Electrochemiluminescence immunosensor for detecting tumor marker and application thereof

Abstract

The application belongs to the technical field of electrochemiluminescence immunosensor, discloses a kind of electrochemiluminescence immunosensor for detecting tumor marker and application thereof, and the preparation system of electrochemiluminescence immunosensor for detecting tumor marker includes: graphite carbon nitride preparation module, working electrode pretreatment module, central control module, antigen standard solution preparation module, modified electrode preparation module, immunosensor preparation module, tumor marker detection module, sensor detection curve drawing module, data storage module, update display module.The electrochemiluminescence immunosensor for detecting tumor marker provided by the application has high analysis sensitivity, strong specificity, is simple to use and low in cost.The application improves the sensitivity of electrochemiluminescence immunosensor by dropping coating bovine serum albumin solution and tumor marker antigen standard solution on the surface of graphite carbon nitride working electrode, and greatly simplifies the electrode preparation process without enzyme and label.

Description

Technical Field

[0001] This invention belongs to the field of electrochemiluminescence immunosensor technology, and particularly relates to an electrochemiluminescence immunosensor for detecting tumor markers and its applications. Background Technology

[0002] Currently, immunosensors combine highly sensitive sensing technology with highly specific immune responses, offering advantages such as real-time output, high analytical sensitivity, strong specificity, ease of use, and low cost. Therefore, immunosensors are widely used in early diagnosis and the detection of tumor markers.

[0003] Given the insufficient sensitivity and specificity of existing tumor markers, it is crucial to rationally select multiple markers for simultaneous detection based on the characteristics of different tumors and markers to enhance their clinical application value. Since the analytical efficiency for detecting a single tumor marker is low, research has focused on high-throughput electrochemical immunosensors capable of simultaneously detecting multiple samples to shorten analysis time, reduce analytical steps, improve analytical efficiency, and lower testing costs.

[0004] Based on the above analysis, the problems and shortcomings of the existing technology are as follows: the sensitivity and specificity of existing tumor markers are not ideal, and the analytical efficiency of detecting a single tumor marker is not high. Summary of the Invention

[0005] To address the problems existing in the prior art, this invention provides an electrochemiluminescence immunosensor for detecting tumor markers and its applications.

[0006] This invention is achieved by providing a fabrication system for an electrochemiluminescence immunosensor for detecting tumor markers, the system comprising:

[0007] The graphite carbon nitride preparation module is connected to the central control module and is used to prepare polyaniline gel using aniline, phytic acid and initiator, and then carbonize it to obtain graphite carbon nitride working electrode.

[0008] The working electrode pretreatment module is connected to the central control module and is used to perform pretreatment operations such as activation, polishing, cleaning and nitrogen drying of the graphite carbon nitride working electrode through the pretreatment equipment.

[0009] The central control module is connected to the graphite carbon nitride preparation module, the working electrode pretreatment module, the antigen standard solution preparation module, the modified electrode preparation module, the immunosensor preparation module, the tumor marker detection module, the sensor detection curve plotting module, the data storage module, and the update display module. It is used to coordinate and control the normal operation of each module of the electrochemiluminescent immunosensor preparation system for detecting tumor markers through the central processor.

[0010] The antigen standard solution preparation module is connected to the central control module and is used to prepare bovine serum albumin solution and tumor marker antigen standard solution respectively through the standard solution preparation device;

[0011] The modified electrode preparation module, connected to the central control module, is used to drop-coat bovine serum albumin solution and tumor marker antigen standard solution onto the surface of the graphite carbon nitride working electrode to obtain the modified electrode.

[0012] An immunosensor fabrication module, connected to a central control module, is used to prepare an electrochemiluminescence immunosensor using an antigen standard solution and a modified electrode through electrochemiluminescence technology.

[0013] The tumor marker detection module, connected to the central control module, is used to detect tumor markers using the prepared electrochemiluminescence immunoassay sensor and obtain a detection report.

[0014] The sensor detection curve plotting module is connected to the central control module and is used to plot the working curve based on the electrochemiluminescence intensity of the electrode in the detection report through the curve plotting program.

[0015] The data storage module, connected to the central control module, is used to store graphite carbon nitride preparation data, working electrode pretreatment data, antigen standard solution preparation data, modified electrode preparation data, immune sensor preparation data, tumor marker detection reports, and working curves via a memory.

[0016] The updated display module, connected to the central control module, is used to update and display real-time data on graphite carbon nitride preparation, working electrode pretreatment, antigen standard solution preparation, modified electrode preparation, immunosensor preparation, tumor marker detection reports, and working curves via a display screen.

[0017] Furthermore, the molar ratio of the initiator, aniline, and phytic acid is 1-3:2-7:1, and the initiator is an ammonium sulfate solution or a hydrogen peroxide solution.

[0018] Furthermore, the pretreatment operations performed by the working electrode pretreatment module using pretreatment equipment to activate, polish, clean, and dry the graphite carbon nitride working electrode include:

[0019] (1) The graphite carbon nitride working electrode is activated by using an activating material to obtain a three-dimensional layered porous graphite carbon nitride working electrode.

