Detection method of multiple biomarkers based on nanozyme chemiluminescence technology

Abstract

The present application discloses a method for detecting multiple biomarkers based on nanozyme chemiluminescence technology, the method comprising: preparing iron oxide nanoparticles as nanozyme cores, coating substrate molecules on the surface of nanoparticles to form nanozyme-substrate complexes; mixing the nanozyme-substrate complexes with the sample to be tested, incubating the mixture, and transferring the mixture to a microplate after adding a hydrogen peroxide solution to collect chemiluminescent signals using a microplate reader; extracting characteristic parameters of the collected luminescence curves including peak luminous intensity, time to peak, half-peak width, rate of rise, rate of decay, integrated intensity, and / or wavelength ratio; constructing and training a multi-layer neural network model to predict the concentrations of multiple biomarkers based on the characteristic parameters of the sample data. Through the scheme of the present application, multiple biomarkers can be detected simultaneously, thereby improving the accuracy of detection.

Description

Technical Field

[0001] The present application relates to the field of bioinformatics, and in particular to a method for detecting multiple biomarkers based on nanozyme chemiluminescence technology. Background Art

[0002] The simultaneous detection of multiple biomarkers has become an important demand in modern medical diagnosis and health monitoring. It is closely related to the early diagnosis, prognosis assessment and personalized treatment of various diseases. However, traditional biomarker detection methods often require separate testing of each marker, which is not only time-consuming and labor-intensive, but may also be unable to complete comprehensive testing due to limited sample size. In addition, the content of some biomarkers in the early stages of the disease is extremely low, making it difficult to accurately detect them using traditional methods. This has led to an urgent need for highly sensitive, highly specific, and multiplexed detection technologies.

[0003] In recent years, the rapid development of nanotechnology and biosensing has provided new ideas for solving this problem. Among them, nanozymes have attracted widespread attention due to their unique catalytic properties and versatility. Nanozymes are a class of nanomaterials with enzyme-like activity. They can mimic the catalytic function of natural enzymes but have higher stability and controllability. However, how to apply nanozyme technology to the simultaneous detection of multiple biomarkers and achieve high sensitivity and high specificity remains a challenge. In addition, traditional multiplex detection often faces problems such as signal overlap and interference.

[0004] Therefore, there is an urgent need for a technical solution that can detect multiple biomarkers simultaneously and improve the accuracy of detection. Summary of the Invention

[0005] To address the shortcomings of the prior art, the present invention provides a method for detecting multiple biomarkers based on nanozyme chemiluminescence technology. This invention solves the technical problems of the prior art, such as the low signal-to-noise ratio in simultaneous detection.

[0006] The embodiment of the present application provides a method for detecting multiple biomarkers based on nanozyme chemiluminescence technology, including: preparing iron oxide nanoparticles as the core of the nanozyme, and coating the substrate molecules on the surface of the nanoparticles to form a nanozyme-substrate complex; mixing the nanozyme-substrate complex with the sample to be tested, incubating the mixture, adding a hydrogen peroxide solution, and transferring the mixture to a microplate to collect the chemiluminescence signal using a microplate reader; extracting characteristic parameters of the collected luminescence curve, including peak luminescence intensity, time to peak, half-peak width, rise rate, decay rate, integrated intensity and / or wavelength ratio; and constructing and training a multi-layer neural network model to predict the concentrations of multiple biomarkers based on the characteristic parameters of the sample data.

[0007] In one possible implementation, iron oxide nanoparticles are prepared as the core of the nanozyme, and substrate molecules are coated on the surface of the nanoparticles to form a nanozyme-substrate complex, including: reacting an iron salt solution with an alkaline reagent under an inert atmosphere, separating, washing and drying to obtain nanoparticles with catalytic activity; dispersing the nanoparticles in an aqueous solution, adding a water-soluble polymer and a luminescent substrate, reacting under heating conditions, separating and washing to obtain a complex coated with the substrate; dispersing the complex in a buffer solution, adding a coupling agent for activation, and then adding multiple specific antibodies and reacting under low temperature conditions; and centrifuging and washing the reaction product to obtain the target nanozyme-substrate complex.

[0008] In one possible implementation, the nanozyme-substrate complex is mixed and incubated with the sample to be tested, and after adding hydrogen peroxide solution, it is transferred to a microplate to collect chemiluminescence signals using an enzyme reader, including: mixing a predetermined amount of nanozyme-substrate complex suspension with the serum sample to be tested, incubating for a preset time under constant temperature conditions to allow the biomarker to fully combine with the recognition molecule; adding a predetermined concentration of hydrogen peroxide solution to the mixture, quickly mixing it, and then transferring the reaction solution to a microplate; using a multifunctional enzyme reader in chemiluminescence mode, collecting the luminescence signal of the reaction solution according to preset measurement parameters to construct a luminescence curve.

