Method for detecting aflatoxin in vegetable oil using fluorescent probe method

By combining fluorescent probe method with deep neural network analysis, and utilizing carbon dots prepared from orange peel and graphene oxide quenchers, the problems of complexity and high cost of traditional detection methods are solved, achieving rapid and accurate aflatoxin detection, which is suitable for large-scale applications.

CN118329857BActive Publication Date: 2024-11-12CHINA NAT INST OF STANDARDIZATION
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202410496282.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-24
Publication Date
2024-11-12
Estimated Expiration
2044-04-24

AI Technical Summary

Technical Problem

Traditional methods for detecting aflatoxin in vegetable oils are complex to operate, require professional personnel and expensive equipment, and cannot meet the needs of rapid detection and large-scale application.

Method used

A fluorescent probe method was used, with carbon dots prepared from orange peel as fluorescent probes and graphene oxide as a quencher. Aflatoxin was detected by the temporal changes in fluorescence intensity. Data analysis was performed using a deep neural network to capture the temporal patterns and trends of fluorescence intensity and infer the toxin concentration.

Benefits of technology

It enables rapid and accurate detection of aflatoxin, reduces detection costs, is suitable for large-scale applications, and utilizes waste resources, thereby improving detection efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118329857B_ABST
    Figure CN118329857B_ABST
Patent Text Reader

Abstract

The present application discloses a method for detecting aflatoxin in vegetable oil using a fluorescent probe method, which introduces data processing and analysis algorithms at the back end to perform time series analysis of time series data of fluorescence intensity, so as to capture the time series pattern and change trend of fluorescence intensity, thereby inferring the concentration value of aflatoxin based on the time series change characteristics of fluorescence brightness, so as to detect the concentration value of aflatoxin.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of intelligent detection, and more specifically, to a method for detecting aflatoxin in vegetable oil using a fluorescent probe method. Background Art

[0002] In the field of food safety, aflatoxin is a toxin produced by Aspergillus flavus, which is commonly found in foods such as vegetable oils. Aflatoxin has strong carcinogenicity and mutagenicity, which can cause serious harm to human health. Therefore, detecting the aflatoxin content in vegetable oils is crucial for food safety.

[0003] However, traditional methods for detecting aflatoxin in vegetable oils usually use high-performance liquid chromatography (HPLC) and enzyme-linked immunosorbent assay (ELISA). Although these methods are highly sensitive and selective, they are complex to operate and require professional operators to operate. They also take a long time to analyze and cannot meet the needs of rapid detection, especially when testing large quantities of samples. In addition, traditional methods for detecting aflatoxin require expensive instruments and reagents, which makes the detection cost high and is not conducive to large-scale application and popularization.

[0004] Therefore, a method for detecting aflatoxins in vegetable oils using a fluorescent probe method is desired. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a method for detecting aflatoxin in vegetable oil using a fluorescent probe method, which introduces a data processing and analysis algorithm at the back end to perform a temporal analysis of the time series data of the fluorescence intensity, so as to capture the temporal pattern and change trend of the fluorescence intensity, thereby inferring the concentration value of aflatoxin based on the temporal change characteristics of the fluorescence brightness, so as to detect the concentration value of aflatoxin.

[0006] According to one aspect of the present application, a method for detecting aflatoxin in vegetable oil using a fluorescent probe method is provided, comprising:

[0007] Acquire the time series of fluorescence intensity;

[0008] Sequentially segmenting the time series of fluorescence intensity according to a predetermined time scale to obtain a set of local time series of fluorescence intensity;

[0009] Arranging each local time series of fluorescence intensity in the set of local time series of fluorescence intensity according to the time dimension to obtain a set of local time series input vectors of fluorescence intensity;

[0010] Performing feature extraction on each of the fluorescence intensity local time series input vectors in the set of fluorescence intensity local time series input vectors by using a fluorescence intensity time series correlation feature extractor based on a deep neural network to obtain a set of fluorescence intensity local time series correlation feature vectors;

[0011] Extracting typical features from the set of local temporal correlation feature vectors of the fluorescence intensity to obtain typical temporal pattern features of the fluorescence intensity;

[0012] Based on the typical time series pattern characteristics of the fluorescence intensity, the concentration value of aflatoxin is determined.

