Biomarker combination and application thereof in prediction of esophageal cancer risk

Abstract

The invention discloses a biomarker combination and application thereof in predicting esophageal cancer risk. According to the application of the biomarker combination in preparation of a kit for predicting and / or diagnosing esophageal cancer, the biomarker combination is composed of 34 biomarkers. The invention also discloses a reagent for detecting the biomarker combination, a kit containing the biomarker combination and the reagent, and applications of the reagent and the kit. The biomarker combination provided by the invention can be used for risk estimation and detection of esophageal cancer patients, the realized sensitivity reaches 100%, the specificity reaches 100%, the biomarker combination has the advantages of high sensitivity and high specificity, and favorable technical support is provided for prediction of esophageal cancer occurrence and development.

Description

Technical Field

[0001] The present invention belongs to the field of biomedical technology and diagnosis, and specifically relates to a biomarker combination and its application in predicting the risk of esophageal cancer. Background Art

[0002] Esophageal cancer ranks fourth among the causes of death from malignant tumors, with 572,000 cases and 508,000 deaths worldwide each year.

[0003] Clinically, lesions can be detected early through B-ultrasound, CT examination, biopsy and pathological examination, and regular self-examination can also help to detect lesions early. However, these methods have disadvantages such as high false positive rate and late detection time.

[0004] At present, the prior art discloses a method for diagnosing esophageal cancer using 44 serum metabolites as markers (Patent Publication No.: CN112151121A), and the sensitivity, specificity and accuracy of the diagnosis are about 94%. Considering the limitations of using metabolites as diagnostic markers in practical operation and the sensitivity and specificity of diagnosis, a more convenient, more sensitive and accurate diagnostic method is urgently needed to achieve early cancer screening.

[0005] Proteomics plays an important role in revealing the complex molecular events of tumorigenesis, such as tumorigenesis, invasion, metastasis and tolerance to treatment. Proteomic tumor diagnosis has the advantages of high sensitivity, strong specificity and clear background mechanism, and has been increasingly used in tumor detection in recent years. Moreover, the research on these tumor markers is often based on a certain amount of experimental data, and the types of cancer involved and the sample size are relatively limited. In recent years, with the continuous development of proteomics, the big data of body fluid proteomics has continued to increase. Therefore, by collecting body fluid proteomics data and using big data analysis methods to find a tumor risk model with a wide range of applicability and high accuracy, it is helpful to achieve early diagnosis and has important clinical significance for early diagnosis and early treatment of patients. Summary of the invention

[0006] In view of the defect of the prior art that there is a lack of a technical solution for predicting the risk of esophageal cancer with a wide range of applications, high prediction accuracy, diagnostic sensitivity and specificity, the present invention provides a biomarker combination and its application in predicting the risk of esophageal cancer. The biomarker combination of the present invention has the advantages of high sensitivity and high specificity in predicting the risk of early esophageal cancer, provides favorable technical support for predicting the occurrence and development of esophageal cancer, has broad scientific research value and provides great convenience for early clinical diagnosis, intervention treatment, etc.

[0007] The present invention obtains a group of biomarkers capable of predicting the risk of esophageal cancer by screening body fluid proteomes. The screening method comprises the following steps:

[0008] (1) Collect body fluid samples from healthy people and patients with esophageal cancer;

[0009] (2) Protein preparation from body fluid samples of healthy people and esophageal cancer patients;

[0010] (3) Detect the expression levels of protein molecules in body fluid samples of healthy people and patients with esophageal cancer;

[0011] (4) Find the proteomic molecules that are highly expressed specifically in the body fluids of tumor patients and construct a classifier to distinguish them.

[0012] In order to solve the above technical problems, the present invention provides a technical solution: use of a biomarker combination in preparing a kit for predicting and / or diagnosing esophageal cancer;

[0013] Among them, the biomarker combination consists of ACTB, ACTG1, ALDH9A1, ARMC8, B3GAT3, CRP, DLG1, DSC3, DUSP3, EIF2B1, EIF5A2, EIF5AL1, GLO1, GP1BB, GSTO1, H1-10, H3-4, H3C1, H3C15, HSPA6, MMP10, MYL6B, MYOF, NAXD, NCALD, PCBP3, PLBD2, RCN1, RECK, RUVBL1, SAA1, SF3A3, SMC2 and SPG21.

