Biomarker combination for predicting severe outcome condition of novel coronavirus infected patient caused by Ommike variant and application of biomarker combination for predicting severe outcome condition of novel coronavirus infected patient caused by Ommike variant

Abstract

The embodiment of the invention discloses a biomarker combination for predicting the severe outcome condition of a novel coronavirus infected patient caused by an Omike variant and application of the biomarker combination. The biomarker combination for predicting the severe outcome condition of the novel coronavirus infected patient caused by the Ommitake variant is composed of tyrosine-leucine-glycine-lysine-arginine, arsanilic acid, Tacalcitol, arginine, arginine, arginine, arginine, arginine, Tacalcitol, arginine, arginine, arginine, arginine, arginine, arginine, arginine, arginine, arginine, arginine, arginine, arginine, arginine and arginine. The invention relates to an alanyl-D-glutamyl-L-lysine compound, which is characterized by being composed of five metabolites, namely L-alanyl-gamma-D-glutamyl-L-lysine (L-Alanyl-gamma-D-glutamyl-L-lysine) and 5-Hydroxy-2 '-deoxyuridine (5-hydroxy-2'-deoxyuridine). The marker combination is used as a detection marker, is high in accuracy and can predict whether a severe patient with the novel coronavirus can outcome or not.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of biotechnology, and in particular to a biomarker combination and application thereof for predicting the severe outcome of patients infected with the novel coronavirus caused by the Omicron variant. Background Art

[0002] Novel coronavirus infection is an acute respiratory infectious disease caused by novel coronavirus infection. Since the outbreak of the novel coronavirus, research on the etiology, vaccines and specific drugs for the novel coronavirus has attracted much attention. Although different types of novel coronavirus vaccines and therapeutic drugs have been approved for use, there is still no specific drug or vaccine that can eliminate the novel coronavirus epidemic. The main reason why the novel coronavirus is difficult to eliminate is that its genome has strong plasticity, which can continue to spread and spread among the population through frequent mutations and recombination. Among them, the Omicron variant was discovered in the infected population in November 2021. Due to its significantly enhanced transmission and immune escape capabilities, it quickly replaced the Delta variant in early 2022 and has now become the global dominant epidemic strain. As of early September 2023, the five subtypes of the Omicron strain (BA.1, BA.2, BA.3, BA.4, BA.5) have evolved into more than 750 sub-branches in a series of generations. At present, the number of confirmed and fatal cases of novel coronavirus caused by the Omicron epidemic strain is still increasing. Compared with the initial strain, although its pathogenicity and mortality rate are significantly reduced, clinically it mainly manifests as asymptomatic and mild upper respiratory tract symptoms including cough, sputum, nasal congestion, runny nose, etc., but people with low immunity such as immunodeficiency, the elderly or those with underlying diseases are considered to be high-risk groups for the new coronavirus, and they are more likely to develop severe infection or even death. At present, the molecular dynamic changes in different disease stages and severity related to Omicron infection have not been clearly defined. Once the condition of Omicron-infected patients worsens, they need to be transferred to a professional intensive care unit for treatment immediately, otherwise they will face life-threatening danger.

[0003] Given that existing drugs and vaccines cannot completely eradicate the Omicron variant, there is an urgent clinical need to determine which novel coronavirus patients will develop severe symptoms so that effective clinical management measures can be taken early in the course of the disease and medical resources can be rationally allocated for rapid treatment, thereby saving lives and reducing mortality. Summary of the invention

[0004] The purpose of the present invention is to provide a biomarker combination and its application for predicting the severe outcome of patients with novel coronavirus infection caused by Omicron variants, which can predict the severe outcome of novel coronavirus infection caused by Omicron infection and may guide the selection of treatment options.

[0005] To achieve the above object, the present invention adopts the following technical solution:

[0006] In a first aspect of an embodiment of the present invention, a biomarker combination for predicting the severe outcome of patients infected with the new coronavirus caused by the Omicron variant is provided, wherein the biomarker combination for predicting the severe outcome of patients infected with the new coronavirus caused by the Omicron variant is composed of five metabolites of tyrosine-leucine-glycine-lysine-arginine (Tyr-Leu-Gly-Lys-Arg), arsenic acid (Arsanilic acid), ttacalcitol (Ttacalcitol), L-Alanyl-gamma-D-glutamyl-L-lysine (L-Alanyl-gamma-D-glutamyl-L-lysine) and 5-Hydroxy-2'-deoxyuridine (5-hydroxy-2'-deoxyuridine).