[0013] Compared with the prior art, the present application provides a method for detecting aflatoxin in vegetable oil using a fluorescent probe method, which introduces data processing and analysis algorithms at the back end to perform time series analysis of time series data of fluorescence intensity, so as to capture the time series pattern and change trend of fluorescence intensity, and thus infer the concentration value of aflatoxin based on the time series change characteristics of fluorescence brightness, so as to detect the concentration value of aflatoxin. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0015] Figure 1 This is a flow chart of a method for detecting aflatoxin in vegetable oil using a fluorescent probe method according to an embodiment of the present application;

[0016] Figure 2 A system architecture diagram of a method for detecting aflatoxin in vegetable oil using a fluorescent probe method according to an embodiment of the present application;

[0017] Figure 3 This is a flow chart of sub-step S5 of the method for detecting aflatoxin in vegetable oil using a fluorescent probe method according to an embodiment of the present application;

[0018] Figure 4 This is a flowchart of sub-step S51 of the method for detecting aflatoxin in vegetable oil using a fluorescent probe method according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0020] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0021] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0022] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0023] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0024] Traditional methods for detecting aflatoxins in vegetable oils usually use high performance liquid chromatography (HPLC) and enzyme-linked immunosorbent assay (ELISA). Although these methods are highly sensitive and highly selective, they are complex to operate and require professional operators to operate. They also require a long analysis time and cannot meet the needs of rapid detection, especially when testing large quantities of samples. In addition, traditional methods for detecting aflatoxins require expensive instruments and reagents, which makes the detection cost high and is not conducive to large-scale application and popularization. In response to the above technical problems, in the technical solution of the present application, a method for detecting aflatoxins in vegetable oils using a fluorescent probe method is proposed, which can use orange peel as a raw material for the preparation of carbon dots, use aptamer-modified carbon dots (DNA-CDs) as fluorescent probes, and combine graphene oxide as a quencher to construct a method for accurately and quickly detecting aflatoxin B1 (AFB1) based on the temporal changes in fluorescence intensity. This method utilizes the abundant carbohydrates in orange peel, including fructose, glucose, sucrose and cellulose, and prepares carbon dots with high oxygen functional groups through a hydrothermal method, which not only improves the performance of the probe but also realizes the recycling of waste.

[0025] In particular, in the process of detecting aflatoxin B1, first, a graphene oxide aqueous solution is added to the DNA-CDs dispersion solution, and then an AFB1 standard solution is added to the above solution system, and the time series of fluorescence intensity is recorded at the same time. Then, a data processing and analysis algorithm is introduced at the back end to perform a temporal analysis of the time series data of these fluorescence intensities, so as to capture the temporal pattern and change trend of the fluorescence intensity, and thus infer the concentration value of aflatoxin based on the temporal change characteristics of the fluorescence brightness, so as to detect the concentration value of aflatoxin. The principle of this method is that first, the carbon dots (CDs) with carboxyl groups are modified by aptamers composed of DNA with amino groups to achieve the functionalization of carbon dots. When graphene oxide is added, the carbon dots modified by the aptamer will interact with graphene oxide, resulting in the effective quenching of the fluorescence of the carbon dots. When AFB1 is present in the system or introduced, the aptamer on the graphene oxide will recognize the target and react with AFB1 to form a well-folded AFB1-aptamer carbon dot complex. At this time, the aptamer-modified carbon dots are no longer attached to the graphene oxide, but are desorbed from the graphene oxide, resulting in the restoration of the fluorescence of the aptamer-modified carbon dots. In this way, based on the above principle, the concentration of AFB1 can be detected by recording the time series data of the fluorescence intensity and analyzing the change characteristics.

[0026] In the technical solution of the present application, a method for detecting aflatoxin in vegetable oil using a fluorescent probe method is proposed. Figure 1 The present invention is a flow chart of a method for detecting aflatoxin in vegetable oil using a fluorescent probe method according to an embodiment of the present application. Figure 2FIG. 1 is a system architecture diagram of a method for detecting aflatoxin in vegetable oil using a fluorescent probe method according to an embodiment of the present application. Figure 1 and Figure 2 As shown, according to an embodiment of the present application, a method for detecting aflatoxin in vegetable oil using a fluorescent probe method includes the following steps: S1, obtaining a time series of fluorescence intensity; S2, segmenting the time series of fluorescence intensity according to a predetermined time scale to obtain a set of local time series of fluorescence intensity; S3, arranging each local time series of fluorescence intensity in the set of local time series of fluorescence intensity according to the time dimension to obtain a set of local time series input vectors of fluorescence intensity; S4, performing feature extraction on each local time series input vector of fluorescence intensity in the set of local time series input vectors of fluorescence intensity by a fluorescence intensity time series correlation feature extractor based on a deep neural network to obtain a set of local time series correlation feature vectors of fluorescence intensity; S5, performing typical feature extraction on the set of local time series correlation feature vectors of fluorescence intensity to obtain typical time series pattern features of fluorescence intensity; S6, determining the concentration value of aflatoxin based on the typical time series pattern features of fluorescence intensity.

