A biomarker, kit, system and application for screening or diagnosing early-stage liver cancer

Abstract

The present invention provides markers, kits, systems and applications for screening or diagnosing early-stage liver cancer. The markers include any one of AK2, DCTN2, DKK4, IFNGR1, TIMM10 or Galectin4 proteins. The marker group includes any combination of AK2, DCTN2, DKK4, IFNGR1, TIMM10 or Galectin4 proteins. The method for constructing the model includes the following steps: S1, determining the training set, test set samples and validation set samples, all of which include healthy person samples, liver cirrhosis patient samples and liver cancer patient samples; S2, determining the protein biomarker / biomarker group and component weights; S3, training a classification algorithm using the training set and test set samples; S4, using the Youden index as the best threshold for distinguishing liver cancer and non-liver cancer individuals, and using the Youden index as the best threshold for distinguishing liver cirrhosis and very early-stage liver cancer individuals; S5, using the validation set samples to evaluate and optimize the performance of the classification algorithm model. The markers provided by the present invention can efficiently and sensitively screen or diagnose early-stage liver cancer.

Description

Technical Field

[0001] The present invention relates to a biomarker, kit, system and application for screening or diagnosing early-stage liver cancer, and belongs to the field of biomedical technology. Background Art

[0002] Hepatocellular carcinoma (HCC) is a common primary liver cancer in China, with a high degree of malignancy. Once discovered, it is basically in the advanced stage and the prognosis is relatively poor. In the early stage of liver cancer, due to its low degree of malignancy, the prognosis of patients is relatively good after treatment. Existing research indicates that focused detection of high-risk populations of hepatocellular carcinoma will significantly improve the survival rate of HCC patients.

[0003] Currently, the commonly used detection methods for liver cancer include alpha fetoprotein (AFP), ultrasound (US), multi-phase dynamic enhanced computed tomography (CT) and / or dynamic contrast-enhanced magnetic resonance imaging (MRI), digital subtraction angiography (DSA), etc.

[0004] Among them, a continuously elevated serum biomarker AFP level usually indicates the occurrence of liver cancer and is a biomarker for liver cancer. The liver cancer diagnostic model based on AFP is also an important method for early liver cancer diagnosis commonly used in the prior art.

[0005] The ASAP early liver cancer diagnostic model consists of four variables: gender, age, AFP, and PIVKA-II, and the ASAP early liver cancer diagnostic model has a relatively high diagnostic value in patients with hepatocellular carcinoma (HCC).

[0006] The GALAD model established by Johnson et al. includes AFP (alpha fetoprotein), AFP-L3 (alpha fetoprotein isoform L3), des-gamma-carboxyprothrombin (DCP), gender, and age, and has a very high diagnostic efficiency in patients with liver cancer and early-stage liver cancer, significantly higher than the single or combined detection of AFP, AFP-L3, and DCP.

[0007] The present invention aims to discover more early liver cancer biomarkers and further explore new diagnostic models to achieve early screening and diagnosis of liver cancer. Summary of the Invention

[0008] The present invention provides 6 new early liver cancer biomarkers, and further prepares a highly efficient and sensitive classification algorithm model for screening or diagnosing early liver cancer, providing new indicators and methods for the screening and diagnosis of early liver cancer.

[0009] To achieve this objective, the present invention provides the following technical solutions:

[0010] In the first aspect of the present invention, there is provided the use of a capture reagent for detecting a protein biomarker / biomarker panel in the preparation of a reagent for screening or diagnosing early liver cancer, characterized in that the protein biomarker includes any one of AK2, DCTN2, DKK4, IFNGR1, TIMM10 or Galectin4 proteins; the protein biomarker panel includes any combination of AK2, DCTN2, DKK4, IFNGR1, TIMM10 or Galectin4 proteins.

[0011] In the present invention, a group of early liver cancer plasma biomarker proteins is provided, including AFP, AK2, DCTN2, DKK4, IFNGR1, TIMM10 and Galectin4 proteins, wherein AFP is a known liver cancer biomarker, and AK2, DCTN2, DKK4, IFNGR1, TIMM10 and Galectin4 are newly discovered liver cancer plasma biomarkers of the present invention.