[0007] In the second aspect of an embodiment of the present invention, provided is the use of a detection reagent for a combination of biomarkers for predicting the severity of a patient infected with the novel coronavirus caused by the Omicron variant in the preparation of a product for predicting the severity of a patient infected with the novel coronavirus caused by the Omicron variant.

[0008] Furthermore, the detection reagent comprises reagents for one or more detection methods selected from the group consisting of high performance liquid chromatography, gas chromatography, enzyme-linked immunosorbent assay, mass spectrometry or rapid liquid chromatography.

[0009] Furthermore, the product comprises at least one of a reagent, a test kit, a test paper, a chip, and a system.

[0010] Furthermore, the test sample of the product is selected from at least one of tissues, cells, and secretions of the subject to be tested.

[0011] In a third aspect of an embodiment of the present invention, a method for constructing a model for predicting the severe outcome of patients infected with the new coronavirus caused by Omicron is provided, the method comprising using the biomarker combination to construct a model to obtain a computational model for predicting the severe outcome of patients infected with the new coronavirus caused by the Omicron variant.

[0012] Furthermore, the construction method is at least one of logistic regression, neural network, extreme gradient boosting, decision tree, and random forest.

[0013] As a specific implementation, the method for constructing the model specifically includes:

[0014] Obtain laboratory test indicators of patients infected with the new coronavirus caused by Omicron;

[0015] The laboratory test indicators were preliminarily screened by baseline analysis and correlation analysis, and the preliminarily screened variables were obtained and randomly divided into training sets and test sets;

[0016] In the training set, the variables after the preliminary screening are ranked by importance using a machine learning method, and the variable set is scored using a random forest algorithm to obtain the final screened variables; the final screened variables are input using multiple initial prediction models to respectively construct multiple trained prediction models;

[0017] The multiple trained prediction models are evaluated using a model evaluation index, and the best trained prediction model after the evaluation is determined as a model for predicting the severe outcome of patients infected with the new coronavirus caused by Omicron.

[0018] In a fourth aspect of an embodiment of the present invention, a model constructed using the method is provided for predicting the severity of the disease in patients infected with the novel coronavirus caused by the Omicron variant.

[0019] In a fifth aspect of an embodiment of the present invention, a system for predicting the severity of a patient infected with the novel coronavirus caused by Omicron is provided, the system comprising:

[0020] A processor and a memory, wherein the memory is coupled to the processor, and the memory stores instructions. When the instructions are executed by the processor, the model is used to calculate the detection results of the biomarker combination to obtain a prediction of the severe outcome of patients infected with the new coronavirus caused by the Omicron variant.

[0021] In a sixth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are used: the detection results of a combination of biomarkers for predicting the severe prognosis of patients infected with the new coronavirus caused by the Omicron variant are input into the system, and the severe prognosis of patients infected with the new coronavirus caused by the Omicron variant is obtained through calculation.

[0022] In the seventh aspect of an embodiment of the present invention, a product for predicting the severe outcome of a patient infected with the novel coronavirus caused by the Omicron variant is provided, the product comprising the system for predicting the severe outcome of a patient infected with the novel coronavirus caused by the Omicron variant or the computer-readable storage medium.

[0023] Furthermore, the product also includes a detection reagent for the biomarker combination for predicting the severe outcome of patients infected with the new coronavirus caused by the Omicron variant.