[0027] In particular, the S1 and S2 obtain the time series of fluorescence intensity; and the time series of fluorescence intensity is segmented according to a predetermined time scale to obtain a set of local time series of fluorescence intensity. Since the fluorescence intensity has different intensity changes when different solutions are added, that is, the fluorescence intensity will continue to change over time in the time dimension, and in the process of monitoring the fluorescence intensity data, the amount of data may be large, and it is easy to ignore the micro-time series fluctuation information of the fluorescence intensity. Therefore, in order to be able to more fully and accurately analyze the time series characteristics of fluorescence intensity, so as to infer the concentration value of aflatoxin, in the technical solution of the present application, it is necessary to segment the time series of fluorescence intensity according to a predetermined time scale to obtain a set of local time series of fluorescence intensity, and arrange the local time series of each fluorescence intensity in the set of local time series of fluorescence intensity according to the time dimension to obtain a set of local time series input vectors of fluorescence intensity. By segmenting the time series of fluorescence intensity, the entire fluorescence intensity time series can be divided into multiple small time periods, so that the time series changes and patterns of fluorescence intensity in the local time period can be analyzed in more detail later.

[0028] In particular, in S3, each local time series of fluorescence intensity in the set of local time series of fluorescence intensity is arranged according to the time dimension to obtain a set of local time series input vectors of fluorescence intensity. It should be understood that by arranging according to the time dimension, the time series distribution information of the fluorescence intensity in each local time period can be retained, providing a data basis for subsequent fluorescence intensity time series feature extraction and change analysis.

[0029] In particular, the S4, through a fluorescence intensity time series correlation feature extractor based on a deep neural network, performs feature extraction on each fluorescence intensity local time series input vector in the set of the fluorescence intensity local time series input vector to obtain a set of fluorescence intensity local time series correlation feature vectors. In particular, in a specific example of the present application, the fluorescence intensity time series correlation feature extractor based on a deep neural network is a fluorescence intensity time series correlation feature extractor based on a one-dimensional convolutional layer. In the technical solution of the present application, in order to be able to mine the local time series pattern and change trend of the fluorescence intensity in each local time period, so as to effectively express the local time series characteristics of the fluorescence intensity, in the technical solution of the present application, each fluorescence intensity local time series input vector in the set of the fluorescence intensity local time series input vector is further subjected to feature mining in a fluorescence intensity time series correlation feature extractor based on a one-dimensional convolutional layer, so as to extract the local time series dynamic feature information of the fluorescence intensity in each local time period, so as to obtain a set of fluorescence intensity local time series correlation feature vectors.

[0030] It is worth noting that the one-dimensional convolution layer is a commonly used layer in deep learning to process data with temporal correlation. In the one-dimensional convolution layer, the convolution operation is performed along one dimension of the input data (usually the time dimension) to extract temporal features.

[0031] In particular, the step S5 extracts typical features from the set of local temporal correlation feature vectors of the fluorescence intensity to obtain typical temporal pattern features of the fluorescence intensity. In particular, in a specific example of the present application, Figure 3 As shown, the S5 includes: S51, performing feature optimization on the set of local temporal correlation feature vectors of fluorescence intensity to obtain a set of optimized local temporal correlation feature vectors of fluorescence intensity; S52, passing the set of optimized local temporal correlation feature vectors of fluorescence intensity through a typical feature extraction network to obtain a typical temporal pattern feature vector of fluorescence intensity as the typical temporal pattern feature of fluorescence intensity.