[0012] Preferably, the protein biomarker panel further includes AFP.

[0013] More preferably, the protein biomarker panel includes: AK2, DCTN2, DKK4, IFNGR1, TIMM10, Galectin4 and AFP proteins.

[0014] Preferably, the detection includes in vitro detection of the concentration of the biomarker / biomarker panel in a biological sample, and the biological sample includes peripheral blood and plasma.

[0015] More preferably, the biological sample is a plasma sample.

[0016] In the second aspect of the present invention, there is provided a kit for screening or diagnosing early liver cancer, including a capture reagent for detecting a protein biomarker / biomarker panel, the protein biomarker includes any one of AK2, DCTN2, DKK4, IFNGR1, TIMM10 or Galectin4 proteins; the protein biomarker panel includes any combination of AK2, DCTN2, DKK4, IFNGR1, TIMM10 or Galectin4 proteins.

[0017] Preferably, the protein biomarker panel further includes AFP.

[0018] Further preferably, the protein biomarker group includes: AK2, DCTN2, DKK4, IFNGR1, TIMM10, Galectin4, and AFP protein.

[0019] Preferably, the capture reagent includes a biotinylated antibody.

[0020] Preferably, the detection includes in vitro detection of the concentration of the biomarker / biomarker group in a biological sample, and the biological sample includes peripheral blood and plasma.

[0021] Further preferably, the biological sample is a plasma sample.

[0022] Preferably, the kit further includes reagents and devices for detecting plasma proteins, and can simultaneously detect the concentrations of multiple plasma proteins, including a sample acquisition device, a sample plasma concentration detection device, a sample plasma protein concentration real-time display device, etc.

[0023] In a third aspect of the present invention, a method for constructing a classification algorithm model for screening or diagnosing early liver cancer is provided, including the following steps:

[0024] S1. Determine the training set, test set samples, and validation set samples, all of which include samples of healthy individuals, liver cirrhosis patients, and liver cancer patients;

[0025] S2. Determine the protein biomarker / biomarker group and component weights;

[0026] S3. Train the classification algorithm using the training set and test set samples;

[0027] S4. Make ROC curves for liver cancer patients and non-liver cancer individuals in the test set, and use the Youden index as the best threshold for distinguishing liver cancer and non-liver cancer individuals; make ROC curves for very early liver cancer and liver cirrhosis individuals in the prospective cohort, and use the Youden index as the best threshold for distinguishing liver cirrhosis and very early liver cancer individuals;

[0028] S5. Use the validation set samples to evaluate and optimize the performance of the classification algorithm model.

[0029] Preferably, the classification algorithm model is a random forest model, and step S3 includes: establishing 100 - 200 decision trees in the training set, using the R language as the program, using the randomForest package, setting the number of decision trees to 100 - 200; setting the number of branches to 3 - 5.

[0030] Preferably, the protein biomarker includes any one of AFP, AK2, DCTN2, DKK4, IFNGR1, TIMM10 or Galectin4 protein; the protein biomarker group includes any combination of AFP, AK2, DCTN2, DKK4, IFNGR1, TIMM10 or Galectin4 protein; and the weight ratio of AFP, AK2, DCTN2, DKK4, IFNGR1, TIMM10, Galectin4 is: (3 - 2):(2 - 1):(2 - 1):(2.5 - 1.5):(1.5 - 0.8):(1.5 - 1):(1.5 - 1).

[0031] More preferably, the protein biomarker group includes: AK2, DCTN2, DKK4, IFNGR1, TIMM10, Galectin4 and AFP protein.

[0032] More preferably, the weight ratio of AFP, AK2, DCTN2, DKK4, IFNGR1, TIMM10, Galectin4 is: 2.11:1.52:1.32:1.89:0.94:1.03:1.17.

[0033] Preferably, the optimal threshold for distinguishing liver cancer and non - liver cancer individuals is 0.329, and the optimal threshold for distinguishing liver cirrhosis and very early - stage liver cancer individuals is 0.338.

