Method and device for measuring content of effective components in traditional Chinese medicinal materials, electronic equipment and medium

Abstract

The invention discloses a traditional Chinese medicinal material effective component content determination method and device, electronic equipment and a medium, and relates to the technical field of traditional Chinese medicinal material identification. The determination method comprises the following steps: acquiring three-dimensional fluorescence spectrum matrix data of a solution corresponding to a to-be-determined traditional Chinese medicinal material; performing self-weighting alternating trilinear factorization on the three-dimensional fluorescence spectrum matrix data of the corresponding solution of the traditional Chinese medicinal material to be detected to obtain three-dimensional fluorescence spectrum matrix data of each component in the corresponding solution of the traditional Chinese medicinal material to be detected; and inputting the three-dimensional fluorescence spectrum matrix data of each component in the corresponding solution of the to-be-detected traditional Chinese medicinal material into a pre-trained partial least square regression model to obtain the content of the effective components in the to-be-detected traditional Chinese medicinal material. By adopting the measuring method, the content of the effective components in the traditional Chinese medicinal materials to be measured can be rapidly obtained, the method is not influenced by unknown interferents, the accuracy is high, meanwhile, the consumption of standard substances is reduced, and the cost is greatly reduced.

Description

Technical Field

[0001] The present application relates to the technical field of Chinese medicinal material identification, and in particular to a method, device, electronic equipment and medium for determining the content of effective ingredients in Chinese medicinal materials. Background Art

[0002] As an important part of traditional culture, Chinese medicine plays a huge role in helping people resist diseases. The quality of Chinese medicine is the core of ensuring the high-quality development of Chinese medicine. It is subject to factors such as the growth environment, harvest time, weather changes and processing methods. Therefore, it is necessary to monitor the content of effective ingredients in Chinese medicinal materials.

[0003] At present, the "Chinese Pharmacopoeia" has stipulated the properties of Chinese medicinal materials, Chinese herbal medicines and preparations, as well as the content of active ingredients. The determination method is High Performance Liquid Chromatography (HPLC), and the test results are accurate, but the required instruments are expensive, the reagent consumption is large, and it takes a long time to determine quickly. The traditional rapid quantitative detection uses near-infrared method, which still requires expensive standard products to establish standard curves. At the same time, it is easily affected by unknown interferences, and the accuracy of the measurement results is poor. Summary of the invention

[0004] In view of the above-mentioned defects or deficiencies in the related art, it is desired to provide a method, device, electronic equipment and medium for determining the content of effective ingredients in Chinese medicinal materials, which can not only quickly determine the content of effective ingredients in Chinese medicinal materials and ensure accuracy, but also save costs.

[0005] In a first aspect, the present application provides a method for determining the content of effective ingredients in traditional Chinese medicine, the method comprising:

[0006] Collect three-dimensional fluorescence spectrum matrix data of the solution corresponding to the Chinese medicinal materials to be tested;

[0007] Performing self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the solution corresponding to the Chinese medicinal material to be tested, to obtain the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the Chinese medicinal material to be tested;

[0008] The three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the Chinese medicinal material to be tested is input into a pre-trained partial least squares regression model to obtain the content of the effective ingredient in the Chinese medicinal material to be tested.

[0009] Optionally, in some embodiments of the present application, the partial least squares regression model is trained by the following steps:

[0010] Collecting three-dimensional fluorescence spectrum matrix data of the test solution corresponding to the Chinese medicinal materials in the sample, and performing self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the test solution corresponding to the Chinese medicinal materials in the sample, to obtain three-dimensional fluorescence spectrum matrix data of each component in the test solution corresponding to the Chinese medicinal materials in the sample;

[0011] Obtaining the effective ingredient content of the medicinal material in the sample calibrated by high performance liquid chromatography;

[0012] The partial least squares regression model is trained based on the mapping relationship between the three-dimensional fluorescence spectrum matrix data of each component in the test solution corresponding to the Chinese medicinal materials in the sample and the effective ingredient content calibrated by the high performance liquid chromatography method.

[0013] Optionally, in some embodiments of the present application, the three-dimensional fluorescence spectrum matrix data M(I×J×K) of the sample Chinese medicinal material corresponding to the test solution includes a relative excitation spectrum matrix A, a relative emission spectrum matrix B, a relative concentration matrix C and a residual matrix E, and each element m in M(I×J×K) ijk for:

[0014]

[0015] Among them, m ijk represents the fluorescence intensity of the kth sample when the excitation wavelength is i and the emission wavelength is j, i = 1, ..., I, I represents the number of excitation wavelengths, j = 1, ..., J, J represents the number of emission wavelengths, k = 1, ..., K, K represents the number of samples; a in Represents the element (i, n) in the relative excitation spectrum matrix A(I×N), b jn Represents the element (j, n), c in the relative emission spectrum matrix B(J×N) kn Represents the elements (k, n), e in the relative concentration matrix C(K×N) ijk represents the element (i, j, k) in the residual matrix E(I×J×K), and N represents the number of groups.

