Neuronal apoptosis risk assessment system based on oxidative stress signal axis

Abstract

The invention discloses a neuronal apoptosis risk assessment system based on an oxidative stress signal axis. The neuronal apoptosis risk assessment system comprises the following steps: acquiring oxidative stress biomarker measurement data; calculating an oxidative stress signal axis activation index based on the oxidative stress biomarker measurement data; determining a neuronal apoptosis key factor expression level based on the oxidative stress signal axis activation index; calculating a neuronal apoptosis risk assessment value based on the neuronal apoptosis key factor expression level; and outputting the neuronal apoptosis risk assessment value. Compared with the prior art, the neuron apoptosis risk assessment method has the following advantages and effects: on the basis of integrated analysis of the oxidative stress signal axis multi-level biomarkers, through dynamic weight adjustment and activation index quantification, more accurate and systematic assessment of the neuron apoptosis risk is realized, and the reliability of risk assessment in non-diagnostic research is remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bioinformatics, and particularly relates to a neuron apoptosis risk assessment system based on an oxidative stress signaling axis. BACKGROUND

[0002] Neuron apoptosis is an important pathological process in the development of various nervous system diseases (such as Alzheimer's disease, Parkinson's disease, etc.), in which oxidative stress, as a key driving factor, triggers neuron apoptosis by activating specific signaling axes (such as signaling pathways involving reactive oxygen species, antioxidant enzymes, and lipid peroxidation products, etc.). The oxidative stress signaling axis is a complex network, including upstream activating signaling molecules, antioxidant defense signaling molecules, and downstream oxidative damage signaling molecules, and the interaction of these signaling molecules collectively determines the fate of neurons.

[0003] In the prior art, the assessment of neuron apoptosis risk usually relies on the measurement of a single or a small number of oxidative stress biomarkers (such as reactive oxygen concentration or antioxidant enzyme activity), and the risk is inferred by simply comparing their values with reference ranges. However, this method has obvious limitations: it cannot comprehensively reflect the overall activation state of the oxidative stress signaling axis, because different levels of biomarkers in the signaling axis have different relative importance, and their synergistic or antagonistic effects are not fully considered. For example, changes in upstream activating signaling molecules can have a nonlinear impact on the expression of downstream apoptosis key factors (such as Bax, Caspase-3, etc.), but the existing method lacks a mechanism to integrate multiple biomarker data into a quantitative index, resulting in inaccurate and unreliable assessment results.

[0004] Therefore, the most core problem in the prior art is the lack of a comprehensive method that can systematically quantify the overall activation degree of the oxidative stress signaling axis and accurately assess the risk of neuron apoptosis based on it. This limits the effective monitoring and prediction of neuron health status in non-diagnostic research (such as drug screening or toxicity testing). The present application aims to solve this core problem. SUMMARY

[0005] The purpose of the present application is to provide a neuron apoptosis risk assessment system based on an oxidative stress signaling axis to solve the problems presented in the background.

[0006] The above technical purpose of the present application is achieved by the following technical solution: The present application provides a neuron apoptosis risk assessment system based on an oxidative stress signaling axis, comprising the following steps: S100, obtaining oxidative stress biomarker measurement data; wherein the oxidative stress biomarker measurement data comprises measurement values of at least one oxidative stress-related biomarker corresponding to a signal molecule in the oxidative stress signaling axis; S200, calculating an oxidative stress signaling axis activation index based on the oxidative stress biomarker measurement data; wherein the oxidative stress signaling axis activation index quantifies the overall activation degree of the oxidative stress signaling axis, and is obtained by multiplying the measurement values of each oxidative stress-related biomarker by corresponding weight coefficients and then summing them up, wherein the weight coefficients are determined based on the relative importance of each oxidative stress-related biomarker in the oxidative stress signaling axis; S300, determining a neuronal apoptosis key factor expression level based on the oxidative stress signaling axis activation index; wherein the neuronal apoptosis key factor expression level comprises the expression amount of at least one protein or gene related to the neuronal apoptosis process; S400, calculating a neuronal apoptosis risk assessment value based on the neuronal apoptosis key factor expression level; wherein the neuronal apoptosis risk assessment value is a comprehensive value obtained by weighting calculation of the expression level of each neuronal apoptosis key factor with corresponding risk coefficients, and is used to reflect the potential risk level of neuronal apoptosis; S500, outputting the neuronal apoptosis risk assessment value; wherein the neuronal apoptosis risk assessment value is presented in the form of a visual chart or a digital report for non-diagnostic purposes of neuronal health status assessment.

[0007] By adopting the above technical solutions, oxidative stress biomarker measurement data can be systematically integrated, oxidative stress signaling axis activation index can be calculated to quantify the overall activation degree, and then neuronal apoptosis key factor expression level can be determined, and finally neuronal apoptosis risk assessment value can be obtained by weighting calculation. This multi-step and hierarchical evaluation process can comprehensively capture the complex correlation between oxidative stress signaling axis and neuronal apoptosis, significantly improving the accuracy and reliability of risk assessment. By introducing weight coefficients and risk coefficients, the relative importance of different biomarkers and key factors in the pathological process is fully considered, making the evaluation results more scientific and objective. At the same time, the output is presented in the form of a visual chart or a digital report, which is convenient for users to intuitively understand the evaluation results, providing a practical tool for non-diagnostic purposes of neuronal health status assessment, suitable for scientific research, drug development or preventive health management scenarios, and helpful for early identification of potential risks and guidance of intervention strategies.

[0008] Further provided is that in the S100, the method specifically comprises the following steps: extracting oxidative stress biomarker raw data corresponding to the target sample from a biological sample database; wherein the biological sample database stores a plurality of groups of oxidative stress biomarker raw data as samples, the target sample is a neuron cell cultured in vitro or an animal model tissue sample, and the oxidative stress biomarker raw data includes measurement values of oxidative stress-related biomarkers corresponding to signal molecules in an oxidative stress signal axis, wherein the oxidative stress-related biomarkers include but are not limited to reactive oxygen species concentration, superoxide dismutase activity, glutathione peroxidase activity and lipid peroxidation product content, wherein the reactive oxygen species corresponds to an upstream activating signal molecule of the oxidative stress signal axis, the superoxide dismutase and the glutathione peroxidase correspond to antioxidant defense signal molecules, and the lipid peroxidation product corresponds to a downstream oxidative damage signal molecule; preprocessing the oxidative stress biomarker raw data; wherein the preprocessing includes data cleaning, outlier rejection and standardization processing; and confirming the preprocessed oxidative stress biomarker raw data as the oxidative stress biomarker measurement data.

[0009] By adopting the above technical solution, the oxidative stress biomarker raw data is extracted from the biological sample database, and the key biomarkers including reactive oxygen species concentration, superoxide dismutase activity, glutathione peroxidase activity and lipid peroxidation product content are covered to cover the upstream activating signal molecules, antioxidant defense signal molecules and downstream oxidative damage signal molecules of the oxidative stress signal axis, so as to ensure the comprehensiveness and biological representativeness of the data. The preprocessing of the oxidative stress biomarker raw data, including data cleaning, outlier rejection and standardization processing, can effectively eliminate measurement errors and noise interference, improve the quality and consistency of the data, provide a reliable basis for subsequent calculation, reduce evaluation bias, and at the same time, the method is suitable for in vitro cultured neuron cells or animal model tissue samples, and the repeatability and applicability of the method to different experimental conditions are enhanced.

