Method and device for detecting TERT gene mutation in glioma tissue sample
Through Raman spectroscopy and machine learning model, the feature extraction and classification prediction of glioma tissue samples was solved, and the problem of high mutation cost for detecting glioma TERT gene in the existing technology was solved, and the rapid and accurate detection effect was achieved. Glioma treatment provides new auxiliary means.
Patent Information
- Application Number
- CN202411534387.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-30
- Publication Date
- 2024-12-31
Smart Images
Figure CN119223936A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of Raman spectroscopy detection, and in particular to a method and device for detecting TERT gene mutations in glioma tissue samples. Background Art
[0002] Gliomas are the most common central nervous system tumors, accounting for about 70% of all primary brain malignant tumors. They are one of the major brain diseases with high mortality and disability rates, and glioblastoma is the most malignant tissue type. Telomerase reverse transcriptase (TERT) is the catalytic subunit of telomerase, and its main function is to maintain the length of telomeres. TERT promoter mutation is one of the common genetic mutations in adult diffuse gliomas. Its clinical significance is related to isocitrate dehydrogenase (IDH) mutation and the histological type of glioma, which leads to differences in prognosis.
[0003] At present, the clinical diagnosis of TERT promoter mutation mainly relies on gene detection technology, which is costly and has low patient acceptance, and cannot be used as a routine detection method to guide the treatment of glioma patients. With the gradual promotion of the concept of precision treatment of glioma, a fast, efficient and low-cost method for detecting TERT gene mutation is urgently needed. Summary of the invention
[0004] The purpose of this application is to provide a method and device for detecting TERT gene mutations in glioma tissue samples, which can realize rapid, efficient and low-cost detection of TERT gene mutation status in gliomas.
[0005] To achieve the above objectives, this application provides the following solutions.
[0006] In a first aspect, the present application provides a method for detecting TERT gene mutation in glioma tissue samples, comprising: performing Raman spectroscopy scanning on the glioma tissue sample to be tested to obtain Raman spectroscopy data; preprocessing the Raman spectroscopy data to obtain normalized Raman spectroscopy data; extracting the intensity value at the characteristic displacement from the normalized Raman spectroscopy data; the characteristic displacement includes the Raman displacement of 842 cm -1 、1161cm -1 、1166cm -1 、1227cm -1 、1513cm -1 、1587cm -1 、1782cm -1 、2822cm -1 、2941cm -1 、3066cm-1 、3390cm -1 、3448cm -1 、3486cm -1 and 3490cm -1 ; The intensity value at the characteristic displacement is input into the classification model to calculate the classification prediction value; the classification model characterizes the relationship between the classification prediction value and the intensity value at the characteristic displacement; the classification prediction value is used to assist in determining the TERT gene mutation status of the glioma tissue sample to be tested; the TERT gene mutation status includes TERT gene mutation and TERT gene non-mutation.
[0007] Optionally, the Raman spectrum data is preprocessed to obtain normalized Raman spectrum data, including: removing fluorescence background from the Raman spectrum data to obtain Raman spectrum data with fluorescence background removed; smoothing and denoising the Raman spectrum data with fluorescence background removed to obtain smoothed and denoised Raman spectrum data; and normalizing the smoothed and denoised Raman spectrum data to obtain normalized Raman spectrum data.
[0008] Optionally, the classification model is determined based on a LASSO regression algorithm and a support vector machine model; the determination process of the classification model includes: obtaining a number of Raman spectral samples annotated with TERT gene mutation status, and preprocessing and extracting characteristic spectral information to construct a sample data set; the sample data set includes characteristic spectral information and TERT gene mutation status corresponding to a number of normalized Raman spectral samples; the characteristic spectral information includes intensity values at a number of Raman shifts; according to the sample data set, a 5-fold cross-validation is used to determine the optimal regularization parameter value, and based on the optimal regularization parameter value, a LASSO regression algorithm is used for feature screening, and the coefficient of irrelevant Raman shifts is gradually reduced to zero to obtain a characteristic shift; the intensity values at the characteristic shifts corresponding to all normalized Raman spectral samples in the sample data set and the TERT gene mutation status are input into a support vector machine model for training to obtain a classification model.
