A screening method for heterologous competitive antigens for improving the sensitivity of immunoassays

Abstract

The application provides a screening method of heterologous competitive antigens for improving the sensitivity of immune detection, which comprises the following steps: performing corresponding molecular descriptor calculation on enrofloxacin analogs, and performing principal component analysis on the molecular descriptors to obtain a principal component analysis result; respectively measuring the half inhibition concentration of enrofloxacin and the half inhibition concentration of each enrofloxacin analog, and then calculating the cross-reactivity of each enrofloxacin analog; according to the principal component analysis result and the cross-reactivity of each enrofloxacin analog, establishing a mathematical model and performing classification learning to obtain a classification learning result; and according to the classification learning result, performing molecular docking on quinolone molecular cross-reactants and lysine to obtain a conformation, and performing configuration optimization to obtain a minimum energy conformation, so as to determine the best heterologous competitive antigen. The application is convenient for screening and determining the heterologous competitive antigens capable of improving the sensitivity of immune detection, and has a good application prospect.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical detection, in particular to a screening method of heterologous competitive antigens for improving the sensitivity of immune detection. BACKGROUND

[0002] The design and synthesis of antigens and the preparation of high-sensitivity antibodies are the core of immune analysis methods. The specificity and affinity of antibodies to antigens directly determine the accuracy and sensitivity of the detection method. In most immune analysis methods, the target to be measured or slightly modified is coupled with different carrier proteins to form an immunogen and a coating antigen. Since the coating antigen and the immunogen in this case have the same hapten structure, it is called homologous coating, and the corresponding hapten is called homologous competitive antigen. The coating antigen different from the hapten structure in the immunogen is called heterologous coating, and the corresponding hapten is called heterologous competitive antigen.

[0003] At present, there are many literatures at home and abroad reporting that heterologous coating can improve the sensitivity of immune analysis methods, but not all heterologous coatings can improve the sensitivity of immune analysis. Only when the antibody affinity is poor, the heterologous coating can significantly improve the sensitivity, and when the antibody affinity is high, the heterologous coating cannot significantly improve the sensitivity of immune analysis. In addition, the degree of improvement of different heterologous coatings on the sensitivity of immune analysis is quite different. Some can improve by tens of times, even dozens of times, and some can only improve by several times. Therefore, if for a certain antibody, if the best competitive antigen can be designed, the sensitivity of immune analysis can be maximized by heterologous competition, and the originally "unqualified" antibody can be changed into "qualified" antibody, which will greatly improve the qualification rate of antibodies and save the cost of antibody preparation.

[0004] However, in the prior art, there is a lack of a screening method of heterologous competitive antigens for effectively improving the sensitivity of immune detection, which limits the practical application to a certain extent. SUMMARY

[0005] The purpose of the present application is to solve the problem in the prior art that there is a lack of a screening method of heterologous competitive antigens for effectively improving the sensitivity of immune detection, which limits the practical application to a certain extent.

[0006] In order to achieve the above purpose, the present application adopts the following technical scheme:

[0007] The present application provides a screening method of heterologous competitive antigens for improving the sensitivity of immune detection, wherein the method comprises the following steps:

[0008] Step one: calculating molecular descriptors of enrofloxacin analogues, and performing principal component analysis on the molecular descriptors to obtain a principal component analysis result, wherein the enrofloxacin analogues are prepared from enrofloxacin and quinolone molecular cross-reactions;

[0009] Step two: respectively determining the half-inhibitory concentration of enrofloxacin and the half-inhibitory concentration of each enrofloxacin analogue by indirect competitive ELISA, and calculating the cross-reactivity of each enrofloxacin analogue according to the half-inhibitory concentration of enrofloxacin and the half-inhibitory concentration of the enrofloxacin analogue;

[0010] Step three: establishing a mathematical model and performing classification learning according to the principal component analysis result and the cross-reactivity of each enrofloxacin analogue to obtain a classification learning result, wherein the principal component analysis result includes molecular descriptors in the quinolone molecular cross-reactions;

[0011] Step four: determining the optimal heterologous competitive antigen by molecular docking of each quinolone molecular cross-reaction and lysine to obtain a conformation, and performing conformation optimization to obtain a minimum energy conformation according to the classification learning result.