[0010] Further, the S200 specifically includes the following steps: based on the types of each oxidative stress-related biomarker in the oxidative stress biomarker measurement data, obtaining a corresponding basic weight coefficient from a preset signal axis hierarchical weight database; wherein the signal axis hierarchical weight database stores basic weight coefficients corresponding to different hierarchical signal molecules in the oxidative stress signal axis, and the signal molecules include upstream activating signal molecules, antioxidant defense signal molecules and downstream oxidative damage signal molecules; the basic weight coefficient corresponding to the upstream activating signal molecule is higher than the basic weight coefficients corresponding to the antioxidant defense signal molecules and the downstream oxidative damage signal molecules; inputting the measured values of each oxidative stress-related biomarker in the oxidative stress biomarker measurement data into a preset dynamic weight adjustment model respectively to obtain a dynamic adjustment factor corresponding to each oxidative stress-related biomarker; multiplying the base weight coefficient corresponding to each oxidative stress-related biomarker and the dynamic adjustment factor corresponding thereto to obtain a final weight coefficient of each oxidative stress-related biomarker; calculating an initial activation index based on the measured values of each oxidative stress-related biomarker in the oxidative stress biomarker measurement data and the final weight coefficient corresponding thereto; wherein the initial activation index is obtained by multiplying the measured values of each oxidative stress-related biomarker and the final weight coefficient corresponding thereto and then summing them up; inputting the initial activation index into a preset activation index normalization model to obtain a normalized oxidative stress signal axis activation index.

[0011] By adopting the above technical solutions, the base weight coefficient is obtained from the preset signal axis level weight database based on the oxidative stress biomarker type, and the relative importance of the upstream activation signal molecules, antioxidant defense signal molecules and downstream oxidative damage signal molecules is distinguished, so that the weight distribution is more in line with the biological hierarchical structure of the oxidative stress signal axis, and the scientificity and rationality of the activation index calculation are improved; the dynamic weight adjustment model is introduced to generate a dynamic adjustment factor, and the final weight coefficient is calculated in combination with the base weight coefficient, and this dynamic mechanism can adaptively adjust the weight according to the actual measurement value, thereby enhancing the adaptability to the sample specificity, and thus improving the accuracy and individualization level of the activation index; after calculating the initial activation index, normalization processing is performed, so that the result has comparability and standardization under different samples or experimental conditions, facilitating cross-study comparison and application, and further strengthening the reliability and universality of the evaluation.

[0012] Further, in the S200, inputting the measured values of each oxidative stress-related biomarker in the oxidative stress biomarker measurement data into a preset dynamic weight adjustment model respectively to obtain a dynamic adjustment factor corresponding to each oxidative stress-related biomarker, specifically includes the steps of: obtaining a reference value range of the preset oxidative stress-related biomarker; wherein the reference value range includes a lower limit of the reference value and an upper limit of the reference value, and the reference value range is obtained based on historical measurement data of the corresponding oxidative stress-related biomarker in healthy neuron cells or normal animal model tissues; calculating the deviation degree of the measured value of each oxidative stress-related biomarker from the corresponding reference value range respectively; determine an adjustment coefficient benchmark value of each oxidative stress-related biomarker based on a relative positional relationship between a measured value of each oxidative stress-related biomarker and a corresponding reference value range; based on the deviation of each oxidative stress-related biomarker, the corresponding adjustment coefficient benchmark value, and the preset sensitivity coefficient, a dynamic adjustment factor corresponding to each oxidative stress-related biomarker is calculated through a preset composite function relationship; wherein the composite function relationship ensures that when the deviation increases, the dynamic adjustment factor correspondingly increases, and different sensitivity coefficients are used for different types of oxidative stress-related biomarkers.

[0013] By using the above technical solutions, by obtaining the reference value range of the oxidative stress-related biomarker and calculating the deviation of the measured value, the abnormality degree of the biomarker can be accurately quantified, and an objective basis is provided for weight adjustment; based on the deviation and the adjustment coefficient benchmark value, combined with the sensitivity coefficient, the dynamic adjustment factor is calculated through the composite function relationship, which ensures the refinement and scientificity of the weight adjustment process, so that the weight can dynamically reflect the actual change trend of the biomarker; different sensitivity coefficients of different types of biomarkers can distinguish the influence intensity of key signal molecules, improve the sensitivity and specificity of evaluation, and thus more accurately capture the activation state of the oxidative stress signal axis and reduce the risk of misjudgment.

[0014] Further provided is that the S300 specifically includes the following steps: based on the oxidative stress signal axis activation index, a corresponding neuron apoptosis key factor benchmark expression level is obtained from a preset signal axis-key factor mapping database; wherein the signal axis-key factor mapping database stores a corresponding relationship between the oxidative stress signal axis activation index and the neuron apoptosis key factor benchmark expression level, the neuron apoptosis key factor benchmark expression level is obtained based on historical experimental data, and the historical experimental data includes oxidative stress signal axis activation indexes and corresponding historical expression measurement values of neuron apoptosis key factors of in vitro neuron culture models or animal models under different oxidative stress conditions; the neuron apoptosis key factor includes at least one protein or gene related to the neuron apoptosis process; based on the oxidative stress signal axis activation index and the neuron apoptosis key factor benchmark expression level, a neuron apoptosis key factor expression level is calculated.

[0015] By adopting the technical scheme, the neuron apoptosis key factor reference expression level is obtained from a preset signal axis-key factor mapping database, the signal axis-key factor mapping database is obtained based on historical experimental data statistics, the reliability and empirical basis of the reference value are ensured, the expression level calculation has high traceability and scientificity, the direct correlation between the oxidative stress signal axis activation and the neuron apoptosis key factor is established based on the correspondence between the oxidative stress signal axis activation index and the reference expression level, the experience law in the historical data can be effectively utilized, and the accuracy and repeatability of the expression level prediction are improved, the method is suitable for an in vitro neuron culture model or an animal model, the applicability and cross-scene consistency of the method are enhanced, and stable and reliable input data are provided for subsequent risk assessment.

[0016] Further, in the S300, based on the oxidative stress signal axis activation index and the neuron apoptosis key factor reference expression level, the neuron apoptosis key factor expression level is calculated, specifically including the steps of: Based on the oxidative stress signal axis activation index and a preset activation index-expression level correction model, a neuron apoptosis key factor expression level correction value is calculated; wherein the activation index-expression level correction model is used to adjust the neuron apoptosis key factor reference expression level according to the change of the oxidative stress signal axis activation index, the activation index-expression level correction model represents a nonlinear relationship between the oxidative stress signal axis activation index and the neuron apoptosis key factor expression level, and the nonlinear relationship is obtained by fitting historical data through a polynomial function or a machine learning model; Based on the neuron apoptosis key factor reference expression level and the neuron apoptosis key factor expression level correction value, a neuron apoptosis key factor final expression level is calculated; wherein the neuron apoptosis key factor final expression level is obtained by adding the neuron apoptosis key factor reference expression level and the neuron apoptosis key factor expression level correction value, and the neuron apoptosis key factor final expression level includes the expression amount of at least one protein or gene related to the neuron apoptosis process; The neuron apoptosis key factor final expression level is confirmed as the neuron apoptosis key factor expression level.