[0009] Optionally, the regression equation corresponding to the characteristic displacement is: y=0.3590+(-0.1599×I 842 )+0.0529×I 1161 +0.1418×I 1166 +0.0457×I 1227 +(-0.0278×I 1513 )+0.2350×I 1587 +(-0.1628×I 1782 )+(-0.0265×I 2822 )+0.0395×I 2941 +0.2109×I3066 +(-0.2389×I 3390 )+0.1081×I 3448 +0.0367×I 3486 +0.0132×I 3490 ; Where y represents the output value of the regression equation; I 842 Indicated at Raman shift 842cm -1 The intensity value at I 1161 Indicated at Raman shift 1161cm -1 The intensity value at I 1166 Indicates that the Raman shift is 1166cm -1 The intensity value at I 1227 Indicates that the Raman shift is 1227cm -1 The intensity value at I 1513 Indicates that the Raman shift is 1513cm -1 The intensity value at I 1587 Indicates that the Raman shift is 1587cm -1 The intensity value at I 1782 Indicated at Raman shift 1782cm -1 The intensity value at I 2822 Indicated at Raman shift 2822cm -1 The intensity value at I 2941 Indicated at Raman shift 2941cm -1 The intensity value at I 3066 Indicates that the Raman shift is 3066cm -1 The intensity value at I 3390 Indicates the Raman shift at 3390cm -1 The intensity value at I 3448 Indicates that the Raman shift is 3448cm -1 The intensity value at I 3486 Indicates that the Raman shift is 3486cm -1 The intensity value at I 3490 Indicates the Raman shift of 3490 cm -1 The regression coefficient before the intensity value at each characteristic displacement represents the importance of the characteristic displacement.
[0010] Optionally, performing fluorescence background removal processing on the Raman spectrum data to obtain Raman spectrum data with fluorescence background removed includes: performing fluorescence background removal processing on the Raman spectrum data using an adaptive iterative reweighted penalized least squares method to obtain Raman spectrum data with fluorescence background removed.
[0011] Optionally, performing smoothing and denoising processing on the Raman spectrum data from which the fluorescence background is removed to obtain smoothed and denoised Raman spectrum data includes: performing smoothing and denoising processing on the Raman spectrum data from which the fluorescence background is removed using a Savitzky-Golay smoothing algorithm to obtain smoothed and denoised Raman spectrum data.
[0012] Optionally, normalizing the smoothed and denoised Raman spectrum data to obtain normalized Raman spectrum data includes: normalizing the smoothed and denoised Raman spectrum data using a maximum-minimum normalization algorithm to obtain normalized Raman spectrum data.
[0013] In a second aspect, the present application provides a device for detecting TERT gene mutations in glioma tissue samples, using the above-mentioned method for detecting TERT gene mutations in glioma tissue samples, including: a laser for emitting laser to the glioma tissue sample to be tested; a spectrum analyzer for collecting Raman light scattered by the glioma tissue sample to be tested to obtain Raman spectrum data, preprocessing the Raman spectrum data to obtain normalized Raman spectrum data, extracting intensity values at characteristic displacements from the normalized Raman spectrum data, and inputting the intensity values at the characteristic displacements into a classification model to calculate a classification prediction value.
[0014] Optionally, the device for detecting TERT gene mutation in glioma tissue samples further comprises: an optical microscopy platform for placing the glioma tissue sample to be tested, and adjusting the position and height of the glioma tissue sample to be tested.
[0015] Optionally, the device for detecting TERT gene mutations in glioma tissue samples also includes: a display connected to the spectrometer, for displaying the classification prediction value and the auxiliary determination result; the auxiliary determination result is determined based on the classification prediction value.
[0016] Optionally, the device for detecting TERT gene mutations in glioma tissue samples also includes: an optical fiber probe, connected to the laser and the spectrometer respectively, for transmitting the laser emitted by the laser to the surface of the glioma tissue sample to be tested, and transmitting the Raman light scattered by the surface of the glioma tissue sample to be tested to the spectrometer.
