Prognostic analysis marker and prognostic analysis system for diffuse large B-cell lymphoma patient and application of prognostic analysis marker and prognostic analysis system

Abstract

The invention belongs to the technical field of disease prognosis and molecular biology, and particularly relates to a prognosis analysis marker and a prognosis analysis system for a diffuse large B-cell lymphoma patient and application of the prognosis analysis marker and the prognosis analysis system. According to the invention, a prognosis analysis system based on key amino acids and clinical related indexes is established in DLBCL patients for the first time. The progression-free lifetime of the DLBCL patient can be effectively predicted, and the progression-free lifetime is closely related to clinical characteristics of the patient. Furthermore, in key amino acids related to prognosis, tryptophan and glutamine are key molecules, which proves that tryptophan and glutamine have good prognosis value in DLBCL patients. Meanwhile, according to the technical scheme, the prognosis model is imported into the autonomous AI system for operation, autonomous operation, autonomous detection and autonomous adjustment are achieved, and efficiency is improved. A new DLBCL patient prognosis evaluation strategy is provided, a theoretical basis is laid for individualized management of DLBCL patients, and therefore the method has good practical application value.

Description

Technical Field

[0001] The invention belongs to the technical field of disease prognosis and molecular biology, and specifically relates to a prognostic analysis marker for diffuse large B-cell lymphoma patients, a prognostic analysis system and applications thereof. Background Art

[0002] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention, and should not necessarily be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art.

[0003] Diffuse large B-cell lymphoma (DLBCL) is the most common B-lymphocyte malignancy with high molecular heterogeneity, accounting for up to 40% of newly diagnosed non-Hodgkin's lymphoma. Although first-line treatment such as R-CHOP (rituximab, cyclophosphamide, doxorubicin and its liposomes, vincristine, and prednisone) has improved the survival of DLBCL patients, the clinical prognosis of resistant and relapsed patients is still not ideal.

[0004] Metabolomics is a research method that quantitatively analyzes all metabolites in an organism and searches for the relative relationship between metabolites and physiological and pathological changes. Using metabolomics methods, a series of metabolites can be detected in one experiment to study low molecular weight metabolites present in biological systems. Bioinformatics is a discipline that uses computers as tools to analyze, collect, and organize DNA, proteins, amino acids, biological information, etc. It provides a basis for the treatment of some major diseases, such as cardiovascular diseases, tumors, and infectious diseases.

[0005] Basic amino acids and amino acid-like substances are the building blocks of proteins and the most basic substances for life activities. They play an important role in special physiological functions such as metabolism, neurotransmission and liposome transport. They generate energy through intermediate metabolites and provide fuel for other biosynthetic pathways. Studies have found that hematological malignancies usually rely on specific amino acids to survive, and insufficient production of these amino acids can cause metabolic vulnerability and treatment opportunities. Some amino acid-targeted enzymes that have been approved for the treatment of hematological tumors have shown promising results. The use of metabolomics methods to quantitatively analyze amino acids in biological samples has played an important role in the diagnosis of hematological diseases and the study of growth and development mechanisms.

[0006] Autonomous artificial intelligence (AI) refers to artificial intelligence systems that can perform tasks without direct human intervention. Such systems have basic attributes such as autonomy, responsiveness, social ability and initiative. Autonomous AI systems are able to perceive their environment, take actions to maximize their chances of success, and are able to learn and improve their performance through techniques such as machine learning, deep learning and reinforcement learning. Autonomous AI has broad application prospects in the field of healthcare, and is gradually changing the traditional medical service model and improving the quality and efficiency of medical services. Summary of the invention

[0007] In view of the deficiencies of the above-mentioned prior art, the present invention provides a prognostic analysis marker for patients with diffuse large B-cell lymphoma, a prognostic analysis system and its application. Specifically, the present invention is based on the analysis of the targeted metabolomics data of the plasma amino acid spectrum of DLBCL patients using liquid chromatography tandem mass spectrometry (LC-MS / MS) technology, and the amino acid sequencing screening results are analyzed by bioinformatics analysis through principal component analysis (PCA) and sparse partial least squares discriminant analysis (sPLS-DA). Finally, partial least squares regression (PLSR) and support vector machine (SVR) are used to establish a prognostic model, and an autonomous AI system is introduced for autonomous operation to further verify that the patient's serum amino acids tryptophan and glutamine have good prognostic value in DLBCL patients. Based on the above research results, the present invention is completed.