[0024] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:

[0025] The embodiments of the present invention provide biomarkers and applications for predicting the severe outcome of patients infected with the novel coronavirus caused by the variant strain of Omicron. The present invention first discovered that tyrosine-leucine-glycine-lysine-arginine, aromatic arsenic acid, takacitol, L-alanyl-γ-D-glutamyl-L-lysine and 5-hydroxy-2'-deoxyuridine can predict the severe outcome of novel coronavirus infection caused by Omicron infection. The AUC of the five specific metabolites is 0.943, of which the optimal cutoff value is 0.455, the corresponding specificity is 0.86, and the sensitivity is 1. Using this biomarker as a detection marker has high specificity, high sensitivity and high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 This is a targeted metabolomics analysis of the recovery and death of critically ill patients infected with the new coronavirus. Figure A is an OPLS-DA comparing the Death group and the Recovery group, Figure B is a differential analysis of any two groups, and the results show that there are a total of 32 differential metabolites, and Figure C is a heat map of the changes in the concentration of differentially expressed metabolites (DEMs) in different groups.

[0028] Figure 2To identify the best combination of metabolites for distinguishing deaths and recovered cases of severe novel coronavirus infection based on random forest models. Figure A shows the ROC curve generated by the multivariate random forest model based on MCCV for the first dataset. The AUC-ROC value and its 95% CI are shown in the figure. Figure B shows the prediction accuracy of the multivariate random forest model with different numbers of DEMs for the second dataset. Figure C shows the importance plot based on the contribution of the variables to the RF model for the five metabolites in the first dataset to predict recovery. Figure D shows the ROC curve generated by the multivariate random forest model based on MCCV for the second dataset. The AUC-ROC value and its 95% CI are shown in the figure. Figure E shows the prediction accuracy of the multivariate random forest model with different numbers of DEMs for the second dataset. Figure F shows the variable importance plot based on the contribution of the variables to the RF model for predicting recovery based on the five metabolites in the second dataset. Figure G shows the random forest prediction and ROC curve analysis using the top five metabolites ranked by the sum of the average importance scores.

[0029] Figure 3 Box plots showing the changes in the five most important different metabolites between fatal and recovered cases of severe novel coronavirus infection. DETAILED DESCRIPTION

[0030] The following will be combined with specific implementation methods and examples to specifically describe the embodiments of the present invention, and the advantages and various effects of the embodiments of the present invention will be more clearly presented. It should be understood by those skilled in the art that these specific implementation methods and examples are used to illustrate the embodiments of the present invention, rather than to limit the embodiments of the present invention.

[0031] Throughout the specification, unless otherwise specified, the terms used herein should be understood as the meanings commonly used in the art. Therefore, unless otherwise defined, all technical and scientific terms used herein have the same meaning as those in the field to which the embodiments of the present invention belong.

[0032] The biomarkers of the present application and their applications will be described in detail below in combination with experimental data.

[0033] Example 1. Biomarker combination and screening method for predicting the prognosis of severe cases of patients infected with the new coronavirus caused by the Omicron variant

[0034] 1. Sample Collection

[0035] A total of 31 severe / critically ill patients with novel coronavirus were recruited, of whom 18 died (Death group) and 13 were discharged (Recovery group). Clinical classification was determined in accordance with the Diagnosis and Treatment Plan for Novel Coronavirus Infection (Trial 10th Edition).

[0036] 2 ml of cubital venous blood was drawn from each subject and placed in a dry tube. Serum samples were centrifuged at 12,000 g for 10 min, and the supernatant was transferred to a new centrifuge tube and stored in a −80 °C refrigerator for subsequent metabolite detection.

[0037] 2. Metabolomics processing and research of 31 samples

[0038] 1. Serum sample processing: (1) After the sample is thawed, vortex for 10 seconds to mix, and transfer 50 μL of the sample to the corresponding numbered centrifuge tube; (2) Add 300 μL of 20% acetonitrile methanol internal standard extract, vortex for 3 minutes, and centrifuge at 12000 r / min for 10 minutes at 4°C; (3) After centrifugation, transfer 200 μL of the supernatant to another corresponding numbered centrifuge tube and place it in a -20°C refrigerator for 30 minutes; (4) Centrifuge again at 12000 r / min for 3 minutes at 4°C, transfer 180 μL of the supernatant to the corresponding sample bottle liner for analysis.