[0016] Optionally, in some embodiments of the present application, when performing self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the sample Chinese medicinal material corresponding to the test solution, the iterative expression of the relative excitation spectrum matrix A is:

[0017]

[0018] The iterative expression of the relative emission spectrum matrix B is:

[0019]

[0020] The iterative expression of the relative concentration matrix C is:

[0021]

[0022] The three-dimensional trilinear matrix is ​​represented as:

[0023] M i.. =Bdiag(a (i) )C T +E i.. ;

[0024] M .j. =Cdiag(b (j) )A T +E .j. ;

[0025] M ..k =Adiag(c (k) )B T +E ..k ;

[0026] Among them, a (i) represents the i-th row of the relative excitation spectrum matrix A, b (j) represents the jth row of the relative emission spectrum matrix B, c (k) represents the kth row of the relative concentration matrix C; M i.. The i-th horizontal plane matrix M represents the three-dimensional fluorescence spectrum matrix data M of the sample Chinese medicinal material corresponding to the test solution, M .j. The j-th side matrix of the three-dimensional fluorescence spectrum matrix data M of the sample Chinese medicinal material corresponding to the test solution, M ..k The kth positive matrix of the three-dimensional fluorescence spectrum matrix data M of the sample Chinese medicinal material corresponding to the test solution; E i.. 、E .j. and E ..k represents the residual, diag represents the diagonalization of the vector, diagm represents the diagonal elements of the matrix, and T represents the transposition; A + represents the Moore-Penrose generalized inverse of the relative excitation spectrum matrix A, B + represents the Moore-Penrose generalized inverse of the relative emission spectrum matrix B, C + represents the Moore-Penrose generalized inverse of the relative concentration matrix C; a (i) , b (j) and c (k) They can be obtained by alternately minimizing the loss function, and the loss function is expressed as:

[0027]

[0028]

[0029]

[0030] in, Represents the Frobenius matrix norm.

[0031] Optionally, in some embodiments of the present application, before performing self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectral matrix data of the test solution corresponding to the medicinal materials in the sample, the method also includes performing spectral correction, background subtraction, scattering subtraction and wavelength range clipping on the three-dimensional fluorescence spectral matrix data of the test solution corresponding to the medicinal materials in the sample.

[0032] Optionally, in some embodiments of the present application, the partial least squares regression model includes:

[0033] X=VP T +F;

[0034] Y=UQ T +G;

[0035] Among them, X represents the independent variable matrix, Y represents the dependent variable matrix; V represents the latent variable score matrix of X, and U represents the latent variable score matrix of Y; P and Q represent orthogonal loading matrices, respectively, and T represents transposition; F and G represent fitting residual matrices, respectively.

[0036] In a second aspect, the present application provides a device for determining the content of effective ingredients in traditional Chinese medicine, the device comprising:

[0037] An acquisition module configured to acquire three-dimensional fluorescence spectrum matrix data of a solution corresponding to the Chinese medicinal material to be tested;

[0038] A factor decomposition module is configured to perform self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the solution corresponding to the Chinese medicinal material to be tested, so as to obtain the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the Chinese medicinal material to be tested;

[0039] The content determination module is configured to input the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the Chinese medicinal material to be tested into a pre-trained partial least squares regression model to obtain the content of the effective ingredient in the Chinese medicinal material to be tested.

[0040] Optionally, in some embodiments of the present application, the content determination module is further configured to collect three-dimensional fluorescence spectrum matrix data of the test solution corresponding to the Chinese medicinal material in the sample, and perform self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the test solution corresponding to the Chinese medicinal material in the sample to obtain the three-dimensional fluorescence spectrum matrix data of each component in the test solution corresponding to the Chinese medicinal material in the sample;

[0041] Obtaining the effective ingredient content of the medicinal material in the sample calibrated by high performance liquid chromatography;

[0042] The partial least squares regression model is trained based on the mapping relationship between the three-dimensional fluorescence spectrum matrix data of each component in the test solution corresponding to the Chinese medicinal materials in the sample and the effective ingredient content calibrated by the high performance liquid chromatography method.

[0043] In a third aspect, the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the instruction, the program, the code set or the instruction set is loaded and executed by the processor to implement the steps of the method for determining the content of active ingredients in traditional Chinese medicines as described in any one of the first aspects.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the method for determining the content of active ingredients in traditional Chinese medicines as described in any one of the first aspects.

[0045] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0046] The embodiments of the present application provide a method, device, electronic device and medium for determining the content of effective ingredients in traditional Chinese medicinal materials. The method completely describes all fluorescence information of the mixed system by collecting three-dimensional fluorescence spectrum matrix data of the solution corresponding to the tested traditional Chinese medicinal material, and then performs self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the solution corresponding to the tested traditional Chinese medicinal material to obtain the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the tested traditional Chinese medicinal material. In other words, mathematical separation is used to replace chemical separation, and then the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the tested traditional Chinese medicinal material is input into a pre-trained partial least squares regression model, so that the content of effective ingredients in the tested traditional Chinese medicinal material can be quickly obtained without being affected by unknown interferents, with high accuracy, while reducing the consumption of standard products and greatly reducing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 A schematic diagram of a method for determining the content of effective ingredients in traditional Chinese medicine provided in an embodiment of the present application;

[0049] Figure 2A schematic diagram of a three-dimensional fluorescence spectrum matrix data processing result of a sample Chinese medicinal material corresponding to a test solution provided in an embodiment of the present application;

[0050] Figure 3 A schematic diagram of a three-dimensional fluorescence spectrum matrix data of a sample Chinese medicinal material corresponding to a test solution provided in an embodiment of the present application before processing;

[0051] Figure 4 The excitation spectrum corresponding to each component in a sample Chinese medicinal material provided in an embodiment of the present application;