[0012] The screening method for the heterologous competitive antigen for improving the sensitivity of immune detection provided by the present application first calculates molecular descriptors of enrofloxacin analogues, then performs principal component analysis on the molecular descriptors to obtain a principal component analysis result, and then calculates the cross-reactivity of enrofloxacin analogues by indirect competitive ELISA; then, according to the principal component analysis result and the cross-reactivity of enrofloxacin analogues, a mathematical model is established and classification learning is performed to obtain a classification learning result, and finally, according to the classification learning result, molecular docking of quinolone molecular cross-reactions and lysine is performed to obtain a conformation, conformation optimization is performed to obtain a minimum energy conformation, and the optimal heterologous competitive antigen is finally determined. The present application is convenient for screening and determining the heterologous competitive antigen for improving the sensitivity of immune detection, and has good application prospects.

[0013] The screening method for the heterologous competitive antigen for improving the sensitivity of immune detection, wherein in the step one, the molecular descriptors include:

[0014] symbols and terms, physical properties, hickel theory descriptors, subdivision surface area, atom count and bond count, connectivity and kappa shape index, adjacency and distance matrix descriptors, pharmacophore feature descriptors, and charge descriptors.

[0015] The screening method for the heterologous competitive antigen for improving the sensitivity of immune detection, wherein in the step two, the method for determining the half-inhibitory concentration of enrofloxacin and the half-inhibitory concentration of the enrofloxacin analogue includes the following steps:

[0016] First, the enrofloxacin coating agent is coated and sealed, and then the pre-prepared enrofloxacin, quinolone molecular cross and standard are added, wherein the quinolone molecular cross includes balofloxacin, besifloxacin, cinoxacin, clinafloxacin, danofloxacin, flumequine, gemifloxacin, lomefloxacin, marbofloxacin, moxifloxacin, nalidixic acid, norfloxacin, orbifloxacin, oxine acid, pefloxacin, prulifloxacin, pyrithioxacin, pazufloxacin, sarafloxacin, sitafloxacin and sparfloxacin, and the standard includes florfenicol, sulfisoxazole and tetracycline;

[0017] 50ul of the standard and 50ul of the anti-enrofloxacin monoclonal antibody diluent are added to each well, and then the enzyme-labeled secondary antibody, color development, termination and light absorption value measurement steps are continued to establish the inhibition standard curve;

[0018] The half-inhibitory concentration of the enrofloxacin and the half-inhibitory concentration of the enrofloxacin analogues are determined according to the inhibition standard curve.

[0019] The screening method of the heterologous competitive antigen for improving the sensitivity of immune detection, wherein the calculation formula of the cross-reactivity of the enrofloxacin analogue is:

[0020] CR%=(IC 50 of ENR / IC 50 of analogue)×100

[0021] Wherein, CR% is the cross-reactivity of the enrofloxacin analogue, IC 50 of ENR is the half-inhibitory concentration of the enrofloxacin, and IC 50 of analogue is the half-inhibitory concentration of the enrofloxacin analogue.

[0022] The screening method of the heterologous competitive antigen for improving the sensitivity of immune detection, wherein in the step three, the quinolone molecular cross for classification learning includes:

[0023] Enrofloxacin, balofloxacin, pyrithioxacin, norfloxacin, danofloxacin, flumequine, balofloxacin, besifloxacin, cinoxacin, clinafloxacin, gemifloxacin, lomefloxacin, marbofloxacin, moxifloxacin, nalidixic acid, orbifloxacin, oxine acid and pazufloxacin;

[0024] The step three includes:

[0025] The molecular descriptors of each of the quinolone molecular cross and the cross-reactivity of each of the enrofloxacin analogues are classified and learned, and the software for classification learning operation is MATLAB.

[0026] The screening method of the heterologous competitive antigen for improving the sensitivity of immune detection, wherein, in the step three,

[0027] In the classification learning, when the cross reactivity of the enrofloxacin analog is less than 0.01, it indicates that the quinolone molecular cross cannot be recognized by the antibody in the enzyme-linked immunosorbent assay system.

[0028] When the cross reactivity of the enrofloxacin analog is greater than 0.07, it indicates that the quinolone molecular cross can be captured by the antibody in the enzyme-linked immunosorbent assay system.