[0017] Optionally, the excitation wavelength of the laser is 532 nm, and the integration time is 1 to 3 seconds.
[0018] According to the specific embodiments provided by the present application, the present application discloses the following technical effects: the present application provides a method and device for detecting TERT gene mutations in glioma tissue samples, firstly performing Raman spectroscopy scanning on the glioma tissue sample to be tested to obtain Raman spectroscopy data, then preprocessing and feature extraction of the Raman spectroscopy data to obtain the intensity value at the characteristic displacement, and finally inputting the intensity value at the characteristic displacement into a pre-trained classification model to calculate the classification prediction value to assist in determining the TERT gene mutation status of the glioma tissue sample to be tested. Compared with the prior art, the present application utilizes Raman spectroscopy technology, performs Raman spectroscopy analysis on the glioma tissue sample to be tested, and combines the trained classification model to achieve fast, efficient, and low-cost detection of TERT gene mutation status, which can partially replace the high-cost tumor gene detection and analysis function. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] 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.
[0020] Figure 1 A flow chart of the method for detecting TERT gene mutations in glioma tissue samples provided in this application.
[0021] Figure 2 This is a graph showing the predictive efficacy curve of the TERT gene mutation status of the classification model provided in this application.
[0022] Figure 3 A structural diagram of a device for detecting TERT gene mutations in glioma tissue samples provided in this application.
[0023] Figure numerals: laser-1, optical microscopy platform-2, spectrum analyzer-3, display-4. DETAILED DESCRIPTION
[0024] 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.
[0025] This application provides a simple, efficient and accurate method and device for detecting TERT gene mutations in glioma tissue samples, providing a new technical means for the auxiliary diagnosis and treatment of brain gliomas. The method uses Raman spectroscopy technology to identify the TERT gene mutation status by performing Raman spectroscopy analysis on the glioma tissue samples to be tested, thereby achieving rapid detection of gliomas with TERT gene mutations and guiding the formulation of treatment plans.
[0026] 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.
[0027] like Figure 1 As shown, the method for detecting TERT gene mutation in glioma tissue samples provided in the present application includes the following steps S1 to S4.
[0028] Step S1: Perform Raman spectrum scanning on the glioma tissue sample to be tested to obtain Raman spectrum data.
[0029] Among them, the glioma tissue samples to be tested can be collected directly during the operation without any slicing processing. Tissue fragments with a long diameter of about 2 to 20 mm can be taken and placed on a glass slide.
[0030] Exemplarily, a Raman spectrum excitation device (such as a laser with an excitation wavelength of 532 nm) is used to perform Raman spectrum scanning on the glioma tissue sample to be tested, and a spectrum analyzer is used to collect Raman spectrum data. The integration time of the Raman spectrum scanning is controlled to be 1 to 3 seconds.
[0031] Step S2: preprocessing the Raman spectrum data to obtain normalized Raman spectrum data.
[0032] Exemplarily, the Raman spectrum data is first processed to remove the fluorescence background to obtain the Raman spectrum data with the fluorescence background removed; secondly, the Raman spectrum data with the fluorescence background removed is smoothed and denoised to obtain the smoothed and denoised Raman spectrum data; finally, the smoothed and denoised Raman spectrum data is normalized to obtain the normalized Raman spectrum data.
[0033] Preferably, the fluorescence background removal process uses adaptive iterative re-weighted penalized least squares (airPLS). The airPLS algorithm removes the background by iteratively adjusting the weight of the signal. In each iteration, it calculates the difference between the signal and the background and updates the weight so that the background can better fit the data.
[0034] Preferably, the smoothing and noise reduction process uses a Savitzky-Golay smoothing algorithm. The Savitzky-Golay smoothing algorithm is a filtering method for smoothing and differentiating digital signals, which achieves smoothing by performing polynomial fitting on data within a local window.