[0008] In order to achieve the above technical objectives, the present invention adopts the following technical solutions:

[0009] The first aspect of the present invention provides a prognostic analysis marker for patients with diffuse large B-cell lymphoma, wherein the prognostic analysis marker includes key amino acids and DLBCL clinical related indicators;

[0010] The amino acids include any one or more of alanine, arginine, aspartic acid, cysteine, glutamine, glutamic acid, histidine, isoleucine, glycine, asparagine, leucine, lysine, methionine, phenylalanine, proline, serine, threonine, tryptophan, tyrosine, and valine;

[0011] Furthermore, the key amino acids are tryptophan and glutamine.

[0012] The DLBCL clinical related indicators include any one or more of the IPI score when the patient is first admitted to the hospital, IPI risk stratification, age, number of extranodal involvement sites, and lactate dehydrogenase (LDH).

[0013] The prognostic analysis included analyzing and evaluating the progression-free survival (PFS) of DLBCL patients.

[0014] The second aspect of the present invention provides the use of a reagent for detecting the above-mentioned prognostic analysis marker in the preparation of a prognostic analysis product for patients with diffuse large B-cell lymphoma.

[0015] The third aspect of the present invention provides a prognostic analysis system for diffuse large B-cell lymphoma, the prognostic analysis system comprising:

[0016] An acquisition unit is configured to: acquire the above-mentioned prognostic analysis marker of the subject;

[0017] An evaluation unit, configured to: predict the progression-free survival of the diffuse large B-cell lymphoma patient according to the prognostic evaluation marker obtained by the acquisition unit;

[0018] An output unit is configured to output a progression-free survival prediction result according to the evaluation unit.

[0019] The prognostic analysis system can perform autonomous AI operation through Python.

[0020] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a program is stored, and when the program is executed by a processor, the function of the diffuse large B-cell lymphoma prognosis analysis system as described in the third aspect of the present invention is realized.

[0021] According to a fifth aspect of the present invention, an electronic device is provided, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the functions of the diffuse large B-cell lymphoma prognosis analysis system as described in the third aspect of the present invention are realized.

[0022] Compared with the existing technical solutions, the above one or more technical solutions have the following beneficial effects:

[0023] The above technical solution established a prognostic analysis system based on key amino acids and clinically relevant indicators in DLBCL patients for the first time. It can effectively predict the prognosis of DLBCL patients and is closely related to the clinical characteristics of patients. Furthermore, among the key amino acids related to prognosis, tryptophan and glutamine are key molecules, which confirms that tryptophan and glutamine have good prognostic value in DLBCL patients. At the same time, the above technical solution imports the prognostic model into the autonomous AI system to realize autonomous operation, autonomous detection, autonomous adjustment, and improve efficiency.

[0024] In summary, the above technical solution provides a new prognosis evaluation strategy for DLBCL patients, lays a theoretical foundation for the individualized management of DLBCL patients, and therefore has good practical application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0026] Figure 1 This is the key roadmap in Example 1 of the present invention.

[0027] Figure 2 A supervised sPL-SDA model was established for the mass spectrometry data and clinical data obtained from the application experiment in Example 1 of the present invention.

[0028] Figure 3 The sPL-SDA model using permutation test for data association in Example 1 of the present invention is further cross-validated.

[0029] Figure 4 This is a box plot of the quantitative analysis of 20 amino acids in the patient in Example 1 of the present invention.

[0030] Figure 5 The variable importance projection (VIP) value is set for the differential amino acids screened out in the plasma in Example 1 of the present invention, and VIP>1 indicates that the variable is of relatively important significance for the classification of the category in the model.

[0031] Figure 6 This is a clustering heat map of the expression of amino acids in the plasma of DLBCL patients and normal controls in Example 1 of the present invention.

[0032] Figure 7 The comparison of plasma amino acid expression between DLBCL patients and normal controls in Example 1 of the present invention; wherein, (a) shows an increasing trend in plasma amino acid expression between DLBCL patients and normal controls, and (b) shows a decreasing trend in plasma amino acid expression between DLBCL patients and normal controls.