[0020] (2) Polish the three-dimensional layered porous graphitic carbon nitride working electrode with Al2O3 polishing powder of 0.05-1.5μm;

[0021] (3) The three-dimensional layered porous graphite carbon nitride working electrode after grinding and polishing is ultrasonically cleaned in ethanol and ultrapure water for 5-15 minutes, and then dried with nitrogen.

[0022] Furthermore, the activating material contains NaOH or KOH, the mass ratio of the activating material to the graphite carbon nitride working electrode is 1:2 to 5:1 to 2, and the activation temperature is 400 to 800°C.

[0023] Furthermore, the electrochemiluminescence immunosensor prepared by the immunosensor preparation module using electrochemiluminescence technology with antigen standard solutions and modified electrodes includes:

[0024] (1) Take 6-10 μL of tumor marker antibody standard solution and drop it onto the surface of the modified electrode. Let it dry at room temperature to form a film. Clean the electrode with PBS buffer solution at pH 7.4.

[0025] (2) After drying, take 10 μL of bovine serum albumin solution with a mass fraction of 1-3% and drop it onto the electrode surface. Incubate at 37°C for 1-1.5 h to block non-specific binding sites and rinse the electrode surface.

[0026] (3) Add 10 μL of tumor marker antigen standard solutions of different concentrations of 0.5 to 100 ng / mL, incubate the antigen and antibody at room temperature for 30 to 40 minutes, rinse and dry to obtain an electrochemiluminescent immunosensor.

[0027] Furthermore, the sensor detection curve plotting module uses a curve plotting program to plot a working curve based on the electrochemiluminescence intensity of the electrode in the detection report, including:

[0028] (1) Connect the electrochemiluminescence immunosensor correctly to the electrochemical workstation;

[0029] (2) Testing was performed using the MPI-B type multi-parameter chemiluminescence analysis system; the multi-parameter chemiluminescence analysis methods include:

[0030] The first step is to generate a gridded tumor tissue sample model and generate training tumor tissue samples;

[0031] The second step is to construct and train a multilayer sensing network for Cherenkov fluorescence tomography. The multilayer sensing network can be divided into a forward network A and a backward network B.

[0032] The third step is to collect Cherenkov fluorescence signals on the surface of tumor tissue samples and reconstruct the three-dimensional distribution information of Cherenkov fluorescence light sources inside the tumor tissue samples.

[0033] The fourth step is to map the preliminary reconstruction results onto the constructed gridded tumor tissue sample model, and then input it into the multilayer sensing network to obtain accurate reconstruction results.

[0034] The first step of generating training tumor tissue samples includes:

[0035] (i) Construct a tumor tissue sample model. Construct a tumor tissue sample model with a size of 5×5×5mm3, and use the finite element theory to mesh the constructed tumor tissue sample model to obtain the meshed tumor tissue sample model.

[0036] (ii) Construct a single Cherenkov fluorescence light source to simulate tumor tissue samples. In the meshed tumor tissue sample model of (1), a single spherical Cherenkov fluorescence light source with a light source radius of 0.1 mm is set. The simulation training tumor tissue samples with a single Cherenkov fluorescence light source are generated using the Monte Carlo simulation MOSE platform.

[0037] (iii) Tumor tissue sample expansion to obtain multi-Cherenkov fluorescence light source simulated tumor tissue sample. Based on the single-Cherenkov fluorescence light source simulated tumor tissue sample set obtained in (ii), the tumor tissue sample is expanded by using the tumor tissue sample combination method to obtain multi-Cherenkov fluorescence light source simulated training tumor tissue sample.

[0038] The second step, constructing and training a multilayer sensing network for Cherenkov fluorescence tomography, includes:

[0039] 1) Construct a feedforward network A, which includes one input layer, four hidden layers and one output layer. The number of nodes in the input layer and the number of nodes in the hidden layer are the same as the number of nodes in the tumor tissue sample model grid, and the number of nodes in the output layer is the same as the number of nodes on the surface of the tumor tissue sample model grid.

[0040] 2) Train the feedforward network A using the obtained multi-Cherenkov fluorescence light source tumor tissue samples. The network input is the distribution data of the multi-Cherenkov fluorescence light source of the simulated tumor tissue samples inside the tumor tissue sample model, and the network output is the predicted distribution data of the multi-Cherenkov fluorescence light source simulated tumor tissue samples on the surface of the tumor tissue sample model.

[0041] 3) Construct an inverse network B, which includes one input layer, four hidden layers and one output layer. The number of nodes in the input layer is the same as the number of nodes on the surface of the tumor tissue sample model grid, and the number of nodes in the output layer and the number of nodes in the hidden layer are the same as the number of nodes in the tumor tissue sample model grid.

[0042] 4) The obtained Docherenkov fluorescence light source tumor tissue samples are used to train the inverse network B. The network input is the distribution data of the Docherenkov fluorescence light source simulated tumor tissue samples on the surface of the tumor tissue sample model, and the network output is the predicted distribution data of the Docherenkov fluorescence light source simulated tumor tissue samples inside the tumor tissue sample model.

