Characteristic extraction method and system for CAR-NK cell data

Abstract

The invention relates to the technical field of feature extraction, in particular to a feature extraction method and system for CAR-NK cell data, and the method comprises the following steps: collecting CAR-NK cell samples, carrying out protein analysis on the CAR-NK cell samples in batches, recording expression change of protein in each batch of CAR-NK cell samples, carrying out quantitative analysis on metabolite samples, and obtaining metabolite concentration data. And carrying out standardization treatment on the concentration data to obtain basic data of the cell sample. According to the method, the protein and the metabolite in the CAR-NK cell sample are quantitatively analyzed, the reaction characteristics of the cell in different immune environments can be comprehensively captured, the influence of the immune environments on the cell function is clarified through immune response grouping and clustering analysis, and the protein-metabolite interaction network reveals the interaction of molecules inside and outside the cell, so that the immunologic function of the cell is enhanced. By screening and verifying immune markers, an accurate immune function evaluation basis and quantitative analysis of immune reactivity characteristics are provided, the immune reaction process can be tracked in real time, and the research precision and depth are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of feature extraction, and particularly to a method and system for extracting features from CAR-NK cell data. Background Art

[0002] Feature extraction is a very important step in data analysis and machine learning, aiming to extract meaningful information from raw data and transform it into a form that is easier to process and analyze. In various fields, especially in bioinformatics and medicine, feature extraction techniques are widely used in data dimensionality reduction, pattern recognition, and classification tasks, including identifying and extracting representative features from data, which can effectively express the characteristics of samples, thereby improving the accuracy and efficiency of machine learning models. It encompasses various methods such as statistical feature extraction, frequency domain analysis, time domain analysis, image processing, signal processing, etc., and usually relies on domain knowledge to select and extract the most useful features for the target task.

[0003] Among them, the method for extracting features from CAR-NK cell data is mainly used for analyzing and processing data in CAR-NK cell therapy. CAR-NK cells are natural killer (NK) cells modified by genetic engineering and have stronger tumor killing ability. Through feature extraction, various biological features of cells can be extracted from experimental data, helping researchers understand the performance and response of CAR-NK cells in different environments, which is of great significance for further CAR-NK cell function analysis, clinical efficacy evaluation, and optimization of the design of CAR-NK cell therapy.

[0004] The prior art relies relatively heavily on a single data dimension during data processing, ignores the interaction relationship between proteins and metabolites, cannot fully mine the multi-dimensional features of cells, cannot reveal the detailed differences in cell reactions, and usually lacks quantitative analysis ability during immune response evaluation, resulting in an incomplete description of the immune response and making it difficult to achieve precise immune function monitoring. Especially in the biomarker verification link, the prior art fails to provide effective multi-dimensional verification means, resulting in the functional confirmation of biomarkers being easily affected by errors and unable to ensure its reliability in a complex immune environment, leading to insufficient depth and accuracy of research results and affecting the further optimization and clinical application of immunotherapy. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art and propose a method for extracting features from CAR-NK cell data.

[0006] To achieve the above purpose, the present invention adopts the following technical scheme: A method for extracting features from CAR-NK cell data, comprising the following steps:

[0007] S1: Collect CAR-NK cell samples, perform protein analysis on the CAR-NK cell samples in batches, record the expression changes of proteins in each batch of CAR-NK cell samples, and perform quantitative analysis on metabolite samples to obtain metabolite concentration data, and perform standardization processing on the concentration data to obtain basic cell sample data;

[0008] S2: According to the basic cell sample data, perform denoising processing on the data, extract the key differences between samples through data dimensionality reduction, cluster according to sample characteristics, group the samples according to immune responses, and extract key information to obtain integrated feature data;

[0009] S3: Based on the integrated feature data, construct a protein-metabolite interaction network, connect proteins with related metabolites, evaluate the interaction between proteins and metabolites during the immune response process, identify the interaction changes between metabolic pathways and proteins, and generate a functional network diagram;

[0010] S4: Based on the functional network diagram, screen key proteins and metabolite markers associated with the immune response, confirm candidate markers according to literature and databases, verify the candidate markers, detect the expression of each marker in CAR-NK cells according to the verification results, and analyze the role of each marker in the immune response to obtain marker verification data;

[0011] S5: According to the verified marker data, perform quantitative analysis on the immune reactivity of CAR-NK cells, monitor the contact reaction between CAR-NK cells and target cells, evaluate the dynamic process of the immune response, and quantify the reactivity of key markers to obtain the extraction result of CAR-NK cell immune reactivity characteristics.

[0012] As a further solution of the present invention, the steps for obtaining the basic cell sample data are as follows:

[0013] S111: Collect CAR-NK cell samples, extract proteins from each batch of samples, and perform protein quantitative analysis to obtain protein expression data in each batch of samples;

[0014] S112: Compare the protein expression data in each batch of samples, determine the expression changes of proteins through differential analysis, record the situation of protein expression changes in each batch of samples, and obtain the protein change data in each sample;

[0015] S113: According to the protein change data in each sample, extract metabolite components from each batch of samples, obtain the concentration data of each metabolite, perform standardization processing on the metabolite concentration data, and combine the protein expression change data in each batch of samples to obtain basic cell sample data.