[0009] In one possible implementation, extracting characteristic parameters including peak luminous intensity, time to peak, half-width, rise rate, decay rate, integrated intensity and / or wavelength ratio from the collected luminous curve includes: obtaining the luminous curve, wherein the luminous curve includes data on the change of luminous intensity over time; using the luminous curve to extract multiple characteristic parameters, wherein the characteristic parameters include peak intensity, time to peak, half-width, rise rate, decay rate, integrated intensity and wavelength ratio; calculating the characteristic parameters based on a preset formula, wherein the rise rate and decay rate are calculated by percentage of peak intensity, the integrated intensity is calculated by integrating the luminous intensity within the measurement time, and the wavelength ratio is calculated by the selected characteristic wavelength intensity ratio.

[0010] In one possible implementation, a multi-layer neural network model is constructed and trained to predict the concentrations of multiple biomarkers based on the characteristic parameters of sample data, including: constructing a multi-layer perceptron neural network model, including an input layer, at least two hidden layers and an output layer, wherein the input layer corresponds to a predetermined number of characteristic parameters, the hidden layer uses a ReLU activation function, and the output layer corresponds to the concentration prediction values ​​of multiple biomarkers; obtaining the characteristic parameters and corresponding concentration values ​​of standard samples of known concentrations, standardizing the characteristic parameters, and randomly initializing the weight matrix using the He initialization method; defining the mean square error as the loss function, using the Adam optimizer for model training, performing forward propagation and back propagation through batch training, and updating the weights and biases according to the calculated gradients; repeating the batch training and parameter update steps until a preset number of iterations is reached or the loss function converges, during which the model performance is evaluated using a cross-validation method, and the model is optimized by adjusting hyperparameters.

[0011] In one possible implementation, constructing a luminescence curve includes: ,in, represents the luminous intensity at time t, Indicates the maximum luminous intensity, represents the rate constant of ascent, Indicates time, represents the decay rate constant.

[0012] In one possible implementation, the step of calculating the characteristic parameter based on a preset formula includes: ,

[0013] in, Indicates the rate of ascent, represents the peak intensity, Indicates the time when the luminous intensity reaches 90% of the peak value. Indicates the time when the luminous intensity reaches 10% of the peak value. represents the decay rate, Indicates the time when the luminous intensity drops to 10% during the attenuation process. Indicates the time when the luminous intensity drops to 90% of the peak value during the attenuation process. represents the integrated intensity, represents the luminous intensity at time t, Indicates the total measurement time, represents the wavelength ratio, represents the luminous intensity at a wavelength of 500 nm, Indicates the luminous intensity at a wavelength of 600 nm.

[0014] In one possible implementation, a multilayer perceptron neural network model is constructed, including an input layer, at least two hidden layers and an output layer, wherein the input layer corresponds to a predetermined number of feature parameters, the hidden layer uses a ReLU activation function, and the output layer corresponds to the concentration prediction values ​​of multiple biomarkers, including: configuring the input layer as 7 nodes to correspond to 7 target feature parameters; configuring hidden layer 1 as 20 nodes, using the ReLU activation function; configuring hidden layer 2 as 10 nodes, using the ReLU activation function; configuring the output layer as 3 nodes to correspond to the output of the concentration prediction values ​​of S100β, NSE and OxLDL.

[0015] In the method for detecting multiple biomarkers based on nanozyme chemiluminescence technology provided above, the embodiment of the present application combines the peroxidase-like activity of the nanozyme with the chemiluminescent substrate and uses a machine learning algorithm to process the luminescent signal, thereby being able to simultaneously detect multiple biomarkers and improve the accuracy of detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 A schematic diagram of a process for detecting multiple biomarkers based on nanozyme chemiluminescence technology provided in an embodiment of the present application;

[0018] Figure 2 A schematic diagram of a process for preparing a nanozyme-substrate complex provided in an embodiment of the present application;

[0019] Figure 3 A schematic diagram of a luminescence curve provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present application.

[0021] Those skilled in the art will understand that the terms "first" and "second" in the embodiments of the present application are only used to distinguish different steps, devices or modules, and do not represent any specific technical meaning or the necessary logical order between them. It should also be understood that in the embodiments of the present application, "multiple" can refer to two or more, and "at least one" can refer to one, two or more. It should also be understood that for any component, data or structure mentioned in the embodiments of the present application, unless explicitly defined or given a contrary suggestion in the context, it can generally be understood as one or more. In addition, the term "and / or" in this application is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this application generally indicates that the associated objects are in an "or" relationship. It should also be understood that the description of each embodiment in this application emphasizes the differences between the embodiments. The same or similar aspects can be referenced to each other. For the sake of brevity, they will not be described one by one.