[0035] The formula of the Savitzky-Golay smoothing algorithm can be expressed as: Among them, b u is the smoothed data point, a u is the original data point, a u+v is the data point after moving v units, m is half the window width (that is, the window width is 2m+1), c v is the coefficient of the polynomial fitting. In this embodiment, the window width is 5 and the polynomial fitting coefficient is 2.
[0036] Preferably, the normalization process adopts the maximum-minimum normalization algorithm. The formula is: x'=(x-min(x)) / (max(x)-min(x)); wherein x' is the normalized Raman spectrum data, x is the smoothed and denoised Raman spectrum data, min(x) is the minimum value of the smoothed and denoised Raman spectrum data, and max(x) is the maximum value of the smoothed and denoised Raman spectrum data.
[0037] Step S3: Extract the intensity value at the characteristic shift from the normalized Raman spectrum data. The characteristic shift includes the Raman shift of 842 cm -1 、1161cm -1 、1166cm -1 、1227cm -1 、1513cm -1 、1587cm -1 、1782cm -1 、2822cm -1 、2941cm -1 、3066cm -1 、3390cm -1 、3448cm -1 、3486cm -1 and 3490cm -1 .
[0038] Step S4: Input the intensity value at the characteristic displacement into the classification model to calculate the classification prediction value. The classification model is a multivariate linear equation of the classification prediction value and the intensity value at the characteristic displacement. The classification prediction value is used to assist in determining the TERT gene mutation status of the glioma tissue sample to be tested. The TERT gene mutation status includes TERT gene mutation and TERT gene non-mutation. Among them, the classification model is determined using machine learning or pattern recognition algorithms.
[0039] Exemplarily, the classification model is determined based on a least absolute shrinkage and selection operator (LASSO) regression algorithm and a support vector machine (SVM) model using a Gaussian kernel function, and the determination process includes: obtaining a number of Raman spectral samples annotated with TERT gene mutation status, and preprocessing and extracting characteristic spectral information to construct a sample data set; the sample data set includes characteristic spectral information and TERT gene mutation status corresponding to a number of normalized Raman spectral samples; the characteristic spectral information includes intensity values at a number of Raman shifts; according to the sample data set, a 5-fold cross-validation is used to determine the optimal regularization parameter value, and based on the optimal regularization parameter value, a LASSO regression algorithm is used for feature screening, and the coefficient of the irrelevant Raman shift is gradually reduced to zero to obtain the characteristic shift; the intensity values at the characteristic shift corresponding to all normalized Raman spectral samples in the sample data set and the TERT gene mutation status are input into the support vector machine model for training to obtain the classification model.
[0040] In this example, training and validation were performed based on 567 spectral data from 117 patients retrospectively included (including 284 TERT mutation spectra and 283 TERT non-mutation spectra), and the LASSO regression algorithm was used for 5-fold cross-validation to select the optimal regularization parameter λ (0.0040) value, gradually reducing the coefficient of the irrelevant Raman shift to zero, and finally selecting 14 characteristic shifts.
[0041] When using the LASSO regression algorithm, first define its cost function expression as: Among them, n is the number of samples, p is the number of features, and y i is the observed value of the i-th sample, x ij is the jth feature of the i-th sample, β is the regression coefficient, β j is the regression coefficient of the jth feature, β0 is the initial value of the regression coefficient, and λ is the regularization parameter used to control the strength of regularization.
[0042] The intensity values corresponding to the characteristic displacements obtained by screening are input into the SVM model with Gaussian kernel function, which is completed using the SVC algorithm function in the python package Sklearn. The main parameters involved include: kernel function kernel, width parameter gamma and penalty parameter C. In this application, the kernel function kernel is "rbf", i.e. Gaussian kernel, and the kernel function can be defined as in σ is the width parameter of the Gaussian kernel function. The kernel function is used to calculate the new input eigenvalue t and the rth support vector t rWhen the "rbf" kernel is used, the width parameter σ of the Gaussian kernel function is specified, which is 1 in this application. The penalty parameter C is used to control the balance between training error and model complexity, which is 1 in this application.
[0043] The parameters of the machine learning model were optimized to predict the TERT gene mutation status of glioma. The area under the receiver operating characteristic curve (ROC) of the trained classification model was as high as 81.5%. Figure 2 shown.