[0016] As a further solution of the present invention, the step of obtaining the integrated feature data is as follows:

[0017] S211: Based on the basic data of the cell samples, evaluate each data point, determine the denoising threshold according to the distribution characteristics of the sample data, and eliminate the outliers exceeding the denoising threshold to obtain the denoised sample data;

[0018] S212: According to the denoised sample data, perform data dimensionality reduction and extract the key differences between samples, retain the key features between samples, and eliminate redundant information to obtain the dimensionality-reduced data;

[0019] S213: Based on the dimensionality-reduced data, perform sample clustering analysis, using the formula:

[0020]

[0021] Calculate the Euclidean distance d between sample i and sample j ij , the smaller the Euclidean distance between samples, the higher the similarity, and group the samples with similar immune response characteristics into the same group to obtain the integrated feature data, where x ik and x jk are the kth eigenvalue of sample i and sample j respectively, and n is the total number of features.

[0022] As a further solution of the present invention, the step of obtaining the functional network diagram is as follows:

[0023] S311: Based on the integrated feature data, analyze the pairing relationship between each protein and its related metabolite, detect the interaction relationship between the protein and the metabolite, establish the connection between each protein and the related metabolite, and generate a preliminary interaction network structure;

[0024] S312: According to the protein-metabolite interaction network structure, use the formula:

[0025]

[0026] Calculate the interaction strength S between protein a and metabolite b ab , to obtain the interaction strength data of each pair of protein-metabolite, where x ak and y bk are the expression levels of protein a and metabolite b on the kth feature respectively; n represents the total number of features;

[0027] S313: Based on the interaction intensity data of each pair of protein-metabolite, identify metabolic pathways related to immune response, analyze the interactive changes between metabolic pathways and proteins during the immune response process, reveal the key protein-metabolite interactions in the immune response mechanism, and generate a functional network diagram.

[0028] As a further aspect of the present invention, the verification step of the candidate biomarker is as follows:

[0029] S411: Based on the functional network diagram, screen key proteins and metabolite biomarkers associated with immune response, combine the key biological events during the immune response process, and rank the screened biomarkers according to their priority of potential roles in the immune response to obtain preliminarily screened candidate biomarkers;

[0030] S412: According to the preliminarily screened candidate biomarkers, consult research literature, analyze and compare the immune relevance of the candidate biomarkers, confirm whether there is biological support in the immune response, and verify whether each candidate biomarker has an expression pattern of known immune function to obtain confirmed candidate biomarkers;

[0031] S413: According to the confirmed candidate biomarkers, verify the candidate biomarkers, obtain the expression data of the biomarkers through experiments, verify their actual roles in the immune response, and detect the changes in immune cells to obtain a list of candidate biomarkers.

[0032] As a further aspect of the present invention, the step of obtaining the verification data of the biomarker is as follows:

[0033] S421: According to the list of candidate biomarkers, detect the expression of each biomarker in CAR-NK cells, analyze the expression level of the biomarker in the cells, reveal the changes of the biomarker in the immune response, and generate biomarker expression data;

[0034] S422: Based on the biomarker expression data, compare the expression changes of the biomarker before and after the immune response and under different stimulation conditions, evaluate its performance during the immune response process, and confirm the association of each biomarker with the key process of the immune response to generate biomarker immune function analysis data;

[0035] S423: According to the immune function analysis data, identify the potential functions of each biomarker in the immune response, and combine experimental data to analyze the potential biological mechanism to obtain biomarker verification data.

[0036] As a further aspect of the present invention, the step of obtaining the extraction result of the immune reactivity characteristics of CAR-NK cells is as follows:

[0037] S511: Based on the verification marker data, quantitatively analyze the immunoreactivity of CAR-NK cells. Through the immune stimulation and the contact reaction with target cells, monitor different stages of the immune reaction, conduct real-time quantitative analysis of the cell contact reaction, and obtain the quantitative data of CAR-NK cell immunoreactivity;

[0038] S512: According to the quantitative data of CAR-NK cell immunoreactivity, observe and record the interaction between target cells and CAR-NK cells, quantify the reactivity of the markers, analyze the performance of the markers in the cell contact reaction under different immune stimulation conditions, and analyze the relationship between the markers and the cell contact reaction to obtain the quantified marker reactivity data;

[0039] S513: Combine the quantified marker reactivity data, analyze the change trend of the markers and their relationship with the CAR-NK cell reaction in different immune reaction stages, determine the time dynamics of cell reactions and marker changes, and obtain the CAR-NK cell immunoreactivity feature extraction results.

[0040] A feature extraction system for CAR-NK cell data, comprising:

[0041] The sample data processing module collects CAR-NK cell samples, extracts proteins in each batch of samples, and conducts protein quantitative analysis. Through differential analysis, determine the expression changes of proteins, extract metabolite components in each batch of samples, obtain concentration data and conduct standardization processing, and combine with the protein expression change data to obtain the basic cell sample data;

[0042] The feature extraction module, based on the basic cell sample data, determines the denoising threshold according to the distribution characteristics of the sample data, conducts data dimensionality reduction and extracts the key differences between samples, calculates the Euclidean distance between samples, and groups samples with similar immune response characteristics into the same group to obtain the integrated feature data;

[0043] The correlation analysis module, based on the integrated feature data, detects the correlation between proteins and metabolites, calculates the interaction intensity between proteins and metabolites, identifies metabolic pathways related to immune reactions, reveals the key protein-metabolite interactions in the immune reaction mechanism, and generates a functional network diagram;

[0044] The marker verification module, based on the functional network diagram, screens key protein and metabolite markers related to immune reactions, verifies whether each candidate marker has an expression pattern with known immune functions, detects changes in immune cells, evaluates the performance during the immune reaction process, confirms the correlation of each marker with the key processes of immune reactions, identifies the potential functions of each marker in immune reactions, and obtains the marker verification data;

[0045] Based on the verified biomarker data, the immune response monitoring module monitors different stages of the immune response through the contact reaction between immune stimulation and target cells, observes and records the interaction between target cells and CAR-NK cells, analyzes the change trends of biomarkers in different immune response stages and their relationship with the reaction of CAR-NK cells, determines the time dynamics of cell reactions and biomarker changes, and obtains the extraction results of CAR-NK cell immunoreactivity characteristics.