[0034] In the fourth aspect of the present invention, there is provided an early - stage liver cancer diagnosis system based on a classification algorithm, including: a processor and a memory. The processor can process sample information according to the classification algorithm model described in the present invention, including inputting the parameters of the protein biomarker / biomarker group of the individual to be tested into the classification algorithm model in the processor; the classification algorithm model in the processor evaluates the liver cancer risk value of the sample to be tested and outputs a risk assessment result by comparing with the threshold; the memory is used to store threshold data information and assessment result information.

[0035] Preferably, the memory includes but is not limited to Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read - Only Memory (PROM), Erasable Programmable Read - Only Memory (EPROM), Electrically Erasable Programmable Read - Only Memory (EEPROM), etc.

[0036] Preferably, the processor may be an integrated circuit chip with signal processing capabilities. The processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; or it may be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FGPA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0037] Preferably, the diagnostic system may be a device such as a server, a cloud platform, a mobile phone, a tablet computer, a laptop computer, an ultra-mobile personal computer (UMPC), a handheld computer, a netbook, a personal digital assistant (PDA), a wearable electronic device, a virtual reality device, etc.

[0038] Compared with the prior art, the beneficial effects and remarkable progress of applying the technical solution of the present invention are as follows: The present invention uses AFP in combination with six other indicators and establishes an early liver cancer warning and diagnosis model. Compared with the existing early liver cancer diagnosis technologies, it has the advantages of high sensitivity and good specificity, and can realize the warning of extremely early liver cancer. Compared with the existing liver cancer markers or early diagnosis models, the warning time can be advanced by more than half a year. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments of the present invention will be briefly introduced below.

[0040] Figure 1 Plasma concentrations of seven markers for healthy people, liver cirrhosis patients, and early liver cancer patients in Example 1.

[0041] Figure 2 Flowchart for constructing the early liver cancer detection model in Example 3;

[0042] Figure 3 Weights of each marker in the early liver cancer diagnosis model in Example 3;

[0043] Figure 4 Number of random forest classification trees and their error values in Example 3;

[0044] Figure 5 For the ROC curves and optimal thresholds of liver cancer and non-liver cancer in Example 3;

[0045] Figure 6 For the ROC curves and optimal thresholds of liver cirrhosis and very early-stage liver cancer in Example 3;

[0046] Figure 7 For the diagnostic model risk scores (RiskScore) of healthy people, liver cirrhosis patients, very early-stage liver cancer patients, and early-stage liver cancer patients in Example 3;

[0047] Figure 8 For the results statistics of the integrated model in Example 4 and the bar chart of the AUC of the results related to liver cancer indicators (AFP) in the test set and validation set to compare the classification results of liver cancer;

[0048] Figure 9 For the results statistics of the integrated model in Example 5 and the comparison of the AUC values of the very early-stage liver cancer prediction effect compared with known liver cancer prediction models or clinical indicators. It includes the known ASAP early liver cancer diagnosis model, PIVKA-II indicator, Galad model, and AFP indicator. It can be seen from the AUC values that the RiskScore integrated model has the highest accuracy;

[0049] Figure 10 For the results statistics of the integrated model in Example 6 and the comparison of the positive prediction rates for the transformation of late-stage liver cirrhosis to liver cancer compared with known liver cancer prediction models or clinical indicators. Detailed implementation manners

[0050] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the present invention will be further described below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and not to limit the scope of the present invention. The experimental methods without specific conditions noted in the following embodiments are usually carried out under conventional conditions or according to the conditions recommended by the manufacturer. Unless otherwise specified, percentages and parts are weight percentages and weight parts. The experimental materials and reagents used in the following embodiments can be obtained from commercial channels without special instructions.

[0051] Unless otherwise specified, the technical and scientific terms used herein have the same meanings as those commonly understood by those of ordinary skill in the technical field to which this application belongs. It should be noted that the terms used herein are only for describing specific implementation manners and are not intended to limit the exemplary embodiments of this application.