[0029] The screening method of the heterologous competitive antigen for improving the sensitivity of immune detection, wherein, in the step three, after obtaining the classification learning result, the method further comprises the following steps:

[0030] The classification learning result is evaluated by using the test sample, wherein the evaluation method comprises the following steps:

[0031] The molecular descriptor of the test sample is subjected to machine learning to obtain the corresponding machine CR value;

[0032] The actual CR value of the test sample is determined by enzyme-linked immunosorbent assay;

[0033] The accuracy of machine learning is calculated according to the machine CR value and the actual CR value of the test sample, so as to evaluate the classification learning result.

[0034] The screening method of the heterologous competitive antigen for improving the sensitivity of immune detection, wherein, the calculation formula of the accuracy of machine learning is:

[0035]

[0036] The screening method of the heterologous competitive antigen for improving the sensitivity of immune detection, wherein, when the conformation is optimized, the force field of molecular mechanics minimization is set to MMFF94x, and the cutoff value of non-bonding interaction is The software for performing conformation optimization is Gaussian software.

[0037] Other features and advantages of the present disclosure will be illustrated in the following description, or some features and advantages can be inferred from the description or determined without doubt, or can be known by implementing the above-mentioned technologies of the present disclosure.

[0038] In order to make the above-mentioned purposes, features and advantages of the present disclosure more obvious and easy to understand, the following preferred embodiments are specifically described with reference to the attached drawings. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 The principle block diagram of the screening method of the heterologous competitive antigen for improving the sensitivity of immunodetection according to the present application is shown in the figure.

[0040] Figure 2 The flow chart of the screening method of the heterologous competitive antigen for improving the sensitivity of immunodetection according to the present application is shown in the figure.

[0041] Figure 3 The electrostatic potential distribution near different quinolone antigenic determinants in the present application. DETAILED DESCRIPTION

[0042] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the accompanying drawings. The preferred embodiments of the present application are shown in the drawings. However, the present application can be realized in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided for the purpose of making the disclosure of the present application more thorough and comprehensive.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terminology used in the description of the present application herein is for the purpose of describing the specific embodiments only and is not intended to be limiting of the present application. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0044] In the prior art, there is a lack of a screening method of heterologous competitive antigen that can effectively improve the sensitivity of immunodetection, which limits the actual application to a certain extent.

[0045] In order to solve this technical problem, the present application proposes a screening method of heterologous competitive antigen for improving the sensitivity of immunodetection, wherein the method comprises the following steps:

[0046] S101, calculating the corresponding molecular descriptors of enoxacin analogues, and performing principal component analysis on the molecular descriptors to obtain the principal component analysis result, wherein the enoxacin analogues are prepared from enoxacin and quinolone molecular cross.

[0047] In this step, MOE 2016.10 software is used to calculate the corresponding molecular descriptors of enoxacin analogues. Specifically, each training sample has 204 molecular descriptors. Specifically, the molecular descriptors include:

[0048] (a) symbols and terms; (b) physical properties; (c) Hückel theory descriptors; (d) subdivided surface area; (e) atom count and bond count; (f) Kier connectivity and Kappa shape indices; (g) adjacency and distance matrix descriptors; (h) pharmacophore feature descriptors; (i) charge descriptors.

[0049] Further, the principal component analysis is performed on the molecular descriptors of the enrofloxacin analogs to obtain a principal component analysis result. Specifically, the principal component analysis is a statistical method of dimension reduction. With the help of an orthogonal transformation, the original random vector with component correlation is converted into a new random vector with component uncorrelation. This is expressed in algebra as transforming the covariance matrix of the original random vector into a diagonal matrix, and in geometry as transforming the original coordinate system into a new orthogonal coordinate system, so that the p orthogonal directions point to the most open sample points. Then, the multi-dimensional variable system is processed by dimension reduction, so that it can be converted into a low-dimensional variable system with high accuracy. Further, the low-dimensional system is converted into a one-dimensional system by constructing a suitable value function.

[0050] In the present embodiment, the principal component analysis program of the molecular descriptors of the training samples is performed on MATLAB 2015a (The Math Works, Inc., USA) software. It should be particularly pointed out here that the enrofloxacin analogs described above are prepared from enrofloxacin and quinolone molecular cross products.