[0017] By using the above technical solution, by using the activation index-expression level correction model, the baseline expression level of the neuron apoptosis key factor is adjusted according to the change of the activation index of the oxidative stress signal axis, the activation index-expression level correction model is based on a polynomial function or a machine learning model to fit historical data, which can accurately represent the nonlinear relationship between the activation index of the oxidative stress signal axis and the expression level of the neuron apoptosis key factor, thereby more truly reflecting the complex dynamics in the living body; based on the baseline expression level and the correction value, the final expression level is calculated, so that the result not only depends on the historical baseline, but also incorporates the specific influence of the current activation index, improving the accuracy and adaptability of the expression level calculation; this method can handle nonlinear effects, avoid the limitations of simple linear models, and enhance the scientificity and reliability of the evaluation.

[0018] Further, the S400 specifically includes the following steps: Based on the expression level of the neuron apoptosis key factor, the basic risk coefficient and the risk adjustment factor of each neuron apoptosis key factor are obtained; The basic risk coefficient corresponding to each neuron apoptosis key factor is multiplied by the corresponding risk adjustment factor to obtain the final risk coefficient of each neuron apoptosis key factor; wherein the final risk coefficient is used to reflect the contribution degree of each neuron apoptosis key factor to the neuron apoptosis risk under the current expression level; Based on the expression level of each neuron apoptosis key factor in the expression level of the neuron apoptosis key factor and the corresponding final risk coefficient, an initial risk assessment value is calculated; wherein the initial risk assessment value is obtained by multiplying the expression level of each neuron apoptosis key factor and the corresponding final risk coefficient and then summing them up; The initial risk assessment value is input into a preset risk assessment value normalization model to obtain a normalized neuron apoptosis risk assessment value.

[0019] By using the above technical solution, by obtaining the basic risk coefficient and the risk adjustment factor of each neuron apoptosis key factor based on the expression level of the neuron apoptosis key factor, and multiplying the basic risk coefficient and the risk adjustment factor to obtain the final risk coefficient, the risk coefficient can dynamically reflect the change of the expression level of the neuron apoptosis key factor, and more accurately quantify the contribution degree of each neuron apoptosis key factor to the neuron apoptosis risk; after calculating the initial risk assessment value, normalization processing is performed, so that the evaluation result is standardized and comparable, facilitating risk level division and comparison under different samples or conditions; this weighting calculation and normalization method ensures the comprehensiveness and objectivity of the risk assessment value, improves the accuracy and practicality of the evaluation, and at the same time, the method is flexible and adaptive to different expression patterns of neuron apoptosis key factors, enhancing the robustness of the overall risk assessment.

[0020] Further, in the S400, based on the expression levels of the neuron apoptosis key factors, the basic risk coefficient and the risk adjustment factor of each neuron apoptosis key factor are obtained, specifically including the steps of: Based on the type of each neuron apoptosis key factor in the expression level of the neuron apoptosis key factor, the corresponding basic risk coefficient is obtained from a preset risk coefficient database; wherein the risk coefficient database stores the basic risk coefficients corresponding to different neuron apoptosis key factors, the basic risk coefficients are determined based on the correlation between each neuron apoptosis key factor and neuron apoptosis risk in historical data, and the historical data includes the expression levels of neuron apoptosis key factors and the corresponding neuron apoptosis incidence statistical values of animal models under different oxidative stress conditions; The expression level of each neuron apoptosis key factor in the expression level of the neuron apoptosis key factor is input into a preset risk adjustment model to obtain the corresponding risk adjustment factor of each neuron apoptosis key factor; wherein the risk adjustment model is used to dynamically adjust the basic risk coefficient according to the deviation degree of the expression level of the neuron apoptosis key factor, and the risk adjustment model is trained based on a machine learning algorithm or a statistical regression method.

[0021] By using the above technical solution, the basic risk coefficient is obtained from the preset risk coefficient database, which is determined based on the correlation between the expression level of the neuron apoptosis key factor and the incidence of neuron apoptosis in the historical data, ensuring the scientificity and empirical support of the basic risk coefficient, and making the risk assessment have an effective statistical basis; the risk adjustment model is used to dynamically adjust the basic risk coefficient according to the deviation degree of the expression level of the neuron apoptosis key factor, which is trained based on a machine learning algorithm or a statistical regression method, can automatically learn the complex relationship between the expression level and the risk, and improve the accuracy and automation level of risk adjustment; this method makes the risk coefficient adapt to the change of the expression level in real time, more finely captures the risk contribution of each key factor, and thus improves the sensitivity and reliability of the overall risk assessment.

[0022] The application also provides a neuron apoptosis risk assessment system based on an oxidative stress signal axis, which comprises the following modules: An oxidative stress biomarker measurement data acquisition module configured to acquire oxidative stress biomarker measurement data; An oxidative stress signal axis activation index calculation module connected to the oxidative stress biomarker measurement data acquisition module and configured to calculate an oxidative stress signal axis activation index based on the oxidative stress biomarker measurement data; A module for determining the expression level of key neuronal apoptosis factors is connected to the module for calculating the oxidative stress signal axis activation index, and is configured to determine the expression level of key neuronal apoptosis factors based on the oxidative stress signal axis activation index. The neuronal apoptosis risk assessment value calculation module is connected to the neuronal apoptosis key factor expression level determination module and is configured to calculate the neuronal apoptosis risk assessment value based on the expression level of the neuronal apoptosis key factor. The neuronal apoptosis risk assessment value output module is connected to the neuronal apoptosis risk assessment value calculation module and is configured to output the neuronal apoptosis risk assessment value.

[0023] In summary, the present invention has the following beneficial effects: based on the integrated analysis of multi-level biomarkers of the oxidative stress signaling axis, through dynamic weight adjustment and activation index quantification, it achieves a more accurate and systematic assessment of neuronal apoptosis risk, significantly improving the reliability of risk assessment in non-diagnostic studies. Attached Figure Description

[0024] Figure 1 This is the main flowchart of an embodiment; Figure 2 This is a flowchart of step S200 in the embodiment; Figure 3 This is a flowchart of step S300 in the embodiment; Figure 4 This is a flowchart of step S400 in the embodiment; Figure 5 This is a system block diagram for an embodiment. Detailed Implementation

[0025] The present invention will be further described in detail below with reference to the accompanying drawings.

[0026] like Figures 1-5 As shown; This embodiment discloses a neuronal apoptosis risk assessment system based on the oxidative stress signal axis, including the following steps: S100. Obtain measurement data of oxidative stress biomarkers; wherein, the measurement data of oxidative stress biomarkers includes the measurement value of at least one oxidative stress-related biomarker, and the oxidative stress-related biomarker corresponds to the signal molecule in the oxidative stress signal axis.