[0052] To more fully understand the present invention, the following explains the professional terms in the present invention.

[0053] AFP is alpha-fetoprotein, a special protein present in the blood during embryonic development. It is synthesized only in the liver cells of the fetus, especially during the 16th to 20th week of pregnancy when the protein content in the fetus is the highest, reaching 300 - 400 milligrams per 100 milliliters of blood. It then gradually decreases and completely disappears one week after birth. Since it only exists in the blood of the fetus, it is called alpha-fetoprotein. Normal liver cells do not produce alpha-fetoprotein. However, when a person has liver cancer, due to the unrestricted growth and deterioration of the immature liver cells, the ability to synthesize alpha-fetoprotein is restored, and sometimes it can reach a level of 1000 milligrams per 100 milliliters of blood. This is the reason why detecting alpha-fetoprotein can assist in diagnosing liver cancer.

[0054] AK2 is adenylate kinase 2 protein.

[0055] DCTN2 is dynactin 2.

[0056] DKK4 is dickkopf WNT signaling pathway inhibitor 4.

[0057] IFNGR1 is interferon gamma receptor 1.

[0058] TIMM10 is translocase of inner mitochondrial membrane 10.

[0059] Galectin4 is galectin 4.

[0060] A kit refers to a box used to hold chemical reagents for detecting chemical components, drug residues, or virus types, etc. It is generally used in hospitals, inspection and quarantine departments, or pharmaceutical enterprises. A kit is an important tool in chemical analysis experiments, and its function is to detect and analyze the substances contained in the sample. In biochemical detection, a kit is also an important method for detecting diseases. Kits can be used in detection methods such as enzyme-linked immunosorbent assay (ELISA) and immunoassay.

[0061] Example 1 Screening of Diagnostic Markers for Early Liver Cancer

[0062] In this example, the protein concentrations in the plasma of three groups of people (healthy individuals, liver cirrhosis patients, and early liver cancer patients) were detected, and 7 biomarkers related to early liver cancer were screened.

[0063] 1.1 Plasma Separation: Collect peripheral blood using a disposable pyrogen-free and endotoxin-free tube (EDTA, citrate, or heparin anticoagulation is acceptable). Avoid using hemolyzed or hyperlipidemic samples. Centrifuge to remove suspended matter in the specimen to make it clear and transparent. The plasma to be tested should be detected as soon as possible. It can be stored at 2 - 8°C for 48 hours, and for longer periods, it must be stored frozen (-20°C or -80°C) to avoid repeated freeze-thaw cycles.

[0064] 1.2. Centrifuge the collected peripheral blood samples at 3000 rpm for 10 minutes.

[0065] 1.3. Aliquot the obtained plasma into 1.5 ml EP tubes.

[0066] 1.4. Standard preparation: Take 8 1.5 ml centrifuge tubes, label them S1, S2, S3, S4, S5, S6, S7, blank respectively. Add 900 μl of standard / sample diluent to the first tube S1, and add 200 μl of standard / sample diluent to the second to eighth tubes respectively. Add 100 μl of standard solution (100.0 ng / ml) to the first tube, mix well on a vortex mixer, then aspirate 200 μl with a pipette and transfer it to the second tube. Repeat the two-fold dilution in this way until S7.

[0067] 1.5. Preparation of biotinylated antibody working solution: 20 minutes before use, dilute the 100× biotinylated antibody with biotinylated antibody diluent to 1× working solution according to the required amount. Prepare it on the day of use and discard the remainder.

[0068] 1.6. Preparation of TMB chromogenic solution: 10 minutes before use, mix TMB chromogenic solution A and B in a ratio of 1:1 and store in the dark for later use.

[0069] 1.7. Detection procedure:

[0070] 1) Sample addition: Add 50 μl of standard / sample diluent to the blank well, and add 50 μl of standard or test sample to the other wells. Mix the reaction plate and incubate at 37°C for 50 minutes.