[0032] Specifically, the S51 performs feature optimization on the set of local temporal correlation feature vectors of the fluorescence intensity to obtain a set of optimized local temporal correlation feature vectors of the fluorescence intensity. In particular, in a specific example of the present application, Figure 4As shown, the S51 includes: S511, respectively calculating the weighting coefficient of each fluorescence intensity local time series correlation feature vector in the set of fluorescence intensity local time series correlation feature vectors to obtain a weighting coefficient vector composed of multiple weighting coefficients; S512, using each weighting coefficient in the weighting coefficient vector as a weighting factor to perform weighted optimization on the set of fluorescence intensity local time series correlation feature vectors to obtain the set of optimized fluorescence intensity local time series correlation feature vectors.

[0033] More specifically, the S511, respectively calculates the weight coefficient of each fluorescence intensity local time series association feature vector in the set of the fluorescence intensity local time series association feature vector to obtain a weight coefficient vector composed of multiple weight coefficients. It should be understood that in the technical solution described above, each fluorescence intensity local time series association feature vector in the set of the fluorescence intensity local time series association feature vector expresses the time series association characteristics of the fluorescence intensity in the local time domain. Therefore, when the set of the fluorescence intensity local time series association feature vector is subjected to the typical feature extraction network to extract the fluorescence intensity time series typical pattern feature, it is expected that the fluorescence intensity typical time series pattern feature vector maintains the temporal association feature distribution distinguishability of each fluorescence intensity local time series association feature vector for the local time domain, while improving the decoding probability certainty of each fluorescence intensity local time series association feature vector to the global time domain temporal feature domain under the local time domain distribution distinguishability, thereby improving the global time domain temporal feature expression effect of the fluorescence intensity typical time series pattern feature vector for the predetermined decoding value of the decoder-based aflatoxin concentration inference device. Based on this, the applicant of the present application respectively calculates the weighting coefficient of each fluorescence intensity local time series correlation feature vector in the set of fluorescence intensity local time series correlation feature vectors, expressed as:

[0034]

[0035] Among them, v i-max and v i-j are respectively the i-th fluorescence intensity local time series correlation feature vector V in the set of the fluorescence intensity local time series correlation feature vectors i The maximum eigenvalue and the jth eigenvalue of , L is the length of the eigenvector, log represents the logarithm with base 2, and α is the weight hyperparameter. Specifically, the eigenvector V is associated with each local time series of fluorescence intensity i The majority voting mechanism of the local temporal correlation distribution in the form of temporal feature crowdsourcing is used to seek the maximum individual information expectation of each feature vector under the distribution subordinate probability model of each local temporal correlation feature vector of fluorescence intensity relative to the global temporal decoding probability space. In this way, the coefficient ω is used to i For each fluorescence intensity local temporal correlation feature vector V iWeighted to optimize the local temporal correlation feature vector V of the fluorescence intensity i , we can then use the local temporal correlation feature vector V of each fluorescence intensity to i The local time domain average information confidence of each eigenvalue is jointly estimated relative to the global time domain decoding probability space to maintain the local time series correlation eigenvector V of each fluorescence intensity i The temporal feature distribution distinguishability is improved while improving the certainty of the decoding probability relative to the decoding probability space, thereby improving the global time domain temporal feature expression effect of the typical temporal pattern feature vector of the fluorescence intensity for the predetermined decoding value of the decoder-based aflatoxin concentration inference device, and improving the accuracy of the inference result. In this way, the concentration value of aflatoxin in vegetable oil can be detected more accurately based on the temporal variation characteristics of fluorescence brightness.

[0036] More specifically, in S512, each weighting coefficient in the weighting coefficient vector is used as a weighting factor to perform weighted optimization on the set of local temporal correlation feature vectors of fluorescence intensity to obtain the set of optimized local temporal correlation feature vectors of fluorescence intensity. That is, each weighting coefficient in the weighting coefficient vector is used as a weighting factor to apply to the set of local temporal correlation feature vectors of fluorescence intensity to achieve the effect of weighted optimization.

[0037] It is worth mentioning that in other specific examples of the present application, the set of local temporal correlation feature vectors of fluorescence intensity can also be feature optimized by other methods to obtain a set of optimized local temporal correlation feature vectors of fluorescence intensity, for example: inputting the set of local temporal correlation feature vectors of fluorescence intensity; transforming the feature vectors to extract more informative features; applying smoothing technology (such as moving average, Gaussian filtering, etc.) to smooth the feature vectors; normalizing the feature vectors to ensure that the numerical ranges of different features are consistent to avoid the model being affected by differences in the range of feature values, so as to obtain the set of optimized local temporal correlation feature vectors of fluorescence intensity.