[0022] At the same time, it should be understood that for ease of description, the dimensions of the various parts shown in the drawings are not drawn according to the actual proportional relationship. The following description of at least one exemplary embodiment is actually only illustrative and is in no way intended to limit the present application and its application or use. Technologies, methods and equipment known to ordinary technicians in the relevant fields may not be discussed in detail, but where appropriate, the technologies, methods and equipment should be considered part of the specification. It should be noted that similar numbers and letters represent similar items in the following figures, so once an item is defined in one figure, it does not need to be further discussed in subsequent figures.

[0023] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0024] Figure 1A flow chart of a method for detecting multiple biomarkers based on nanozyme chemiluminescence technology provided in an embodiment of the present application. The embodiment of the present application designs a new type of nanozyme-substrate complex that can simultaneously detect multiple biomarkers, and develops an intelligent algorithm for analyzing chemiluminescence signals and identifying different biomarkers. This method has the advantages of high sensitivity, high specificity and multiple detection. Biomarkers refer to indicators that can objectively measure and evaluate normal biological processes, pathological processes or drug treatment responses. These indicators can be proteins, nucleic acids, metabolites or other biological molecules. In the fields of medical diagnosis and biotechnology, rapid and accurate detection of multiple biomarkers is of great significance. Traditional detection methods usually require complex instruments and professional operations, and are often only able to detect a single or a few markers. The method disclosed in the present invention overcomes these limitations, realizes the simultaneous detection of multiple biomarkers, and improves detection efficiency and accuracy.

[0025] like Figure 1 As shown, in step S101, iron oxide nanoparticles are prepared as the core of the nanozyme, and substrate molecules are coated on the surface of the nanoparticles to form a nanozyme-substrate complex. Figure 2 (as shown) which includes: reacting an iron salt solution with an alkaline reagent under an inert atmosphere, separating, washing and drying to obtain nanoparticles with catalytic activity; dispersing the nanoparticles in an aqueous solution, adding a water-soluble polymer and a luminescent substrate, reacting under heating conditions, separating and washing to obtain a complex coated with the substrate; dispersing the complex in a buffer solution, adding a coupling agent for activation, and then adding multiple specific antibodies and reacting under low temperature conditions; and centrifuging and washing the reaction products to obtain the target nanozyme-substrate complex.

[0026] Specifically, first, an iron salt solution is reacted with an alkaline reagent under an inert atmosphere, and then separated, washed, and dried to obtain catalytically active nanoparticles. The "inert atmosphere" here can be nitrogen, argon, or other gas environments that do not chemically react with the reactants. The purpose of selecting an inert atmosphere is to prevent the oxidation of iron ions and ensure that the resulting nanoparticles have the expected structure and properties. The "iron salt solution" can be a soluble salt of iron such as ferric chloride or ferrous sulfate, while the "alkaline reagent" can be sodium hydroxide, ammonia water, etc. During the reaction, the iron ions undergo hydrolysis and condensation in an alkaline environment to form iron oxide nanoparticles. The separation, washing, and drying steps are intended to remove reaction by-products and unreacted raw materials to obtain pure nanoparticles.

[0027] Next, the nanoparticles are dispersed in an aqueous solution, and a water-soluble polymer and a luminescent substrate are added. The reaction is carried out under heating conditions. After separation and washing, a substrate-coated complex is obtained. The purpose of this step is to form a polymer coating containing the luminescent substrate on the surface of the nanoparticles. The "water-soluble polymer" can be polyethylene glycol, polyacrylamide, etc., which can increase the stability and biocompatibility of the nanoparticles. The "luminescent substrate" refers to a substance that can produce chemiluminescence under specific conditions, such as luminol and nitroso compounds. The heating conditions help promote the binding of the polymer and substrate to the nanoparticle surface.

[0028] Finally, the complex is dispersed in a buffer solution, activated by adding a coupling agent, and then a variety of specific antibodies are added and reacted under low temperature conditions. The reaction product is centrifuged and washed to obtain the target nanozyme-substrate complex. The key to this step is to connect specific antibodies to the surface of the complex, giving it the ability to recognize and bind to specific biomarkers. The "coupling agent" can be a commonly used protein cross-linking agent such as EDC / NHS, which can activate the carboxyl groups on the surface of the complex to facilitate reaction with the amino groups of the antibody. "Low temperature conditions" usually refer to around 4°C, which helps maintain the activity of the antibody and reduce nonspecific binding.