[0046] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0047] In the present invention, by quantitatively analyzing proteins and metabolites in CAR-NK cell samples, it is possible to comprehensively capture the reaction characteristics of cells in different immune environments. Immune response grouping and clustering analysis clarify the influence of the immune environment on cell functions. The protein-metabolite interaction network reveals the molecular interactions inside and outside the cells. By screening and verifying immune markers, it provides a basis for accurate immune function evaluation. The quantitative analysis of immunoreactivity characteristics can track the immune response process in real time, improving the research accuracy and depth. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is the main process flow chart of the present invention;

[0049] Figure 2 is the flow chart for obtaining the basic data of cell samples of the present invention;

[0050] Figure 3 is the flow chart for obtaining the integrated feature data of the present invention;

[0051] Figure 4 is the flow chart for obtaining the functional network diagram of the present invention;

[0052] Figure 5 is the flow chart for verifying candidate markers of the present invention;

[0053] Figure 6 is the flow chart for obtaining the marker verification data of the present invention;

[0054] Figure 7 is the flow chart for obtaining the extraction results of CAR-NK cell immunoreactivity characteristics of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0056] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by terms such as "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0057] Please refer to Figure 1 , a method for extracting features of CAR-NK cell data, comprising the following steps:

[0058] S1: Collect CAR-NK cell samples, batch-analyze the CAR-NK cell samples for proteins, record the expression changes of proteins in each batch of CAR-NK cell samples, perform quantitative analysis on metabolite samples to obtain metabolite concentration data, and perform standardization processing on the concentration data to obtain basic cell sample data;

[0059] S2: According to the basic cell sample data, perform denoising processing on the data, extract the key differences between samples through data dimensionality reduction, cluster according to sample characteristics, group the samples according to immune responses, and extract key information to obtain integrated feature data;

[0060] S3: Based on the integrated feature data, construct a protein-metabolite interaction network, connect proteins with related metabolites, evaluate the interaction between proteins and metabolites during the immune response process, identify the interaction changes between metabolic pathways and proteins, and generate a functional network diagram;

[0061] S4: Based on the functional network diagram, screen key proteins and metabolite markers associated with the immune response, confirm candidate markers according to literature and databases, verify the candidate markers, detect the expression of each marker in CAR-NK cells according to the verification results, and analyze the role of each marker in the immune response to obtain marker verification data;

[0062] S5: According to the verified marker data, perform quantitative analysis on the immunoreactivity of CAR-NK cells, monitor the contact reaction between CAR-NK cells and target cells, evaluate the dynamic process of the immune response, and combine flow cytometry data to quantify the reactivity of key markers to obtain the results of extracting the immunoreactivity characteristics of CAR-NK cells.

[0063] The basic data of cell samples include protein expression data, metabolite concentration data, and normalization data. The integrated feature data include the data after noise reduction, key differential features, and immune response grouping results. The functional network diagram includes protein-metabolite interaction relationships, analysis results of metabolic pathway changes, and analysis results of protein interaction changes. The biomarker validation data include the selected candidate biomarkers, confirmation results from literature and databases, and expression data of biomarkers in CAR-NK cells. The results of immune reactivity feature extraction include contact reaction data between CAR-NK cells and target cells, analysis results of the dynamic process of immune responses, and reactivity quantification data of key biomarkers.

[0064] Please refer to Figure 2 , the steps for obtaining the basic data of cell samples are as follows:

[0065] S111: Collect CAR-NK cell samples, extract the proteins in each batch of samples, and perform protein quantitative analysis to obtain the protein expression data in each batch of samples;

[0066] After collecting CAR-NK cell samples, first use an appropriate lysate to extract the proteins in the cells. The extraction steps include mixing the cell samples with the lysate containing buffer, and through appropriate temperature and time control, rupturing the cell membrane and releasing the proteins therein. To ensure that the extracted proteins can be stably and completely separated and measured, it is necessary to pay attention to using a lysate without enzymes to avoid protein degradation. In the extracted samples, the proteins need to go through a centrifugation process to remove cell debris and other impurities, obtaining a purified protein solution containing proteins available for analysis. Subsequently, transfer the purified protein samples to an analysis platform for protein quantification analysis, and use high-precision techniques to detect the concentration and types of proteins in each batch of samples, thereby recording the protein data of each sample. In this step, the detection of protein content not only needs to ensure the accuracy of the protein expression level in the samples, but also requires multiple rechecks to ensure that the protein data extracted from each batch of samples has sufficient representativeness and consistency.

[0067] S112: Compare the protein expression data in each batch of samples, determine the expression changes of proteins through differential analysis, record the situation of protein expression changes in each batch of samples, and obtain the protein change data in each sample;

[0068] After obtaining the protein data for each batch of samples, the next step is to perform differential analysis on the protein expression data. First, the protein data measured in each batch of samples are compared one by one, and the difference in expression levels of each protein in different samples is recorded. When comparing, it is necessary to analyze whether there are obvious expression fluctuations or significant changes between different batches. During the analysis process, the selected protein expression differences should meet the set standards, and statistical tests are usually used to detect these changes. For example, a paired t-test or analysis of variance is performed to determine whether the difference in protein expression between different batches is statistically significant. In this process, the p-value of each protein expression needs to be calculated and the significance level is set to determine which proteins have statistically significant differences in expression in different samples. After completing the differential analysis, the generated protein expression change data will be recorded in a special file or database to provide the necessary background data support for subsequent metabolite analysis.