[0027] The specific implementation process involves systematically extracting the raw data of oxidative stress biomarkers corresponding to the target sample from the biological sample database, and performing comprehensive preprocessing operations to generate high-quality oxidative stress biomarker measurement data. The biological sample database, as a structured storage system, is usually deployed on a local server or cloud platform, and its internal storage contains multiple sets of oxidative stress biomarker raw data records derived from in vitro cultured neuron cells or animal model tissue samples. Each record includes a sample identifier, an experimental batch, a measurement timestamp, and the raw measurement values of multiple oxidative stress-related biomarkers. These oxidative stress-related biomarkers strictly correspond to key signaling molecules in the oxidative stress signaling axis, specifically including reactive oxygen species concentration (as a quantitative indicator of upstream activating signaling molecules), superoxide dismutase activity (reflecting the functional state of antioxidant defense signaling molecules), glutathione peroxidase activity (also belonging to the antioxidant defense signaling molecule category), and lipid peroxidation product content (as a direct manifestation of downstream oxidative damage signaling molecules). During the data extraction stage, by calling the database query interface, the matching records are automatically retrieved based on the user input target sample identifier (such as sample number or experimental group), and the complete raw data set is loaded to ensure the accuracy and traceability of the data source. At the same time, data integrity is verified, such as checking for null values or format errors in key fields to preliminarily exclude invalid records.

[0028] Subsequently, the extracted oxidative stress biomarker raw data is subjected to a preprocessing procedure, which includes data cleaning, outlier removal, and standardization processing. Data cleaning first deals with missing values or obviously erroneous records: for missing measurement values, linear interpolation or regression interpolation based on historical data distribution is used for filling, such as estimating the value of reactive oxygen species concentration for a sample with missing data based on the trend of reactive oxygen species concentration for other samples in the same experimental batch; for obviously erroneous records (such as measurement values exceeding the instrument range or contradicting biological common sense), they are automatically identified and corrected by rule library comparison, such as replacing the superoxide dismutase activity value of negative with the median of this biomarker in historical data. Outlier removal uses statistical analysis methods to calculate the Z-score of each oxidative stress-related biomarker measurement value, and if the absolute value of Z-score exceeds the pre-set threshold (value of 3), it is determined as an outlier and removed to ensure the robustness and representativeness of the data set. Standardization processing aims to eliminate the dimensional differences and inconsistent numerical ranges between different biomarkers, and the Min-Max normalization method is applied to map each oxidative stress-related biomarker measurement value to the [0,1] interval, with the specific formula being ; where is the measurement value of the oxidative stress-related biomarker; and The minimum and maximum values of the oxidative stress-related biomarkers in the historical data set, which is usually derived from long-term monitoring data of healthy neuronal cells or normal animal model tissues to establish a reliable reference benchmark. After preprocessing, the cleaned, outlier-removed, and standardized data is confirmed as oxidative stress biomarker measurement data and converted into a structured format (such as a multidimensional vector or matrix) for storage in a temporary cache or persistent database for direct invocation by subsequent steps such as oxidative stress signal axis activation index calculation. The entire preprocessing process is implemented through automated scripts and verification modules to ensure efficiency, repeatability, and preservation of the biological significance of the data, providing reliable input for subsequent analysis.

[0029] S200, calculating an oxidative stress signal axis activation index based on the oxidative stress biomarker measurement data; wherein the oxidative stress signal axis activation index is used to quantify the overall activation level of the oxidative stress signal axis, and the oxidative stress signal axis activation index is obtained by multiplying the measurement value of each oxidative stress-related biomarker by the corresponding weight coefficient and then summing them up, wherein the weight coefficient is determined based on the relative importance of each oxidative stress-related biomarker in the oxidative stress signal axis.

[0030] The implementation process is as follows: First, based on the types of each oxidative stress-related biomarker in the oxidative stress biomarker measurement data, the corresponding basic weight coefficient is obtained from the preset signal axis hierarchical weight database. The signal axis hierarchical weight database, as a structured knowledge base, stores the basic weight coefficients corresponding to different levels of signal molecules in the oxidative stress signal axis. These signal molecules include upstream activating signal molecules (such as reactive oxygen species), antioxidant defense signal molecules (such as superoxide dismutase, glutathione peroxidase), and downstream oxidative damage signal molecules (such as lipid peroxidation products). The setting of the basic weight coefficient follows the biological principle of the oxidative stress signal axis: the upstream activating signal molecules play a dominant role in triggering the oxidative stress response, so their basic weight coefficient is higher (for example, set to 0.5), while the antioxidant defense signal molecules and downstream oxidative damage signal molecules as response and effect links, the basic weight coefficient is relatively low (for example, set to 0.3 and 0.2 respectively). By querying the signal axis hierarchical weight database, the basic weight coefficient corresponding to each oxidative stress-related biomarker is automatically matched, ensuring the scientificity and consistency of weight allocation.

[0031] Next, the measured values ​​of each oxidative stress-related biomarker in the oxidative stress biomarker measurement data are input into a preset dynamic weight adjustment model to obtain the dynamic adjustment factor corresponding to each oxidative stress-related biomarker. The dynamic weight adjustment model aims to dynamically adjust the weights of biomarkers based on their actual deviations from the measured values, thereby enhancing the adaptability and accuracy of the index calculation. Specifically, the execution of the dynamic weight adjustment model includes the following sub-steps: First, a preset reference range for oxidative stress-related biomarkers is obtained. This reference range includes a lower limit and an upper limit, which are statistically obtained based on historical measurement data of the corresponding oxidative stress-related biomarkers in healthy neurons or normal animal model tissues (for example, the reference range for reactive oxygen species concentration may be [10, 50] μM, and the reference range for superoxide dismutase activity may be [20, 80] U / mg). Subsequently, the deviation between the measured value of each oxidative stress-related biomarker and the corresponding reference range is calculated. The deviation calculation formula is: ;in, Deviation is used to quantify the degree of abnormality of a measured value relative to a health baseline; These are measurements of biomarkers related to oxidative stress. The midpoint of the reference range is calculated using the following formula: ,in and Refer to the lower and upper limits of the value range respectively; The range of reference values ​​is calculated using the following formula: Deviation A larger value indicates a more significant deviation of the measured value from the health baseline. Based on the relative position of the measured values ​​of each oxidative stress-related biomarker to its corresponding reference range, a baseline adjustment coefficient for each oxidative stress-related biomarker is determined. For example, if the measured value exceeds the upper limit of the reference range, the baseline adjustment coefficient is set to 1.2, indicating that the weight of this biomarker needs to be strengthened; if the measured value is within the reference range, the baseline adjustment coefficient is set to 1.0; if the measured value is below the lower limit of the reference range, the baseline adjustment coefficient is set to 0.8, indicating that the weight needs to be weakened. Finally, based on the deviation of the measured values ​​of each oxidative stress-related biomarker from its corresponding reference range, the corresponding baseline adjustment coefficient, and the preset sensitivity coefficient, the dynamic adjustment factor corresponding to each oxidative stress-related biomarker is calculated through a preset composite function relationship. The composite function relationship is designed as follows: ;in, For dynamic adjustment factors; To adjust the baseline value of the coefficient, it is set based on the relative position of the measured value and the reference value range; The sensitivity coefficient is preset, and different values ​​are used for different types of oxidative stress-related biomarkers (e.g., for upstream activating signaling molecules). A value of 0.1 is used to enhance the response; for downstream oxidative damage signaling molecules, (Use 0.05 to smooth out fluctuations). This indicates the degree of deviation. This composite function ensures that as the degree of deviation increases, the dynamic adjustment factor increases accordingly, thereby dynamically amplifying the contribution of abnormal biomarkers. At the same time, it differentiates different types of biomarkers through sensitivity coefficients to match their biological characteristics.