[0029] The above steps yield a nanozyme-substrate complex that combines the catalytic activity of the nanozyme, the signal-generating ability of the luminescent substrate, and the specific recognition function of the antibody. This complex is a key material for the simultaneous detection of multiple biomarkers.

[0030] In step S102 , the nanozyme-substrate complex is mixed with the sample to be tested and incubated, and after adding hydrogen peroxide solution, it is transferred to a microplate to collect the chemiluminescence signal using a microplate reader.

[0031] The "test sample" here can be a biological sample containing the target biomarker, such as serum, urine, or tissue homogenate. The incubation process is typically performed at a specific temperature (e.g., 37°C) and time (e.g., 30 minutes) to allow the biomarker in the sample to fully bind to the antibody on the surface of the complex. The incubation time and temperature must be optimized based on the specific antigen-antibody reaction kinetics to ensure equilibrium without compromising sample stability.

[0032] After incubation, hydrogen peroxide solution is added. Hydrogen peroxide plays a key role here, serving as the substrate for the nanozyme-catalyzed reaction. The iron oxide nanoparticles, acting as nanozymes, exhibit catalytic activity similar to that of natural peroxidases, catalyzing the decomposition of hydrogen peroxide to produce reactive oxygen species. These reactive oxygen species then react with the luminescent substrate on the surface of the complex, generating a chemiluminescent signal.

[0033] Transferring the reaction mixture to a microplate facilitates subsequent signal detection. Microplates typically come in standard 96- or 384-well formats, with each well accommodating a separate reaction system. This design allows for simultaneous analysis of multiple samples, improving assay efficiency.

[0034] Finally, the chemiluminescent signal is collected using a microplate reader. A microplate reader is a commonly used bioanalytical instrument that accurately measures the intensity of the light signal in each well of a microplate. In this method, a microplate reader is used to detect the chemiluminescent signal. It records the change in luminescence intensity over time in real time, generating complete luminescence kinetic curves. These curves contain a wealth of information that can be used for subsequent data analysis and biomarker concentration prediction.

[0035] Because multiple specific antibodies are attached to the surface of the complex, each antibody can recognize and bind to a specific biomarker. When different biomarkers bind to the complex, they affect the catalytic activity of the nanozyme or the reaction kinetics of the luminescent substrate, resulting in different chemiluminescent signal characteristics. This multiplex detection capability greatly improves detection efficiency and reduces sample consumption and detection time.

[0036] Furthermore, the embodiment of the present application includes: mixing a predetermined amount of nanozyme-substrate complex suspension with a serum sample to be tested, incubating for a preset time under constant temperature conditions to allow the biomarker to fully bind to the recognition molecule; adding a predetermined concentration of hydrogen peroxide solution to the mixture, quickly mixing it, and transferring the reaction solution to a microplate; using a multifunctional microplate reader in chemiluminescence mode to collect the luminescent signal of the reaction solution according to preset measurement parameters to construct a luminescence curve. For example, in one implementation scenario, 20 μL of the above-mentioned nanozyme-substrate complex suspension is taken and 80 μL of the serum sample to be tested is added. Incubate at 37°C for 30 minutes to allow the biomarker to fully bind to the recognition molecule. Add 100 μL of H2O2 solution (final concentration 5 mM) and mix it quickly. Immediately transfer the reaction solution to a 96-well black flat-bottom microplate. Use a multifunctional microplate reader (such as MR-96A) to collect signals in chemiluminescence mode. Set the measurement parameters: integration time 0.5 seconds, interval 7 seconds, total measurement time 4 minutes.

[0037] The construction of the luminescence curve includes: ,in, represents the luminous intensity at time t, Indicates the maximum luminous intensity, represents the rate constant of ascent, Indicates time, represents the decay rate constant. The presence of different biomarkers will affect these parameters, resulting in different luminescence curves.

[0038] In step S103, characteristic parameters including peak luminous intensity, time to peak, half-peak width, rise rate, decay rate, integrated intensity and / or wavelength ratio are extracted from the collected luminous curve.

[0039] Peak luminescence intensity (PLI) refers to the maximum luminescence intensity in the luminescence curve. This parameter directly reflects the intensity of the chemiluminescent reaction and is generally positively correlated with the concentration of the biomarker. Time to peak intensity (TTP) refers to the time from the start of the reaction to the peak luminescence intensity. This parameter reflects the kinetics of the reaction and may be affected by the interaction between the biomarker and the nanozyme-substrate complex.