[0038] Specifically, in S52, the set of the optimized local temporal correlation feature vectors of the fluorescence intensity is passed through a typical feature extraction network to obtain a typical temporal pattern feature vector of the fluorescence intensity as the typical temporal pattern feature of the fluorescence intensity. It should be understood that since each local temporal correlation feature vector of the fluorescence intensity in the set of local temporal correlation feature vectors of the fluorescence intensity respectively represents the local temporal characteristics of the fluorescence intensity in each local time period, in order to enhance the expression ability of the local temporal characteristics of the fluorescence intensity in the local time period after adding the graphene oxide aqueous solution and the AFB1 standard solution, thereby highlighting the semantics of the local temporal characteristics of the fluorescence intensity related to the concentration detection of aflatoxin, in the technical solution of the present application, the set of the local temporal correlation feature vectors of the fluorescence intensity is further passed through a typical feature extraction network to obtain a typical temporal pattern feature vector of the fluorescence intensity. It should be understood that the typical feature extraction network can learn and capture the correlation relationship and interaction between the local temporal correlation feature vectors of the fluorescence intensity, so as to identify the local temporal correlation characteristics of the fluorescence intensity of the key nodes in the set of the local temporal correlation feature vectors of the fluorescence intensity, and highlight and display them. In this way, it is possible to capture and highlight the typical patterns and change characteristics between the local time series characteristics of fluorescence intensity in each local time period, and capture the correlation relationship and mutual influence between the local time series characteristics of fluorescence intensity, which helps to better describe the time series pattern and change trend of fluorescence intensity, thereby facilitating a more accurate inference of the concentration value of aflatoxin based on the time series change characteristics of fluorescence brightness. More specifically, the set of the optimized local time series correlation feature vectors of fluorescence intensity is passed through a typical feature extraction network to obtain a typical time series pattern feature vector of fluorescence intensity as the typical time series pattern feature of fluorescence intensity, including: the set of the optimized local time series correlation feature vectors of fluorescence intensity is processed through the typical feature extraction network with the following typical feature extraction formula to obtain the typical time series pattern feature vector of fluorescence intensity; wherein, the typical feature extraction formula is:

[0039]

[0040]

[0041] Among them, v i (x) and v j (x) are the eigenvalues ​​of each position of the i-th and j-th optimized local temporal correlation feature vectors of fluorescence intensity in the set of the optimized local temporal correlation feature vectors of fluorescence intensity, respectively, i and v j are respectively the i-th and j-th optimized local temporal correlation feature vectors of fluorescence intensity in the set of optimized local temporal correlation feature vectors of fluorescence intensity, V kis the set of the optimized local temporal correlation feature vectors of fluorescence intensity, log represents the logarithmic function value with base 2, L is the length of each optimized local temporal correlation feature vector of fluorescence intensity, M is the number of vectors in the set of optimized local temporal correlation feature vectors of fluorescence intensity minus one, D i is the eigenvalue of each position in the feature vector of the local temporal semantic fluctuation of fluorescence intensity, N s is the length of the local temporal semantic fluctuation feature vector of the fluorescence intensity, exp(·) is an exponential operation, and V is the typical temporal pattern feature vector of the fluorescence intensity.

[0042] It is worth mentioning that in other specific examples of the present application, typical features of the set of local temporal correlation feature vectors of fluorescence intensity can be extracted by other methods to obtain typical temporal pattern features of fluorescence intensity, for example: inputting the set of local temporal correlation feature vectors of fluorescence intensity; performing dimensionality reduction processing on the set of local temporal correlation feature vectors of fluorescence intensity; clustering the feature vectors after dimensionality reduction using a clustering algorithm to classify similar feature vectors into the same category; analyzing the feature vectors in each cluster to find representative patterns or center points representing the typical features in the cluster to obtain the typical temporal pattern features of fluorescence intensity.