[0052] Figure 5 The emission spectra corresponding to the components in a sample Chinese medicinal material provided in an embodiment of the present application;

[0053] Figure 6 A distribution diagram of the concentration of different components in each sample provided in an embodiment of the present application;

[0054] Figure 7 A factor decomposition iterative residual graph provided in an embodiment of the present application;

[0055] Figure 8 This is a spectrum corresponding to component 1 in a sample Chinese medicinal material provided in an embodiment of the present application;

[0056] Fig. 9 A spectrum corresponding to component 2 in a sample Chinese medicinal material provided in an embodiment of the present application;

[0057] Fig.10 This is a spectrum corresponding to component 3 in a sample Chinese medicinal material provided in an embodiment of the present application;

[0058] Fig.11 A spectrum corresponding to component 4 in a sample Chinese medicinal material provided in an embodiment of the present application;

[0059] Fig.12 This is a spectrum corresponding to component 5 in a sample Chinese medicinal material provided in an embodiment of the present application;

[0060] Fig.13 This is an excitation-emission spectrum corresponding to a Stephania tetrandra sample provided in an embodiment of the present application, wherein Fig.13 (a) is the spectrum corresponding to the Stephania tetrandra sample. Fig.13 (b) is the spectrum corresponding to each component in the Stephania tetrandra sample;

[0061] Fig.14 This is an excitation-emission spectrum corresponding to a mixed reference substance of tetrandrine and fangchinoline provided in an embodiment of the present application, wherein Fig.14 (a) is the spectrum corresponding to the mixed reference substance of tetrandrine and fangchinoline. Fig.14(b) is the spectrum corresponding to each component in the mixed reference substance of tetrandrine and fangchinoline;

[0062] Fig.15 A spectrum corresponding to tetrandrine provided in an embodiment of the present application;

[0063] Fig.16 A spectrum corresponding to fangchinoline provided in an embodiment of the present application;

[0064] Fig.17 An emission spectrum corresponding to a mixed reference substance of tetrandrine and fangchinoline provided in an embodiment of the present application;

[0065] Fig.18 An excitation spectrum corresponding to a mixed reference substance of tetrandrine and fangchinoline provided in an embodiment of the present application;

[0066] Fig.19 A comparison chart of regression equations of different quantitative methods of Stephania tetrandra provided in the embodiments of the present application;

[0067] Fig. 20 A comparison chart of the results of different quantitative methods for tetrandrine and fangchinoline in Stephania tetrandra provided in an embodiment of the present application;

[0068] Fig.21 A schematic diagram of a regression prediction curve obtained by a working curve method provided in an embodiment of the present application;

[0069] Fig. 22 A schematic diagram of a regression prediction curve obtained by the method of the present application provided in an embodiment of the present application;

[0070] Fig.23 This is a structural block diagram of a device for determining the content of effective ingredients in traditional Chinese medicine provided in an embodiment of the present application. DETAILED DESCRIPTION

[0071] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0072] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0073] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. Figures 1 to 23The method, device, electronic equipment and medium for determining the content of effective ingredients in traditional Chinese medicine provided in the embodiments of the present application are described in detail.

[0074] Please refer to Figure 1 , which is a flow chart of a method for determining the content of effective ingredients in traditional Chinese medicine provided in an embodiment of the present application, and the determination method specifically comprises the following steps:

[0075] S101, collecting three-dimensional fluorescence spectrum matrix data of the solution corresponding to the Chinese medicinal material to be tested.

[0076] S102, performing self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the solution corresponding to the tested Chinese medicinal material to obtain the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the tested Chinese medicinal material.

[0077] S103, inputting the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the tested Chinese medicinal material into a pre-trained partial least squares regression model to obtain the content of the effective ingredient in the tested Chinese medicinal material.

[0078] Exemplarily, when training a partial least squares regression model, the embodiment of the present application first ① collects the three-dimensional fluorescence spectrum matrix data of the sample Chinese medicinal materials corresponding to the test solution, and performs self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the sample Chinese medicinal materials corresponding to the test solution, and obtains the three-dimensional fluorescence spectrum matrix data of each component in the sample Chinese medicinal materials corresponding to the test solution. For example, taking the determination of the total amount of aconitine and aconitine in a Stephania tetrandra sample as an example, (1) 5-10g of the Stephania tetrandra sample is crushed through a 60-mesh sieve, and 0.05g of the powder is accurately weighed and placed in a 25mL volumetric flask; methanol (chromatographically pure) solution is added to the scale, extracted or ultrasonically extracted and centrifuged; the supernatant is taken as the mother liquor, and it is further diluted with a solvent to a concentration of 1mg / ml for use as a test solution. The quality control (QC) sample is a polystyrene solid standard, and the instrument selected is UltraFLUOR 1000 Fluorescence spectrometer, excitation wavelength λ ex 200~500nm, bandwidth is 5nm, emission wavelength λ em The wavelength is 200-600 nm, the bandwidth is 5 nm, and the voltage of the photomultiplier diode (PMT) is 600 V. The test solution of the Stephania tetrandra sample is placed in a cuvette, and the three-dimensional fluorescence spectrum matrix data of the test solution is collected by a fluorescence spectrometer, thereby fully describing all the fluorescence information of the mixed system.