[0040] The half-width (FWHM) is the time span over which the luminescence intensity reaches half its peak value. This parameter describes the duration of the luminescence signal and can reflect the stability and persistence of the reaction. The rise rate and decay rate describe the speed at which the luminescence signal increases and decreases, respectively. These two parameters can be obtained by calculating the slope of the luminescence curve over a specific time period and reflect the kinetic characteristics of the reaction.

[0041] Integrated intensity refers to the area under the luminescence curve. It comprehensively considers both luminescence intensity and duration, providing a more comprehensive picture of signal strength. Wavelength ratio refers to the ratio of luminescence intensities measured at different wavelengths. This parameter may reflect the impact of different biomarkers on the luminescence spectrum and help distinguish between different biomarkers.

[0042] It is important to note that different biomarkers may have different effects on these parameters. For example, some biomarkers may primarily affect peak intensity, while others may affect reaction kinetics more, altering the time to peak or decay rate. By comprehensively analyzing these parameters, more comprehensive and accurate biomarker information can be obtained.

[0043] Specifically, it includes: obtaining the luminescence curve, wherein the luminescence curve includes data on the change of luminescence intensity over time; using the luminescence curve to extract multiple characteristic parameters, the characteristic parameters including peak intensity, peak time, half-peak width, rise rate, decay rate, integrated intensity and wavelength ratio; calculating the characteristic parameters based on a preset formula, wherein the rise rate and decay rate are calculated by percentage of peak intensity, the integrated intensity is calculated by integrating the luminescence intensity within the measurement time, and the wavelength ratio is calculated by the selected characteristic wavelength intensity ratio.

[0044] Calculating the characteristic parameters based on a preset formula includes: ,in, Indicates the rate of ascent, represents the peak intensity, Indicates the time when the luminous intensity reaches 90% of the peak value. Indicates the time when the luminous intensity reaches 10% of the peak value. represents the decay rate, Indicates the time when the luminous intensity drops to 10% during the attenuation process. Indicates the time when the luminous intensity drops to 90% of the peak value during the attenuation process. represents the integrated intensity, represents the luminous intensity at time t, Indicates the total measurement time, represents the wavelength ratio, represents the luminous intensity at a wavelength of 500 nm, Indicates the luminous intensity at a wavelength of 600 nm.

[0045] At step S104, a multi-layer neural network model is constructed and trained to predict the concentrations of multiple biomarkers based on the characteristic parameters of the sample data. Specifically, the method includes: constructing a multi-layer perceptron neural network model, comprising an input layer, at least two hidden layers, and an output layer, wherein the input layer corresponds to a predetermined number of characteristic parameters, the hidden layers use a ReLU activation function, and the output layer corresponds to the predicted concentration values ​​of the multiple biomarkers; obtaining the characteristic parameters and corresponding concentration values ​​of standard samples of known concentrations, normalizing the characteristic parameters, and randomly initializing the weight matrix using the He initialization method; defining mean square error as the loss function, using the Adam optimizer for model training, performing forward and backward propagation through batch training, and updating the weights and biases based on the calculated gradients; repeating the batch training and parameter update steps until a predetermined number of iterations is reached or the loss function converges, during which the model performance is evaluated using a cross-validation method, and the model is optimized by adjusting hyperparameters.

[0046] In one embodiment, a multi-layer perceptron neural network model is constructed, including an input layer, at least two hidden layers, and an output layer, wherein the input layer corresponds to a predetermined number of feature parameters, the hidden layer uses a ReLU activation function, and the output layer corresponds to the concentration prediction values ​​of multiple biomarkers, including: configuring the input layer as 7 nodes to correspond to 7 target feature parameters; configuring hidden layer 1 as 20 nodes and using a ReLU activation function; configuring hidden layer 2 as 10 nodes and using a ReLU activation function; configuring the output layer as 3 nodes to correspond to the output of the concentration prediction values ​​of S100β, NSE, and OxLDL.

[0047] The forward propagation process of the model can be expressed as:

[0048] H_1 = ReLU(W_1 * X + b_1);

[0049] H_2 = ReLU(W_2 * H_1 + b_2);

[0050] Y = W_3 * H_2 + b_3;

[0051] Among them, X is the input feature vector, H_1 and H_2 are the hidden layer outputs, Y is the prediction result, W and b are the weight matrix and bias vector respectively.

[0052] The model training steps are as follows:

[0053] (1) Prepare the training data set: Use standard samples with known concentrations (such as S100β, NSE, and OxLDL in the range of 0-100 ng / mL) for detection to obtain characteristic parameters and corresponding concentration values.

[0054] (2) Data preprocessing: Standardize the feature parameters so that their mean is 0 and their standard deviation is 1.