[0043] 5) Merge the feedforward network A and the inverse network B, and use the output layer of the trained feedforward network A as the input layer of the trained inverse network B to obtain the final multilayer perceptron network.

[0044] In steps 2) and 4), the output of each layer is corrected using a correction function; negative values ​​in the output of the linear units of the hidden and output layers are corrected using the following formula:

[0045]

[0046] Where X represents the output of the linear unit in the current layer, and ReLU represents the correction function; when the output is negative or zero, the correction function will set the negative value to zero.

[0047] In 2) and 4), the relationship between the current layer and the previous layer is as follows:

[0048] X i =Dropout 0.4 (ReLu(W i X i-1 +b i i≥2;

[0049] Where X i W represents the node value at the i-th layer. i b represents the weight of the i-th layer. i Represents the bias of the i-th layer, Dropout 0.4 It is a random function that indicates that there is a 40% probability that the nodes in each layer will be reset to zero;

[0050] In steps 2) and 4), the multilayer sensing network is trained under constraints using the following formula:

[0051]

[0052] Where ||·||2 represents the second norm, minypred Denotes the y-values ​​that satisfy the least second norm. pred In 2), y true To train on the known Cherenkov fluorescence signal distribution information in tumor tissue samples, y pred The network outputs the corresponding predicted Cherenkov fluorescence signal distribution information; in 4), y true To train on the known three-dimensional distribution information of Cherenkov fluorescence sources in tumor tissue samples, y pred The network outputs the corresponding predicted three-dimensional distribution information of Cherenkov fluorescence sources.

[0053] The third step, acquiring Cherenkov fluorescence signals from the surface of the tumor tissue sample and reconstructing the three-dimensional distribution information of the Cherenkov fluorescence source inside the tumor tissue sample, specifically includes:

[0054] Cherenkov fluorescence signals were collected from tumor tissue sample tables;

[0055] Reconstruction methods were used to obtain preliminary distribution results of Cherenkov fluorescence sources within tumor tissue samples.

[0056] (3) Plot working curves based on the relationship between the current response obtained from different electronic mediators and the concentrations of their corresponding tumor marker antigen standard solutions.

[0057] Another objective of this invention is to provide an electrochemiluminescent immunosensor for detecting tumor markers prepared using the aforementioned electrochemiluminescent immunosensor preparation system. The electrochemiluminescent immunosensor for detecting tumor markers includes a working electrode, bovine serum albumin solution, and tumor marker antigen standard solution.

[0058] Another object of the present invention is to provide a computer program product stored on a computer-readable medium, comprising a computer-readable program that, when executed on an electronic device, provides a user input interface for applying the preparation system of the electrochemiluminescent immunosensor for detecting tumor markers.

[0059] Another object of the present invention is to provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to apply the preparation system of the electrochemiluminescent immunosensor for detecting tumor markers.

[0060] Another objective of this invention is to provide an information data processing terminal, characterized in that the information data processing terminal is used to implement the preparation system of the electrochemiluminescence immunosensor for detecting tumor markers.

[0061] Combining all the above technical solutions, the advantages and positive effects of this invention are as follows: The electrochemiluminescence immunosensor for detecting tumor markers provided by this invention has high analytical sensitivity, strong specificity, is easy to use, and is low in cost. This invention improves the sensitivity of the electrochemiluminescence immunosensor by drop-coating bovine serum albumin solution and tumor marker antigen standard solution onto the surface of a graphite carbon nitride working electrode; it detects AFP through the mechanism of protein blocking electron transfer and thus changing the luminescence intensity, without enzymes or labels, greatly simplifying the electrode preparation process. Simultaneously, this invention uses graphite carbon nitride as the working electrode, which improves photoelectric conversion efficiency and stability, effectively enhancing the electrochemiluminescence intensity.

[0062] This invention utilizes a multi-parameter chemiluminescence analysis method to generate a gridded tumor tissue sample model and to generate training tumor tissue samples.

[0063] A multilayer sensing network for Cherenkov fluorescence tomography was constructed and trained. The multilayer sensing network can be divided into a forward network A and a backward network B.

[0064] Cherenkov fluorescence signals were collected from the surface of tumor tissue samples, and the three-dimensional distribution information of Cherenkov fluorescence sources inside the tumor tissue samples was reconstructed.

[0065] The preliminary reconstruction results are mapped onto the constructed gridded tumor tissue sample model, and then input into a multilayer sensing network to obtain accurate reconstruction results; accurate detection data can be obtained. Attached Figure Description

[0066] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0067] Figure 1 This is a structural block diagram of the preparation system for the electrochemiluminescence immunosensor for detecting tumor markers provided in this embodiment of the invention;

[0068] In the diagram: 1. Graphite carbon nitride preparation module; 2. Working electrode pretreatment module; 3. Central control module; 4. Antigen standard solution preparation module; 5. Modified electrode preparation module; 6. Immunosensor preparation module; 7. Tumor marker detection module; 8. Sensor detection curve plotting module; 9. Data storage module; 10. Update display module.