[0051] S102, the half-inhibitory concentration of enrofloxacin and the half-inhibitory concentration of each enrofloxacin analog are determined by indirect competitive ELISA method, and the cross-reactivity of each enrofloxacin analog is calculated according to the half-inhibitory concentration of enrofloxacin and the half-inhibitory concentration of the enrofloxacin analog.

[0052] In this step, the preparation of the cross-reactivity of the enrofloxacin analogs is as follows:

[0053] (1), first, the enrofloxacin coating agent is coated and sealed, and then the pre-prepared enrofloxacin (ENR), quinolone molecular cross product and standard are added.

[0054] The quinolone molecular cross-links include balofloxacin (BAL), besifloxacin (BES), sinofloxacin (CIN), clinfloxacin (CLI), dalofopinion (DAN), floxacin (FLE), gemifloxacin (GEM), lomefloxacin (LOM), mabofloxacin (MAR), moxifloxacin (MOX), naproxenic acid (NAL), norfloxacin (NOR), oxadiazine (ORB), pefloxacin (OXO), pefloxacin (PEF), proprulifloxacin (PRU), pipemidic acid (PIP), pazufloxacin (PAZ), sarafloxacin (SAR), sitafloxacin (SIT), and sparfloxacin (SPA). The aforementioned standards include florfenicol (FLO), sulfadiazine (SMZ), and tetracycline (TET).

[0055] (2) Add 50 μL of standard and 50 μL of anti-enrofloxacin monoclonal antibody dilution to each well. After completion, add enzyme-labeled secondary antibody, perform color development, stop the reaction and measure absorbance to establish an inhibition standard curve.

[0056] (3) Determine the half-inhibitory concentration of enrofloxacin and the half-inhibitory concentration of enrofloxacin analogues based on the inhibition standard curve.

[0057] The formula for calculating the cross-reactivity rate of enrofloxacin analogues is:

[0058] CR% = (IC of ENR) 50 ICs of similar types 50 )×100

[0059] Wherein, CR% represents the cross-reactivity rate of enrofloxacin analogues, and the IC50 of ENR is... 50 The half-maximal inhibitory concentration (WMC) of enrofloxacin, and the IC50 of its analogues. 50 This is the half-inhibitory concentration of enrofloxacin analogues.

[0060] It should be noted that, using step S102 above, the half-maximal inhibitory concentration (WMC) of enrofloxacin and the corresponding WMC of each enrofloxacin analogue can be determined. Then, based on the WMC of enrofloxacin and the corresponding WMC of each enrofloxacin analogue, the actual CR value for each enrofloxacin analogue can be calculated.

[0061] S103. Based on the principal component analysis results and the corresponding cross-reactivity rates of each of the enrofloxacin analogues, a mathematical model is established and classification learning is performed to obtain the classification learning results, wherein the principal component analysis results include the molecular descriptors in the quinolone molecular cross-links.

[0062] In this step, the molecular descriptors of each quinolone molecular cross-reaction and the cross-reactivity of each said enrofloxacin analog are classified and learned respectively, wherein the software for performing the classification learning operation is MATLAB 2015a.

[0063] Specifically, the quinolone molecular cross-reaction for classification learning includes:

[0064] Enrofloxacin (ENR), Balofloxacin (PEF), Pipemidic acid (PIP), Norfloxacin (NOR), Danofloxacin (DAN), Flumequine (FLE), Balofloxacin (BAL), Besifloxacin (BES), Cinoxacin (CIN), Clinafloxacin (CLI), Gemifloxacin (GEM), Lomefloxacin (LOM), Marbofloxacin (MAR), Moxifloxacin (MOX), Nalidixic acid (NAL), Orbifloxacin (ORB), Oxolinic acid (OXO), and Pazufloxacin (PAZ).

[0065] In the classification learning, when the cross-reactivity of enrofloxacin analog is less than 0.01, it indicates that the quinolone molecular cross-reaction cannot be recognized by the antibody in the enzyme-linked immunosorbent assay system. When the cross-reactivity of enrofloxacin analog is greater than 0.07, it indicates that the quinolone molecular cross-reaction can be captured by the antibody in the enzyme-linked immunosorbent assay system.