[0055] (3) Initialize model parameters: Use the He initialization method to randomly initialize the weight matrix.

[0056] (4) Define the loss function: Use mean square error (MSE) as the loss function.

[0057] (5) Optimization algorithm: Adam optimizer is used, and the learning rate is set to 0.001.

[0058] (6) Batch training: 32 samples are selected in each batch for forward propagation and backward propagation.

[0059] (7) Update parameters: Update weights and biases based on the calculated gradients.

[0060] (8) Repeat steps 6-7 until the preset number of iterations (e.g., 1000) is reached or the loss function converges.

[0061] During the training process, 5-fold cross-validation can be used to evaluate model performance, and the model can be optimized by adjusting hyperparameters (such as the number of hidden layer nodes, learning rate, etc.).

[0062] Furthermore, in conjunction with the above-described embodiment, the steps for testing and predicting the concentration of an unknown serum sample can be as follows: testing the unknown sample to obtain a chemiluminescence curve; extracting characteristic parameters; normalizing the characteristic parameters using the mean and standard deviation of the training dataset; inputting the normalized characteristic parameters into the trained neural network model; and obtaining the predicted S100β, NSE, and OxLDL concentrations output by the model.

[0063] Furthermore, to improve prediction accuracy, ensemble learning methods can be used. For example, multiple neural network models with different structures or initial parameters are trained. For each unknown sample, all models are used to make predictions. The median of all the predictions is taken as the final prediction value.

[0064] This approach can reduce the bias and variance of a single model and improve the stability and accuracy of predictions.

[0065] Figure 2 A schematic flow chart of a method for preparing a nanozyme-substrate complex provided in an embodiment of the present application.

[0066] like Figure 2 As shown, in step S201, an iron salt solution is reacted with an alkaline reagent under an inert atmosphere. After separation, washing, and drying, catalytically active nanoparticles are obtained. First, Fe3O4 nanoparticles need to be prepared as the nanozyme core. For example, a coprecipitation method can be used. The specific steps are as follows: 100 mL of deionized water is added to a 250 mL three-necked flask and nitrogen is introduced to deoxygenate for 30 minutes. 1.35 g of FeCl3·6H2O and 0.695 g of FeCl2·4H2O are added and stirred to dissolve. Heat in a 60°C water bath while rapidly adding 25 mL of ammonia water (25-28%) dropwise. The reaction is continued for 30 minutes while maintaining nitrogen protection and stirring. The product is separated using a permanent magnet and washed three times with deionized water and ethanol. The product is vacuum dried for 12 hours to obtain Fe3O4 nanoparticles.

[0067] At step S202, the nanoparticles are dispersed in an aqueous solution, a water-soluble polymer and a luminescent substrate are added, and the mixture is reacted under heating conditions. After separation and washing, a substrate-coated complex is obtained. Next, a substrate-coated polymer layer is coated on the surface of the Fe3O4 nanoparticles: 100 mg of Fe3O4 nanoparticles are dispersed in 50 mL of deionized water and sonicated for 10 minutes. 200 mg of polyvinylpyrrolidone (PVP, Mw≈40,000) is added and stirred to dissolve. 50 mg of luminol is added and sonicated for 5 minutes. The mixture is reacted in a 60°C water bath for 2 hours while stirring. The product is centrifuged and washed three times with deionized water.

[0068] In step S203, the complex is dispersed in a buffer solution and activated with a coupling agent. Subsequently, various specific antibodies are added and reacted at low temperature. The recognition molecule is modified and the product is dispersed in 10 mL of PBS buffer (pH 7.4). 20 mg of EDC and 10 mg of NHS are added and activated for 30 minutes. 100 μg of S100β antibody, 100 μg of NSE antibody, and 100 μg of OxLDL antibody are added, respectively. The reaction is allowed to proceed overnight at 4°C.

[0069] Finally, in step S204, the reaction product is centrifuged and washed to obtain the target nanozyme-substrate complex, for example, by centrifugation, washing three times with PBS, and resuspending in 1 mL of PBS for storage.

[0070] Furthermore, it's important to note the following points during this process: The size of the Fe₃O₄ nanoparticles significantly influences catalytic activity and can be controlled by adjusting the reaction temperature and time. The molecular weight of PVP affects the coating effect and can be selected based on specific needs. The amount of modified recognition molecules needs to be optimized; excessive amounts can affect nanozyme activity, while insufficient amounts can reduce detection sensitivity.