[0043] In particular, the S6 determines the concentration value of aflatoxin based on the typical time series pattern characteristics of the fluorescence intensity. In particular, in a specific example of the present application, the characteristic vector of the typical time series pattern of fluorescence intensity is passed through an aflatoxin concentration inference device based on a decoder to obtain an inference result, and the inference result is the concentration value of aflatoxin. That is to say, the typical time series pattern characteristics of fluorescence intensity are used to perform decoding regression, so as to infer the concentration value of aflatoxin based on the time series change characteristics of fluorescence brightness, so as to detect the concentration value of aflatoxin in vegetable oil using the fluorescent probe method. Specifically, the characteristic vector of the typical time series pattern of fluorescence intensity is passed through an aflatoxin concentration inference device based on a decoder to obtain an inference result, and the inference result is the concentration value of aflatoxin, including: using the decoder to decode and regress the characteristic vector of the typical time series pattern of fluorescence intensity according to the following formula to obtain a decoded value used to represent the concentration value of aflatoxin; wherein the formula is: Where X represents the characteristic vector of the typical temporal pattern of the fluorescence intensity, Y is the decoded value, and W is the weight matrix. Represents matrix multiplication.

[0044] In summary, according to the embodiment of the present application, a method for detecting aflatoxin in vegetable oil using a fluorescent probe method is explained, which introduces data processing and analysis algorithms at the back end to perform time series analysis of the time series data of fluorescence intensity, so as to capture the time series pattern and change trend of fluorescence intensity, and thus infer the concentration value of aflatoxin based on the time series change characteristics of fluorescence brightness, so as to detect the concentration value of aflatoxin.

[0045] In the technical solution of the present application, orange peel is used as a raw material for the preparation of carbon dots, aptamer-modified carbon dots (DNA-CDs) are used as fluorescent probes, and graphene oxide is used as a quencher to construct a new method for accurate and rapid detection of aflatoxin B1 (AFB1). Orange peel, as a common form of domestic waste, contains a large amount of carbohydrates, including fructose, glucose, sucrose and cellulose. The abundance of these raw materials will form a large number of oxygen functional groups during the hydrothermal preparation of carbon dots, thereby improving the performance of the carbon dots. In addition, orange peel is widely available and low-cost, which can achieve waste utilization.

[0046] 1. Preparation of Orange Peel Carbon Dots

[0047] Collect the discarded orange peel, wash it in water and dry it in the sun. Then, wash 2g of the pretreated orange peel in 100mL of 0.1M H2SO4 aqueous solution and rinse it with water, filter it and dry it in an oven at 150℃ for 2 hours. Soak the treated orange peel in sodium hypochlorite solution for 4 hours for oxidation treatment, and then rinse it in water several times until the pH value of the washing water reaches 7. Weigh 1g of urea and dissolve it in 25ml of ultrapure water, and ultrasonicate it for 15min. Put the oxidized orange peel in the above solution in a polytetrafluoroethylene-lined autoclave, react at 230℃ for 4h, let the autoclave cool naturally, and wash the obtained brown solution with dichloromethane to remove the unreacted organic part. The obtained carbon dot solution was centrifuged at 4000rmp for 15min, and filtered with a 0.22μm filter membrane to remove the residue to obtain a brown carbon dot solution, which was stored at 4℃ in the dark. During the preparation of carbon dots, the reaction temperature and time were optimized. The preparation was carried out at 180℃, 190℃, 200℃, 210℃, 220℃, 230℃, 4h, 6h, 8h and 10h, respectively. It was finally found that the quantum yield of carbon dots obtained at 230℃ and 4h was the highest.

[0048] 2. Aptamer Modification

[0049] First, weigh 30 μL of EDC (1 mg / μL) powder and 30 μL of NHS (0.25 mg / μL) particles in a beaker, add 1 mL of pH 7.4 PBS buffer solution, and then add 100 μL of the prepared CDs solution. The mixed solution is ultrasonically stirred for 30 min until the solution is mixed evenly. Next, 20 μL of AFB1 aptamer (10 μM) is added to 10 μL of the mixed solution and ultrasonically stirred for 2 h to ensure that the aptamer is successfully modified onto the carbon dots.

[0050] 3. Selection of quencher

[0051] The carbon dot material was quenched by using five different quenchers of the same concentration (1 mg / ml), namely, graphene oxide ethanol solution, graphene oxide aqueous solution, gold nanocolloid, and tungsten disulfide nanosheet (WS2) ethanol solution. The results showed that the quenching efficiency was 88.79%, 94.51%, 69.46%, and 45.19%, respectively. Therefore, the graphene oxide aqueous solution with the highest quenching efficiency was selected for subsequent experiments.