[0032] Then, the baseline weight coefficients for each oxidative stress-related biomarker are multiplied by the corresponding dynamic adjustment factor to obtain the final weight coefficients for each oxidative stress-related biomarker. For example, for reactive oxygen species (upstream activation signaling molecules), if the baseline weight coefficient is 0.5 and the dynamic adjustment factor is 1.15, the final weight coefficient is 0.5 × 1.15 = 0.575. This step achieves dynamic optimization of the weights, making the index calculation more reflective of the current oxidative stress state of the sample. Based on the measured values ​​of each oxidative stress-related biomarker and the corresponding final weight coefficients in the oxidative stress biomarker measurement data, the initial activation index is calculated. The initial activation index is obtained by weighted summation: ;in, This is the initial activation index; For the first Measurement values ​​of oxidative stress-related biomarkers; Indicates the first The final weighting coefficients of oxidative stress-related biomarkers; This indicates the number of biomarkers related to oxidative stress. This initial activation index integrates information on oxidative stress from multiple dimensions, but the numerical range may vary from sample to sample and requires further standardization.

[0033] Finally, the initial activation index is input into a preset activation index normalization model to obtain the normalized oxidative stress signal axis activation index. The activation index normalization model uses the Sigmoid function for nonlinear mapping. ;in, The normalized activation index of the oxidative stress signal axis; This represents the scaling factor, which controls the steepness of the Sigmoid curve (value is 0.1). The offset is set based on the median of the initial activation index in historical data (e.g., 50). Normalization compresses the initial activation index to the [0,1] interval, facilitating cross-sample comparisons and subsequent analysis. The closer the value is to 1, the higher the activation level of the oxidative stress signal axis.

[0034] S300, determine the expression level of a neuron apoptosis key factor based on the oxidative stress signal axis activation index; wherein the expression level of the neuron apoptosis key factor includes the expression amount of at least one protein or gene related to the neuron apoptosis process.

[0035] The specific implementation process is as follows: first, based on the calculated oxidative stress signal axis activation index, the corresponding neuron apoptosis key factor reference expression level is obtained from the pre-set signal axis-key factor mapping database. The signal axis-key factor mapping database serves as a structured knowledge base, storing the mapping relationship between the oxidative stress signal axis activation index and the reference expression level of various neuron apoptosis key factors. These relationships are based on a large amount of historical experimental data statistics. The historical experimental data comes from long-term observation records of in vitro neuron culture models or animal models under different oxidative stress conditions, including the measurement value of the oxidative stress signal axis activation index and the corresponding historical expression amount measurement value of the neuron apoptosis key factor, such as quantitative data obtained by Western blotting, real-time fluorescent quantitative PCR or immunohistochemical technology. The neuron apoptosis key factor includes but is not limited to Bax protein (pro-apoptotic protein), Bcl-2 protein (anti-apoptotic protein), Caspase-3 enzyme activity (apoptosis execution protein) and p53 gene expression level (apoptosis regulation gene), etc., which play a core role in the neuron apoptosis process. The database fits the historical data through machine learning algorithms (such as support vector regression or neural network) to establish a nonlinear mapping function between the oxidative stress signal axis activation index and the expression level of each key factor, ensuring that the reference expression level can accurately reflect the typical expression pattern under different activation levels. For example, when the oxidative stress signal axis activation index is 0.7, the database may return the reference expression level of Bax protein as 1.5 ng / mL and the reference expression level of Caspase-3 enzyme activity as 2.0 U / mg. These reference values serve as the initial reference for subsequent calculations.

[0036] Next, based on the oxidative stress signal axis activation index and the pre-set activation index-expression level correction model, the neuron apoptosis key factor expression level correction value is calculated. The activation index-expression level correction model is used to fine-tune the reference expression level to adapt to the specific oxidative stress state of the current sample. This model is obtained by fitting the nonlinear relationship in the historical data through a polynomial function or a machine learning model (such as random forest or gradient boosting tree), and its core is to capture the dynamic response characteristics between the oxidative stress signal axis activation index and the expression level of the neuron apoptosis key factor. The model input is the oxidative stress signal axis activation index, and the output is the expression level correction value of each key factor, which reflects the expression level change amplitude caused by the deviation of the current activation index from the historical typical value. For example, the model may use a quadratic polynomial function: ; wherein, For the first Corrected values ​​for the expression levels of key factors in neuronal apoptosis; The activation index of the oxidative stress signal axis; , , These are model parameters, obtained through regression analysis of historical data, and can take values ​​such as... , , Different key factors correspond to different parameter sets to reflect their differences in biological response (e.g., Bax protein is highly sensitive to oxidative stress, and its parameters...). (The value may be large, causing the correction value to increase rapidly with the activation index). During model training, the activation index of the oxidative stress signal axis in historical data is used as a feature, and the corresponding key factor expression level measurements are used as labels. Parameters are optimized using least squares or gradient descent to ensure that the prediction error is minimized. In addition, the model also introduces a confidence check mechanism. If the current activation index exceeds the range of historical data, it will automatically switch to extrapolation mode, using linear interpolation or conservative estimation based on biological priors to avoid overcorrection. For machine learning models, support vector machines or neural networks can be used. The training data includes the historical oxidative stress signal axis activation index as input and the corresponding change in expression level as output. The model learns the nonlinear mapping relationship by iteratively optimizing the loss function (such as mean squared error). Inputting the current oxidative stress signal axis activation index into the model automatically calculates the expression level correction value of each neuronal apoptosis key factor. For example, if the oxidative stress signal axis activation index is 0.8, the correction value of Bax protein may be 0.3 ng / mL, and the correction value of Caspase-3 enzyme activity may be 0.4 U / mg, indicating that the baseline expression level needs to be upregulated to reflect the enhanced activation degree.

[0037] Then, based on the baseline expression levels of key neuronal apoptosis factors and their correction values, the final expression levels of these factors were calculated. The final expression levels were obtained by adding the baseline expression levels to the correction values. ;in, For the first The final expression levels of key factors for neuronal apoptosis; For the first Benchmark expression levels of key factors for neuronal apoptosis; For the first The expression level of each neuron apoptosis key factor is corrected by adding the individualized adjustment value. This addition operation ensures that the final expression level not only contains the historical typical value but also incorporates the current oxidative stress state, thus more accurately reflecting the actual biological state of the sample. For example, if the baseline expression level of Bax protein is 1.5 ng / mL and the correction value is 0.3 ng / mL, the final expression level is 1.8 ng / mL. After calculation, the final expression level of the neuron apoptosis key factor is confirmed as the neuron apoptosis key factor expression level, which is converted into a structured data format (such as a vector or a JSON object) and stored in a temporary cache or a database for direct calling by subsequent neuron apoptosis risk assessment steps.