[0014] To solve the above technical problems, the present invention provides a technical solution: a reagent for detecting a biomarker combination, wherein the biomarker combination consists of ACTB, ACTG1, ALDH9A1, ARMC8, B3GAT3, CRP, DLG1, DSC3, DUSP3, EIF2B1, EIF5A2, EIF5AL1, GLO1, GP1BB, GSTO1, H1-10, H3-4, H3C1, H3C15, HSPA6, MMP10, MYL6B, MYOF, NAXD, NCALD, PCBP3, PLBD2, RCN1, RECK, RUVBL1, SAA1, SF3A3, SMC2 and SPG21.

[0015] As described in the present invention, the reagent is used to detect the expression level of the biomarker combination; the expression level is the protein expression level and / or the mRNA transcription level.

[0016] As described in the present invention, the reagent is a biomolecular reagent that specifically binds to the biomarker or specifically hybridizes with the nucleic acid encoding the biomarker.

[0017] According to the reagent of the present invention, the biomolecule reagent is selected from the group consisting of primers, probes and antibodies.

[0018] The reagent according to the present invention is a reagent for genome, transcriptome and / or proteome sequencing.

[0019] In order to solve the above technical problems, the present invention provides a technical solution: use of a reagent for detecting a combination of biomarkers in the preparation of a kit for predicting and / or diagnosing esophageal cancer;

[0020] Among them, the biomarker combination consists of ACTB, ACTG1, ALDH9A1, ARMC8, B3GAT3, CRP, DLG1, DSC3, DUSP3, EIF2B1, EIF5A2, EIF5AL1, GLO1, GP1BB, GSTO1, H1-10, H3-4, H3C1, H3C15, HSPA6, MMP10, MYL6B, MYOF, NAXD, NCALD, PCBP3, PLBD2, RCN1, RECK, RUVBL1, SAA1, SF3A3, SMC2 and SPG21.

[0021] According to the use described in the present invention, the reagent is as described in the present invention.

[0022] To solve the above technical problems, the present invention provides a technical solution: a biomarker combination, wherein the biomarker combination consists of ACTB, ACTG1, ALDH9A1, ARMC8, B3GAT3, CRP, DLG1, DSC3, DUSP3, EIF2B1, EIF5A2, EIF5AL1, GLO1, GP1BB, GSTO1, H1-10, H3-4, H3C1, H3C15, HSPA6, MMP10, MYL6B, MYOF, NAXD, NCALD, PCBP3, PLBD2, RCN1, RECK, RUVBL1, SAA1, SF3A3, SMC2 and SPG21.

[0023] In order to solve the above technical problems, the present invention provides a technical solution: a kit, which comprises the reagent as described in the present invention and the biomarker combination as described in the present invention.

[0024] To solve the above technical problems, the present invention provides a technical solution: a method for detecting esophageal cancer for non-diagnostic purposes, the method comprising detecting the expression level of a combination of biomarkers in a sample to be tested;

[0025] wherein the biomarker combination consists of ACTB, ACTG1, ALDH9A1, ARMC8, B3GAT3, CRP, DLG1, DSC3, DUSP3, EIF2B1, EIF5A2, EIF5AL1, GLO1, GP1BB, GSTO1, H1-10, H3-4, H3C1, H3C15, HSPA6, MMP10, MYL6B, MYOF, NAXD, NCALD, PCBP3, PLBD2, RCN1, RECK, RUVBL1, SAA1, SF3A3, SMC2, and SPG21;

[0026] The expression level is protein expression level and / or mRNA transcription level.

[0027] In the present invention, the "non-diagnostic purpose" refers to the purpose of scientific research and pathological data statistics, and applicable scenarios include verifying whether the animal model is successfully constructed, in vitro drug efficacy experiments, epidemiological statistics of tumors, etc.