[0033] Figure 8 This is the hierarchical cluster analysis performed in Example 1 of the present invention, which observes the obvious variation characteristics of the same type of differential metabolites among samples.

[0034] Fig. 9 The pathway analysis of the two amino acids that significantly affect the prognostic grouping in Example 1 of the present invention is performed, and the pathway enrichment bubble diagram obtained by the analysis and the enrichment analysis diagram using the KEGG method are shown.

[0035] Fig.10 This is a comparison diagram of the actual values ​​and predicted values ​​of the PLSR model established using MATLAB in Example 1 of the present invention, showing the relationship between the standardized actual values ​​and predicted values, and the red dotted line represents the ideal fitting curve.

[0036] Fig.11This is a diagram showing the difference (residual) between the predicted value and the actual value of the PLSR model established using MATLAB in Example 1 of the present invention. The blue dotted line represents the zero residual line.

[0037] Fig.12 For the SVR machine learning model established by using MATLAB in Example 1 of the present invention, the sample ratio of the training set is 75% (n=15), and the remaining samples are the test set, and good model training parameters are obtained. DETAILED DESCRIPTION

[0038] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0039] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof. In addition, the molecular biology methods not described in detail in the examples are all conventional methods in the art, and the specific operations can be referred to the molecular biology guide or product manual.

[0040] In a typical embodiment of the present invention, a prognostic analysis marker for patients with diffuse large B-cell lymphoma is provided, wherein the prognostic analysis marker includes key amino acids and clinically relevant indicators of DLBCL;

[0041] The amino acids include any one or more of alanine, arginine, aspartic acid, cysteine, glutamine, glutamic acid, histidine, isoleucine, glycine, asparagine, leucine, lysine, methionine, phenylalanine, proline, serine, threonine, tryptophan, tyrosine, and valine;

[0042] Furthermore, the key amino acids are tryptophan and glutamine.

[0043] The DLBCL clinical related indicators include any one or more of the IPI score when the patient is first admitted to the hospital, IPI risk stratification, age, number of extranodal involvement sites, and lactate dehydrogenase (LDH).

[0044] The prognostic analysis included analyzing and evaluating the progression-free survival (PFS) of DLBCL patients.

[0045] In another specific embodiment of the present invention, there is provided use of a reagent for detecting the above-mentioned prognostic analysis marker in the preparation of a prognostic analysis product for patients with diffuse large B-cell lymphoma.

[0046] The reagents for detecting the above-mentioned prognostic analysis markers include reagents for detecting key amino acids and reagents for detecting clinically relevant indicators of DLBCL, which are not specifically limited here. In a specific embodiment of the present invention, the reagents for detecting key amino acids include but are not limited to reagents required for detecting amino acids based on the selective reaction / multiple reaction monitoring technology (SRM / MRM) method and / or based on the LC-MS / MS mass spectrometry method.

[0047] The prognostic analysis included an analytical assessment of PFS in patients with DLBCL.

[0048] The diffuse large B-cell lymphoma patient prognosis analysis product may specifically be a detection kit, a detection device or equipment.

[0049] In another specific embodiment of the present invention, a prognostic analysis system for diffuse large B-cell lymphoma is provided, and the prognostic analysis system comprises:

[0050] An acquisition unit is configured to: acquire the above-mentioned prognostic analysis marker of the subject;

[0051] An evaluation unit, configured to: predict the progression-free survival of the diffuse large B-cell lymphoma patient according to the prognostic evaluation marker obtained by the acquisition unit;

[0052] An output unit is configured to output a progression-free survival prediction result according to the evaluation unit.

[0053] Wherein, the evaluation unit includes at least one diffuse large B-cell lymphoma prognosis evaluation model, and the prognosis evaluation model is specifically a PLSR model and / or an SVR model:

[0054] Wherein, the PLSR model can be a MATLAB model, that is, by MATLAB, the data set is randomly divided into a training set and a test set, the training data is used to fit the PLSR model, the test data set is used to predict the model, and the predicted correlation coefficient is calculated. According to the verification results, the number of potential variables or other parameters are adjusted, and the training and verification steps are repeated to improve the prediction effect of the model to obtain a PLSR model, which can be used for the prediction of progression-free survival, and the formula is PFS=110.2092+(-5.5576*Gln)+(-6.7974*Trp)+(0.1395*age)+(3.1042*number of extranodal sites)+(0.0047*LDH)+(-7.2143*IPI risk stratification)+(-2.8840*IPI score).

