterial species mentioned above, and it could not be effectively used to predict the severity of COVID-19 patients.

[0061] The embodiments of the present invention have been described in detail above with reference to the examples. However, the present invention is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of the present invention.

Claims

1. A biomarker for predicting or assisting in predicting the severity of COVID-19 in patients, characterized in that, Including Gemella haemolysans, Streptococcus sp.A12, Fusobacterium pseudoperiodonticum, Gemella morbillorum, Veillonella atypica, Veillonella rogosae, Prevotellamelaninogenica.

2. A reagent kit, characterized in that, Includes substances for detecting the abundance of the biomarker described in claim 1.

3. The reagent kit according to claim 2, characterized in that, The substance includes reagents for detecting the abundance of the biomarker by metatranscriptomics or metagenomic sequencing.

4. The use of the biomarker of claim 1 or a substance for detecting the abundance of the biomarker of claim 1 in the preparation of a product for predicting or assisting in the prediction of severe illness in COVID-19 patients.

5. The application according to claim 4, characterized in that, The product is selected from reagent kits, chips, or prediction systems; And / or, the method of using the product includes the following steps: S1. Obtain abundance data of the biomarker described in claim 1 from pharyngeal swabs of patients with severe COVID-19 and patients without severe COVID-19; construct a predictive or auxiliary predictive model for the progression of COVID-19 to severe illness using machine learning methods; S2. Collect abundance data of the biomarker of claim 1 in samples from COVID-19 patients in progressive stages to be predicted; S3. Input the abundance data collected in step S2 into the COVID-19 patient severe illness prediction or auxiliary prediction model constructed in step S1 to assess or assist in assessing the risk of the COVID-19 patient in the progressive stage developing severe illness.

6. A method for constructing a predictive or auxiliary predictive model for the progression of COVID-19 patients to severe illness, characterized in that, Includes the following steps: Obtain abundance data of the biomarker of claim 1 from pharyngeal swabs of patients with severe COVID-19 and patients without severe COVID-19; construct a predictive or auxiliary predictive model for the severity of COVID-19 patients using machine learning methods.

7. The construction method according to claim 6, characterized in that, The abundance data were obtained from the analysis of bacterial species metagenomic or metagenomic sequencing data. And / or, the machine learning method includes a random forest classifier.

8. A model for predicting or assisting in predicting the severity of COVID-19 patients, characterized in that, It is constructed by the construction method described in claim 6 or 7.

9. A system for predicting or assisting in the prediction of severe illness in COVID-19 patients, characterized in that, include: A data collection module for collecting abundance data of the biomarker of claim 1 in samples from COVID-19 patients in a progressive stage; The prediction module inputs the abundance data into the COVID-19 patient severe illness prediction or auxiliary prediction model as described in claim 8 to assess the risk of the COVID-19 patient developing severe illness.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, can implement the construction method of any one of claims 6 to 7 or the COVID-19 patient severe illness prediction or auxiliary prediction system of claim 9.

Images