[0028] In order to solve the above technical problems, the present invention provides a technical solution: a prediction system for esophageal cancer risk, the prediction system comprising: a detection module and an analysis and judgment module;

[0029] The detection module detects the expression level of the biomarker combination in the sample to be tested, and transmits the expression level data to the analysis and judgment module;

[0030] The analysis and judgment module processes the expression level data through Firmiana software, and the expression level data is preferably FOT (Fraction of total, defined as the iBAQ of the protein divided by the total iBAQ of all identified proteins in the sample), and is preset as a machine learning algorithm based on a generalized linear regression model, and a prediction model is constructed to predict the probability of the sample suffering from esophageal cancer and the probability of not suffering from esophageal cancer, respectively, and judge whether the expression level data meets the preset judgment condition to predict the risk of the sample suffering from esophageal cancer, and output the prediction result; the judgment condition is that the probability of suffering from esophageal cancer is greater than or equal to the probability of not suffering from esophageal cancer;

[0031] When the expression level data meets the judgment condition, the output prediction result is "having esophageal cancer risk"; when the expression level data does not meet the judgment condition, that is, the probability of suffering from esophageal cancer is less than the probability of not suffering from esophageal cancer, the output prediction result is "not having esophageal cancer risk";

[0032] wherein the biomarker combination consists of ACTB, ACTG1, ALDH9A1, ARMC8, B3GAT3, CRP, DLG1, DSC3, DUSP3, EIF2B1, EIF5A2, EIF5AL1, GLO1, GP1BB, GSTO1, H1-10, H3-4, H3C1, H3C15, HSPA6, MMP10, MYL6B, MYOF, NAXD, NCALD, PCBP3, PLBD2, RCN1, RECK, RUVBL1, SAA1, SF3A3, SMC2, and SPG21;

[0033] The expression level is protein expression level and / or mRNA transcription level.

[0034] In some embodiments of the present invention, the prediction system is used to process the expression level data through Firmiana software after the receiving or input is completed, and a machine learning algorithm based on a generalized linear regression model is preset to construct a prediction system.

[0035] According to the prediction system of the present invention, the sample to be tested is a human plasma sample.

[0036] As described in the prediction system of the present invention, the prediction system also includes a data collection module for collecting data on the expression level of the biomarker combination in the sample to be tested, and the expression level data is preferably FOT (Fraction of total, defined as the iBAQ of the protein divided by the total iBAQ of all identified proteins in the sample).

[0037] To solve the above technical problems, the present invention provides a technical solution: a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the functions of the prediction system described in the present invention, or implement the steps of the method described in the present invention.

[0038] In the present invention, the readable storage medium may more specifically include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0039] In a possible implementation, the present invention can also be implemented in the form of a program product, which includes a program code. When the program product runs on a terminal device, the program code is used to enable the terminal device to execute the functions of the prediction system as described in the present invention, or to implement the steps of the method as described in the present invention.

[0040] The program code for executing the present invention may be written in any combination of one or more programming languages, and may be executed entirely on a user device, partially on a user device, as an independent software package, partially on a user device and partially on a remote device, or entirely on a remote device.

[0041] To solve the above technical problems, the present invention provides a technical solution: an electronic device, which can be expressed in the form of a computing device (for example, a server device), comprising a memory and a processor, the memory storing a computer program, and the processor being used to execute the computer program to implement the functions of the prediction system as described in the present invention, or to implement the steps of the method as described in the present invention.

[0042] The electronic device can further communicate with one or more external devices (e.g., keyboard, pointing device, etc.). Such communication can be performed through an input / output (I / O) interface. In addition, the electronic device can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) through a network adapter. The network adapter communicates with other modules of the electronic device through a bus. It is known in the art that other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0043] The division of features and functions of the units / modules or sub-units / modules of the electronic device described in the present invention may be specific according to the conventional practice in the art.

[0044] On the basis of being in accordance with the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present invention.

[0045] The reagents and raw materials used in the present invention are commercially available.