[0069] S113: extracting metabolite components in each batch of samples according to the protein change data in each sample, obtaining the concentration data of each metabolite, and standardizing the metabolite concentration data, and combining with the protein expression change data to obtain the basic data of the cell samples;

[0070] When extracting the metabolite components in each batch of CAR-NK cell samples, the cell samples are first placed in a solution and the metabolites in the cells are separated using a solvent. In order to ensure that the separated metabolites can be accurately detected in subsequent analysis, a suitable solvent system is selected to dissolve the cell contents. Subsequently, the sample is subjected to an appropriate filtration or centrifugation process to remove unwanted impurities and insolubles to ensure that only metabolites are contained in the solution. During the analysis, the treated sample is introduced into the analysis equipment and the metabolites are quantitatively analyzed using mass spectrometry. In this process, it is necessary to set an appropriate detection standard curve to ensure that the concentration measurement of the metabolites is accurate. The concentration of each metabolite in the sample is calculated by comparing the standard curve, and the metabolite concentration data of each sample is ensured to be stable and repeatable in multiple experiments. Finally, the obtained concentration data is standardized, usually using the Z-score method for standardization, so that the concentration data of each metabolite in each batch of samples are comparable, which can ensure the consistency of data between different batches and provide reliable quantitative results for further analysis.

[0071] See also Figure 3 , the steps to obtain the integrated feature data are:

[0072] S211: Based on the basic data of the cell sample, each data point is evaluated, a denoising threshold is determined according to the distribution characteristics of the sample data, and outliers exceeding the denoising threshold are removed to obtain denoised sample data;

[0073] Based on the basic data of CAR-NK cell samples, the data is denoised to ensure the accuracy and reliability of the analysis results. The denoising process starts from detecting each data point. First, statistical analysis is performed on each data in the sample to calculate basic statistics such as its mean and standard deviation. Then, according to the set denoising criteria, abnormal data points that exceed the normal distribution range or exceed a certain standard deviation are removed. Specifically, if the deviation of a data point from the mean exceeds the set threshold (such as mean ± 3 times the standard deviation), it is regarded as an outlier. After the preliminary screening, any duplicates, missing data, or significantly deviated values in the data are continuously checked and corresponding processing is carried out, such as filling in missing values or removing duplicates. After the denoising process ends, the remaining data set will be cleaner and meet the analysis requirements, providing real and effective sample data for subsequent dimensionality reduction and clustering analysis.

[0074] S212: According to the sample data after denoising, perform dimensionality reduction on the data and extract the key differences between samples, retain the key features between samples, and eliminate redundant information to obtain the data after dimensionality reduction;

[0075] Perform dimensionality reduction on the denoised cell sample data to more clearly show the main differences between samples. The core of the dimensionality reduction process is to extract the most representative features from multi-dimensional data. First, analyze each dimension of each data point to find the key dimensions that can explain the data variance. In this process, it is necessary to evaluate the relationship between each feature in the data set and other features, as well as its role in sample discrimination, and select those features that are most helpful for sample differences. By calculating the contribution degree of each feature, determine the impact of each dimension on data variation, so as to retain the feature dimensions with the largest contribution degree and reduce redundant data. Then, by reconstructing the data points, use the selected main features to represent each sample again, so as to compress the original multi-dimensional data into a lower-dimensional space, ensuring that the data can still retain sufficient information after dimensionality reduction. The data after dimensionality reduction will help to discover the significant differences between samples and provide a more concise and highly representative data set for the subsequent clustering analysis.

[0076] S213: Based on the data after dimensionality reduction, perform sample clustering analysis, using the formula:

[0077]

[0078] Calculate the Euclidean distance d between sample i and sample j ij , the smaller the Euclidean distance between samples, the higher the similarity, and group the samples with similar immune response characteristics into the same group to obtain the integrated feature data, where x ik and x jk are the k-th eigenvalue of sample i and sample j respectively, and n is the total number of features;

[0079] There are two samples, sample i and sample j, and their values on two features (feature 1 and feature 2) are respectively:

[0080] Sample i: Feature 1 = 10, Feature 2 = 5;

[0081] Sample j: Feature 1 = 12, Feature 2 = 6;

[0082] Calculate the Euclidean distance according to the above formula:

[0083]

[0084] Calculate the square of the difference of each feature:

[0085] (10 - 12) 2 = (-2) 2 = 4

[0086] (5 - 6) 2 = (-1) 2 = 1

[0087] Add the two squared results:

[0088] 4 + 1 = 5

[0089] Calculate the square root:

[0090]

[0091] The calculated result is 2.236, which indicates a relatively low similarity between sample i and sample j. The smaller the Euclidean distance, the smaller the difference between the two samples and the more similar they are; while the larger the distance, the greater the difference and the lower the similarity between the samples. A distance of 2.236 indicates that the difference between sample i and sample j on feature 1 and feature 2 is relatively small, but the difference still exists, and it is suitable to be used as a similarity measure for subsequent clustering analysis or other classification tasks.