[0055] In the present invention, Gln, Trp, age, number of extranodal sites and LDH are all raw data. Among them, Gln and Trp adopt the method of targeted metabolomics analysis to directly detect the concentration in serum, and the unit is μmol / L. Age is the actual age of the patient. The number of extranodal sites adopts raw data, and specifically, the number of extranodal sites is directly calculated based on imaging examinations such as CT, ultrasound, PET / CT, etc. LDH is the actual value of lactate dehydrogenase in serum of patients, and the unit is (U / L). PFS is in months.

[0056] The international prognostic index (IPI) is a classic evaluation system for the prognosis of DLBCL patients. In the present invention, the patient's corresponding IPI score is obtained according to the IPI scoring standard specified in the "Guidelines for the Treatment of Lymphoma in China (2021 Edition)".

[0057] Similarly, according to the "Guidelines for the Treatment of Lymphoma in China (2021 Edition)", the calculation method for IPI risk stratification is:

[0058] Risk stratification <![CDATA[IPI score (points) a > Low risk group 0～1 Low-medium risk group 2 Medium-high risk group 3 High-risk group 4～5

[0059] Based on this, the present invention calculated the risk stratification of each patient and assigned points to them: 1 point for the low-risk group; 2 points for the low-medium-risk group; 3 points for the medium-high-risk group; and 4 points for the high-risk group.

[0060] In the present invention, the SVR model is obtained by using an algorithm to train the model using the pre-collected results of the prognostic analysis markers of the diffuse large B-cell lymphoma patients. Further, the present invention uses the fitrsvm function of MATLAB to construct the SVR model. Cross-validation is used to automatically adjust the hyperparameters to improve the performance of the model. The SVR model is trained using the training data set and the test data set is used for prediction, the prediction performance index is calculated, the model performance is analyzed, the parameters are adjusted, and repeated training and evaluation are performed to obtain the best performance.

[0061] Furthermore, the prognostic analysis system can perform autonomous AI operation through Python.

[0062] In another specific embodiment of the present invention, a computer-readable storage medium is provided, on which a program is stored, and when the program is executed by a processor, the function of the prognostic analysis system for diffuse large B-cell lymphoma is realized.

[0063] In another specific embodiment of the present invention, an electronic device is provided, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor implements the functions of the diffuse large B-cell lymphoma prognostic analysis system when executing the program.

[0064] The present invention is further described below in conjunction with specific examples, which are only for the purpose of explaining the present invention and are not intended to limit the content thereof. If the specific experimental conditions are not specified in the examples, they are usually carried out according to conventional conditions or the conditions recommended by the sales company; unless otherwise specified in the present invention, they can all be purchased through commercial channels.

[0065] Example

[0066] Materials and methods

[0067] 1.1 Research subjects and sample collection methods

[0068] Peripheral blood samples were collected from 20 confirmed DLBCL patients and 10 healthy volunteers. All patients were diagnosed for the first time and had never received any treatment. The control group consisted of healthy volunteers with normal laboratory test results during the same period. Informed consent was obtained from the patients, and basic information such as gender, age, and general condition of the patients was recorded. The results of tumor immunohistochemistry, tumor staging, and international prognostic index (IPI) of the patients were recorded, and risk stratification was performed based on the clinical information collected from the patients. 2 ml of fasting venous blood was collected from all subjects in the morning and anticoagulated with ethylenediaminetetraacetic acid (EDTA). The blood samples were allowed to coagulate for about 10-20 minutes, and then centrifuged at 2000-3000 rpm for 10 minutes. The supernatant (plasma) was stored at -80°C until analysis.

[0069] 1.2 Sample Information

[0070] Sample information: There are 2 groups of blood samples. One group has 10 biological replicates of healthy control group, and the other group has 20 biological replicates of DLBCL group (see Table 1 for details)

[0071] Table 1 Sample information

[0072]

[0073] Note: DLBCL represents the disease group, and H represents the healthy control group.

[0074] 1.3 Sequencing method of 20 amino acids in DLBCL

[0075] LC-MS / MS was used to perform targeted metabolomics analysis of plasma amino acid profiles in DLBCL patients and controls, and 20 common amino acids in plasma were quantified.