[0046] The positive and progressive effects of the present invention are:

[0047] The above-mentioned protein molecular markers provided by the present invention have been found through experiments to have significant changes in expression levels in body fluid samples of tumor patients and healthy people. Therefore, the body fluid protein molecular markers provided by the present invention can be used for risk estimation and detection of tumor patients, and have the advantages of high sensitivity and high specificity, providing favorable technical support for predicting the occurrence and development of esophageal cancer.

[0048] The development of a corresponding prediction device based on protein molecular markers of body fluid samples of healthy people and esophageal cancer patients has broad scientific research value and provides great convenience for early clinical diagnosis, intervention treatment, etc. The 34 marker combinations provided by the present invention have achieved a sensitivity of 100% and a specificity of 100%. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 Schematic diagram of the area under the ROC curve of the marker combination in the training set.

[0050] Figure 2 Schematic diagram of the area under the ROC curve of the marker combination in the test set.

[0051] Figure 3 Schematic diagram of the area under the ROC curve of the marker combination in the external validation set.

[0052] Figure 4 Schematic diagram of the system for predicting esophageal cancer.

[0053] Figure 5 A schematic diagram of the structure of an electronic device. DETAILED DESCRIPTION

[0054] The present invention is further described below by way of examples, but the present invention is not limited to the scope of the examples. The experimental methods in the following examples without specifying specific conditions are carried out according to conventional methods and conditions, or selected according to the product specifications.

[0055] The present invention includes plasma samples from 114 normal people and 44 patients with esophageal cancer. The design and implementation of this study have been approved and supervised by ethics committees, and written informed consent has been obtained from all patients.

[0056] Example 1 Screening and validation of a combination of biomarkers for predicting esophageal cancer risk

[0057] 1.1 Separation of plasma

[0058] Collect whole blood samples in EDTA anticoagulant tubes, mix by inversion, and centrifuge at 1,600×g for 10 min in a 4°C low-temperature centrifuge. Collect the supernatant (plasma) into new EP tubes after centrifugation at 16,000×g for 10 min to remove cell debris. Dispense the plasma into centrifuge tubes and freeze at -80°C for later use.

[0059] 1.2 Plasma sample pretreatment

[0060] Add 100uL 50mM ammonium bicarbonate to 2μL plasma sample, vortex mix for 1min, heat and incubate the sample at 95℃ for 4min to denature the protein, cool to room temperature, add 2μg trypsin to the system, oscillate at 37℃ for 18h, and then add 10μL ammonia water to the system to stop enzymatic hydrolysis. Desalt the peptide samples after enzymatic hydrolysis, drain, and freeze at -80℃ until mass spectrometry detection.

[0061] 1.3 Mass spectrometry detection of plasma samples

[0062] The Orbitrap Fusion Lumos three-in-one high-resolution mass spectrometry system (Thermo Fisher Scientific, Rockford, USA) was used in series with a high-performance liquid chromatography system (EASY-nLC 1200, Thermo Fisher) to obtain the mass spectrometry data of the whole protein corresponding to the peptide sample. The specific operation was as follows:

[0063] Nanoflow liquid chromatography was used, and the chromatographic column was a homemade C18 chromatographic column (150 μm ID×8 cm, 1.9 μm / Filler). The column oven temperature was 60°C. The dry powder peptide was reconstituted with loading buffer (0.1% formic acid in water), loaded and separated by chromatographic column, eluted with 600nL / min linear 6–30% mobile phase B (ACN and 0.1% formic acid), and a 10-min liquid phase gradient was combined with data-independent acquisition (DIA) mass spectrometry detection. The DIA mass spectrometry detection parameters were set as follows: ion mode was positive ion; primary mass spectrometry resolution was 30K, maximum injection time was 20ms, AGC Target was 3e6, and the scanning range was 300-1400m / z; secondary scanning resolution was 15K, 30 variable isolation windows were acquired, and collision energy was 27%. The liquid chromatography tandem mass spectrometry system was controlled by Xcalibur software for data acquisition.