[0071] 2) Plate washing: Wash the reaction plate thoroughly 3 times with 1× washing solution. Add 300 μl of 1× washing solution to each well, shake / soak for 1 - 2 minutes each time, and blot dry on filter paper.

[0072] 3) Add 100 μl of biotinylated antibody diluent to the blank well, and add 100 μl of 1× biotinylated antibody working solution to the other wells. Mix well and incubate at 37°C for 50 minutes.

[0073] 4) Plate washing: The same as above.

[0074] 5) Add 100 μl of SABC working solution to each well, mix well and incubate at 37°C for 30 minutes.

[0075] 6) Plate washing: The same as above.

[0076] 7) Add 100 μl of the pre-prepared TMB mixture to each well, mix well and incubate at 37°C in the dark for 10 - 20 minutes (the specific chromogenic time depends on the chromogenic result).

[0077] 8) Add 50 μl of stop solution to each well, mix well, and measure the absorbance at 450 nm using a microplate reader within 30 minutes.

[0078] 1.8. Result calculation

[0079] It is recommended to subtract the value of the blank well from all OD values before calculation. If the OD of the blank well is less than 0.1, it can also be calculated directly. Use the standard product concentration as the abscissa and the OD value as the ordinate to manually draw or use software to draw a standard curve, and calculate the corresponding content according to the OD value of the sample.

[0080] In this example, a total of 7 biomarkers related to early liver cancer were screened, namely AFP, AK2, DKK4, DCTN2, IFNGR1, Galentin4, and TIMM10. The contents of the 7 biomarkers in each group of people are as Figure 1 shown.

[0081] Example 2 Prediction of early liver cancer based on a classification algorithm model for 7 biomarker groups

[0082] This example provides a method for predicting early liver cancer using the 7 biomarker groups (AFP, AK2, DKK4, DCTN2, IFNGR1, Galentin4, and TIMM10) screened in Example 1, including the following steps:

[0083] 2.1. Obtain the plasma of the person to be tested. When collecting blood, an anticoagulant blood vessel treated with a disposable pyrogen-free and endotoxin-free test tube (EDTA, citrate, or heparin anticoagulation is acceptable) is required for collection;

[0084] 2.2. Centrifuge at 3000 rpm for 10 minutes. (Centrifuge within 1 hour after the blood sample is placed at room temperature; if the blood sample is placed on ice, it can be processed within 4 hours), and take the supernatant;

[0085] 2.3. Detect the concentrations of AFP, AK2, DCTN2, IFNGR1, TIMM10, Galectin4, and DKK4 in the plasma;

[0086] 2.4. Input the results obtained in step 2.3 into the classification algorithm model to obtain a score;

[0087] 2.5. Compare the score obtained in step 2.4 with the set threshold, and the comparison result is used to evaluate the risk of liver cancer in the person being tested.

[0088] In this embodiment, any one of the classification algorithms such as Random Forrest, Support Vector Machine (SVM), Logistic Regression, Ridge Regression, and Deep Neural Network can be used to construct a model for the 7 classification metrics.

[0089] Example 3: Training a Random Forest Model

[0090] As Figure 2 shown, in this embodiment, the peripheral blood samples of the subjects and the 7 biomarker groups screened in Example 1 are used to train the random forest model.

[0091] 3.1. Collect the peripheral blood of 518 subjects, including 188 healthy people, 155 patients with liver cirrhosis, 175 patients with liver cancer, and 77 patients with extremely early liver cancer. Centrifuge to obtain plasma samples, and detect the concentrations of seven proteins, namely AFP, AK2, DKK4, DCTN2, IFNGR1, Galentin4, and TIMM10, in the plasma. Randomly divide the recruited samples into a training set and a test set according to a ratio of 7:3. The training set contains a total of 361 samples, including 120 healthy people, 111 patients with liver cirrhosis, and 130 patients with liver cancer.

[0092] 3.2. As Figure 3 shown, determine the weights of the 7 proteins. The weight ratio of AFP, AK2, DCTN2, DKK4, IFNGR1, TIMM10, and Galectin4 is: 2.11:1.52:1.32:1.89:0.94:1.03:1.17.