[0066] In addition, after obtaining the above classification learning results, the classification learning results need to be evaluated. Specifically, the test sample is used to evaluate the classification learning results, and the evaluation method includes the following steps:

[0067] (1) The molecular descriptors of the test sample are machine learned to obtain the corresponding machine CR value;

[0068] (2) The test sample is determined by enzyme-linked immunosorbent assay to obtain the actual CR value of the test sample;

[0069] (3) The accuracy of machine learning is calculated according to the machine CR value and the actual CR value of the test sample to evaluate the classification learning results.

[0070] It should be pointed out here that in this embodiment, the test sample includes PRL, Sarafloxacin (SAR), Sitafloxacin (SIT), Sparfloxacin (SPA), Florfenicol (FLO), Sulfamethoxazole (SMZ), and Tetracycline (TET).

[0071] Specifically, the calculation formula of the accuracy of machine learning is:

[0072]

[0073] S104, according to the classification learning result, using each of the quinolone molecular cross and lysine to perform molecular docking to obtain a conformation, and performing configuration optimization on the conformation to obtain a minimum energy conformation, so as to determine the best heterogenous competitive antigen.

[0074] Further, in this step, the molecular operation environment (MOE) 2016.10 software is used to perform molecular docking on the quinolone molecular cross and lysine, so as to clarify the recognition ability between the monoclonal antibody and the heterogenous coated antigen.

[0075] When performing configuration optimization, specifically, the force field of molecular mechanics minimization is set to MMFF94x, and the cutoff value of non-bonding interaction is set to 10 angstrom. By using the Gaussian 09 software, the conformation after the preliminary minimization is further determined to realize more accurate geometry optimization and frequency analysis at the HF / 6-31G(d) level, and finally the minimum energy conformation of all condensation products is obtained. In addition, the Gaussian 09 software is used to calculate the atomic point charge and the static electric potential at the same level, and the GaussView 5.0 software is used for observation, so as to finally determine the best heterogenous competitive antigen.

[0076] The screening method for the heterogenous competitive antigen for improving the sensitivity of immune detection provided by the present application firstly performs molecular descriptor calculation on the enrofloxacin analog, then performs principal component analysis on the molecular descriptor to obtain a principal component analysis result, then adopts the indirect competitive ELISA method to measure and calculate the cross-reactivity of the enrofloxacin analog; then according to the principal component analysis result and the cross-reactivity of the enrofloxacin analog, a mathematical model is established and classification learning is performed to obtain a classification learning result, finally according to the classification learning result, the quinolone molecular cross and lysine are performed molecular docking to obtain a conformation, configuration optimization is performed to obtain a minimum energy conformation, and finally the best heterogenous competitive antigen is determined. The present application is convenient for screening and determining the heterogenous competitive antigen capable of improving the sensitivity of immune detection, and has good application prospect.

[0077] Finally, it should be noted that the above-described embodiments are merely specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not to limit the same. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that any person skilled in the art can still modify or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features, within the technical scope disclosed by the present application. The modifications, changes or replacements do not cause the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for screening heterologous competitive antigens to improve the sensitivity of immunoassays, characterized in that, The method includes the following steps: Step 1: Calculate the corresponding molecular descriptor for the enrofloxacin analog and perform principal component analysis on the molecular descriptor to obtain the principal component analysis results, wherein the enrofloxacin analog is prepared by cross-linking enrofloxacin and quinolone molecules; Step 2: The half-inhibitory concentration (WIC) of enrofloxacin and the WIC of each enrofloxacin analogue were determined by indirect competitive ELISA. The cross-reactivity rate of each enrofloxacin analogue was calculated based on the WIC of enrofloxacin and the WIC of each enrofloxacin analogue. Step 3: Based on the principal component analysis results and the corresponding cross-reactivity rates of each of the enrofloxacin analogues, establish a mathematical model and perform classification learning to obtain classification learning results, wherein the principal component analysis results include molecular descriptors in the quinolone molecular cross-links; Step 4: Based on the classification learning results, molecular docking is performed using the quinolone molecular cross-links and lysine to obtain a conformation, and the conformation is optimized to obtain the minimum energy conformation in order to determine the optimal heterologous competitive antigen. In step one, the molecular descriptor includes: Symbols and terminology, physical properties, Hückel theory descriptors, subdivided surface regions, atomic and bond counts, connectivity and Kappa shape indices, adjacency and distance matrix descriptors, pharmacophore feature descriptors, and charge descriptors; In step two, the method for determining the half-inhibitory concentration of enrofloxacin and the half-inhibitory concentration of enrofloxacin analogues includes the following steps: First, the enrofloxacin coating agent is sealed in a plate. Then, pre-prepared enrofloxacin, quinolone molecular cross-linkers, and standards are added. The quinolone molecular cross-linkers include balofloxacin, besifloxacin, sinofloxacin, clinfloxacin, dalofop-floxacin, floxacin, gemifloxacin, lomefloxacin, mabofloxacin, moxifloxacin, naproxen, norfloxacin, oxadiazine, pefloxacin, propullifloxacin, pipemidic acid, pazufloxacin, sarafloxacin, sitafloxacin, and sparfloxacin. The standards include florfenicol, sulfadiazine, and tetracycline. Add 50 μL of standard and 50 μL of anti-enrofloxacin monoclonal antibody dilution buffer to each well. After completion, continue with the steps of adding enzyme-labeled secondary antibody, color development, termination, and measuring absorbance to establish an inhibition standard curve. The half-inhibitory concentration (WIC) of enrofloxacin and the WIC of enrofloxacin analogues were determined based on the inhibition standard curve.