[0064] 1.4 Data Analysis

[0065] All data were processed using Firmiana (V1.0). Firmiana is a workflow based on the Galaxy system, consisting of multiple functional modules such as user login interface, raw data, identification and quantification, data analysis and knowledge mining. The DIA data were searched using DIANN (v12.1) against the UniProt human protein database (updated on 2019.12.17, 20406 entries). The mass difference of the parent ion is 20ppm, and the mass difference of the daughter ion is 50mmu. A maximum of two missed cleavage sites are allowed. The search engine sets cysteine ​​carbamidomethylation as a fixed modification and methionine N-acetylation and oxidation as variable modifications. The parent ion charge range is set to +2, +3 and +4. The false discovery rate (FDR) is set to 1%. The results of the DIA data were merged into the reference library using SpectraST software. A total of 327 libraries were used as reference libraries.

[0066] The quantitative results of the identified peptides were recorded as the average of the peak areas of the chromatographic fragment ions in all reference spectral libraries. Protein quantification was performed using the label-free intensity-based absolute quantification (iBAQ) method. The peak area values ​​were calculated as part of the corresponding protein. The total fraction (FOT) is used to represent the standardized abundance of a specific protein in a sample. FOT is defined as the iBAQ of a protein divided by the total iBAQ of all identified proteins in the sample. Proteins with at least one unique peptide and a 1% FDR were selected. The FOT of each protein was calculated and the FOT of each protein was input into the generalized linear regression model as protein expression data.

[0067] The Firmiana selected in this embodiment is preset as a machine learning algorithm based on a generalized linear regression model to build a prediction model to predict the probability of a sample suffering from esophageal cancer and the probability of not suffering from esophageal cancer. The code for building the prediction model is:

[0068]

[0069] The experiment found that the expression levels of some proteins in the body fluid samples of tumor patients and healthy people were significantly changed. The relative expression levels of 34 protein molecular markers (ACTB, ACTG1, ALDH9A1, ARMC8, B3GAT3, CRP, DLG1, DSC3, DUSP3, EIF2B1, EIF5A2, EIF5AL1, GLO1, GP1BB, GSTO1, H1-10, H3-4, H3C1, H3C15, HSPA6, MMP10, MYL6B, MYOF, NAXD, NCALD, PCBP3, PLBD2, RCN1, RECK, RUVBL1, SAA1, SF3A3, SMC2, SPG21) in the plasma samples of esophageal cancer patients were plotted to draw ROC curves (Receiver Operating Curve) and calculate AUC (Area Under the ROC Curve), where the training set includes 22 positive cases and 55 negative cases, AUC = 1.00, diagnostic sensitivity 100.00%, and specificity 100.00% (see Figure 1 ); the test set includes 9 positive cases and 24 negative cases, AUC = 1.00, diagnostic sensitivity 100%, specificity 100% (see Figure 2 ); the external validation set included 13 positive cases and 35 negative cases, AUC = 0.94, diagnostic sensitivity 76.92%, specificity 94.29% (see Figure 3 ). For modeling and analysis methods, see Hajian-Tilaki K. Receiver Operating Characteristic (ROC) Curve Analysis for Medical Diagnostic Test Evaluation. Caspian J Intern Med. 2013; 4(2): 627-635. The FOT values ​​of 34 protein markers in the training set, test set, and external validation set are shown in Tables 2-4, 5-7, and 8-10, respectively.

[0070] For unknown samples, the expression levels of the above biomarkers are substituted into the model to obtain the esophageal cancer risk prediction of the sample and output the result. When the probability of having esophageal cancer is greater than or equal to the probability of not having esophageal cancer, the output prediction result is "having the risk of esophageal cancer"; when the probability of having esophageal cancer is less than the probability of not having esophageal cancer, the output prediction result is "not having the risk of esophageal cancer".

[0071] Table 1 Protein information list of all markers

[0072]

[0073]

[0074] The Gene IDs of the markers in Table 1 can be retrieved from the biological database National Center for Biotechnology Information (https: / / www.ncbi.nlm.nih.gov / ).

[0075] From the above results, it can be seen that the combination of 34 protein molecular markers in the plasma of cancer patients (ACTB, ACTG1, ALDH9A1, ARMC8, B3GAT3, CRP, DLG1, DSC3, DUSP3, EIF2B1, EIF5A2, EIF5AL1, GLO1, GP1BB, GSTO1, H1-10, H3-4, H3C1, H3C15, HSPA6, MMP10, MYL6B, MYOF, NAXD, NCALD, PCBP3, PLBD2, RCN1, RECK, RUVBL1, SAA1, SF3A3, SMC2, SPG21) can be used to predict tumor risk.