[0076] 1.3.1 Standard curve

[0077] Take the standard sample and dilute it with water to make a standard working solution with a series of concentrations. Prepare the standard curve solution according to 1.3.2 and establish the annotation curve.

[0078] 1.3.2 Metabolite extraction

[0079] Plasma samples were thawed at room temperature and analyzed by LC-MS / MS. Take 100 μL of blood, add pre-cooled methanol (Merck, 144282) / acetonitrile (Merck, 1499230-935) (1:1, V / V), vortex mix for 30 seconds, let stand for 10 minutes, centrifuge at 12000rpm 4℃ for 10 minutes, take the supernatant, and blow dry with nitrogen. Redissolve in 1000 μL of water, filter, and inject. All samples were mixed in equal amounts to prepare quality control samples (Quality Control, QC) for machine detection.

[0080] 1.3.3 Chromatography-mass spectrometry analysis

[0081] 1) HPLC conditions

[0082] The samples were separated using a Nexera X2 LC-30AD high performance liquid chromatography system (Shimadzu). A QC sample was set every certain number of experimental samples in the sample queue to detect and evaluate the stability and repeatability of the system; a standard mixture of amino acid metabolites was set in the sample queue to correct the chromatographic retention time.

[0083] 2) LC-MS / MS mass spectrometry analysis based on MRM method

[0084] Mass spectrometry analysis was performed using a 5500QTRAP mass spectrometer (AB SCIEX) in positive ion mode. The 5500QTRAP ESI source conditions were as follows: source temperature 500°C; ion Source Gas 1 (GS1): 50; Ion Source Gas 2 (GS2): 50; Curtain gas (CUR): 35; Ion Spray Voltage (IS) 5500V; and MRM mode was used to detect the ion pairs to be tested.

[0085] 1.3.4 Data Analysis

[0086] Analyst and SCIEX OS software were used to extract chromatographic peak areas and retention times. Amino acid standards were used to correct retention times and identify metabolites. All samples were mixed in equal amounts to prepare QC samples, and the stability and repeatability of the data were evaluated.

[0087] 1.4 Bioinformatics analysis methods for amino acid sequencing screening results

[0088] Further bioinformatics analysis was performed on the amino acid sequencing results and the collected clinically relevant information. Multivariate statistical analysis was used to reduce the dimension and perform regression analysis on the collected multidimensional data while retaining the original information to the greatest extent, and then screen for differential metabolites and conduct subsequent analysis. This mainly included principal component analysis (PCA) and sparse partial least squares discriminant analysis (sPLS-DA). The metabolites responsible for distinguishing the severe DLBCL group from the mild group were those that showed statistical significance in multivariate analysis (VIP>1.0 and P<0.05).

[0089] 1.4.1 Sample selection

[0090] Sample selection: A total of 17 samples including DLBCL2, 4-11, 13-20 were used.

[0091] Classification label, IPI scores 1-2 are mild cases, and 3-5 are severe cases.

[0092] 1.4.2 Spectrum-effect correlation analysis

[0093] 1) Principal component analysis + sparse partial least squares regression analysis

[0094] Variable selection: clinical + mass spectrometry variables

[0095] Usage: This study used the PCA+sPLS-DA method to perform spectrum-effect correlation analysis. First, PCA was used to preview the data distribution of all sample points, and then sPLS-DA was used to model and analyze the data to explore the mathematical relationship between the amino acid spectrum and the clinical prognosis value.

[0096] 2) Variable Importance Plot

[0097] The VIP value, also known as variable projection importance, indicates the contribution of each metabolite ion to distinguishing between groups. The higher the VIP value, the stronger the correlation.

[0098] 1.4.3 Permutation test

[0099] The sample labels (mild and severe) were randomly shuffled 100 times, and the average Euclidean distance of the two groups of samples after clustering was calculated, and the distance of the real data was used as the denominator for standardization. The P value is the number of times the average distance is greater than the real data in a random case / 100.

[0100] 1.4.4 Cluster heat map analysis

[0101] Hierarchical clustering was used to draw a cluster heat map, with colors from blue to red representing the content of related amino acids from low to high.