[0079] (2) Using polystyrene solid standard, the three-dimensional fluorescence spectrum matrix data of the test solution is spectrally corrected. The advantage of this setting is that it can eliminate the adverse effects of the instrument and environment on the sample spectrum; using methanol solvent, the three-dimensional fluorescence spectrum matrix data of the test solution is background subtracted, and the segmented Hemite spline interpolation algorithm is used to select appropriate Rayleigh scattering, Raman scattering and secondary Rayleigh scattering bandwidth values ​​to perform scattering subtraction on the three-dimensional fluorescence spectrum matrix data of the test solution, and according to the characteristic distribution range of the three-dimensional fluorescence spectrum matrix data of the test solution, the appropriate excitation wavelength and emission wavelength range are selected to achieve wavelength range clipping. The processing results are shown in FIG. Figure 2 As shown, compared Figure 3 From the three-dimensional fluorescence spectrum matrix data of the test solution before treatment, it can be seen that Figure 2 The spectrum results with extremely clean background were obtained.

[0080] (3) The three-dimensional fluorescence spectrum matrix data of the test solution is processed by self-weighted alternating trilinear factor decomposition, which can decompose the overlapping spectral information into different fluorescent components, and realize the analytical reconstruction of the three-dimensional fluorescence spectrum of the sample. It can not only overcome the defects of the classical parallel factor algorithm (PARAFAC) that are sensitive to the estimated number of components and slow convergence, but also overcome the limitations of the rank vanishing factor analysis method (RAFA) on the number of samples and the number of components to be tested, and the defects of the method being invalid due to the frequent occurrence of imaginary solutions. It has the advantages of extremely fast analysis speed, good reproducibility of analytical component results, insensitivity to the number of components, and no influence from unknown interferences, and realizes mathematical separation instead of chemical separation. It should be noted that the process of collecting the three-dimensional fluorescence spectrum matrix data of the solution corresponding to the Chinese medicinal material to be tested and factoring the three-dimensional fluorescence spectrum matrix data in the embodiment of the present application is similar to the process of collecting the three-dimensional fluorescence spectrum matrix data of the test solution corresponding to the sample Chinese medicinal material and factoring. For example, the three-dimensional fluorescence spectrum matrix data M(I×J×K) of the sample Chinese medicinal material corresponding to the test solution includes the relative excitation spectrum matrix A, the relative emission spectrum matrix B, the relative concentration matrix C and the residual matrix E. Each element m in M(I×J×K) ijk for:

[0081]

[0082] In formula (1), m ijk represents the fluorescence intensity of the kth sample when the excitation wavelength is i and the emission wavelength is j, i = 1, ..., I, I represents the number of excitation wavelengths, j = 1, ..., J, J represents the number of emission wavelengths, k = 1, ..., K, K represents the number of samples; a in Represents the element (i, n) in the relative excitation spectrum matrix A(I×N), b jn Represents the element (j, n), c in the relative emission spectrum matrix B(J×N) knRepresents the elements (k, n), e in the relative concentration matrix C(K×N) ijk represents the element (i, j, k) in the residual matrix E(I×J×K), and N represents the number of groups.

[0083] When the three-dimensional fluorescence spectrum matrix data of the sample Chinese medicinal materials corresponding to the test solution is decomposed by self-weighted alternating trilinear factors, the iterative expression of the relative excitation spectrum matrix A is:

[0084]

[0085] The iterative expression of the relative emission spectrum matrix B is:

[0087]

[0088] The iterative expression of the relative concentration matrix C is:

[0089]

[0090] The three-dimensional trilinear matrix is ​​represented as:

[0091] M i.. =Bdiag(a (i) )C T +E i..

[0092] M .j. =Cdiag(b (j) )A T +E .j.

[0093] M ..k =Adiag(c (k) )B T +E ..k (5)

[0094] In formula (2) to formula (5), a (i) represents the i-th row of the relative excitation spectrum matrix A, b (j) represents the jth row of the relative emission spectrum matrix B, c (k) represents the kth row of the relative concentration matrix C; M i.. The i-th horizontal plane matrix M represents the three-dimensional fluorescence spectrum matrix data M of the sample Chinese medicinal material corresponding to the test solution, M .j. The j-th side matrix of the three-dimensional fluorescence spectrum matrix data M of the sample Chinese medicinal material corresponding to the test solution, M ..k The kth positive matrix of the three-dimensional fluorescence spectrum matrix data M of the sample Chinese medicinal material corresponding to the test solution; E i.. 、E .j. and E ..krepresents the residual, diag represents the diagonalization of the vector, diagm represents the diagonal elements of the matrix, and T represents the transposition; A + represents the Moore-Penrose generalized inverse of the relative excitation spectrum matrix A, B + represents the Moore-Penrose generalized inverse of the relative emission spectrum matrix B, C + represents the Moore-Penrose generalized inverse of the relative concentration matrix C; a (i) , b (j) and c (k) They can be obtained by alternately minimizing the loss function, and the loss function is expressed as:

[0095]

[0096]

[0097]

[0098] In formula (6), Represents the Frobenius matrix norm.

[0099] For example, in the embodiment of the present application, it is assumed that the number of groups is 5 and the iterative residual is 1×e 14 .like Figure 4 The excitation spectra corresponding to each component are shown in Fig. Figure 5 The emission spectra corresponding to each component are shown. When the set number of components deviates from the true value, the self-weighted alternating trilinear factor decomposition method can still resolve and obtain the correct component excitation spectrum and emission spectrum, and present the redundant components as background noise. Figure 6 The concentration distribution diagram of different components in each sample is shown in Figure 2. Figure 7 The figure shows the iterative residual graph of factor decomposition, which shows the extremely fast convergence speed of self-weighted alternating trilinear factor decomposition. Usually, the result tends to be a stable optimal solution after 10 iterations. Figures 8 to 12 Shown are the spectra corresponding to components 1 to 5, respectively, showing the excitation-emission spectra corresponding to each component after factor decomposition.