[0092] Please refer to Figure 4 , and the steps for obtaining the functional network diagram are as follows:

[0093] S311: Based on the integrated feature data, by analyzing the pairing relationship between each protein and its related metabolite, detect the interaction relationship between the protein and the metabolite, establish the connection between each protein and its related metabolite, and generate a preliminary interactive network structure;

[0094] Based on the integrated feature data, it is first necessary to construct a protein-metabolite interaction network. First, all proteins and metabolites are extracted from the existing cell sample data, and the expression data of each protein and metabolite are collected and sorted. Then, the relationship between each protein and its related metabolites is evaluated, and pairings between proteins and metabolites are established to ensure that the metabolites paired with each protein have biological relevance. To ensure the accuracy of the network, clinical data or experimental data related to immune responses need to be combined to further confirm the connection between proteins and metabolites. Through these data, the connections between proteins and metabolites are gradually constructed, and the importance of each pair of proteins and metabolites is evaluated based on the interaction strength, functional relevance, and immune response performance between them. Finally, a complete interaction network is formed, which will be able to reflect the interaction relationship between each protein and its related metabolites in immune responses and provide basic data for subsequent analysis.

[0095] S312: According to the protein-metabolite interaction network structure, use the formula:

[0096]

[0097] Calculate the interaction strength S between protein a and metabolite b ab , to obtain the interaction strength data of each pair of protein-metabolite, where, x ak and y bk are the expression levels of protein a and metabolite b on the k-th feature respectively, and n represents the total number of features;

[0098] There are two pairs of protein-metabolite, protein a and metabolite b, and their values on two features (feature 1 and feature 2) are:

[0099] Protein a: Feature 1 = 10, Feature 2 = 5;

[0100] Metabolite b: Feature 1 = 12, Feature 2 = 6;

[0101] Calculate the dot product:

[0102] x a1 ·y b1 +x a2 ·y b2 =(10×12)+(5×6)=120 + 30 = 150

[0103] Calculate the modulus length:

[0104]

[0105] Calculate the interaction strength:

[0106]

[0107] The calculation result is S ab ≈0.999, indicating a very high interaction strength between protein a and metabolite b. The closer the value of the interaction strength is to 1, the stronger the interaction between this pair of protein and metabolite. 0.999 indicates that this pair of protein and metabolite has a very close biological association and plays a key role in the immune response process.

[0108] S313: Based on the interaction strength data of each pair of protein-metabolite, identify the metabolic pathways related to the immune response, analyze the interaction changes between the metabolic pathways and proteins during the immune response process, reveal the key protein-metabolite interactions in the immune response mechanism, and generate a functional network diagram;

[0109] After establishing the protein-metabolite interaction network and evaluating their relationships, the next step is to identify the metabolic pathways related to the immune response and the interaction changes between the metabolic pathways and proteins. First, all metabolic pathways involved in the network need to be analyzed by identifying the key nodes and key proteins of the metabolic pathways and analyzing the roles they play during the immune response process. This process includes identifying which metabolic pathways play important roles in the immune response and analyzing the change trends of proteins and metabolites in each pathway. By combining the performance data of the immune response, analyze how the pathways interact with other biological events (such as cell activation, immune cell responses, etc.) during the immune response. Next, based on the identified metabolic pathways and their key protein-metabolite interaction relationships, generate a functional network diagram to show the interaction changes between different metabolic pathways and proteins during the immune response process. This functional network diagram not only helps to understand the key interaction relationships during the immune response process but also provides visual support for further studying the immune response mechanism.

[0110] Please refer to Figure 5 , and the verification steps for candidate markers are as follows:

[0111] S411: Based on the functional network diagram, screen the key protein and metabolite markers related to the immune response, and combine the key biological events during the immune response process. The screened markers will be ranked according to their priority of potential roles in the immune response to obtain the initially screened candidate markers;

[0112] Based on the functional network diagram, it is first necessary to comprehensively analyze the interaction relationships between proteins and metabolites. In this process, first collect and organize the data of proteins and metabolites contained in all networks, and compare the data with the key features in the immune response process to screen out the markers that may play an important role in the immune response process. The relationship between each protein and metabolite and the immune response needs to be confirmed by analyzing its expression changes, and the expression changes should be compared with the data of known immune-related biomarkers. During the screening process, the existing immune response mechanism analysis should be combined to ensure the importance of the selected markers in the immune response. Finally, select the markers with high research potential and establish a list of candidate markers to prepare for subsequent verification experiments.

[0113] S412: According to the preliminarily screened candidate markers, consult the research literature, analyze and compare the immune relevance of the candidate markers, confirm whether there is biological support in the immune response, and verify whether each candidate marker has an expression pattern of known immune function to obtain the confirmed candidate markers;

[0114] Next, confirm the screened candidate markers. This process mainly involves extensive literature research and database comparison. Specifically, first search for relevant research literature to find experimental data related to the candidate markers, and confirm the known functions and expression patterns of these markers in the immune response. At the same time, combine the bioinformatics database of the immune response to verify whether the candidate markers have high biological rationality and whether they have been widely studied and confirmed. In the database verification stage, it is necessary to ensure that the candidate markers have clear manifestations under immune-related conditions and can be reproduced in different experiments, so as to confirm the immune relevance of the candidate markers.

[0115] S413: According to the confirmed candidate markers, verify the candidate markers, obtain the expression data of the markers through experiments, verify the actual role in the immune response, and detect the changes in immune cells to obtain a list of candidate markers;

[0116] After confirming the candidate markers, enter the experimental verification phase. This phase first involves designing and performing a series of verification experiments. The experimental content includes detecting the expression of candidate markers in CAR-NK cells, usually using experimental methods such as flow cytometry, Western Blot, qPCR, etc. Through these experimental techniques, the expression level of markers in immune cells can be accurately detected. Compare the expression changes of markers under different immune states, and further analyze their roles in immune responses. At the same time, it is necessary to compare the performance of markers in different experimental groups, confirm whether these markers play key roles in immune responses, verify their actual roles in immune responses through experimental data, and obtain a list of candidate markers to provide support for subsequent analysis of immune response mechanisms.