[0102] 1.4.5 Pathway enrichment bubble diagram analysis

[0103] The screened differential metabolites were subjected to KEGG annotation and pathway analysis, and the key metabolic pathways mapped by the differential metabolites were retrieved through enrichment analysis.

[0104] 1.4.6 Data Analysis

[0105] SPSS18.0 statistical analysis software was used to analyze the experimental data. The quantitative data were expressed as mean ± standard deviation (Mean ± SD), univariate analysis: t test; multivariate analysis: linear regression analysis was performed using multiple groups of amino acids with specific characteristics, and stepwise regression was performed using the backward method. P < 0.05 was considered statistically significant.

[0106] 1.5 Establishment and operation of the prognostic model

[0107] 1.5.1 Selection of variables for inclusion in the prognostic model

[0108] Combining the molecular characteristics and microenvironment of tumors into IPI can better guide prognostic analysis. The key clinical information and key amino acids of 20 patients were included as input variables in the prognostic model. By reviewing the patients' treatment records and telephone follow-up, PFS was calculated as the output variable.

[0109] 1.5.2 Establishment and operation of PLSR prognostic model

[0110] The data set was randomly divided into training set and test set using MATLAB. The PLSR model was fitted with the training data. The model was predicted with the test data set, and the correlation coefficient of the prediction was calculated. The number of potential variables or other parameters were adjusted according to the verification results. The training and verification steps were repeated to improve the prediction effect of the model and obtain the PLSR mathematical model. The trained PLSR model was saved in Matlab and exported to a format that can be read by Python. The scikit-learn library of Python software was used to train and save the PLSR model and save it to a file. Finally, the model was integrated into a Flask API to carry and use the PLSR model and realize autonomous operation.

[0111] 1.5.3 Construction and operation of SVR machine learning model

[0112] MATLAB was used to divide the dataset into training and test sets, and the appropriate kernel function was selected. The SVR model was constructed using the fitrsvm function of MATLAB. Cross-validation was used to automatically adjust the hyperparameters to improve the performance of the model. The SVR model was trained using the training dataset and the test dataset was used for prediction. The prediction performance indicators were calculated, the model performance was analyzed, the parameters were adjusted, and repeated training and evaluation were performed to obtain the best performance. The SVR model was exported to MATLAB's portable file format using MATLAB. In the Python environment, the MATLAB Engine API for Python was used for integration, and the MATLAB model code was run directly in Python. Scripts were written for data input processing, model calling, and result output. Subsequently, logging and monitoring mechanisms were set up to monitor the operation and performance of the model in real time.

[0113] Experimental Results

[0114] 2.1 Quantitative results of plasma amino acids in patients with diffuse large B-cell lymphoma

[0115] A total of 20 amino acids were detected in the QC samples. The quantitative results of amino acids are shown in Table 2. The RSD results of the analytes in the QC samples were all <30%, which means that our data are reliable and stable. We drew a box plot of patients and healthy controls based on the detailed quantitative data of amino acids in the samples ( Figure 4 ), the clustering heat map of metabolites in positive ion mode is shown in Figure 6 , which helps us compare the distribution characteristics of amino acid quantitative data between patients and healthy controls. We can clearly see that the expression of 8 kinds of amino acids in the plasma of DLBCL patients is significantly different from that of normal healthy controls, among which Asp (aspartic acid), Glu (glutamic acid), Phe (phenylalanine), Thr (threonine) show an upward trend in DLBCL, while Gly (glycine), His (histidine), Ser (serine), Trp (tryptophan) show a downward trend in DLBCL. The trend chart is as follows: Figure 7 As shown, the differences were statistically significant (P<0.05).

[0116] Table 2 Quantitative results of 20 amino acids

[0117]

[0118] 2.2 Using bioinformatics to analyze the potential relationship and network between amino acid expression and patient prognosis

[0119] 2.2.1 Establishment of a model to analyze the relationship between amino acid expression and clinical prognosis

[0120] The amino acid expression of the patients and their clinical characteristics were used as variables. Based on PCA, the mass spectrometry data obtained from the experiment and the clinical data were used to establish a supervised sPLSDA model. It showed that patients with differences in amino acid expression and poor clinical prognostic factors also had poor prognosis. sPLSDA can force the regression coefficients of variables with smaller effects to zero, and the effect is better in this set of data, which indirectly indicates that more variables do not play a role in classification. The basic information and clinical related data of the 20 patients are shown in Table 3.