[0039] 2. TM broad-target detection: TM broad-target is a combination of non-target (high resolution, wide coverage) and broad-target (high sensitivity, precise quantification). First, use a high-resolution quadrupole time-of-flight mass spectrometer to perform a secondary spectrum scan on the sample and extract the multiple reaction monitoring (MRM) ion pair information; then integrate the broad-target library, and Myvi integrates public databases (including Metlin (Metabolite Link), HMDB (The Human Metabolome Database), KEGG and other databases) AI prediction library to qualitatively identify the substances in the high-resolution mass spectrometer; then transfer the qualitative substance ion pairs to the mass spectrometer, collect retention time (RT) data, obtain the peak area, and construct a sample-specific database; finally, use a triple quadrupole linear ion trap mass spectrometer to perform MRM precision detection on the substances in the library.

[0040] 3. Analysis and screening of biomarkers

[0041] 1. Data preprocessing: Use K-Nearest Neighbor (KNN) algorithm to fill missing data. PCA: Use prcomp function in R language to perform PCA principal component analysis on Death group and Recovery group. OPLS-DA: Use Maiwei metabolomics analysis platform to perform OPLS-DA analysis on Death group and Recovery group respectively, and obtain VIP value. In order to evaluate whether the OPLS-DA model is reliable, 200 random permutation and combination experiments were performed on the data. R2X, R2Y and Q2 were used as evaluation. Among them, R2X and R2Y represent the explanation rate of the constructed model for X and Y matrices respectively, and Q2 represents the predictive ability of the model.

[0042] 2. Sample clustering: Cluster analysis of samples was performed based on unsupervised class average hierarchical clustering measured by Euclidean distance. Difference analysis: After correcting for age and gender, difference analysis was performed on the Death group and Recovery group, and hypothesis testing was performed using t-test. P-value and projection variable importance VIP value were used for screening by fold change (FC). p-value < 0.05, VIP ≥ 1 and FC > 1.5 were up-regulated, and p-value < 0.05, VIP ≥ 1 and FC less than 0.7 were down-regulated. Volcano maps were drawn using the R language ggplo2 package (version 3.4.0). Heatmap function of ComplexHeatmap package (version 2.14.0) was used to draw heat maps of concentration changes of differential metabolites in the eath group and Recovery group.

[0043] 4. Validation of a biomarker combination for predicting severe outcomes in patients with novel coronavirus infection caused by the Omicron variant

[0044] In order to verify whether the identified metabolites can be used as potential predictors for distinguishing the stages of the Death and Recovery groups, we used the differential metabolite data from 11 Death patients and 8 Recovery patients as the training set, and the differential metabolite data from 7 Death patients and 5 Recovery patients as the test set. The same strategy was used to generate a multivariate random forest model for the two data sets through Monte Carlo cross-validation (MCCV) to select the best biomarker combination. The variables in the two data sets were ranked according to importance and the intersection was taken for prediction using the random forest model.

[0045] 5. Orthogonal Partial Least Squares Discriminant Analysis

[0046] The 31 serum samples enrolled in this project were tested by TM broad targeted metabolomics, and a total of 1864 metabolites were detected. In order to test whether metabolic analysis can distinguish between the patients in the Death group who died of the new coronavirus caused by Omicron infection and the patients in the Recovery group who were discharged, we used supervised orthogonal partial least squares discriminant analysis (Orthogonal Projections to Latent Structures Discriminant Analysis, OPLS-DA) to study. The Death group and the Recovery group were compared pairwise.

[0047] 6. Screening of Differential Metabolites

[0048] We performed differential analysis between any two groups, and the results showed that there were 32 differential metabolites in total, of which 23 metabolites were down-regulated and 9 metabolites were up-regulated ( Figure 1 B). Figure 1 C is a heat map of the changes in the concentrations of differentially expressed metabolites (DEMs) in different groups. The upregulated metabolites include Tyr-Lys-Val-Glu-Ile, 5-Hydroxy-2'-deoxyuridine, etc., and the downregulated metabolites include 5beta-Cholanic acid, gamma-Glutamyl-Se-methylselenocysteine, Gln-Tyr-Thr-Lys, Arsanilic acid, etc.