[0100] Secondly, ②, obtain the effective ingredient content of the Chinese medicinal materials in the sample corresponding to the HPLC calibration, for example, obtain the content of tetrandrine and fangchinoline calibrated by HPLC. Finally, ③, based on the mapping relationship between the three-dimensional fluorescence spectrum matrix data of each component in the test solution corresponding to the Chinese medicinal materials in the sample and the effective ingredient content calibrated by HPLC, train a partial least squares regression model. For example, the partial least squares regression model includes:

[0101] X=VP T +F

[0102] Y=UQ T +G (7)

[0103] In formula (7), X represents the independent variable matrix, Y represents the dependent variable matrix; V represents the latent variable (also called main factor) score matrix of X (projection of X), and U represents the latent variable score matrix of Y (projection of Y); P and Q represent orthogonal loading matrices, T represents transposition; F and G represent fitting residual matrices, respectively. For example, the independent variable matrix X is the component matrix obtained by factor decomposition, the dependent variable matrix Y is the content of effective ingredients in the sample Chinese medicinal materials, and the independent variable matrix X and the dependent variable matrix Y are decomposed on the principle of maximizing the covariance of the score matrix V and the score matrix U. The partial least squares regression method includes the nonlinear iterative partial least squares algorithm (NIPALS) and the fast iterative partial least squares algorithm (SIMPLS), and the calculation process is as follows:

[0104] W α =X T y

[0105] t α =Xw α

[0106] q α =y T t α

[0107] p α =X T t α

[0108] β=W(P T W) -1 q (8)

[0109] In formula (8), α represents the number of latent variables, w represents the weight, t represents the score, q represents the covariance, p represents the loading, β represents the regression coefficient, and W represents the covariance matrix.

[0110] The following is a methodological investigation of the partial least squares regression model of the examples of the present application, with the reference substances being tetrandrine and fangchinoline.

[0111] Precision test: Take the same batch of test solution and collect three-dimensional fluorescence spectrum matrix data according to the above spectral conditions for 6 times in total, and record the corresponding fluorescence signal intensity to calculate the relative standard deviation (RSD) of the fluorescence signal intensity of tetrandrine and fangchinoline.

[0112] Stability test: Take the test solution of the same batch and measure it at 0, 2h, 4h, 8h, 12h and 24h after preparation. Collect the three-dimensional fluorescence spectrum matrix data according to the above-mentioned spectral conditions, and record the relative standard deviation values ​​of the total contents of tetrandrine and fangchinoline measured in the test solution six times.

[0113] Repeatability test: Take 6 samples of the same batch of Tetrandrakine and prepare the test solution according to the above method. Collect the three-dimensional fluorescence spectrum matrix data based on the above spectral conditions, and record the relative standard deviation of the total content of tetrandrine and fangchinoline measured in the test solution 6 times.

[0114] Sample recovery rate: Take 0.5g of the powder of the medicinal material of Stephania tetrandra with known total content of tetrandrine and fangchinoline, weigh it accurately, and add one milliliter of the reference solution of tetrandrine and fangchinoline (1mg / mL) accurately, and prepare the test solution according to the above method. Collect the three-dimensional fluorescence spectrum matrix data based on the above spectral conditions, and calculate the sample recovery rate and the relative standard deviation of the total content of tetrandrine and fangchinoline.

[0115] The results are as follows Fig.13 (a) shows the spectrum corresponding to the Stephania tetrandra sample. Fig.13 (b) shows the spectra corresponding to the components in the Stephania tetrandra sample; Fig.14 (a) shows the spectrum corresponding to the mixed reference substance of tetrandrine and fangchinoline. Fig.14 (b) shows the spectra corresponding to the components in the mixed reference substance of tetrandrine and fangchinoline; Fig.15 The spectrum corresponding to tetrandrine is shown in FIG. Fig.16 Shown is the spectrum corresponding to fangchinoline; and Fig.17 The emission spectrum of the mixed reference substance of tetrandrine and fangchinoline is shown in FIG. Fig.18 Shown is the excitation spectrum corresponding to the mixed reference substance of tetrandrine and fangchinoline.

[0116] Compare the working curve method and the method of the present application. Specifically, accurately weigh a total of 5 mg of the reference substance (tetracycline: tetracycline = 2:1), and add methanol to make up to 5 mL as the mother liquor, and then dilute the mother liquor with methanol to mixed reference substance solutions with concentrations of 0.009 mg / mL, 0.015 mg / mL, 0.021 mg / mL, 0.027 mg / mL, 0.033 mg / mL and 0.036 mg / mL for use. Collect three-dimensional fluorescence spectrum matrix data under the same spectral conditions, and record the corresponding fluorescence signal intensity. Draw a standard curve with the mass concentration of the reference solution as the horizontal axis (X) and the fluorescence signal intensity as the vertical axis (Y), establish a regression working curve, and calculate the determination coefficient R 2 The results are as follows Fig.19 and Fig. 20 As shown, the regression prediction curve obtained by the working curve method is as follows Fig.21 As shown, the regression prediction curve obtained by the present application method is as follows Fig. 22 As shown in Figure 4, the main isoquinoline alkaloids in Stephania tetrandriae include fangjiine, fangchinoline, isofangjiine and cyclohexanine.