[0052] 4. Detection of aflatoxin B1

[0053] First, add graphene oxide aqueous solution to the DNA-CDs dispersion solution, and accurately record the fluorescence intensity before adding graphene oxide and 3 minutes after adding graphene oxide. Add different concentrations of AFB1 standard solution to the above solution system, and record the fluorescence intensity after incubation at room temperature for 30 minutes. First, the aptamer composed of DNA with amino groups modifies the carbon dots (CDs) with carboxyl groups to functionalize the carbon dots. At this time, when graphene oxide is added, the carbon dots modified by the aptamer will interact with graphene oxide due to π-π stacking, resulting in the adsorption of the aptamer-modified carbon dots on the surface of graphene oxide, thereby effectively quenching the fluorescence of the carbon dots; when AFB1 exists in the system or AFB1 is introduced into the system, the aptamer attached to the graphene oxide recognizes the target and reacts with AFB1 to form a well-folded AFB1-aptamer carbon dot complex, and the bases involved in the π-π stacking interaction have been occupied by AFB1, so the aptamer-modified carbon dots can no longer attach to the graphene oxide, but will be desorbed from the graphene oxide, thereby restoring the fluorescence of the aptamer-modified carbon dots. This part of the experiment detected AFB1 based on the above principle.

[0054] 5. Detection of AFB1 in vegetable oils

[0055] 50 μL of aflatoxin B1 solution of different concentrations was added to 200 μL household peanut oil sample, and then the pH value was adjusted to neutral, and the graphene oxide aqueous solution was added to the DNA-CDs dispersion, and the fluorescence intensity before and 3 minutes after the addition of graphene oxide was accurately recorded. Then the mixed solution and 0.01 M phosphate buffer (PB, pH 7.0) containing different concentrations of aflatoxin B1 were incubated at room temperature for 30 minutes, and the fluorescence intensity was recorded. The above experiment was repeated five times and the relative standard deviation was calculated.

[0056] 6. Selectivity and stability of fluorescence sensors

[0057] In order to evaluate the selectivity of orange peel-aptamer functionalized carbon dots system for AFB1 detection, the effects of possible interferents including aflatoxin B2 (AFB2), aflatoxin G1 (AFG1), aflatoxin G2 (AFG2), ochratoxin A (OTA), patulin (PTL), deoxynivalenol (DON) and zearalenone (ZEN) on the system were selected. The carbon dots solution was stored at 4℃ in the dark, and its fluorescence intensity was recorded and tested after 15 days, 30 days and 45 days to determine the stability of the sensor. Five batches of aptamer-modified carbon dots were prepared and AFB1 sensors were prepared using different batches of carbon dots solution to study the repeatability of the sensor.

[0058] 7. Calculation of the fluorescence recovery rate of the system by AFB1

[0059] The calculation equation of the fluorescence recovery rate (I%) of the system by AFB1 is shown as follows, where F0 is the fluorescence intensity of the carbon dot solution, F HAs represents the fluorescence intensity three minutes after adding graphene oxide aqueous solution, F HAs / AFB1 Represents the fluorescence intensity after incubation with graphene oxide and aflatoxin B1 solution.

[0060] I%=(FHAs / AFB1-FHAs) / (F0-FHAs)