[0044] In the process of spectral feature screening using the LASSO regression algorithm, the possible main characteristic peaks involved are as follows.
[0045] 842cm -1 :The peak position may be related to the content of α-glucan, including biological metabolites such as glycogen.
[0046] 1161~1166cm -1 :The peak position of this region is similar to 1513cm -1 The opposite trend may be caused by the change of tyrosine content rather than β-carotene.
[0047] 1513cm -1 : This peak position is the characteristic peak position of β-carotene.
[0048] 1587cm -1 :This peak may be related to the Amide I band, and it may also correspond to the characteristic vibration of tryptophan, which is a synthetic precursor of biologically active molecules such as hormones and neurotransmitters.
[0049] 1782cm -1 :The peak is close to the spectral silence region, which may be the comprehensive result of changes in the content of multiple substances.
[0050] 2822cm -1 :This peak position represents the characteristic peak position of protein content and is caused by the stretching vibration of the CH bond in the methyl group.
[0051] 2941~3066cm -1 :The peak position in this area usually represents the characteristic peak of methyl bond CH3, reflecting the lipid content in the tissue.
[0052] 3390~3490cm -1 :The peak in this area is likely to come from the hydroxyl (OH) effect of water molecules.
[0053] Specifically, the regression equation corresponding to the characteristic displacement after characteristic screening is expressed as: y = 0.3590 + (-0.1599 × I 842 )+0.0529×I 1161 +0.1418×I 1166 +0.0457×I 1227 +(-0.0278×I 1513 )+0.2350×I 1587 +(-0.1628×I 1782 )+(-0.0265×I 2822 )+0.0395×I 2941 +0.2109×I 3066 +(-0.2389×I 3390 )+0.1081×I 3448 +0.0367×I 3486 +0.0132×I 3490 .
[0054] Where y represents the output value of the regression equation; I represents the normalized intensity value at the Raman shift, hereinafter referred to as the intensity value; I 842 Indicated at Raman shift 842cm -1 The intensity value at I 1161 Indicated at Raman shift 1161cm -1 The intensity value at I 1166 Indicates that the Raman shift is 1166cm -1 The intensity value at I 1227 Indicates that the Raman shift is 1227cm -1 The intensity value at I 1513 Indicates that the Raman shift is 1513cm -1 The intensity value at I 1587 Indicates that the Raman shift is 1587cm -1 The intensity value at I 1782 Indicated at Raman shift 1782cm -1 The intensity value at I 2822 Indicated at Raman shift 2822cm -1 The intensity value at I 2941 Indicated at Raman shift 2941cm -1 The intensity value at I 3066 Indicates that the Raman shift is 3066cm -1 The intensity value at I 3390 Indicates the Raman shift of 3390 cm -1 The intensity value at I 3448 Indicates that the Raman shift is 3448cm -1 The intensity value at I 3486Indicates that the Raman shift is 3486cm -1 The intensity value at I 3490 Indicates the Raman shift of 3490 cm -1 The regression coefficient before the intensity value at each characteristic displacement represents the importance of the characteristic displacement.
[0055] like Figure 3 As shown, the device for detecting TERT gene mutation in glioma tissue samples provided by the present application includes: a laser 1 and a spectrum analyzer 3. Among them, the laser 1 is used to emit laser (i.e., 532nm excitation light) to the glioma tissue sample to be tested; the spectrum analyzer 3 is used to collect Raman light (i.e., scattered light) scattered by the glioma tissue sample to be tested, obtain Raman spectrum data, pre-process the Raman spectrum data to obtain normalized Raman spectrum data, extract the intensity value at the characteristic displacement from the normalized Raman spectrum data, and input the intensity value at the characteristic displacement into the classification model to calculate the classification prediction value.
[0056] Preferably, the excitation wavelength of the laser 1 is 532 nm, and the integration time is 1 to 3 seconds.