[0069] Figure 2 This is a flowchart illustrating the preparation method of the electrochemiluminescent immunosensor for detecting tumor markers provided in this embodiment of the invention.

[0070] Figure 3 This is a flowchart of a method for pre-treating a graphite carbon nitride working electrode by means of a working electrode pre-treatment module and a pre-treatment device, as provided in an embodiment of the present invention, including activation, polishing, cleaning, and nitrogen drying.

[0071] Figure 4 This is a flowchart of a method for preparing an electrochemiluminescence immunosensor using an immunosensor preparation module with an antigen standard solution and a modified electrode, according to an embodiment of the present invention.

[0072] Figure 5 This is a flowchart of a method provided in this embodiment of the invention for plotting a working curve using a curve plotting program based on the electrochemiluminescence intensity of the electrode in the detection report through a sensor detection curve plotting module. Detailed Implementation

[0073] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0074] To address the problems existing in the prior art, the present invention provides an electrochemiluminescence immunosensor for detecting tumor markers and its application. The present invention will be described in detail below with reference to the accompanying drawings.

[0075] like Figure 1 As shown, the preparation system for an electrochemiluminescence immunosensor for detecting tumor markers provided in this embodiment of the invention includes a graphite carbon nitride preparation module 1, a working electrode pretreatment module 2, a central control module 3, an antigen standard solution preparation module 4, a modified electrode preparation module 5, an immunosensor preparation module 6, a tumor marker detection module 7, a sensor detection curve plotting module 8, a data storage module 9, and an update display module 10.

[0076] The graphite carbon nitride preparation module 1 is connected to the central control module 3 and is used to prepare polyaniline gel using aniline, phytic acid and initiator, and then carbonize it to obtain the graphite carbon nitride working electrode.

[0077] The working electrode pretreatment module 2 is connected to the central control module 3 and is used to perform pretreatment operations such as activation, polishing, cleaning and nitrogen drying of the graphite carbon nitride working electrode through the pretreatment equipment.

[0078] The central control module 3 is connected to the graphite carbon nitride preparation module 1, the working electrode pretreatment module 2, the antigen standard solution preparation module 4, the modified electrode preparation module 5, the immunosensor preparation module 6, the tumor marker detection module 7, the sensor detection curve plotting module 8, the data storage module 9, and the update display module 10. It is used to coordinate and control the normal operation of each module of the preparation system of the electrochemiluminescent immunosensor for detecting tumor markers through the central processor.

[0079] The antigen standard solution preparation module 4 is connected to the central control module 3 and is used to prepare bovine serum albumin solution and tumor marker antigen standard solution respectively through the standard solution preparation device.

[0080] The modified electrode preparation module 5 is connected to the central control module 3 and is used to drop-coat bovine serum albumin solution and tumor marker antigen standard solution onto the surface of graphite carbon nitride working electrode to obtain the modified electrode.

[0081] The immunosensor preparation module 6 is connected to the central control module 3 and is used to prepare an electrochemiluminescence immunosensor using an antigen standard solution and a modified electrode through electrochemiluminescence technology.

[0082] The tumor marker detection module 7 is connected to the central control module 3 and is used to detect tumor markers through the prepared electrochemiluminescence immunosensor and obtain a detection report.

[0083] The sensor detection curve plotting module 8 is connected to the central control module 3 and is used to plot the working curve based on the electrochemiluminescence intensity of the electrode in the detection report through the curve plotting program.

[0084] Data storage module 9, connected to central control module 3, is used to store graphite carbon nitride preparation data, working electrode pretreatment data, antigen standard solution preparation data, modified electrode preparation data, immune sensor preparation data, tumor marker detection reports, and working curves via a memory.

[0085] The updated display module 10 is connected to the central control module 3 and is used to update and display real-time data on graphite carbon nitride preparation, working electrode pretreatment, antigen standard solution preparation, modified electrode preparation, immune sensor preparation, tumor marker detection report, and working curve through the display.

[0086] like Figure 2 As shown, the control method for the electrochemiluminescence immunosensor for detecting tumor markers provided in this embodiment of the invention includes the following steps:

[0087] S101, a polyaniline gel is prepared by using aniline, phytic acid and an initiator through a graphite carbon nitride preparation module, and then carbonized to obtain a graphite carbon nitride working electrode.

[0088] S102, the pretreatment operation of the graphite carbon nitride working electrode is carried out by the working electrode pretreatment module using pretreatment equipment, including activation, polishing, cleaning and nitrogen drying.

[0089] S103, The central control module uses the central processor to coordinate and control the normal operation of each module of the preparation system for the electrochemiluminescent immunosensor for detecting tumor markers;

[0090] S104, using the standard solution preparation device in the antigen standard solution preparation module, bovine serum albumin solution and tumor marker antigen standard solution are prepared respectively;

[0091] S105, Bovine serum albumin solution and tumor marker antigen standard solution are respectively drop-coated onto the surface of graphite carbon nitride working electrode through the modified electrode preparation module to obtain modified electrode;

[0092] S106, an electrochemiluminescence immunosensor was prepared using an immunosensor preparation module with an antigen standard solution and a modified electrode via electrochemiluminescence technology.