[0117] The results show that the deviation between the total content of tetrandrine and fangchinoline in Stephania tetrandra obtained by the working curve method and its actual content (HPLC) is 2 to 120%. This is mainly due to the fact that the total isoquinoline alkaloid content in Stephania tetrandra is 2% to 5%, among which the content of tetrandrine (tetrandrine≈1%) is slightly higher than that of tetrandrine B (tetrandrine≈0.5%), and the isoquinoline alkaloids have similar fluorescent chromophores, and their fluorescence spectra are difficult to distinguish. Therefore, the working curve method calculates the total alkaloid content in similar samples, which makes the calculation results inconsistent with the results of the determination of tetrandrine and fangchinoline content by HPLC. The prediction results of the method of the present application are consistent with those of HPLC, and cross-validation shows that the result deviation is less than 5%, indicating that for complex component systems such as Chinese medicinal materials, the classical chemometric spectral quantitative method is also applicable to three-dimensional fluorescence spectrum matrix data, and the factor decomposition by self-weighted alternating trilinear factorization can reduce the influence of unknown interferences in the sample on quantitative regression. In summary, the partial least squares regression curve constructed using the Stephania tetrandra sample has a good prediction effect on the total content of tetrandrine and fangchinoline in the sample. The methodology was verified, and the relative standard deviation values ​​of the regression curve precision, stability and repeatability tests were 1.53%, 1.30% and 1.23%, respectively. The average sample recovery rate was 102.37%, and the relative standard deviation value was 2.52%, indicating that the method has good precision and repeatability, and the tetrandrine and fangchinoline in the test sample are stable within 24 hours.

[0118] The method for determining the content of effective ingredients in Chinese medicinal materials provided in the embodiment of the present application completely describes all fluorescence information of the mixed system by collecting three-dimensional fluorescence spectrum matrix data of the solution corresponding to the Chinese medicinal material to be tested, and then performs self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the solution corresponding to the Chinese medicinal material to be tested, so as to obtain the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the Chinese medicinal material to be tested. In other words, mathematical separation is used to replace chemical separation, and then the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the Chinese medicinal material to be tested is input into a pre-trained partial least squares regression model, so that the content of effective ingredients in the Chinese medicinal material to be tested can be quickly obtained, which is not affected by unknown interferents and has high accuracy. At the same time, the consumption of standard products is reduced, and the cost is greatly reduced.

[0119] Based on the above embodiments, the present application provides a device for measuring the content of effective ingredients in Chinese medicinal materials. The device 100 for measuring the content of effective ingredients in Chinese medicinal materials can be applied to Figure 1 to Figure 22 In the method for determining the content of effective ingredients in Chinese medicinal materials in the corresponding embodiment. Please refer to Fig.23 The device 100 for determining the content of effective ingredients in Chinese medicinal materials comprises:

[0120] The acquisition module 101 is configured to acquire three-dimensional fluorescence spectrum matrix data of the solution corresponding to the Chinese medicinal material to be tested;

[0121] The factor decomposition module 102 is configured to perform self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the solution corresponding to the Chinese medicinal material to be tested, so as to obtain the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the Chinese medicinal material to be tested;

[0122] The content determination module 103 is configured to input the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the Chinese medicinal material to be tested into a pre-trained partial least squares regression model to obtain the content of the effective ingredient in the Chinese medicinal material to be tested.

[0123] Optionally, in some embodiments of the present application, the content determination module 103 is further configured to collect three-dimensional fluorescence spectrum matrix data of the sample Chinese medicinal material corresponding to the test solution, and perform self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the sample Chinese medicinal material corresponding to the test solution to obtain the three-dimensional fluorescence spectrum matrix data of each component in the sample Chinese medicinal material corresponding to the test solution;

[0124] Obtain the effective ingredient content of the Chinese medicinal materials in the sample calibrated by high performance liquid chromatography;

[0125] Based on the mapping relationship between the three-dimensional fluorescence spectrum matrix data of each component in the test solution corresponding to the sample Chinese medicinal materials and the effective ingredient content calibrated by high performance liquid chromatography, a partial least squares regression model was trained.

[0126] Optionally, in some embodiments of the present application, the three-dimensional fluorescence spectrum matrix data M (I × J × K) of the sample Chinese medicinal material corresponding to the test solution includes a relative excitation spectrum matrix A, a relative emission spectrum matrix B, a relative concentration matrix C and a residual matrix E, and each element m in M ​​(I × J × K) ijk for:

[0127]

[0128] Among them, m ijk represents the fluorescence intensity of the kth sample when the excitation wavelength is i and the emission wavelength is j, i = 1, ..., I, I represents the number of excitation wavelengths, j = 1, ..., J, J represents the number of emission wavelengths, k = 1, ..., K, K represents the number of samples; a in Represents the element (i, n) in the relative excitation spectrum matrix A(I×N), b jnRepresents the element (j, n), c in the relative emission spectrum matrix B(J×N) kn Represents the elements (k, n), e in the relative concentration matrix C(K×N) ijk represents the element (i, j, k) in the residual matrix E(I×J×K), and N represents the number of groups.