[0061] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for detecting aflatoxin in vegetable oil using a fluorescent probe method, characterized in that: include: Acquire the time series of fluorescence intensity; Sequentially segmenting the time series of fluorescence intensity according to a predetermined time scale to obtain a set of local time series of fluorescence intensity; Arranging each local time series of fluorescence intensity in the set of local time series of fluorescence intensity according to the time dimension to obtain a set of local time series input vectors of fluorescence intensity; Performing feature extraction on each of the fluorescence intensity local time series input vectors in the set of fluorescence intensity local time series input vectors by using a fluorescence intensity time series correlation feature extractor based on a deep neural network to obtain a set of fluorescence intensity local time series correlation feature vectors; Extracting typical features from the set of local temporal correlation feature vectors of the fluorescence intensity to obtain typical temporal pattern features of the fluorescence intensity; Determining the concentration value of aflatoxin based on the typical time series pattern characteristics of the fluorescence intensity; The fluorescence intensity temporal correlation feature extractor based on a deep neural network is a fluorescence intensity temporal correlation feature extractor based on a one-dimensional convolutional layer; The method comprises: extracting features from each of the fluorescence intensity local time series input vectors in the set of the fluorescence intensity local time series input vectors by using a fluorescence intensity time series correlation feature extractor based on a deep neural network to obtain a set of fluorescence intensity local time series correlation feature vectors, including: extracting features from each of the fluorescence intensity local time series input vectors in the set of the fluorescence intensity local time series input vectors by using a fluorescence intensity time series correlation feature extractor based on a one-dimensional parametric layer to obtain a set of fluorescence intensity local time series correlation feature vectors; Extracting typical features from the set of local temporal correlation feature vectors of the fluorescence intensity to obtain typical temporal pattern features of the fluorescence intensity includes: Performing feature optimization on the set of local temporal correlation feature vectors of fluorescence intensity to obtain an optimized set of local temporal correlation feature vectors of fluorescence intensity; Passing the set of the optimized local temporal correlation feature vectors of the fluorescence intensity through a typical feature extraction network to obtain a typical temporal pattern feature vector of the fluorescence intensity as the typical temporal pattern feature of the fluorescence intensity; Performing feature optimization on the set of local temporal correlation feature vectors of fluorescence intensity to obtain an optimized set of local temporal correlation feature vectors of fluorescence intensity, comprising: respectively calculating the weighting coefficient of each fluorescence intensity local time series correlation feature vector in the set of fluorescence intensity local time series correlation feature vectors to obtain a weighting coefficient vector composed of a plurality of weighting coefficients; Using each weighting coefficient in the weighting coefficient vector as a weighting factor, weighted optimization is performed on the set of local temporal correlation feature vectors of fluorescence intensity to obtain the set of optimized local temporal correlation feature vectors of fluorescence intensity; The method comprises: processing the set of the optimized local temporal correlation feature vectors of the fluorescence intensity through the typical feature extraction network to obtain the typical temporal pattern feature vector of the fluorescence intensity as the typical temporal pattern feature of the fluorescence intensity, including: processing the set of the optimized local temporal correlation feature vectors of the fluorescence intensity through the typical feature extraction network using the following typical feature extraction formula to obtain the typical temporal pattern feature vector of the fluorescence intensity; Among them, the typical feature extraction formula is: Among them, v i () and v j () are the eigenvalues ​​of each position of the i-th and j-th optimized local temporal correlation feature vectors of fluorescence intensity in the set of the optimized local temporal correlation feature vectors of fluorescence intensity, respectively, i and v j are respectively the i-th and j-th optimized local temporal correlation feature vectors of fluorescence intensity in the set of optimized local temporal correlation feature vectors of fluorescence intensity, V k is the set of the optimized local temporal correlation feature vectors of fluorescence intensity, log represents the logarithmic function value with base 2, L is the length of each optimized local temporal correlation feature vector of fluorescence intensity, M is the number of vectors in the set of optimized local temporal correlation feature vectors of fluorescence intensity minus one, D i is the eigenvalue of each position in the feature vector of the local temporal semantic fluctuation of fluorescence intensity, N s is the length of the local temporal semantic fluctuation feature vector of the fluorescence intensity, exp(·) is the exponential operation, and V is the typical temporal pattern feature vector of the fluorescence intensity; Determining the concentration value of aflatoxin based on the typical time series pattern characteristics of the fluorescence intensity, including: passing the characteristic vector of the typical time series pattern of the fluorescence intensity through an aflatoxin concentration inference device based on a decoder to obtain an inference result, wherein the inference result is the concentration value of aflatoxin; The typical time series pattern feature vector of the fluorescence intensity is passed through an aflatoxin concentration inference device based on a decoder to obtain an inference result, wherein the inference result is a concentration value of aflatoxin, including: using the decoder to decode and regress the typical time series pattern feature vector of the fluorescence intensity according to the following formula to obtain a decoded value for representing the concentration value of aflatoxin; Wherein, the formula is: Where X represents the characteristic vector of the typical temporal pattern of the fluorescence intensity, Y is the decoded value, and W is the weight matrix. Represents matrix multiplication.

Citation Information

Patent Citations

  • Time resolved fluorescent kit for synchronously detecting aflatoxin, cyclopiazonic acid, ochratoxin A and zearalenone

    CN110108873A

  • Preparation method of novel BODIPY dynamic fluorescent probe and application of same to real-time detection of concentration changes of glutathione in living cells

    CN111138466A

  • Efficient nucleic acid detection and gene sequencing method and device thereof

    CN111926065A

  • Basic group recognition method based on fluorescently labeled dNTP gene sequencing, sequencer and medium

    CN117274614A

  • Extraction method of features related with diabetic vascular disorders using indocyanine green pharmacokinetic dynamics

    KR1020170041933A