[0121] Table 3 Basic information of 20 patients

[0122]

[0123] 2) The permutation test was used to further cross-validate the model associated with the data. The results of the permutation test showed that the expression of amino acids was significantly correlated with the patient's prognosis (P<0.05), further indicating that the difference in amino acid expression in patients can affect the patient's prognosis. We can also find that the R^2 and Q^2 values ​​after permutation are lower than the original left point, indicating that the model is not overfitting and has good stability and predictive ability.

[0124] 2.2.2 Amino acid analysis related to patient prognosis

[0125] The variable importance projection (VIP) value was set. VIP>1 indicates that the variable is of great significance for the classification of the categories in the model. The differential amino acids screened out in plasma are tryptophan and glutamine, which are significantly correlated with the patient's prognosis. We also performed a hierarchical clustering analysis to observe the obvious change characteristics of similar differential metabolites among samples. The hierarchical clustering results showed that the difference in amino acid expression in medium- and high-risk patients (severe cases) was more obvious than that in medium- and low-risk patients (mild cases).

[0126] 2.2.3 Analysis of differential amino acid metabolic pathways associated with patient prognosis

[0127] Pathway analysis was performed on the two amino acids that significantly affected the prognostic groups. The pathway enrichment bubble diagram obtained by the analysis is shown in the figure below. Fig. 9. Through analysis, it was found that three metabolic pathways may be most closely related to the patient's prognosis. These three pathways have the largest number of enriched metabolites, namely the D-Glutamine and D-Glutamate Metabolism pathway, the Phenylalanine, tyrosine and tryptophan biosynthesis pathway, and the Alanine, aspartate and glutamate metabolism pathway, namely D-Gln, D-Glu metabolism, phenylalanine, tyrosine and tryptophan biosynthesis, and alanine, aspartate and glutamate metabolism. The KEGG method was also used for enrichment analysis.

[0128] 2.3 Construction and operation of the prognostic model

[0129] 2.3.1 Selection of prognostic model variables

[0130] The differential amino acids screened in plasma were tryptophan and glutamine, which were shown to be significantly correlated with prognosis and were therefore included in the prognostic model as important independent variables (input variables). In the clinical data, IPI score, grouping, age, number of extranodal sites, and lactate dehydrogenase (LDH) were included in the prognostic model as independent variables (input variables). After the follow-up, we obtained the PFS of 20 patients. The final variable data set is shown in Table 4.

[0131] Table 4 Prognostic model dataset

[0132]

[0133]

[0134] 2.3.2PLSR prognostic model

[0135] The PLSR prognostic model was established using MATLAB. By repeating the training and validation steps, we obtained the prognostic expression for PFS: PFS = 110.2092 + -5.5576*Gln + -6.7974*Trp + 0.1395*age + 3.1042*number of extranodal sites + 0.0047*LDH + -7.2143*IPI risk stratification + -2.8840*IPI score. We validated the predictive ability of the PLSR prognostic model by comparing the actual values ​​with the predicted values ​​( Fig.10 ) shows the relationship between the standardized actual value and the predicted value, and the red dotted line represents the ideal fitting curve. The distribution of points is relatively concentrated, mainly distributed near the red dotted line (ideal fitting curve), which indicates that the model can generally predict the output value well. Fig.11) shows the difference (residual) between the predicted value and the actual value, and the blue dashed line indicates the zero residual line. Most of the residuals are distributed in a range close to zero, indicating that the overall error of the model is small. There is no obvious systematic deviation or trend in the residuals, indicating that there are no obvious problems with the model fit. By trying to run it autonomously, an individualized prediction of PFS was achieved.

[0136] 2.3.3SVR machine learning prognostic model

[0137] The SVR machine learning model was established using MATLAB. The sample ratio of the training set was 75% (n=15), and the remaining samples were used as the test set. Good model training parameters were obtained. After accessing the AI ​​system, the parameter features were input, and PFS could be predicted, and the prediction accuracy and confidence interval were given. The results are shown in Figure 2. Fig.12 shown.