[0038] S400, calculating a neuron apoptosis risk assessment value based on the expression levels of the neuron apoptosis key factors; wherein the neuron apoptosis risk assessment value is a comprehensive value obtained by weighting the expression levels of each neuron apoptosis key factor with the corresponding risk coefficient, and the neuron apoptosis risk assessment value is used to reflect the potential risk level of neuron apoptosis.

[0039] The specific implementation process is as follows: First, based on the type of each neuron apoptosis key factor in the neuron apoptosis key factor expression level, the corresponding basic risk coefficient is obtained from the pre-set risk coefficient database. The risk coefficient database, as a structured knowledge base, stores the basic risk coefficients corresponding to different neuron apoptosis key factors. These coefficients are determined based on the correlation between each neuron apoptosis key factor and neuron apoptosis risk in historical data. The historical data comes from long-term observation records of in vitro neuron culture models or animal models under different oxidative stress conditions, including neuron apoptosis key factor expression levels (such as Bax protein, Bcl-2 protein, Caspase-3 enzyme activity, and p53 gene expression level) and corresponding neuron apoptosis incidence statistics (such as the percentage of apoptotic cells obtained by cell apoptosis detection kit or histological analysis). The setting of the basic risk coefficient follows the biological principle: for pro-apoptotic factors (such as Bax protein and Caspase-3 enzyme activity), the basic risk coefficient is higher (for example, the basic risk coefficient of Bax protein is set to 0.4, and the basic risk coefficient of Caspase-3 enzyme activity is set to 0.5) to reflect its direct pro-apoptotic effect; for anti-apoptotic factors (such as Bcl-2 protein), the basic risk coefficient is set to a negative value (for example, -0.3) to reflect its protective effect; for regulatory factors (such as p53 gene expression level), the basic risk coefficient is set to a moderate positive value (for example, 0.2) to capture its indirect influence. By querying the risk coefficient database, the basic risk coefficient corresponding to each neuron apoptosis key factor is automatically matched, ensuring the scientificity and consistency of risk assessment.

[0040] Next, the expression levels of each key neuronal apoptosis factor are input into a pre-defined risk adjustment model to obtain the risk adjustment factor corresponding to each key neuronal apoptosis factor. The risk adjustment model dynamically adjusts the baseline risk coefficient based on the deviation of the expression levels of key neuronal apoptosis factors. This model is trained using machine learning algorithms or statistical regression methods, and its core is to capture the non-linear relationship between expression levels and risk contribution. The model training data comes from historical datasets, where the input feature is the expression level of key neuronal apoptosis factors, and the output label is the baseline value of the risk adjustment factor calculated through logistic regression or covariance analysis. The specific execution process of the risk adjustment model includes: First, obtaining the healthy reference range for each key neuronal apoptosis factor, which is statistically obtained based on historical expression data of healthy neurons or normal animal model tissues (e.g., the reference range for Bax protein expression level is [0.5, 2.0] ng / mL, and the reference range for Caspase-3 enzyme activity is [1.0, 3.0] U / mg). Then, calculating the deviation of the expression level of each key neuronal apoptosis factor from its reference range, the deviation calculation formula is: ;in, For the first Deviation of key factors in neuronal apoptosis; For the first Expression levels of key factors for neuronal apoptosis; , indicating the first The median of the reference range for key factors of neuronal apoptosis. and These are the lower and upper limits of the reference range, respectively. Indicates the span of the reference range. Deviation. A higher value indicates a more significant deviation of the expression level from the healthy baseline. Based on the degree of deviation, the risk-adjusted model calculates the risk adjustment factor using a composite function: ;in, For the first Risk modulators of key neuronal apoptosis factors; For the first Risk sensitivity coefficients of key neuronal apoptosis factors; For the first Deviation in expression levels of key factors for neuronal apoptosis; This represents the nonlinear amplification index (with a value of 2). This composite function ensures that as the deviation from the expression level increases, the risk adjustment factor increases accordingly, thereby dynamically adjusting the risk coefficient to reflect the degree of abnormality in the current expression state. For example, if the expression level of Bax protein is 2.5 ng / mL, its reference range median is 1.25 ng / mL, and the range is 1.5 ng / mL, then the deviation... ,like Then the risk adjustment factor .

[0041] Then, the baseline risk coefficient for each key neuronal apoptosis factor is multiplied by its corresponding risk adjustment factor to obtain the final risk coefficient for each key neuronal apoptosis factor. The final risk coefficient reflects the contribution of each key neuronal apoptosis factor to the risk of neuronal apoptosis at its current expression level. The calculation formula is as follows: ;in, For the first The final risk coefficient of key factors for neuronal apoptosis; For the first The baseline risk coefficients for key neuronal apoptosis factors. For example, for Bax protein, if the baseline risk coefficient is 0.4 and the risk adjustment factor is 1.139, then the final risk coefficient is... This step enables dynamic optimization of the risk coefficient, making the risk assessment more adaptable to the expression characteristics of the current sample. Based on the expression levels of each key neuronal apoptosis factor and its corresponding final risk coefficient, an initial risk assessment value is calculated. The initial risk assessment value is obtained through weighted summation: ;in, This is the initial risk assessment value; For the first The final expression levels of key factors for neuronal apoptosis; For the first The final risk coefficient of key factors for neuronal apoptosis; This indicates the number of key factors contributing to neuronal apoptosis. This initial risk assessment value integrates the risk contributions of multiple key factors, but the numerical range may vary from sample to sample and requires further standardization for interpretation and comparison.

[0042] Finally, the initial risk assessment value is input into a pre-defined risk assessment value normalization model to obtain the normalized neuronal apoptosis risk assessment value. The risk assessment value normalization model uses a Logistic function for nonlinear mapping: ;in, This represents the normalized neuronal apoptosis risk assessment value. This represents the scaling factor, which controls the steepness of the function curve (usually set to 0.1, optimized based on historical data). represents the offset, which is set based on the median value of the initial risk assessment values in historical data (for example, take the value 5.0). The normalization process compresses the initial risk assessment values to the interval [0, 1], and the value closer to 1 indicates a higher risk of neuron apoptosis, and the value closer to 0 indicates a lower risk. The normalized neuron apoptosis risk assessment value is output in a structured format (such as a scalar value or a percentage), and is stored in a database or cache for subsequent steps such as visualization report generation. The dynamic adjustment and normalization mechanism enhances the accuracy and comparability of risk assessment, providing a reliable basis for neuron health status assessment.

[0043] S500, output the neuron apoptosis risk assessment value; wherein the neuron apoptosis risk assessment value is presented in the form of a visual chart or a digital report for non-diagnostic purposes of neuron health status assessment.