[0071] Figure 3 A schematic diagram of a luminescence curve provided in an embodiment of the present application. This figure shows a kinetic curve of a chemiluminescence detection method based on nanozyme catalysis in the presence of different biomarkers. The method utilizes Fe3O4 nanoparticles as the core of the nanozyme, and through surface modification of luminol substrate and specific recognition molecules, realizes the simultaneous detection of multiple cardiovascular and cerebrovascular disease markers such as S100β protein antigen (PSA), anti-human neuron-specific enolase (NSE) and oxidized low-density lipoprotein (OxLDL). The figure shows the curve of the change of chemiluminescence intensity over time in the presence of the control group and three different biomarkers, which intuitively reflects the working principle and performance characteristics of the detection method.

[0072] It can be observed from the figure that all curves show typical chemiluminescence kinetic characteristics, that is, a trend of rapid rise followed by slow decay. This kinetic behavior can be described by the double exponential equation Describe, where Represents the maximum luminous intensity, and By comparing the shapes and parameters of different curves, we can obtain rich analytical information.

[0073] First, the control curve shows the lowest peak intensity ( = 1023.7), indicating that the nanozyme-substrate complex exhibits a certain background signal in the absence of target analytes. This background signal may originate from the inherent catalytic activity of the nanozyme or nonspecific reactions and is an important reference for evaluating the sensitivity and specificity of the detection method.

[0074] After adding different biomarkers, the chemiluminescence curves all showed significant changes. In the presence of S100β, the peak intensity increased to 1578.3, the rise rate constant k1 increased to 0.0537, and the decay rate constant k2 decreased slightly. This indicates that the presence of S100β enhances the catalytic activity of the nanozyme, possibly because S100β causes conformational changes in the nanozyme or exposes more active sites after binding to the recognition molecule. Similarly, NSE and OxLDL also caused changes in peak intensity and kinetic parameters, but to different degrees. Among them, the changes caused by NSE were the most significant, with the peak intensity reaching 1897.6, k1 increasing to 0.0583, and k2 decreasing to 0.00728. This differential response provides a basis for multiple detection. By establishing a standard curve and pattern recognition algorithm, quantitative analysis of multiple biomarkers can be achieved.

[0075] The curve characteristics can be used to evaluate multiple performance indicators of the detection method. First, the signal-to-noise ratio (S / N) can be estimated by the ratio of the peak intensity in the presence of the target to the peak intensity of the control group. Taking NSE as an example, the S / N is approximately 1.85, indicating that the method has good sensitivity. Secondly, the curve change patterns caused by different biomarkers are different, reflecting that the method has a certain specific recognition ability. Furthermore, all curves completed the rise and most of the decay process within 300 seconds, indicating that the method has a faster response speed and a shorter detection cycle.

[0076] It is worth noting that the slope of the rising section of the curve (i.e., the k1 value) shows a positive correlation with the peak intensity, which suggests the kinetic mechanism of the nanozyme catalytic reaction. A possible explanation is that after the biomarker binds to the recognition molecule, it not only increases the number of active sites of the nanozyme, but also increases the binding affinity or reaction rate of the substrate molecule to the active site. This synergistic effect leads to the acceleration and enhancement of the chemiluminescent reaction. At the same time, the slight change in the k2 value indicates that the biomarker mainly affects the initial stage of the reaction, but has little effect on the stability of the luminescent product.

[0077] Furthermore, an embodiment of the present application also provides a biomarker detection device, comprising: a processor, a memory, and a system bus; the processor and the memory are connected via the system bus; the memory is used to store one or more programs, and the one or more programs include instructions, which, when executed by the processor, enable the processor to perform any of the above methods.

[0078] Furthermore, an embodiment of the present application also provides a computer program product, which, when running on a terminal device, enables the terminal device to execute any of the above methods.

[0079] Through the description of the above embodiments, it can be seen that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network communication device such as a media gateway, etc.) to execute the methods described in each embodiment of the present application or certain parts of the embodiments.

[0080] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the methods.

[0081] It should also be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0082] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for detecting multiple biomarkers based on nanozyme chemiluminescence technology, characterized in that: include: Iron oxide nanoparticles are prepared as the core of the nanozyme, and substrate molecules are coated on the surface of the nanoparticles to form a nanozyme-substrate complex; The nanozyme-substrate complex is mixed with the sample to be tested and incubated, and after adding hydrogen peroxide solution, it is transferred to a microplate to collect the chemiluminescent signal using a microplate reader; Extract characteristic parameters of the collected luminescence curve, including peak luminescence intensity, time to peak, half-peak width, rise rate, decay rate, integrated intensity and wavelength ratio; Build and train a multi-layer neural network model to predict the concentrations of multiple biomarkers based on characteristic parameters of sample data; The method of preparing iron oxide nanoparticles as the nanozyme core and coating the substrate molecules on the surface of the nanoparticles to form a nanozyme-substrate complex comprises: An iron salt solution is reacted with an alkaline reagent under an inert atmosphere, and nanoparticles with catalytic activity are obtained through separation, washing and drying. The nanoparticles are dispersed in an aqueous solution, a water-soluble polymer and a luminescent substrate are added, reacted under heating conditions, and separated and washed to obtain a complex coated with the substrate; The complex is dispersed in a buffer, a coupling agent is added for activation, and then a plurality of specific antibodies are added and reacted under low temperature conditions; The reaction product is centrifuged and washed to obtain the target nanozyme-substrate complex.