[0093] S107, the tumor marker detection module uses the prepared electrochemiluminescence immunosensor to detect tumor markers and obtain a detection report; the sensor detection curve plotting module uses a curve plotting program to plot the working curve based on the electrochemiluminescence intensity of the electrode in the detection report.

[0094] S108 uses a data storage module to store graphite carbon nitride preparation data, working electrode pretreatment data, antigen standard solution preparation data, modified electrode preparation data, immune sensor preparation data, tumor marker detection reports, and working curves.

[0095] S109 updates and displays real-time data on graphite carbon nitride preparation, working electrode pretreatment, antigen standard solution preparation, modified electrode preparation, immunosensor preparation, tumor marker detection report, and working curves via the updated display module.

[0096] In step S101 provided in this embodiment of the invention, the molar ratio of the initiator, aniline and phytic acid is 1-3:2-7:1, and the initiator is an ammonium sulfate solution or a hydrogen peroxide solution.

[0097] like Figure 3As shown, in step S102 of this embodiment of the invention, the pretreatment operations of activating, polishing, cleaning, and drying the graphite carbon nitride working electrode using a pretreatment device via the working electrode pretreatment module include:

[0098] S201, the graphite carbon nitride working electrode is activated using an activating material to obtain a three-dimensional layered porous graphite carbon nitride working electrode.

[0099] S202, a three-dimensional layered porous graphitic carbon nitride working electrode is polished with Al2O3 polishing powder of 0.05~1.5μm;

[0100] S203, after grinding and polishing, the three-dimensional layered porous graphite carbon nitride working electrode is ultrasonically cleaned in ethanol and ultrapure water for 5-15 minutes, and then dried with nitrogen.

[0101] The activation material provided in this embodiment of the invention contains NaOH or KOH, the mass ratio of the activation material to the graphite carbon nitride working electrode is 1:2 to 5:1 to 2, and the activation temperature is 400 to 800°C.

[0102] like Figure 4 As shown, in step S106 of this embodiment of the invention, the preparation of an electrochemiluminescence immunosensor using an antigen standard solution and a modified electrode via an immunosensor preparation module includes:

[0103] S301, take 6-10 μL of tumor marker antibody standard solution and drop it onto the surface of the modified electrode, let it dry at room temperature to form a film, and clean the electrode with PBS buffer solution at pH 7.4;

[0104] S302, after drying, take 10 μL of bovine serum albumin solution with a mass fraction of 1-3% and drop it onto the electrode surface. Incubate at 37℃ for 1-1.5 h to block non-specific binding sites, and then rinse the electrode surface.

[0105] Add 10 μL of tumor marker antigen standard solutions of different concentrations (0.5–100 ng / mL) to S303, incubate the antigen and antibody at room temperature for 30–40 minutes, rinse and air dry to obtain an electrochemiluminescent immunosensor.

[0106] like Figure 5 As shown, in step S107 of this embodiment of the invention, the step of plotting a working curve using a curve plotting program based on the electrochemiluminescence intensity of the electrode in the detection report by the sensor detection curve plotting module includes:

[0107] S401, Connect the electrochemiluminescence immunosensor correctly to the electrochemical workstation;

[0108] S402 was tested using the MPI-B type multi-parameter chemiluminescence analysis and testing system.

[0109] S403. Based on the relationship between the current response obtained from different electron mediators and the concentrations of their corresponding tumor marker antigen standard solutions, a working curve is plotted.

[0110] Step S402, the multi-parameter chemiluminescence analysis method, includes:

[0111] The first step is to generate a gridded tumor tissue sample model and generate training tumor tissue samples;

[0112] The second step is to construct and train a multilayer sensing network for Cherenkov fluorescence tomography. The multilayer sensing network can be divided into a forward network A and a backward network B.

[0113] The third step is to collect Cherenkov fluorescence signals on the surface of tumor tissue samples and reconstruct the three-dimensional distribution information of Cherenkov fluorescence light sources inside the tumor tissue samples.

[0114] The fourth step is to map the preliminary reconstruction results onto the constructed gridded tumor tissue sample model, and then input it into the multilayer sensing network to obtain accurate reconstruction results.

[0115] The first step of generating training tumor tissue samples includes:

[0116] (i) Construct a tumor tissue sample model with a size of 5×5×5mm. 3 A tumor tissue sample model was constructed, and the constructed tumor tissue sample model was meshed using the finite element theory, thus obtaining the meshed tumor tissue sample model.

[0117] (ii) Construct a single Cherenkov fluorescence light source to simulate tumor tissue samples. In the meshed tumor tissue sample model of (1), a single spherical Cherenkov fluorescence light source with a light source radius of 0.1 mm is set. The simulation training tumor tissue samples with a single Cherenkov fluorescence light source are generated using the Monte Carlo simulation MOSE platform.