[0044] The implementation process is as follows: first, the neuron apoptosis risk assessment value is post-processed and format-converted. The neuron apoptosis risk assessment value is stored in a temporary cache or structured database after calculation, and its value is a normalized scalar value (range [0, 1]). The result formatting module is called to standardize the neuron apoptosis risk assessment value: if the neuron apoptosis risk assessment value is less than 0.3, it is automatically classified as "low risk" level; if it is between 0.3 and 0.7, it is classified as "medium risk" level; if it is higher than 0.7, it is classified as "high risk" level. The classification rule is determined based on the correlation analysis of the neuron apoptosis incidence rate and the risk assessment value in historical data, for example, by fitting historical sample data with a logistic regression model, and setting a threshold to optimize the classification accuracy. At the same time, a unique identifier (such as sample ID, timestamp) is generated for each risk assessment value, and is associated with the original data (such as oxidative stress signal axis activation index, neuron apoptosis key factor expression level) to ensure the traceability of the results. The formatted data is converted to a structured format such as JSON or XML, which is convenient for subsequent visualization engine or report generation module to call.

[0045] Next, the visualization chart generation process is executed. Based on the formatted neuron apoptosis risk assessment value and its classification level, the visualization chart generation module automatically creates various graphical display forms, including radar chart, column chart, heat map and trend curve chart. Specifically, the radar chart is used to multi-dimensionally display the correlation between the oxidative stress signal axis activation index, the neuron apoptosis key factor expression level and the neuron apoptosis risk assessment value: each axis of the radar chart represents a key indicator (such as reactive oxygen species concentration, Bax protein expression level, Caspase-3 enzyme activity, etc.), and the scale on the axis corresponds to the standardized value. The neuron apoptosis risk assessment value is displayed as the overall area size, and the larger the area, the higher the risk. The column chart is used to compare the risk assessment values of different samples or time points. The horizontal axis is the sample identification or time sequence, and the vertical axis is the neuron apoptosis risk assessment value. The column color is dynamically adjusted according to the risk level (low risk is green, medium risk is yellow, and high risk is red). The heat map is suitable for batch sample analysis. The row represents the sample, and the list represents the evaluation index (such as oxidative stress biomarker, key factor expression level). The cell color reflects the value size, and the neuron apoptosis risk assessment value is superimposed as a row label to quickly identify high-risk samples. The trend curve chart is used for dynamic monitoring. The horizontal axis is the time point, and the vertical axis is the neuron apoptosis risk assessment value. The data points are connected to form a curve, and key events (such as drug treatment time points) are marked to visually display the risk change trend. During the chart generation process, the visualization library (such as Matplotlib, D3.js or ECharts) is called to render the graph, and legends, coordinate axis labels and risk level annotations are automatically added. For example, if the neuron apoptosis risk assessment value is 0.85, a "high risk" red warning label is displayed at the top of the chart, and the contributing factors (such as excessive Bax protein expression level and Caspase-3 enzyme activity surge) are listed in detail in the legend. The chart output is in high-resolution PNG or SVG format, supports interactive operation (such as mouse hover to display detailed values), and is embedded into the user interface or exported as a standalone file.

[0046] Meanwhile, a digital report generation process is performed in parallel, specifically a structured report. The structured report includes header information, an evaluation summary, a detailed data table, and risk interpretation suggestions. The header information includes sample identification, experimental batch, evaluation date, and report version. The evaluation summary lists core indicators in table form: oxidative stress signal axis activation index (e.g., 0.72), expression levels of key factors of neuronal apoptosis (e.g., Bax protein: 1.8 ng / mL, Caspase-3 enzyme activity: 2.4 U / mg), and neuronal apoptosis risk assessment values (e.g., 0.85), with risk level classification (e.g., "high risk"). The detailed data table expands all intermediate calculation data, such as oxidative stress biomarker measurement values (reactive oxygen species concentration: 55 μM, superoxide dismutase activity: 25 U / mg), weight coefficients (e.g., the maximum weight coefficient of reactive oxygen species: 0.575), and risk coefficients (e.g., the final risk coefficient of Bax protein: 0.456), ensuring process transparency and verifiability. The risk interpretation suggestions section generates non-diagnostic description text based on a pre-set knowledge base, such as: "The current sample has a high degree of oxidative stress signal axis activation, with significant increases in the expression levels of key factors of neuronal apoptosis Bax and Caspase-3, indicating that the neuronal health status may be affected by oxidative stress, and further monitoring or adjustment of experimental conditions is recommended." The report language strictly avoids diagnostic terms (such as "disease" and "pathology") and is limited to research use instructions. The report output is in PDF or HTML format, automatically distributed to designated users via email or file server, with data integrity verification codes (such as MD5 hash values) to prevent tampering.

[0047] The entire output process is implemented through an automated pipeline, with an average time of less than 5 seconds from data reception to chart report generation, supporting high concurrency requests. The visual charts and digital reports are ultimately delivered to users through a web interface, mobile application, or API interface, providing multi-platform compatibility and real-time update functions, thereby providing an efficient and reliable support tool for neuronal health status evaluation.

[0048] The embodiment also discloses a neuronal apoptosis risk assessment system based on an oxidative stress signal axis, comprising the following modules: An oxidative stress biomarker measurement data acquisition module configured to acquire oxidative stress biomarker measurement data; An oxidative stress signal axis activation index calculation module connected to the oxidative stress biomarker measurement data acquisition module and configured to calculate an oxidative stress signal axis activation index based on the oxidative stress biomarker measurement data; A neuronal apoptosis key factor expression level determination module connected to the oxidative stress signal axis activation index calculation module and configured to determine neuronal apoptosis key factor expression levels based on the oxidative stress signal axis activation index; The neuron apoptosis risk assessment value calculation module is connected with the neuron apoptosis key factor expression level determination module, and is configured to calculate a neuron apoptosis risk assessment value based on the neuron apoptosis key factor expression level; The neuron apoptosis risk assessment value output module is connected with the neuron apoptosis risk assessment value calculation module, and is configured to output the neuron apoptosis risk assessment value.

[0049] The specific embodiment is merely an explanation of the present application, which is not a limitation of the present application. Those skilled in the art can make modifications to the embodiment without creative contribution after reading the specification, as long as the modifications are within the scope of the claims of the present application.

Claims

1. A neuronal apoptosis risk assessment system based on oxidative stress signaling axis, characterized by, The method comprises the following steps: S100, acquiring oxidative stress biomarker measurement data; wherein the oxidative stress biomarker measurement data comprises measurement values of at least one oxidative stress-related biomarker corresponding to a signal molecule in the oxidative stress signal axis; S200, calculating an oxidative stress signal axis activation index based on the oxidative stress biomarker measurement data; wherein the oxidative stress signal axis activation index is used to quantify the overall activation degree of the oxidative stress signal axis, and the oxidative stress signal axis activation index is obtained by multiplying the measurement values of each oxidative stress-related biomarker by the corresponding weight coefficient and then summing them up, wherein the weight coefficient is determined based on the relative importance of each oxidative stress-related biomarker in the oxidative stress signal axis; S300, determining the expression level of a neuron apoptosis key factor based on the oxidative stress signal axis activation index; wherein the expression level of the neuron apoptosis key factor comprises the expression amount of at least one protein or gene related to the neuron apoptosis process; S400, calculating a neuron apoptosis risk assessment value based on the expression level of the neuron apoptosis key factor; wherein the neuron apoptosis risk assessment value is a comprehensive value obtained by weighting calculation of the expression level of each neuron apoptosis key factor and the corresponding risk coefficient, and the neuron apoptosis risk assessment value is used to reflect the potential risk grade of neuron apoptosis; S500, outputting the neuron apoptosis risk assessment value; wherein the neuron apoptosis risk assessment value is presented in the form of a visual chart or a digital report, and is used for non-diagnostic purpose of neuron health status evaluation.