[0117] Please refer to Figure 6 , the steps for obtaining marker verification data are as follows:

[0118] S421: According to the list of candidate markers, detect the expression of each marker in CAR-NK cells, analyze the expression level of the marker in the cells, reveal the changes of the marker in the immune response, and generate marker expression data;

[0119] Based on the list of candidate markers, collect CAR-NK cell samples for immune stimulation treatment. When collecting samples, it is necessary to ensure that the number of cells in each sample is sufficient and maintain their biological activity. Then, according to the specific conditions of the immune response, the cells are treated at different time points to ensure that the cells can express the expected immune response under specific immune stimulation. Then, analyze the treated cells, collect cell samples and lyse them to extract the proteins and RNAs inside the cells. These extracts will then be used for subsequent quantitative detection. In the experimental operation, appropriate control groups also need to be set up to ensure that the stimulating effect of the immune response can be accurately monitored. The treatment of all experimental samples should be consistent to ensure the reliability of the data, and finally obtain accurate marker expression data.

[0120] S422: Based on the marker expression data, compare the expression changes of the markers before and after the immune response and under different stimulation conditions, evaluate their performance during the immune response, confirm the association of each marker with the key processes of the immune response, and generate marker immune function analysis data;

[0121] After obtaining the expression data of the biomarker, more in-depth analysis is required to evaluate the role of the biomarker in the immune response. First, group the cell samples according to different stages of the immune response and compare the biomarker expression data in each group. Specifically, it is necessary to analyze the role of the biomarker in the process of the immune response based on the change patterns of the biomarker such as the activation state of immune cells and the secretion of immune factors. If there are significant expression changes of the biomarker during the immune response and it is highly correlated with the functional changes of immune cells, it can be further speculated that it may be involved in the activation or regulation of immune cells. In addition, for different time points of the immune response, it is necessary to compare the expression changes of the biomarker, and finally obtain the potential function of each biomarker in the immune response.

[0122] S423: According to the immune function analysis data, identify the potential function of each biomarker in the immune response, combine the experimental data analysis of the potential biological mechanism, and obtain the biomarker verification data;

[0123] After completing the preliminary analysis of the immune function of the biomarker, the next step is to conduct a comprehensive evaluation of the biomarker to further confirm its specific biological function in the immune response. At this time, first, it is necessary to integrate all the previously obtained biomarker expression and immune function data and compare the performance of the biomarker in different immune response states. In particular, attention should be paid to the changes of the biomarker at the key time points of the immune response, and combined with the functional state of immune cells, speculate on its specific role in the immune response. By comparing with other known key factors in the immune response, confirm whether the biomarker plays a regulatory or controlling role in the immune response. Finally, through systematic integration of all data, obtain the biomarker verification data, providing strong support for the subsequent research on the immune response mechanism.

[0124] Please refer to Figure 7 , and the steps for obtaining the results of the extraction of the immunoreactivity characteristics of CAR-NK cells are as follows:

[0125] S511: Based on the verified biomarker data, quantitatively analyze the immunoreactivity of CAR-NK cells. Through the immune stimulation and target cell contact reaction, monitor the different stages of the immune response, and conduct real-time quantitative analysis of the cell contact reaction to obtain the quantitative data of the immunoreactivity of CAR-NK cells;

[0126] It is necessary to quantitatively analyze the immunoreactivity of CAR-NK cells based on the validation biomarker data. This process includes detailed recording of the quantity and change amplitude of each biomarker during the immune response process. By sorting out and statistically analyzing the quantified biomarker data in the experiment, its performance in different immune response stages is judged, and an immunoreactivity index is constructed using the detection values of the corresponding biomarkers. Analyze the relationship between biomarker changes and immune response intensity, and combine the time and intensity of the interaction between immune cells and target cells to further deduce the characteristics of the immune response, ultimately providing data support for the evaluation of the immunoreactivity of CAR-NK cells. The analysis results help to understand the expression of biomarkers and their impact on the immune response, provide quantified immunoreactivity data, and lay a foundation for subsequent immune response analysis.

[0127] S512: According to the quantitative data of CAR-NK cell immunoreactivity, observe and record the interaction between target cells and CAR-NK cells, quantify the reactivity of biomarkers, analyze the performance of biomarkers in cell contact reactions under different immune stimulation conditions, analyze the relationship between biomarkers and cell contact reactions, and obtain quantified biomarker reactivity data;

[0128] During the monitoring of the contact reaction between CAR-NK cells and target cells, it is first necessary to regularly collect cell samples at different time points. Record the contact situation at each time point, and analyze the contact reaction frequency, intensity, and duration between CAR-NK cells and target cells. When performing flow cytometry experiments, the expression of cell surface biomarkers is observed in real time to quantify cell contact events. The quantity and quality of these contact events can be further analyzed through the activation of intracellular signaling pathways to understand the progress of the immune response. Through the changes of various biomarkers during the reaction process, combined with data from multiple links of the immune response, the intensity of the immune response and the target cell response are ultimately evaluated, and the relationship between immunoreactivity and target cell contact reaction is obtained, providing a basis for further analysis of immune effects.