[0057] Furthermore, the above-mentioned device for detecting TERT gene mutation in glioma tissue samples also includes: an optical microscopic platform 2. The optical microscopic platform 2 is used to place the glioma tissue sample to be tested, and to adjust the position and height of the glioma tissue sample to be tested.
[0058] Furthermore, the above-mentioned device for detecting TERT gene mutation in glioma tissue samples further comprises: a display 4. The display 4 is connected to the spectrum analyzer 3 and is used to display the classification prediction value and the auxiliary determination result; the auxiliary determination result is determined based on the classification prediction value.
[0059] Furthermore, the above-mentioned device for detecting TERT gene mutation in glioma tissue samples also includes: an optical fiber probe. The optical fiber probe is connected to the laser 1 and the spectrum analyzer 3 respectively, and is used to transmit the laser emitted by the laser 1 to the surface of the glioma tissue sample to be tested, and transmit the Raman light scattered by the surface of the glioma tissue sample to be tested to the spectrum analyzer 3.
[0060] The method and device for detecting TERT gene mutation in glioma tissue samples provided in the present application have the following advantages.
[0061] 1. Fast: Using Raman spectroscopy technology, results can be obtained in seconds, and the detection time is short.
[0062] 2. Accurate: Analyze the characteristic spectral information to accurately identify the mutation status of the TERT gene.
[0063] 3. Non-destructive: No additional processing of tissue samples is required, maintaining the integrity of the samples.
[0064] 4. Simple: The process is simple to operate and does not require complex experimental conditions and professional skills.
[0065] In summary, the present application provides a method and device for detecting TERT gene mutations in glioma tissue samples, which has the advantages of being fast, accurate, and non-destructive, and is suitable for clinical medicine and scientific research fields.
[0066] 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.
[0067] 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 detecting TERT gene mutation in glioma tissue samples, characterized in that: include: Performing Raman spectrum scanning on the glioma tissue sample to be tested to obtain Raman spectrum data; Preprocessing the Raman spectrum data to obtain normalized Raman spectrum data; Extract the intensity value at the characteristic shift from the normalized Raman spectrum data; the characteristic shift includes the Raman shift of 842 cm -1 、1161cm -1 、1166cm -1 、1227cm -1 、1513cm -1 、1587cm -1 、1782cm -1 、2822cm -1 、2941cm -1 、3066cm -1 、3390cm -1 、3448cm -1 、3486cm -1 and 3490cm -1 ; Inputting the intensity value at the characteristic displacement into the classification model to calculate the classification prediction value; The classification model characterizes the relationship between the classification prediction value and the intensity value at the characteristic displacement; the classification prediction value is used to assist in determining the TERT gene mutation status of the glioma tissue sample to be tested; the TERT gene mutation status includes TERT gene mutation and TERT gene non-mutation.
2. The method for detecting TERT gene mutation in glioma tissue samples according to claim 1, characterized in that: Preprocessing the Raman spectrum data to obtain normalized Raman spectrum data includes: Performing fluorescence background removal processing on the Raman spectrum data to obtain Raman spectrum data with fluorescence background removed; Performing smoothing and noise reduction processing on the Raman spectrum data after the fluorescence background is removed to obtain smoothed and noise-reduced Raman spectrum data; The smoothed and denoised Raman spectrum data is normalized to obtain normalized Raman spectrum data.
3. The method for detecting TERT gene mutation in glioma tissue samples according to claim 1, characterized in that: The classification model is determined based on the LASSO regression algorithm and the support vector machine model; the determination process of the classification model includes: Acquire several Raman spectrum samples annotated with TERT gene mutation status, perform preprocessing and extract characteristic spectrum information, and construct a sample data set; the sample data set includes characteristic spectrum information and TERT gene mutation status corresponding to several normalized Raman spectrum samples; the characteristic spectrum information includes intensity values at several Raman shifts; According to the sample data set, a 5-fold cross validation is used to determine the optimal regularization parameter value, and based on the optimal regularization parameter value, a LASSO regression algorithm is used to perform feature screening, and the coefficient of the uncorrelated Raman shift is gradually reduced to zero to obtain a characteristic shift; The intensity values at the characteristic shifts corresponding to all normalized Raman spectral samples in the sample data set and the TERT gene mutation status are input into a support vector machine model for training to obtain a classification model.