[0076] Table 2 FOT values ​​of 34 protein markers in the training set

[0077]

[0078]

[0079] Table 3 FOT values ​​of 34 protein markers in the training set

[0080]

[0081]

[0082] Table 4 FOT values ​​of 34 protein markers in the training set

[0083]

[0084]

[0085]

[0086] Table 5 FOT values ​​of 34 protein markers in the test set

[0087]

[0088]

[0089] Table 6 FOT values ​​of 34 protein markers in the test set

[0090]

[0091] Table 7 FOT values ​​of 34 protein markers in the test set

[0092]

[0093]

[0094] Table 8 FOT values ​​of 34 protein markers in the external validation set

[0095]

[0096]

[0097] Table 9 FOT values ​​of 34 protein markers in the external validation set

[0098]

[0099]

[0100] Table 10 FOT values ​​of 34 protein markers in the external validation set

[0101]

[0102]

[0103] Example 2 System for predicting esophageal cancer risk

[0104] The system 61 for predicting esophageal cancer includes a detection module 51 and an analysis and judgment module 52, and also includes a data collection module 53 ( Figure 4 ).

[0105] The detection module 51 detects the expression level of the biomarker combination in the sample to be tested, and transmits the expression level data to the analysis and judgment module 52 .

[0106] The analysis and judgment module 52 processes the expression level data through the Firmiana software, which is preset as a machine learning algorithm based on a generalized linear regression model, constructs a prediction model, predicts the probability of the sample suffering from esophageal cancer and the probability of not suffering from esophageal cancer, respectively, judges whether the expression level data meets the preset judgment conditions to predict the risk of the sample suffering from esophageal cancer, and outputs the prediction result; the judgment condition is that the probability of suffering from esophageal cancer is greater than or equal to the probability of not suffering from esophageal cancer.

[0107] When the expression level data meets the judgment condition, the output prediction result is "having the risk of esophageal cancer"; when the expression level data does not meet the judgment condition, that is, the probability of having esophageal cancer is less than the probability of not having esophageal cancer, the output prediction result is "not having the risk of esophageal cancer".

[0108] The data collection module 53 is used to collect data on the expression level of the biomarker combination in the sample to be tested.

[0109] Embodiment 3 Electronic device

[0110] This embodiment provides an electronic device, which can be expressed in the form of a computing device (for example, a server device), including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the method for predicting esophageal cancer in Embodiment 1 of the present invention can be implemented when the processor executes the computer program.

[0111] Figure 5 The hardware structure diagram of this embodiment is shown, and the electronic device 9 specifically includes:

[0112] At least one processor 91, at least one memory 92, and a bus 93 for connecting different system components (including the processor 91 and the memory 92), wherein:

[0113] The bus 93 includes a data bus, an address bus, and a control bus.

[0114] The memory 92 includes a volatile memory, such as a random access memory (RAM) 921 and / or a cache memory 922 , and may further include a read-only memory (ROM) 923 .

[0115] Memory 92 also includes a program / utility 925 having a set (at least one) of program modules 924, such program modules 924 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0116] The processor 91 executes various functional applications and data processing by running the computer programs stored in the memory 92, such as the data analysis method of embodiment 1 of the present invention.

[0117] The electronic device 9 can further communicate with one or more external devices 94 (e.g., keyboards, pointing devices, etc.). Such communication can be performed through an input / output (I / O) interface 95. In addition, the electronic device 9 can also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter 96. The network adapter 96 communicates with other modules of the electronic device 9 through a bus 93. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 9, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0118] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0119] Embodiment 4 Computer readable storage medium

[0120] The embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method for predicting esophageal cancer in Embodiment 1 of the present invention are implemented.

[0121] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0122] In a possible implementation, the present invention can also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of the method for predicting esophageal cancer in Example 1 of the present invention.