[0129] Optionally, in some embodiments of the present application, when the factor decomposition module 102 performs self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the sample Chinese medicinal material corresponding to the test solution, the iterative expression of the relative excitation spectrum matrix A is:

[0130]

[0131] The iterative expression of the relative emission spectrum matrix B is:

[0132]

[0133] The iterative expression of the relative concentration matrix C is:

[0134]

[0135] The three-dimensional trilinear matrix is ​​represented as:

[0136] M i.. =Bdiag(a (i) )C T +E i.. ;

[0137] M .j. =Cdiag(b (j) )A T +E .j. ;

[0138] M ..k =Adiag(c (k) )B T +E ..k ;

[0139] Among them, a (i) represents the i-th row of the relative excitation spectrum matrix A, b (j) represents the jth row of the relative emission spectrum matrix B, c (k) represents the kth row of the relative concentration matrix C; M i.. The i-th horizontal plane matrix M represents the three-dimensional fluorescence spectrum matrix data M of the sample Chinese medicinal material corresponding to the test solution, M .j. The j-th side matrix of the three-dimensional fluorescence spectrum matrix data M of the sample Chinese medicinal material corresponding to the test solution, M ..k The kth positive matrix of the three-dimensional fluorescence spectrum matrix data M of the sample Chinese medicinal material corresponding to the test solution; E i.. 、E.j. and E ..k represents the residual, diag represents the diagonalization of the vector, diagm represents the diagonal elements of the matrix, and T represents the transposition; A + represents the Moore-Penrose generalized inverse of the relative excitation spectrum matrix A, B + represents the Moore-Penrose generalized inverse of the relative emission spectrum matrix B, C + represents the Moore-Penrose generalized inverse of the relative concentration matrix C; a (i) , b (j) and c (k) They can be obtained by alternately minimizing the loss function, and the loss function is expressed as:

[0140]

[0141]

[0142]

[0143] in, Represents the Frobenius matrix norm.

[0144] Optionally, in some embodiments of the present application, the factor decomposition module 102 performs spectral correction, background subtraction, scattering subtraction, and wavelength range clipping on the three-dimensional fluorescence spectral matrix data of the test solution corresponding to the sample Chinese medicinal materials before performing self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectral matrix data of the test solution corresponding to the sample Chinese medicinal materials.

[0145] Optionally, in some embodiments of the present application, the partial least squares regression model includes:

[0146] X=VP T +F;

[0147] Y=UQ T +G;

[0148] Among them, X represents the independent variable matrix, Y represents the dependent variable matrix; V represents the latent variable score matrix of X, and U represents the latent variable score matrix of Y; P and Q represent orthogonal loading matrices, respectively, and T represents transposition; F and G represent fitting residual matrices, respectively.

[0149] It should be noted that, for the description of the same steps and the same contents in this embodiment as those in other embodiments, reference can be made to the description in other embodiments and will not be repeated here.

[0150] The apparatus for determining the content of effective ingredients in Chinese medicinal materials provided in the embodiment of the present application fully describes all fluorescence information of the mixed system by collecting three-dimensional fluorescence spectrum matrix data of the solution corresponding to the Chinese medicinal material to be tested, and then performs self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the solution corresponding to the Chinese medicinal material to be tested, so as to obtain the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the Chinese medicinal material to be tested. In other words, mathematical separation is used to replace chemical separation, and then the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the Chinese medicinal material to be tested is input into a pre-trained partial least squares regression model, so that the content of effective ingredients in the Chinese medicinal material to be tested can be quickly obtained without being affected by unknown interferents, with high accuracy, while reducing the consumption of standard products and greatly reducing costs.

[0151] Based on the above embodiments, the embodiments of the present application provide an electronic device. The electronic device may include a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set or instruction set, and the instruction, program, code set or instruction set is loaded and executed by the processor to implement Figure 1 to Figure 22 The steps of the method for determining the content of effective ingredients in Chinese medicinal materials in the corresponding embodiment.

[0152] As another aspect, the present application provides a computer-readable storage medium for storing program code, the program code for executing the aforementioned Figure 1 to Figure 22 Any one of the implementation modes of the method for determining the content of effective ingredients in Chinese medicinal materials in the corresponding embodiment.

[0153] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0154] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms. The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0155] In addition, each functional module in each embodiment of the present application may be integrated into a processing unit, or each module may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.

[0156] Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method for determining the content of the active ingredient of the medicinal material in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0157] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0158] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for determining the content of effective ingredients in Chinese medicinal materials, characterized in that: The determination method comprises: Collect three-dimensional fluorescence spectrum matrix data of the solution corresponding to the Chinese medicinal materials to be tested; Performing self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the solution corresponding to the Chinese medicinal material to be tested, to obtain the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the Chinese medicinal material to be tested; The three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the Chinese medicinal material to be tested is input into a pre-trained partial least squares regression model to obtain the content of the effective ingredient in the Chinese medicinal material to be tested.

2. The measuring method according to claim 1, characterized in that The partial least squares regression model is trained by the following steps: Collecting three-dimensional fluorescence spectrum matrix data of the test solution corresponding to the Chinese medicinal materials in the sample, and performing self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the test solution corresponding to the Chinese medicinal materials in the sample, to obtain three-dimensional fluorescence spectrum matrix data of each component in the test solution corresponding to the Chinese medicinal materials in the sample; Obtaining the effective ingredient content of the medicinal material in the sample calibrated by high performance liquid chromatography; The partial least squares regression model is trained based on the mapping relationship between the three-dimensional fluorescence spectrum matrix data of each component in the test solution corresponding to the Chinese medicinal materials in the sample and the effective ingredient content calibrated by the high performance liquid chromatography method.