4. The method for detecting TERT gene mutation in glioma tissue samples according to claim 1, characterized in that: The regression equation corresponding to the characteristic displacement is: and=0.3590+(-0.1599×I 842 )+0.0529×I 1161 +0.1418×I 1166 +0.0457×I 1227 + (-0.0278×I 1513 )+0.2350×I 1587 +(-0.1628×I 1782 )+(-0.0265×I 2822 )+0.0395×I 2941 +0.2109×I 3066 +(-0.2389×I 3390 )+0.1081×I 3448 +0.0367×I 3486 +0.0132×I 3490 ; Where y represents the output value of the regression equation; I 842 Indicated at Raman shift 842cm -1 The intensity value at I 1161 Indicates that the Raman shift is 1161cm -1 The intensity value at I 1166 Indicates that the Raman shift is 1166cm -1 The intensity value at I 1227 Indicates that the Raman shift is 1227cm -1 The intensity value at I 1513 Indicates that the Raman shift is 1513cm -1 The intensity value at I 1587 Indicates that the Raman shift is 1587cm -1 The intensity value at I 1782 Indicated at Raman shift 1782cm -1 The intensity value at I 2822 Indicated at Raman shift 2822cm -1 The intensity value at I 2941 Indicated at Raman shift 2941cm -1 The intensity value at I 3066 Indicates that the Raman shift is 3066cm -1 The intensity value at I 3390 Indicates the Raman shift at 3390cm -1 The intensity value at I 3448 Indicates that the Raman shift is 3448cm -1 The intensity value at I 3486 Indicates that the Raman shift is 3486cm -1 The intensity value at I 3490 Indicates the Raman shift of 3490 cm -1 The regression coefficient before the intensity value at each characteristic displacement represents the importance of the characteristic displacement.
5. The method for detecting TERT gene mutation in glioma tissue samples according to claim 2, characterized in that: Adopting adaptive iterative reweighted penalty least squares method to remove fluorescence background from the Raman spectrum data; The Savitzky-Golay smoothing algorithm is used to perform smoothing and noise reduction processing on the Raman spectrum data after removing the fluorescence background; and the maximum and minimum normalization algorithm is used to perform normalization processing on the smoothed and noise-reduced Raman spectrum data.
6. A device for detecting TERT gene mutation in glioma tissue samples, using the method for detecting TERT gene mutation in glioma tissue samples as claimed in claim 1, characterized in that: include: A laser, used for emitting laser light to the glioma tissue sample to be tested; The spectrum analyzer is used to collect Raman light scattered by the glioma tissue sample to be tested to obtain Raman spectrum data, pre-process the Raman spectrum data to obtain normalized Raman spectrum data, extract the intensity value at the characteristic displacement from the normalized Raman spectrum data, and input the intensity value at the characteristic displacement into a classification model to calculate a classification prediction value.
7. The device for detecting TERT gene mutation in glioma tissue samples according to claim 6, characterized in that: Also includes: The optical microscopy platform is used to place the glioma tissue sample to be tested, and to adjust the position and height of the glioma tissue sample to be tested.
8. The device for detecting TERT gene mutation in glioma tissue samples according to claim 6, characterized in that: Also includes: A display, connected to the spectrum analyzer, for displaying the classification prediction value and the auxiliary determination result; The auxiliary determination result is determined based on the classification prediction value.
9. The device for detecting TERT gene mutation in glioma tissue samples according to claim 6, characterized in that: Also includes: The optical fiber probe is connected to the laser and the spectrum analyzer respectively, and is used to transmit the laser light emitted by the laser to the surface of the glioma tissue sample to be tested, and transmit the Raman light scattered by the surface of the glioma tissue sample to be tested to the spectrum analyzer.
10. The device for detecting TERT gene mutation in glioma tissue samples according to claim 6, characterized in that: The excitation wavelength of the laser is 532 nm, and the integration time is 1 to 3 seconds.