2. The detection method according to claim 1, wherein in, The nanozyme-substrate complex is mixed with the sample to be tested and incubated, and hydrogen peroxide solution is added and transferred to a microplate for collecting chemiluminescent signals using a microplate reader, including: A predetermined amount of nanozyme-substrate complex suspension is mixed with the serum sample to be tested and incubated at a constant temperature for a preset time to allow the biomarker to fully bind to the recognition molecule; Add a predetermined concentration of hydrogen peroxide solution to the mixture, mix quickly, and transfer the reaction solution to a microplate; The luminescence signal of the reaction solution was collected using a multifunctional microplate reader in chemiluminescence mode according to preset measurement parameters to construct a luminescence curve.

3. The detection method according to claim 1, wherein in, The extracted luminescence curves include characteristic parameters such as peak luminescence intensity, time to peak, half-peak width, rise rate, decay rate, integrated intensity and wavelength ratio, including: Acquiring the luminescence curve, wherein the luminescence curve includes data of luminescence intensity varying with time; Extracting multiple characteristic parameters using the luminescence curve, the characteristic parameters including peak intensity, time to peak, half-peak width, rise rate, decay rate, integrated intensity and wavelength ratio; The characteristic parameters are calculated based on a preset formula, wherein the rise rate and decay rate are calculated by percentage of peak intensity, the integrated intensity is calculated by integrating the luminous intensity within the measurement time, and the wavelength ratio is calculated by the selected characteristic wavelength intensity ratio.

4. The detection method according to claim 1, wherein in, Build and train a multi-layer neural network model to predict the concentrations of multiple biomarkers based on characteristic parameters of sample data, including: Constructing a multi-layer perceptron neural network model, including an input layer, at least two hidden layers, and an output layer, wherein the input layer corresponds to a predetermined number of feature parameters, the hidden layer uses a ReLU activation function, and the output layer corresponds to the predicted concentration values ​​of multiple biomarkers; Obtain the characteristic parameters and corresponding concentration values ​​of standard samples with known concentrations, standardize the characteristic parameters, and randomly initialize the weight matrix using the He initialization method; Define mean square error as the loss function, use Adam optimizer for model training, perform forward propagation and back propagation through batch training, and update weights and biases according to the calculated gradients; The batch training and parameter update steps are repeated until the preset number of iterations is reached or the loss function converges. During this period, the cross-validation method is used to evaluate the model performance, and the model is optimized by adjusting the hyperparameters.

5. The detection method according to claim 2, characterized in that in, Constructing a glow curve, including: ， in, represents the luminous intensity at time t, Indicates the maximum luminous intensity, represents the rate constant of ascent, Indicates time, represents the decay rate constant.

6. The detection method according to claim 3, characterized in that in, Calculating the characteristic parameters based on a preset formula includes: ， in, Indicates the rate of ascent, represents the peak intensity, Indicates the time when the luminous intensity reaches 90% of the peak value. Indicates the time when the luminous intensity reaches 10% of the peak value. represents the decay rate, Indicates the time when the luminous intensity drops to 10% during the attenuation process. Indicates the time when the luminous intensity drops to 90% of the peak value during the attenuation process. represents the integrated intensity, represents the luminous intensity at time t, Indicates the total measurement time, represents the wavelength ratio, represents the luminous intensity at a wavelength of 500 nm, Indicates the luminous intensity at a wavelength of 600 nm.

7. The detection method according to claim 4, characterized in that in, Construct a multi-layer perceptron neural network model, including an input layer, at least two hidden layers, and an output layer, wherein the input layer corresponds to a predetermined number of feature parameters, the hidden layer uses a ReLU activation function, and the output layer corresponds to the predicted concentration values ​​of multiple biomarkers, including: The input layer is configured as 7 nodes to correspond to 7 target feature parameters; Configure hidden layer 1 to have 20 nodes and use the ReLU activation function; Configure hidden layer 2 to have 10 nodes and use the ReLU activation function; The output layer is configured as 3 nodes to output the predicted concentration values ​​of S100β, NSE, and OxLDL.

Images