[0129] S513: Combine the quantified biomarker reactivity data, analyze the change trend of biomarkers and their relationship with CAR-NK cell reactions in different immune response stages, determine the time dynamics of cell reactions and biomarker changes, and obtain the results of CAR-NK cell immunoreactivity feature extraction;

[0130] In the process of quantifying the reactivity of key markers in combination with flow cytometry data, it is first necessary to convert the data collected in the experiment into a standardized reactivity index. By analyzing the performance of markers at each reaction stage, quantifying the range and rate of change of each marker, measuring the fluctuations in marker expression levels with the progress of the immune response, and using these quantified reactivity data, a dynamic analysis curve of the immune response intensity is constructed. Further, by comparing the data of the experimental control group and the experimental group, the key roles of each marker in the immune response are evaluated. The relationship between the quantitative reactivity data of the markers and the immune response intensity provides a theoretical basis for further analyzing the immune response process, and by summarizing and statistically analyzing the marker validation data, the results of extracting the immune reactivity characteristics of CAR-NK cells are generated.

[0131] A system for extracting the characteristics of CAR-NK cell data, comprising:

[0132] The sample data processing module collects CAR-NK cell samples, extracts the proteins in each batch of samples, and performs protein quantitative analysis. By differential analysis, the expression changes of the proteins are determined. The metabolite components in each batch of samples are extracted, the concentration data is obtained and standardized, and combined with the protein expression change data to obtain the basic data of the cell samples;

[0133] The feature extraction module, based on the basic data of the cell samples, determines the denoising threshold according to the distribution characteristics of the sample data, performs data dimensionality reduction and extracts the key differences between samples, calculates the Euclidean distance between samples, and groups the samples with similar immune response characteristics into the same group to obtain the integrated feature data;

[0134] The correlation analysis module, based on the integrated feature data, detects the correlation between proteins and metabolites, calculates the interaction intensity between proteins and metabolites, identifies the metabolic pathways related to the immune response, reveals the key protein-metabolite interactions in the immune response mechanism, and generates a functional network diagram;

[0135] The marker validation module, based on the functional network diagram, screens the key protein and metabolite markers related to the immune response, verifies whether each candidate marker has an expression pattern with known immune functions, detects the changes in immune cells, evaluates the performance during the immune response process, confirms the correlation of each marker with the key processes of the immune response, and identifies the potential functions of each marker in the immune response to obtain the marker validation data;

[0136] Based on the validated biomarker data, the immune response monitoring module monitors different stages of the immune response through the contact reaction between immune stimulation and target cells, observes and records the interaction between target cells and CAR-NK cells, analyzes the changing trends of biomarkers in different immune response stages and their relationship with the CAR-NK cell response, determines the temporal dynamics of cell responses and biomarker changes, and obtains the results of extracting the immunoresponsive characteristics of CAR-NK cells.

[0137] The above are only the preferred embodiments of the present invention and do not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A method for feature extraction of CAR-NK cell data, characterized in that, Including the following steps: S1: Collect CAR-NK cell samples, conduct protein analysis on the CAR-NK cell samples in batches, record the expression changes of proteins in each batch of CAR-NK cell samples, perform quantitative analysis on metabolite samples to obtain metabolite concentration data, and standardize the concentration data to obtain basic cell sample data; S2: According to the basic cell sample data, perform denoising processing on the data, extract the key differences between samples through data dimensionality reduction, cluster according to sample characteristics, group the samples according to immune responses, and extract key information to obtain integrated feature data; S3: Based on the integrated feature data, construct a protein-metabolite interaction network, connect proteins with related metabolites, evaluate the interaction between proteins and metabolites during the immune response process, identify the interaction changes between metabolic pathways and proteins, and generate a functional network diagram; S4: Based on the functional network diagram, screen key proteins and metabolite markers associated with the immune response, confirm candidate markers according to literature and databases, verify the candidate markers, detect the expression of each marker in CAR-NK cells according to the verification results, and analyze the role of each marker in the immune response to obtain marker verification data; S5: According to the verified marker data, perform quantitative analysis on the immune reactivity of CAR-NK cells, monitor the contact reaction between CAR-NK cells and target cells, evaluate the dynamic process of the immune response, and quantify the reactivity of key markers to obtain the extraction results of CAR-NK cell immune reactivity characteristics.

2. The method for extracting features of CAR-NK cell data according to claim 1, wherein The steps for obtaining the basic cell sample data are as follows: S111: Collect CAR-NK cell samples, extract proteins from each batch of samples, and conduct protein quantitative analysis to obtain protein expression data for each batch of samples; S112: Compare the protein expression data in each batch of samples, determine the expression changes of proteins through differential analysis, record the protein expression change conditions in each batch of samples, and obtain the protein change data for each sample; S113: According to the protein change data for each sample, extract the metabolite components from each batch of samples, obtain the concentration data for each metabolite, standardize the metabolite concentration data, and combine with the protein expression change data in each batch of samples to obtain basic cell sample data.

3. The method for extracting features of CAR-NK cell data according to claim 2, wherein The steps for obtaining the integrated feature data are as follows: S211: Based on the basic cell sample data, evaluate each data point, determine the denoising threshold according to the distribution characteristics of the sample data, and remove outliers exceeding the denoising threshold to obtain denoised sample data; S212: According to the denoised sample data, perform data dimensionality reduction and extract the key differences between samples, retain the key features between samples, and eliminate redundant information to obtain the data after dimensionality reduction; S213: Based on the data after dimensionality reduction, perform sample clustering analysis using the formula: Calculate the Euclidean distance d between sample i and sample j ij , the smaller the Euclidean distance between samples, the higher the similarity, and samples with similar immune response characteristics are grouped into the same group to obtain the integrated feature data, where x ik and x jk are the k-th eigenvalue of sample i and sample j respectively, and n is the total number of features.