[0049] 7. Further screening

[0050] We tried to classify the Severe and Non-Severe groups using the above 32 differential metabolites. The MCCV determined using the multivariate random forest model showed that five metabolites had strong predictive power. The data of 11 patients who died and 8 patients who recovered were used as one dataset, and the data of 7 patients who died and 5 patients who recovered were used as another dataset. The AUC obtained in the first dataset was 0.798 and the ACC was 74.2% ( Figure 2 A, B), in the second data set, AUC value = 0.709, ACC = 66.0% ( Figure 2 D, E). The variables of the two data sets were ranked according to their average importance ( Figure 2 C, F) The top five metabolites in the sum ranking are Tyr-Leu-Gly-Lys-Arg, Arsanilicacid, Ttacalcitol, L-Alanyl-gamma-D-glutamyl-L-lysine and 5-Hydroxy-2'-deoxyuridine. These five metabolites were significantly downregulated in the deceased patients. The box plots of the changes in the recovered patients and the deceased patients are shown in Figure 3 As shown. The five metabolites were used to construct a random forest model in the training cohort and predicted in the test cohort, with AUC = 0.943 ( Figure 2G), where the optimal cutoff value was 0.455, the corresponding specificity was 0.86, and the sensitivity was 1, indicating that Tyr-Leu-Gly-Lys-Arg, Arsanilic acid, Ttacalcitol, L-Alanyl-gamma-D-glutamyl-L-lysine and 5-Hydroxy-2'-deoxyuridine can be used as reference biomarkers for the prognosis of critically ill patients.

[0051] Example 2: Model for predicting the prognosis of severe cases of novel coronavirus infection caused by Omicron and its construction method

[0052] 1. A method for constructing a model for predicting the prognosis of severe cases of patients infected with the novel coronavirus caused by Omicron includes:

[0053] S1. Process serum samples for TM broad-target detection, build a sample-specific database, randomly extract 60% of the data as a training set to train the model, and use the remaining 40% of the abundance data as a validation set;

[0054] S2. In the training set, use machine learning methods to rank the differential metabolites and identify key classification variables;

[0055] S3, inputting the final screened markers to construct a model using a random forest model;

[0056] S4. Evaluate the trained prediction model using the validation set, and determine the best trained prediction model after evaluation as the prediction model for the severe outcome of patients infected with the novel coronavirus caused by the Omicron variant. The preset model evaluation indicators include: drawing the receiver operating characteristic curve of the prediction model, and evaluating the effectiveness of the prediction model by the area under the ROC curve AUC and accuracy.

[0057] From the above results, it can be seen that five metabolites of Tyr-Leu-Gly-Lys-Arg, Arsanilic acid, Ttacalcitol, L-Alanyl-gamma-D-glutamyl-L-lysine and 5-Hydroxy-2'-deoxyuridine can predict the severe outcome of novel coronavirus infection (novel coronavirus) caused by Omicron infection. The AUC of the five specific metabolites was 0.943, with the best cutoff value of 0.455, corresponding to a specificity of 0.86 and a sensitivity of 1.

[0058] Example 3: System for predicting the prognosis of severe cases of patients infected with novel coronavirus caused by Omicron

[0059] An embodiment of the present invention provides a system for predicting the severity of a patient infected with the novel coronavirus caused by Omicron, the system comprising:

[0060] A processor and a memory, the memory being coupled to the processor, the memory storing instructions which, when executed by the processor, use the following steps:

[0061] The test results of the input biomarker combination are used to determine whether the patient with the novel coronavirus infection caused by Omicron can recover from severe illness.

[0062] In the above technical solution, the input is the peak area detection result of the biomarker, and the model / system output value is either 1 or 0; if the output value is 1, it means that the patient with severe novel coronavirus infection caused by Omicron is difficult to recover; if the output value is 0, it means that the patient with severe novel coronavirus infection caused by Omicron can recover.

[0063] Embodiment 4: Computer readable storage medium

[0064] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method in Example 2 and / or the method in Example 3 are implemented.

[0065] Of course, the computer executable instructions of a storage medium including computer executable instructions provided by an embodiment of the present invention are not limited to the operations of the method described above, but can also execute related operations in the method provided by any embodiment of the present invention.