[0123] The program code for executing the present invention may be written in any combination of one or more programming languages, and may be executed entirely on a user device, partially on a user device, as an independent software package, partially on a user device and partially on a remote device, or entirely on a remote device.

[0124] Finally, the above specific implementation method is only used to illustrate the technical solution of the present invention, but not to limit it.

Claims

1. A reagent for detecting a combination of biomarkers, characterized in that: The biomarker panel consists of ACTB, ACTG1, ALDH9A1, ARMC8, B3GAT3, CRP, DLG1, DSC3, DUSP3, EIF2B1, EIF5A2, EIF5AL1, GLO1, GP1BB, GSTO1, H1-10, H3-4, H3C1, H3C15, HSPA6, MMP10, MYL6B, MYOF, NAXD, NCALD, PCBP3, PLBD2, RCN1, RECK, RUVBL1, SAA1, SF3A3, SMC2, and SPG21; Preferably, the reagent is used to detect the expression level of the biomarker combination, and the expression level is the protein expression level and / or the mRNA transcription level; More preferably, the reagent is a biomolecular reagent that specifically binds to the biomarker, or specifically hybridizes with the nucleic acid encoding the biomarker, and the biomolecular reagent is preferably selected from primers, probes and antibodies; and / or, the reagent is a reagent for genome, transcriptome and / or proteome sequencing.

2. A biomarker combination, characterized in that: The combination of biomarkers consists of ACTB, ACTG1, ALDH9A1, ARMC8, B3GAT3, CRP, DLG1, DSC3, DUSP3, EIF2B1, EIF5A2, EIF5AL1, GLO1, GP1BB, GSTO1, H1-10, H3-4, H3C1, H3C15, HSPA6, MMP10, MYL6B, MYOF, NAXD, NCALD, PCBP3, PLBD2, RCN1, RECK, RUVBL1, SAA1, SF3A3, SMC2 and SPG21.

3. A kit, characterized in that: The kit comprises the reagent according to claim 1 and the biomarker combination according to claim 2.

4. Use of the reagent according to claim 1, the biomarker combination according to claim 2, or the kit according to claim 3 in the preparation of a product for predicting and / or diagnosing esophageal cancer.

5. A prediction system for esophageal cancer risk, characterized in that: The prediction system comprises: Detection module and analysis and judgment module; The detection module detects the expression level of the biomarker combination in the sample to be tested, and transmits the expression level data to the analysis and judgment module; The analysis and judgment module processes the expression level data through the Firmiana software, which is preset as a machine learning algorithm based on a generalized linear regression model, constructs a prediction model, predicts the probability of the sample suffering from esophageal cancer and the probability of not suffering from esophageal cancer, respectively, judges whether the expression level data meets the preset judgment condition, so as to predict the risk of the sample suffering from esophageal cancer, and outputs the prediction result; the judgment condition is that the probability of suffering from esophageal cancer is greater than or equal to the probability of not suffering from esophageal cancer; When the expression level data meets the judgment condition, the output prediction result is "having esophageal cancer risk"; when the expression level data does not meet the judgment condition, that is, the probability of suffering from esophageal cancer is less than the probability of not suffering from esophageal cancer, the output prediction result is "not having esophageal cancer risk"; Wherein, the biomarker combination consists of ACTB, ACTG1, ALDH9A1, ARMC8, B3GAT3, CRP, DLG1, DSC3, DUSP3, EIF2B1, EIF5A2, EIF5AL1, GLO1, GP1BB, GSTO1, H1-10, H3-4, H3C1, H3C15, HSPA6, MMP10, MYL6B, MYOF, NAXD, NCALD, PCBP3, PLBD2, RCN1, RECK, RUVBL1, SAA1, SF3A3, SMC2 and SPG21; the expression level is protein expression level and / or mRNA transcription level; Preferably, the sample to be tested is a human plasma sample; and / or, the prediction system further comprises a data collection module for collecting data on the expression level of the biomarker combination in the sample to be tested.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the functions of the prediction system according to claim 5 can be realized.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: The processor is configured to execute the computer program to implement the functions of the prediction system according to claim 5.

Images