[0093] 3.3. Use the plasma protein concentration of each biomarker in the samples of the training set as input data to construct a random forest model. The algorithm process of the random forest is as follows:

[0094] 1) Establish N decision trees in the training set. The number of classification trees and their error values are as Figure 4 shown;

[0095] 2) According to the model error value, the number of decision trees used is 100;

[0096] 3) The program used is the R language, and the program package used is randomForest. Set the number of decision trees to 100 (ntree = 100), and set the number of branches to 3 (mtry = 3);

[0097] 3.3. The model output result is the liver cancer risk score of the sample.

[0098] 3.4. Additionally, collect the plasma of 126 patients with early-stage liver cancer, the plasma of 92 patients with liver cirrhosis, and the plasma of 126 healthy individuals as an external validation set, and collect the plasma of 78 patients with extremely early-stage liver cancer as a prospective cohort, serving as the validation cohort of the model;

[0099] 3.5. Threshold division: Make the ROC curves of liver cancer patients and non-liver cancer individuals in the test set (as shown in Figure 5 ), and use the Youden Index as the best threshold to distinguish liver cancer and non-liver cancer individuals. Make the ROC curves of extremely early-stage liver cancer and liver cirrhosis individuals in the prospective cohort (as shown in Figure 6 ), and use the Youden Index as the best threshold to distinguish liver cirrhosis and extremely early-stage liver cancer individuals;

[0100] 3.6. Compare the obtained liver cancer risk score with the known threshold to obtain the liver cancer risk level. As shown in Figure 7 , the risk level assessment rules of the liver cancer detection model are as follows: The risk score lower than 0.329 is the low-risk population, higher than 0.329 and lower than 0.338 is the medium-risk population, with a relatively high probability of developing liver cancer within half a year, and the risk score higher than 0.338 is the high-risk population. It is recommended to regularly detect the liver lesion situation.

[0101] Example 4 Comparative experiment between the integrated model of 7 markers and the single marker model

[0102] 4.1. Divide the blood samples to be tested into test set samples and validation set samples by a method similar to that in Example 3;

[0103] 4.2. The construction of the integrated model is as shown in Example 3. By a method similar to that in Example 3, only use the single marker AFP to train the random forest model to obtain the AFP group model;

[0104] 4.3. In the integrated model and the AFP group model, the model evaluation index AUC of the test set samples and the validation set samples is as shown in Figure 8 . Figure 8 It can be clearly seen that the result of the integrated model is better than that of the single AFP group model.

[0105] This example also compares the AUC values in the test sets of the integrated model and other single markers. The results are shown in Table 1 below.

[0106] Table 1

[0107] Biomarkers AUC(95%CI) AFP 0.56(0.52-0.60) DCTN2 0.45(0.37-0.53) AK2 0.37(0.32-0.43) DKK4 0.38(0.32-0.44) Galentin4 0.14(0.3-0.44) IFNGR1 0.38(0.33-0.44) TIMM10 0.60(0.507-0.693) Integrated Score (Risk Score) 0.917(0.866-0.968)

[0108] According to the AUC of the model in Table 1, it can be judged that the AUC of the integrated score is significantly greater than that of other classification indicators. This embodiment verifies that the effect of diagnosing early liver cancer by using the combination of 7 biomarkers of the present invention is significantly better than that of only using one biomarker in the prior art.

[0109] Example 5 Comparative Experiments on Several Liver Cancer Screening Methods

[0110] In this embodiment, the liver cancer screening model provided in Example 3 of the present application is compared with the ASAP early liver cancer diagnosis model, the ASAP model and their single-index models in the prior art.

[0111] The specific operation steps are similar to those in Example 4, and the AUC values of different models are compared to judge the accuracy of the models.

[0112] The results are as Figure 9 shown. The model provided by the present invention is more sensitive and efficient than the ASAP early liver cancer diagnosis model and the ASAP model in the prior art.

[0113] Example 6

[0114] In this embodiment, the plasma of 78 cirrhotic individuals who developed cancer within six months to three years after blood sampling was collected. The protein concentration in the plasma was detected and input into the model.