[0118] (iii) Tumor tissue sample expansion to obtain multi-Cherenkov fluorescence light source simulated tumor tissue sample. Based on the single-Cherenkov fluorescence light source simulated tumor tissue sample set obtained in (ii), the tumor tissue sample is expanded by using the tumor tissue sample combination method to obtain multi-Cherenkov fluorescence light source simulated training tumor tissue sample.

[0119] The second step, constructing and training a multilayer sensing network for Cherenkov fluorescence tomography, includes:

[0120] 1) Construct a feedforward network A, which includes one input layer, four hidden layers and one output layer. The number of nodes in the input layer and the number of nodes in the hidden layer are the same as the number of nodes in the tumor tissue sample model grid, and the number of nodes in the output layer is the same as the number of nodes on the surface of the tumor tissue sample model grid.

[0121] 2) Train the feedforward network A using the obtained multi-Cherenkov fluorescence light source tumor tissue samples. The network input is the distribution data of the multi-Cherenkov fluorescence light source of the simulated tumor tissue samples inside the tumor tissue sample model, and the network output is the predicted distribution data of the multi-Cherenkov fluorescence light source simulated tumor tissue samples on the surface of the tumor tissue sample model.

[0122] 3) Construct an inverse network B, which includes one input layer, four hidden layers and one output layer. The number of nodes in the input layer is the same as the number of nodes on the surface of the tumor tissue sample model grid, and the number of nodes in the output layer and the number of nodes in the hidden layer are the same as the number of nodes in the tumor tissue sample model grid.

[0123] 4) The obtained Docherenkov fluorescence light source tumor tissue samples are used to train the inverse network B. The network input is the distribution data of the Docherenkov fluorescence light source simulated tumor tissue samples on the surface of the tumor tissue sample model, and the network output is the predicted distribution data of the Docherenkov fluorescence light source simulated tumor tissue samples inside the tumor tissue sample model.

[0124] 5) Merge the feedforward network A and the inverse network B, and use the output layer of the trained feedforward network A as the input layer of the trained inverse network B to obtain the final multilayer perceptron network.

[0125] In steps 2) and 4), the output of each layer is corrected using a correction function; negative values ​​in the output of the linear units of the hidden and output layers are corrected using the following formula:

[0126]

[0127] Where X represents the output of the linear unit in the current layer, and ReLU represents the correction function; when the output is negative or zero, the correction function will set the negative value to zero.

[0128] In 2) and 4), the relationship between the current layer and the previous layer is as follows:

[0129] X i =Dropout 0.4 (ReLu(W i X i-1 +b i i≥2;

[0130] Where X i W represents the node value at the i-th layer. i b represents the weight of the i-th layer. i Represents the bias of the i-th layer, Dropout 0.4 It is a random function that indicates that there is a 40% probability that the nodes in each layer will be reset to zero;

[0131] In steps 2) and 4), the multilayer sensing network is trained under constraints using the following formula:

[0132]

[0133] Where ||·||2 represents the second-order norm, min ypred Denotes the y-values ​​that satisfy the least second norm. pred In 2), y true To train on the known Cherenkov fluorescence signal distribution information in tumor tissue samples, y pred The network outputs the corresponding predicted Cherenkov fluorescence signal distribution information; in 4), y true To train on the known three-dimensional distribution information of Cherenkov fluorescence sources in tumor tissue samples, y pred The network outputs the corresponding predicted three-dimensional distribution information of Cherenkov fluorescence sources.

[0134] The third step, acquiring Cherenkov fluorescence signals from the surface of the tumor tissue sample and reconstructing the three-dimensional distribution information of the Cherenkov fluorescence source inside the tumor tissue sample, specifically includes:

[0135] Cherenkov fluorescence signals were collected from tumor tissue sample tables;

[0136] Reconstruction methods were used to obtain preliminary distribution results of Cherenkov fluorescence sources within tumor tissue samples.

[0137] In the description of this invention, unless otherwise stated, "a plurality of" means two or more; the terms "upper," "lower," "left," "right," "inner," "outer," "front end," "rear end," "head," "tail," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0138] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented, in whole or in part, as a computer program product, the computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0139] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions, and improvements made by those skilled in the art within the scope of the technology disclosed in the present invention, and within the spirit and principles of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A system for preparing an electrochemiluminescent immunosensor for detecting tumor markers, characterized in that, The fabrication system for the electrochemiluminescence immunosensor for detecting tumor markers includes: The graphite carbon nitride preparation module is connected to the central control module and is used to prepare polyaniline gel using aniline, phytic acid and initiator, and then carbonize it to obtain graphite carbon nitride working electrode. The working electrode pretreatment module is connected to the central control module and is used to perform pretreatment operations such as activation, polishing, cleaning and nitrogen drying of the graphite carbon nitride working electrode through the pretreatment equipment. The central control module is connected to the graphite carbon nitride preparation module, the working electrode pretreatment module, the antigen standard solution preparation module, the modified electrode preparation module, the immunosensor preparation module, the tumor marker detection module, the sensor detection curve plotting module, the data storage module, and the update display module. It is used to coordinate and control the normal operation of each module of the electrochemiluminescent immunosensor preparation system for detecting tumor markers through the central processor. The antigen standard solution preparation module is connected to the central control module and is used to prepare bovine serum albumin solution and tumor marker antigen standard solution respectively through the standard solution preparation device; The modified electrode preparation module, connected to the central control module, is used to drop-coat bovine serum albumin solution and tumor marker antigen standard solution onto the surface of the graphite carbon nitride working electrode to obtain the modified electrode. An immunosensor fabrication module, connected to a central control module, is used to prepare an electrochemiluminescence immunosensor using an antigen standard solution and a modified electrode through electrochemiluminescence technology. The tumor marker detection module, connected to the central control module, is used to detect tumor markers using the prepared electrochemiluminescence immunoassay sensor and obtain a detection report. The sensor detection curve plotting module is connected to the central control module and is used to plot the working curve based on the electrochemiluminescence intensity of the electrode in the detection report through the curve plotting program.