[0138] Example 2

[0139] This embodiment provides a prognostic analysis system for diffuse large B-cell lymphoma, the prognostic analysis system comprising:

[0140] An acquisition unit is configured to: acquire the above-mentioned prognostic analysis marker of the subject;

[0141] An evaluation unit, configured to: predict the progression-free survival of the diffuse large B-cell lymphoma patient according to the prognostic evaluation marker obtained by the acquisition unit;

[0142] An output unit is configured to output a progression-free survival prediction result according to the evaluation unit.

[0143] Wherein, the evaluation unit at least includes a diffuse large B-cell lymphoma prognosis evaluation model, and the prognosis evaluation model is specifically a PLSR model and / or an SVR model.

[0144] The specific operation of the system can be carried out according to the method for performing prognostic analysis (PFS) on patients with diffuse large B-cell lymphoma in Example 1 of the present invention.

[0145] Example 3

[0146] This embodiment provides a computer-readable storage medium having a program stored thereon. When the program is executed by a processor, the steps of performing prognostic analysis (PFS) on patients with diffuse large B-cell lymphoma as in Embodiment 1 of the present invention are implemented.

[0147] Example 4

[0148] This embodiment provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps of performing prognostic analysis (PFS) on patients with diffuse large B-cell lymphoma as in Embodiment 1 of the present invention are implemented.

[0149] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0150] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0151] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0152] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0153] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0154] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A prognostic analysis marker for patients with diffuse large B-cell lymphoma, characterized in that: The prognostic analysis markers include key amino acids and DLBCL clinical related indicators; The amino acids include any one or more of alanine, arginine, aspartic acid, cysteine, glutamine, glutamic acid, histidine, isoleucine, glycine, asparagine, leucine, lysine, methionine, phenylalanine, proline, serine, threonine, tryptophan, tyrosine, and valine; The DLBCL clinical related indicators include any one or more of the IPI score when the patient is first admitted to the hospital, IPI risk stratification, age, number of extranodal involvement sites and LDH.

2. The prognostic analysis marker for diffuse large B-cell lymphoma patients according to claim 1, characterized in that: The key amino acids are tryptophan and glutamine; The prognostic analysis included an analysis and evaluation of PFS in patients with DLBCL.

3. Use of a reagent for detecting the prognostic analysis marker according to claim 1 or 2 in the preparation of a product for prognostic analysis of diffuse large B-cell lymphoma patients.

4. The use according to claim 3, characterized in that: The prognostic analysis includes an analysis and evaluation of PFS in patients with DLBCL; The prognosis analysis product for patients with diffuse large B-cell lymphoma is a detection kit, a detection device or equipment.

5. A prognostic analysis system for diffuse large B-cell lymphoma, characterized in that: The prognostic analysis system comprises: An acquisition unit, configured to: acquire the prognostic analysis marker of the subject according to claim 1 or 2; An evaluation unit, configured to: predict the progression-free survival of the diffuse large B-cell lymphoma patient according to the prognostic evaluation marker obtained by the acquisition unit; An output unit is configured to output a progression-free survival prediction result according to the evaluation unit.

6. The prognostic analysis system for diffuse large B-cell lymphoma according to claim 5, characterized in that: The evaluation unit at least includes a diffuse large B-cell lymphoma prognosis evaluation model, and the prognosis evaluation model is specifically a PLSR model and / or an SVR model.

7. The prognostic analysis system for diffuse large B-cell lymphoma according to claim 6, characterized in that: The PLSR model is a MATLAB model, and its formula is PFS=110.2092+(-5.5576*Gln)+(-6.7974*Trp)+(0.1395*age)+(3.1042*number of extranodal sites)+(0.0047*LDH)+(-7.2143*IPI risk stratification)+(-2.8840*IPI score); The SVR model is obtained by using an algorithm to train the model using the pre-collected prognostic analysis marker-related results of the diffuse large B-cell lymphoma patients; further, the SVR model is constructed using the fitrsvm function of MATLAB.

8. The prognostic analysis system for diffuse large B-cell lymphoma according to any one of claims 5 to 7, characterized in that: The prognostic analysis system performs autonomous AI operation through Python.

9. A computer-readable storage medium having a program stored thereon, wherein when the program is executed by a processor, the function of the prognostic analysis system for diffuse large B-cell lymphoma as claimed in any one of claims 5 to 8 is realized.

10. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor implements the function of the prognostic analysis system for diffuse large B-cell lymphoma according to any one of claims 5 to 8 when executing the program.

Images