4. The method for extracting features of CAR-NK cell data according to claim 3, wherein The steps for obtaining the functional network diagram are as follows: S311: Based on the integrated feature data, by analyzing the pairing relationship between each protein and its related metabolite, detect the interaction relationship between the protein and the metabolite, establish the connection between each protein and the related metabolite, and generate a preliminary interaction network structure; S312: According to the protein-metabolite interaction network structure, use the formula: Calculate the interaction strength S between protein a and metabolite b ab , and obtain the interaction strength data for each pair of protein-metabolite, where x ak and y bk are the expression levels of protein a and metabolite b on the k-th feature respectively, and n represents the total number of features; S313: According to the interaction intensity data of each pair of protein-metabolite, identify the metabolic pathways related to the immune response, analyze the interaction changes between the metabolic pathways and proteins during the immune response, reveal the key protein-metabolite interactions in the immune response mechanism, and generate a functional network diagram.

5. The method for extracting features of CAR-NK cell data according to claim 4, wherein, The verification steps for the candidate markers are as follows: S411: Based on the functional network diagram, screen the key proteins and metabolite markers related to the immune response, combine the key biological events during the immune response, and rank the screened markers according to the priority of their potential roles in the immune response to obtain the preliminarily screened candidate markers; S412: According to the preliminarily screened candidate markers, consult the research literature, analyze and compare the immune relevance of the candidate markers, confirm whether there is biological support in the immune response, and verify whether each candidate marker has an expression pattern of known immune function to obtain the confirmed candidate markers; S413: According to the confirmed candidate markers, verify the candidate markers, obtain the expression data of the markers through experiments, verify the actual role in the immune response, and detect the changes in immune cells to obtain a list of candidate markers.

6. The method for extracting the characteristics of CAR-NK cell data according to claim 5, wherein, The steps for obtaining the verification data of the markers are as follows: S421: According to the list of candidate markers, detect the expression of each marker in CAR-NK cells, analyze the expression level of the marker in the cells, reveal the changes of the marker in the immune response, and generate marker expression data; S422: Based on the marker expression data, compare the expression changes of the markers before and after the immune response and under different stimulation conditions, evaluate the performance during the immune response, and confirm the association of each marker with the key processes of the immune response to generate marker immune function analysis data; S423: According to the immune function analysis data, identify the potential functions of each marker in the immune response, and combine the experimental data to analyze the potential biological mechanism to obtain the marker verification data.

7. The method for extracting features of CAR-NK cell data according to claim 6, wherein The steps for obtaining the results of the immune reactivity characteristics of CAR-NK cells are as follows: S511: Based on the verified marker data, quantitatively analyze the immune reactivity of CAR-NK cells. Through the immune stimulation and the contact reaction with target cells, monitor the different stages of the immune response, and perform real-time quantitative analysis of the cell contact reaction to obtain the quantitative data of the immune reactivity of CAR-NK cells; S512: According to the quantitative data of the CAR-NK cell immunoreactivity, observe and record the interaction between the target cells and CAR-NK cells, quantify the reactivity of the markers, analyze the performance of the markers in the cell contact reaction under different immune stimulation conditions, analyze the relationship between the markers and the cell contact reaction, and obtain the quantified marker reactivity data; S513: Combine the quantified marker reactivity data, analyze the change trend of the markers and their relationship with the CAR-NK cell reaction in different immune response stages, determine the temporal dynamics of cell reactions and marker changes, and obtain the results of CAR-NK cell immunoreactivity feature extraction.

8. A feature extraction system for CAR-NK cell data, characterized in that, The system is used to execute the method for extracting features of CAR-NK cell data according to any one of claims 1-7, and includes: The sample data processing module collects CAR-NK cell samples, extracts proteins in each batch of samples, performs protein quantitative analysis, determines the expression changes of proteins through differential analysis, extracts metabolite components in each batch of samples, obtains concentration data and performs normalization processing, and combines the protein expression change data to obtain the basic cell sample data; The feature extraction module, based on the basic cell sample data, determines the denoising threshold according to the distribution characteristics of the sample data, performs data dimensionality reduction and extracts the key differences between samples, calculates the Euclidean distance between samples, and groups samples with similar immune response characteristics into the same group to obtain the integrated feature data; The correlation analysis module, based on the integrated feature data, detects the correlation between proteins and metabolites, calculates the interaction strength between proteins and metabolites, identifies metabolic pathways related to immune responses, reveals the key protein-metabolite interactions in the immune response mechanism, and generates a functional network diagram; The marker verification module, based on the functional network diagram, screens key protein and metabolite markers related to immune responses, verifies whether each candidate marker has an expression pattern with known immune functions, detects changes in immune cells, evaluates the performance during the immune response process, confirms the association of each marker with the key processes of immune responses, and identifies the potential functions of each marker in immune responses to obtain marker verification data; The immune response monitoring module, based on the verified marker data, monitors different stages of the immune response through the contact reaction between immune stimulation and target cells, observes and records the interaction between target cells and CAR-NK cells, analyzes the change trend of the markers and their relationship with the CAR-NK cell reaction in different immune response stages, determines the temporal dynamics of cell reactions and marker changes, and obtains the results of CAR-NK cell immunoreactivity feature extraction.

Images