2. The preparation system for the electrochemiluminescence immunosensor for detecting tumor markers as described in claim 1, characterized in that, The preparation system further includes: The data storage module, connected to the central control module, is used to store graphite carbon nitride preparation data, working electrode pretreatment data, antigen standard solution preparation data, modified electrode preparation data, immune sensor preparation data, tumor marker detection reports, and working curves via a memory. The updated display module, connected to the central control module, is used to update and display real-time data on graphite carbon nitride preparation, working electrode pretreatment, antigen standard solution preparation, modified electrode preparation, immunosensor preparation, tumor marker detection reports, and working curves via a display screen.

3. The preparation system for the electrochemiluminescence immunosensor for detecting tumor markers as described in claim 1, characterized in that, The molar ratio of the initiator, aniline, and phytic acid is 1-3:2-7:1, and the initiator is an ammonium sulfate solution or a hydrogen peroxide solution. The pretreatment module utilizes pretreatment equipment to perform activation, polishing, cleaning, and nitrogen drying pretreatment operations on the graphite carbon nitride working electrode, including: (1) The graphite carbon nitride working electrode is activated by using an activating material to obtain a three-dimensional layered porous graphite carbon nitride working electrode. (2) Polish the three-dimensional layered porous graphitic carbon nitride working electrode with Al2O3 polishing powder of 0.05-1.5μm; (3) The three-dimensional layered porous graphite carbon nitride working electrode after grinding and polishing is ultrasonically cleaned in ethanol and ultrapure water for 5-15 minutes, and then dried with nitrogen.

4. The preparation system for the electrochemiluminescence immunosensor for detecting tumor markers as described in claim 3, characterized in that, The activating material contains NaOH or KOH, and the activation temperature is 400–800℃.

5. The preparation system for the electrochemiluminescence immunosensor for detecting tumor markers as described in claim 1, characterized in that, An electrochemiluminescence immunosensor was prepared using an immunosensor fabrication module with an antigen standard solution and a modified electrode, comprising: (1) Take 6-10 μL of tumor marker antibody standard solution and drop it onto the surface of the modified electrode. Let it dry at room temperature to form a film. Clean the electrode with PBS buffer solution at pH 7.

4. (2) After drying, take 10 μL of bovine serum albumin solution with a mass fraction of 1-3% and drop it onto the electrode surface. Incubate at 37°C for 1-1.5 h to block non-specific binding sites and rinse the electrode surface. (3) Add 10 μL of tumor marker antigen standard solutions of different concentrations of 0.5 to 100 ng / mL, incubate the antigen and antibody at room temperature for 30 to 40 minutes, rinse and dry to obtain an electrochemiluminescent immunosensor.