3. The measuring method according to claim 2, characterized in that The three-dimensional fluorescence spectrum matrix data M(I×J×K) of the sample Chinese medicinal material corresponding to the test solution includes a relative excitation spectrum matrix A, a relative emission spectrum matrix B, a relative concentration matrix C and a residual matrix E. Each element m in M(I×J×K) ijk for: Among them, m ijk represents the fluorescence intensity of the kth sample at the excitation wavelength i and the emission wavelength j, i = 1, ..., I, I represents the number of excitation wavelengths, j = 1, ..., J, J represents the number of emission wavelengths, k = 1, ..., K, K represents the number of samples; a in Represents the element (i,n) in the relative excitation spectrum matrix A(I×N), b jn Represents the element (j,n) in the relative emission spectrum matrix B(J×N), c kn Represents the element (k,n) in the relative concentration matrix C(K×N), e ijk represents the element (i, j, k) in the residual matrix E(I×J×K), and N represents the number of groups.

4. The measuring method according to claim 2, characterized in that When the three-dimensional fluorescence spectrum matrix data of the sample Chinese medicinal material corresponding to the test solution is subjected to self-weighted alternating trilinear factor decomposition, the iterative expression of the relative excitation spectrum matrix A is: The iterative expression of the relative emission spectrum matrix B is: The iterative expression of the relative concentration matrix C is: The three-dimensional trilinear matrix is ​​represented as: M i.. =Bdiag(a (i) )C T +E i.. ; M .j. =Cdiag(b (j) )A T +E .j. ; M ..k =Adiag(c (k) )B T +E ..k ; Among them, a (i) represents the i-th row of the relative excitation spectrum matrix A, b (j) represents the jth row of the relative emission spectrum matrix B, c (k) represents the kth row of the relative concentration matrix C; M i.. The i-th horizontal plane matrix M represents the three-dimensional fluorescence spectrum matrix data M of the sample Chinese medicinal material corresponding to the test solution, M .j. The j-th side matrix of the three-dimensional fluorescence spectrum matrix data M of the sample Chinese medicinal material corresponding to the test solution, M ..k The kth positive matrix of the three-dimensional fluorescence spectrum matrix data M of the sample Chinese medicinal material corresponding to the test solution; E i.. 、E .j. and E ..k represents the residual, diag represents the diagonalization of the vector, diagm represents the diagonal elements of the matrix, and T represents the transposition; A + represents the Moore-Penrose generalized inverse of the relative excitation spectrum matrix A, B + represents the Moore-Penrose generalized inverse of the relative emission spectrum matrix B, C + represents the Moore-Penrose generalized inverse of the relative concentration matrix C; a (i) 、b (j) and c (k) They can be obtained by alternately minimizing the loss function, and the loss function is expressed as: in, Represents the Frobenius matrix norm.

5. The measuring method according to claim 4, characterized in that Before performing self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the test solution corresponding to the medicinal materials in the sample, the method also includes performing spectral correction, background subtraction, scattering subtraction and wavelength range clipping on the three-dimensional fluorescence spectrum matrix data of the test solution corresponding to the medicinal materials in the sample.

6. The measuring method according to any one of claims 1 to 5, characterized in that The partial least squares regression model includes: X=VP T +F; Y=UQ T +G; Among them, X represents the independent variable matrix, Y represents the dependent variable matrix; V represents the latent variable score matrix of X, and U represents the latent variable score matrix of Y; P and Q represent orthogonal loading matrices, respectively, and T represents transposition; F and G represent fitting residual matrices, respectively.

7. A device for measuring the content of effective ingredients in Chinese medicinal materials, characterized in that: The measuring device comprises: An acquisition module configured to acquire three-dimensional fluorescence spectrum matrix data of a solution corresponding to the Chinese medicinal material to be tested; A factor decomposition module is configured to perform self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the solution corresponding to the Chinese medicinal material to be tested, so as to obtain the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the Chinese medicinal material to be tested; The content determination module is configured to input the three-dimensional fluorescence spectrum matrix data of each component in the solution corresponding to the Chinese medicinal material to be tested into a pre-trained partial least squares regression model to obtain the content of the effective ingredient in the Chinese medicinal material to be tested.

8. The measuring device according to claim 7, characterized in that The content determination module is also configured to collect three-dimensional fluorescence spectrum matrix data of the test solution corresponding to the Chinese medicinal material in the sample, and perform self-weighted alternating trilinear factor decomposition on the three-dimensional fluorescence spectrum matrix data of the test solution corresponding to the Chinese medicinal material in the sample to obtain the three-dimensional fluorescence spectrum matrix data of each component in the test solution corresponding to the Chinese medicinal material in the sample; Obtaining the effective ingredient content of the medicinal material in the sample calibrated by high performance liquid chromatography; The partial least squares regression model is trained based on the mapping relationship between the three-dimensional fluorescence spectrum matrix data of each component in the test solution corresponding to the Chinese medicinal materials in the sample and the effective ingredient content calibrated by the high performance liquid chromatography method.

9. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set or instruction set, and the instruction, the program, the code set or the instruction set is loaded and executed by the processor to implement the steps of the method for determining the content of active ingredients in traditional Chinese medicines as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the method for determining the content of active ingredients in traditional Chinese medicines as described in any one of claims 1 to 6.

Images