[0066] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0067] It is worth noting that in the above embodiments, the various units and modules included are only divided according to functional logic, but are not limited to the above divisions, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0068] Application example 1: Predicting the severity of the disease in patients infected with the novel coronavirus caused by Omicron

[0069] 1. Experimental methods

[0070] S1: Extract samples;

[0071] S2: Use mass spectrometry (ordinary mass spectrometer) to detect the peak area of ​​5 metabolites in the sample, including Tyr-Leu-Gly-Lys-Arg, Arsanilicacid, Ttacalcitol, L-Alanyl-gamma-D-glutamyl-L-lysine and 5-Hydroxy-2'-deoxyuridine;

[0072] S3: According to the quantitative detection results of step S2, the severe disease prognosis of patients infected with the new coronavirus caused by Omicron is output.

[0073] 2. Experimental results

[0074] The peak area of ​​Tyr-Leu-Gly-Lys-Arg is 40476, the peak area of ​​Arsanilic acid is 230034, the peak area of ​​Ttacalcitol is 120445, the peak area of ​​L-Alanyl-gamma-D-glutamyl-L-lysine is 20061 and the peak area of ​​5-Hydroxy-2'-deoxyuridine is 2108609. The value in the final output model is 0, indicating that patients with severe novel coronavirus infection caused by Omicron can recover.

[0075] Finally, it should be noted that the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements that are inherent to such process, method, article, or apparatus.

[0076] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0077] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present invention without departing from the spirit and scope of the embodiments of the present invention. Thus, if these modifications and variations of the embodiments of the present invention fall within the scope of the claims of the embodiments of the present invention and their equivalents, the embodiments of the present invention are also intended to include these modifications and variations.

Claims

1. A biomarker combination for predicting the prognosis of severe cases of patients infected with the novel coronavirus caused by a variant of Omicron, characterized in that: The biomarker combination consists of five metabolites of tyrosine-leucine-glycine-lysine-arginine, aryl arsenic acid, takacitol, L-alanyl-γ-D-glutamyl-L-lysine and 5-hydroxy-2'-deoxyuridine.

2. Use of the detection reagent of the biomarker combination according to claim 1 in the preparation of a product for predicting the severity of the new coronavirus infection caused by the Omicron variant.

3. The use according to claim 2, characterized in that: The detection reagent comprises reagents of one or more detection methods selected from the group consisting of: high performance liquid chromatography, gas chromatography, enzyme-linked immunosorbent assay, mass spectrometry or rapid liquid chromatography.

4. A method for constructing a model for predicting the severe outcome of patients infected with the new coronavirus caused by the variant strain of Omicron, the method comprising using the biomarker combination described in claim 1 to construct a model to obtain a computational model for predicting the severe outcome of patients infected with the new coronavirus caused by the variant strain of Omicron.

5. The construction method according to claim 4, characterized in that: The construction method includes at least one of logistic regression, neural network, extreme gradient boosting, decision tree, and random forest.

6. A model constructed according to the method according to any one of claims 4-5 for predicting the severity of the disease in patients infected with the new coronavirus caused by the Omicron variant.

7. A system for predicting the prognosis of severe cases of patients infected with the novel coronavirus caused by the variant strain of Omicron, characterized in that: The system comprises: A processor and a memory, wherein the memory is coupled to the processor, and the memory stores instructions. When the instructions are executed by the processor, the model described in claim 6 is used to calculate the detection results of the biomarker combination described in claim 1 to obtain a prediction of the severe outcome of patients infected with the new coronavirus caused by the Omicron variant.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the following steps are used: the detection results of the biomarker combination used to predict the severe disease outcome of patients infected with the new coronavirus caused by the Omicron variant are input into the system as described in claim 7, and the severe disease outcome of patients infected with the new coronavirus caused by the Omicron variant is obtained through calculation.

9. A product for predicting the prognosis of severe cases of patients infected with the novel coronavirus caused by the variant strain of Omicron, characterized in that: The product includes: the system for predicting the severity of the disease in patients infected with the new coronavirus caused by Omicron as described in claim 7 or the computer-readable storage medium as described in claim 8.

10. A product for predicting the severity of a patient infected with the novel coronavirus caused by an Omicron variant according to claim 1 according to claim 9, characterized in that: The products also include: biomarker combination detection reagents for predicting the severe outcome of patients infected with the new coronavirus caused by the Omicron variant.

Images