6. The preparation system for the electrochemiluminescence immunosensor for detecting tumor markers as described in claim 1, characterized in that, The sensor detection curve plotting module uses a curve plotting program to plot the working curve based on the electrochemiluminescence intensity of the electrode in the detection report, including: (1) Connect the electrochemiluminescence immunosensor correctly to the electrochemical workstation; (2) Testing was performed using a multi-parameter chemiluminescence analysis system; the multi-parameter chemiluminescence analysis methods include: The first step is to generate a gridded tumor tissue sample model and generate training tumor tissue samples; The second step is to construct and train a multilayer sensing network for Cherenkov fluorescence tomography. The multilayer sensing network can be divided into a forward network A and a backward network B. The third step is to collect Cherenkov fluorescence signals on the surface of tumor tissue samples and reconstruct the three-dimensional distribution information of Cherenkov fluorescence light sources inside the tumor tissue samples. The fourth step is to map the preliminary reconstruction results onto the constructed gridded tumor tissue sample model, and then input it into the multilayer sensing network to obtain accurate reconstruction results. The first step of generating training tumor tissue samples includes: (i) Construct a tumor tissue sample model with a size of 5×5×5mm. 3 A tumor tissue sample model was constructed, and the constructed tumor tissue sample model was meshed using the finite element theory, thus obtaining the meshed tumor tissue sample model. (ii) Construct a single Cherenkov fluorescence light source to simulate tumor tissue samples. In the meshed tumor tissue sample model of (1), a single spherical Cherenkov fluorescence light source with a light source radius of 0.1 mm is set. The simulation training tumor tissue samples with a single Cherenkov fluorescence light source are generated using the Monte Carlo simulation MOSE platform. (iii) Tumor tissue sample expansion to obtain multi-Cherenkov fluorescence light source simulated tumor tissue sample. Based on the single-Cherenkov fluorescence light source simulated tumor tissue sample set obtained in (ii), the tumor tissue sample is expanded by using the tumor tissue sample combination method to obtain multi-Cherenkov fluorescence light source simulated training tumor tissue sample. The second step involves constructing and training a multilayer sensing network for Cherenkov fluorescence tomography, including: 1) Construct a feedforward network A, which includes one input layer, four hidden layers and one output layer. The number of nodes in the input layer and the number of nodes in the hidden layer are the same as the number of nodes in the tumor tissue sample model grid, and the number of nodes in the output layer is the same as the number of nodes on the surface of the tumor tissue sample model grid. 2) Train the feedforward network A using the obtained multi-Cherenkov fluorescence light source tumor tissue samples. The network input is the distribution data of the multi-Cherenkov fluorescence light source of the simulated tumor tissue samples inside the tumor tissue sample model, and the network output is the predicted distribution data of the multi-Cherenkov fluorescence light source simulated tumor tissue samples on the surface of the tumor tissue sample model. 3) Construct an inverse network B, which includes one input layer, four hidden layers and one output layer. The number of nodes in the input layer is the same as the number of nodes on the surface of the tumor tissue sample model grid, and the number of nodes in the output layer and the number of nodes in the hidden layer are the same as the number of nodes in the tumor tissue sample model grid. 4) The obtained Docherenkov fluorescence light source tumor tissue samples are used to train the inverse network B. The network input is the distribution data of the Docherenkov fluorescence light source simulated tumor tissue samples on the surface of the tumor tissue sample model, and the network output is the predicted distribution data of the Docherenkov fluorescence light source simulated tumor tissue samples inside the tumor tissue sample model. 5) Merge the feedforward network A and the inverse network B, and use the output layer of the trained feedforward network A as the input layer of the trained inverse network B to obtain the final multilayer perceptron network. In steps 2) and 4), the output of each layer is corrected using a correction function; negative values ​​in the output of the linear units of the hidden and output layers are corrected using the following formula: ； Where X represents the output of the linear unit in the current layer, and ReLU represents the correction function; when the output is negative or zero, the correction function will set the negative value to zero. In 2) and 4), the relationship between the current layer and the previous layer is as follows: X i =Dropout 0.4 (ReLu(W i X i -1+b i )) i≥2; Where X i W represents the node value at the i-th layer. i b represents the weight of the i-th layer. i Represents the bias of the i-th layer, Dropout 0.4 It is a random function that indicates that there is a 40% probability that the nodes in each layer will be reset to zero; In steps 2) and 4), the multilayer sensing network is trained under constraints using the following formula: ； Where ||·||2 represents the second-order norm, min ypred Denotes the y-values ​​that satisfy the least second norm. pred In 2), y true To train on the known Cherenkov fluorescence signal distribution information in tumor tissue samples, y pred The network outputs the corresponding predicted Cherenkov fluorescence signal distribution information; in 4), y true To train on the known three-dimensional distribution information of Cherenkov fluorescence sources in tumor tissue samples, y pred The network outputs the corresponding predicted three-dimensional distribution information of Cherenkov fluorescence sources. The third step involves collecting Cherenkov fluorescence signals from the surface of tumor tissue samples and reconstructing the three-dimensional distribution information of Cherenkov fluorescence sources within the tumor tissue samples. Specifically, this includes: Cherenkov fluorescence signals were collected from tumor tissue sample tables; Reconstruction methods were used to obtain preliminary distribution results of Cherenkov fluorescence sources within tumor tissue samples. (3) Plot working curves based on the relationship between the current response obtained from different electronic mediators and the concentrations of their corresponding tumor marker antigen standard solutions.

7. An electrochemiluminescent immunosensor for detecting tumor markers, prepared using the preparation system of the electrochemiluminescent immunosensor for detecting tumor markers as described in any one of claims 1 to 6, characterized in that, The electrochemiluminescent immunosensor for detecting tumor markers includes a working electrode, bovine serum albumin solution, and tumor marker antigen standard solution.

8. A computer program product stored on a computer-readable medium, comprising a computer-readable program that, when executed on an electronic device, provides a user input interface for applying the preparation system of the electrochemiluminescent immunosensor for detecting tumor markers as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to apply the preparation system of the electrochemiluminescent immunosensor for detecting tumor markers as described in any one of claims 1 to 6.

10. An information data processing terminal, characterized in that, The information data processing terminal is used to implement the preparation system of the electrochemiluminescence immunosensor for detecting tumor markers as described in any one of claims 1 to 6.

Images