2. The method for screening heterologous competitive antigens to improve the sensitivity of immunoassays according to claim 1, characterized in that, The formula for calculating the cross-reactivity rate of the enrofloxacin analogue is as follows: ； in, The cross-reactivity rate of the enrofloxacin analogue. This is the half-maximal inhibitory concentration (WMC) of the enrofloxacin. This is the half-inhibitory concentration of the enrofloxacin analogue.

3. The method for screening heterologous competitive antigens to improve the sensitivity of immunoassays according to claim 2, characterized in that, In step three, the quinolone molecular cross-links used for classification learning include: Enrofloxacin, Balofloxacin, Piperidin, Norfloxacin, Daflonax, Frofloxacin, Balofloxacin, Besifloxacin, Sinoxacin, Clinfloxacin, Gimidafloxacin, Lomefloxacin, Mapofloxacin, Moxifloxacin, Naphadine, Obiboxacin, Oxyquinacrine, and Pazufloxacin; Step three includes: The molecular descriptors of each quinolone molecule cross-link and the corresponding cross-reactivity rates of each enrofloxacin analog were classified and learned, with MATLAB being the software used for the classification and learning operation.

4. The method for screening heterologous competitive antigens to improve the sensitivity of immunoassays according to claim 3, characterized in that, In step three; In classification learning, when the cross-reactivity rate of the enrofloxacin analogue is less than 0.01, it indicates that the quinolone molecule cross-reactivity cannot be recognized by the antibody in the enzyme-linked immunosorbent assay system. When the cross-reactivity rate of the enrofloxacin analogue is greater than 0.07, it indicates that the quinolone molecular cross-reactivity can be captured by antibodies in the enzyme-linked immunosorbent assay (ELISA) system.

5. The method for screening heterologous competitive antigens to improve the sensitivity of immunoassays according to claim 4, characterized in that, In step three, after obtaining the classification learning result, the method further includes the following steps: The classification learning results are evaluated using test samples, and the evaluation method includes the following steps: The molecular descriptors of the test samples are processed by machine learning to obtain the corresponding machine CR values; The actual CR value of the test sample was obtained by measuring the enzyme-linked immunosorbent assay (ELISA). The accuracy of the machine learning is calculated based on the machine's CR value and the actual CR value of the test sample, in order to evaluate the classification learning results.

6. The method for screening heterologous competitive antigens to improve the sensitivity of immunoassays according to claim 5, characterized in that, The formula for calculating the accuracy of the machine learning is expressed as follows: ； 7. The method for screening heterologous competitive antigens to improve the sensitivity of immunoassays according to claim 6, characterized in that, When optimizing the conformation, the force field for minimizing molecular mechanics was set to MMFF94x, the cutoff value for nonbonded interactions was 8 Å, and the software used for conformation optimization was [software name missing]. Gaussian software.

Images