[0115] The results are as Figure 10 shown. When the threshold of the method (risk score) of the present invention is 0.338, 55 cases are detected as positive, and the positive rate reaches 70.5%. The positive rate of AFP is 16.7%, the positive rate of PIVAK-II is 11.5%, the positive rate of the Galad model is 37.2%, and the positive rate of the ASAP model is 31.6%. It shows that the early liver cancer prediction diagnosis model has a high accuracy rate for the detection of extremely early liver cancer, and the early warning time can be advanced by more than half a year.

[0116] Example 7

[0117] This embodiment is an early liver cancer diagnosis system, including a processor and a memory. The memory is used to store one or more programs. When the program is executed by the processor, the processor realizes the construction of a random forest model.

[0118] The electronic device of this embodiment may include a memory, a processor, a bus and a communication interface. The memory, the processor and the communication interface are directly or indirectly electrically connected to each other to realize data interaction and transmission.

[0119] In this embodiment, the memory may be, but is not limited to, random access memory (RAM), read only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0120] In this embodiment, the processor may be an integrated circuit chip with signal processing capabilities. The processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; or it may be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FGPA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0121] In practical applications, the diagnostic system may be an electronic device, which may be a server, a cloud platform, a mobile phone, a tablet computer, a laptop computer, an ultra-mobile personal computer (UMPC), a handheld computer, a netbook, a personal digital assistant (PDA), a wearable electronic device, a virtual reality device, etc. Therefore, the types of electronic devices are not limited in the embodiments of the present application.

[0122] In this embodiment, a device for detecting plasma proteins is further provided, which can simultaneously detect the concentrations of multiple plasma proteins, including a sample acquisition unit, a sample plasma concentration detection device, and a sample plasma protein concentration real-time display device.

[0123] In this embodiment, a computer-readable medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, it can implement the construction of a random forest model. The computer-readable medium includes: USB flash drives, mobile hard disks, read-only memories, random access memories, magnetic disks, floppy disks, or optical discs, etc., which are various media that can store program codes.

[0124] The applicant declares that during the description of the above-mentioned specification:

[0125] Descriptions of terms such as "this embodiment", "embodiment of the present invention", "as shown in...", "further", "further improved technical solution", etc. mean that the specific features, structures, materials or characteristics described in the embodiment or example are included in at least one embodiment or example of the present invention; in this specification, the schematic expressions of the above terms are not necessarily directed to the same embodiment or example, and moreover, the specific features, structures, materials or characteristics described can be combined or combined in any one or more embodiments or examples in a suitable manner; in addition, on the premise of not generating contradictions, those of ordinary skill in the art can combine or combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0126] Finally, it should be noted that:

[0127] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them;

[0128] Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features, and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention. Non-essential improvements, adjustments or replacements made by those skilled in the art according to the content of this specification all fall within the scope of protection required by the present invention.

Claims

1. Use of a capture reagent for detecting a panel of protein biomarkers in the preparation of a reagent for screening or diagnosing early-stage liver cancer, characterized in that, The protein biomarker panel is: a combination of AFP, AK2, DCTN2, DKK4, IFNGR1, TIMM10, and Galectin4 proteins.

2. The application according to claim 1, wherein The detection includes in vitro detection of the concentration of the biomarker panel in a biological sample, and the biological sample is peripheral blood or plasma.

3. A kit for screening or diagnosing early-stage liver cancer, characterized in that, A capture reagent for detecting a protein biomarker panel, the protein biomarker panel being: a combination of AFP, AK2, DCTN2, DKK4, IFNGR1, TIMM10, and Galectin4 proteins.

4. The kit for screening or diagnosing early-stage liver cancer according to claim 3, characterized in that, The capture reagent includes a biotinylated antibody.

5. The kit for screening or diagnosing early-stage liver cancer according to claim 3, wherein The detection includes in vitro detection of the concentration of the biomarker panel in a biological sample, and the biological sample is peripheral blood or plasma.

Images