2. The oxidative stress signaling axis-based neuronal apoptosis risk assessment system according to claim 1, wherein: In the S100, specifically comprising steps of: extracting oxidative stress biomarker raw data corresponding to the target sample from a biological sample database; wherein the biological sample database stores multiple groups of oxidative stress biomarker raw data as samples, the target sample is a neuron cell cultured in vitro or an animal model tissue sample, the oxidative stress biomarker raw data comprises measurement values of oxidative stress-related biomarkers corresponding to signal molecules in the oxidative stress signal axis, the oxidative stress-related biomarkers include but are not limited to reactive oxygen species concentration, superoxide dismutase activity, glutathione peroxidase activity and lipid peroxidation product content, wherein reactive oxygen species correspond to upstream activation signal molecules of the oxidative stress signal axis, superoxide dismutase and glutathione peroxidase correspond to antioxidant defense signal molecules, and lipid peroxidation products correspond to downstream oxidative damage signal molecules; preprocessing the oxidative stress biomarker raw data; wherein the preprocessing includes data cleaning, outlier rejection and standardization processing; confirming the preprocessed oxidative stress biomarker raw data as the oxidative stress biomarker measurement data.

3. The oxidative stress signaling axis-based neuronal apoptosis risk assessment system according to claim 1, wherein: The S200 specifically comprises steps of: acquire a corresponding basic weight coefficient from a preset signal axis hierarchical weight database based on the type of each oxidative stress-related biomarker in the oxidative stress biomarker measurement data; wherein the signal axis hierarchical weight database stores basic weight coefficients corresponding to different hierarchical signal molecules in the oxidative stress signal axis, and the signal molecules include upstream activating signal molecules, antioxidant defense signal molecules, and downstream oxidative damage signal molecules; the basic weight coefficient corresponding to the upstream activating signal molecules is higher than the basic weight coefficients corresponding to the antioxidant defense signal molecules and the downstream oxidative damage signal molecules; input the measurement values of each oxidative stress-related biomarker in the oxidative stress biomarker measurement data into a preset dynamic weight adjustment model respectively to obtain a dynamic adjustment factor corresponding to each oxidative stress-related biomarker; multiply the basic weight coefficient corresponding to each oxidative stress-related biomarker and the corresponding dynamic adjustment factor to obtain a final weight coefficient of each oxidative stress-related biomarker; calculate an initial activation index based on the measurement values of each oxidative stress-related biomarker in the oxidative stress biomarker measurement data and the corresponding final weight coefficient; wherein the initial activation index is obtained by multiplying the measurement values of each oxidative stress-related biomarker and the corresponding final weight coefficient and then summing them up; input the initial activation index into a preset activation index normalization model to obtain a normalized oxidative stress signal axis activation index.

4. The oxidative stress signaling axis-based neuronal apoptosis risk assessment system according to claim 3, wherein: In S200, the measurement values of each oxidative stress-related biomarker in the oxidative stress biomarker measurement data are input into a preset dynamic weight adjustment model respectively to obtain a dynamic adjustment factor corresponding to each oxidative stress-related biomarker, which specifically includes the following steps: acquire a reference value range of the oxidative stress-related biomarker; wherein the reference value range includes a lower limit of the reference value and an upper limit of the reference value, and the reference value range is obtained based on historical measurement data of the corresponding oxidative stress-related biomarker in healthy neuron cells or normal animal model tissues; calculate the deviation degree of the measurement value of each oxidative stress-related biomarker from the corresponding reference value range respectively; determine an adjustment coefficient benchmark value of each oxidative stress-related biomarker based on the relative positional relationship between the measurement value of each oxidative stress-related biomarker and the corresponding reference value range; acquire a corresponding dynamic adjustment factor of each oxidative stress-related biomarker by a preset composite function relationship based on the deviation degree of the measurement value of each oxidative stress-related biomarker from the corresponding reference value range, the corresponding adjustment coefficient benchmark value, and a preset sensitivity coefficient; wherein the composite function relationship ensures that the dynamic adjustment factor increases accordingly when the deviation degree increases, and different sensitivity coefficients are used for different types of oxidative stress-related biomarkers.

5. The oxidative stress signaling axis-based neuronal apoptosis risk assessment system according to claim 1, wherein: S300 specifically includes the following steps: obtaining a corresponding neuron apoptosis key factor benchmark expression level from a preset signal axis-key factor mapping database based on the oxidative stress signal axis activation index, wherein the signal axis-key factor mapping database stores a corresponding relationship between oxidative stress signal axis activation indexes and neuron apoptosis key factor benchmark expression levels, the neuron apoptosis key factor benchmark expression level is obtained based on historical experimental data, and the historical experimental data includes oxidative stress signal axis activation indexes and corresponding historical expression measurement values of neuron apoptosis key factors of an in-vitro neuron culture model or an animal model under different oxidative stress conditions; the neuron apoptosis key factor includes at least one protein or gene related to a neuron apoptosis process; calculating a neuron apoptosis key factor expression level based on the oxidative stress signal axis activation index and the neuron apoptosis key factor benchmark expression level.

6. The oxidative stress signaling axis-based neuronal apoptosis risk assessment system according to claim 5, wherein: In the S300, the neuron apoptosis key factor expression level is calculated based on the oxidative stress signal axis activation index and the neuron apoptosis key factor benchmark expression level, and specifically includes the following steps: calculating a neuron apoptosis key factor expression level correction value based on the oxidative stress signal axis activation index and a preset activation index-expression level correction model, wherein the activation index-expression level correction model is used to adjust the neuron apoptosis key factor benchmark expression level according to changes in the oxidative stress signal axis activation index, the activation index-expression level correction model represents a nonlinear relationship between the oxidative stress signal axis activation index and the neuron apoptosis key factor expression level, and the nonlinear relationship is obtained by fitting historical data through a polynomial function or a machine learning model; calculating a final neuron apoptosis key factor expression level based on the neuron apoptosis key factor benchmark expression level and the neuron apoptosis key factor expression level correction value, wherein the final neuron apoptosis key factor expression level is obtained by adding the neuron apoptosis key factor benchmark expression level and the neuron apoptosis key factor expression level correction value, and the final neuron apoptosis key factor expression level includes expression amounts of at least one protein or gene related to a neuron apoptosis process; confirming the final neuron apoptosis key factor expression level as the neuron apoptosis key factor expression level.

7. The oxidative stress signaling axis-based neuronal apoptosis risk assessment system according to claim 1, wherein: The S400 specifically includes the following steps: obtaining a basic risk coefficient and a risk adjustment factor of each neuron apoptosis key factor based on the neuron apoptosis key factor expression level; multiplying the basic risk coefficient and the risk adjustment factor of each neuron apoptosis key factor to obtain a final risk coefficient of each neuron apoptosis key factor, wherein the final risk coefficient is used to reflect a contribution degree of each neuron apoptosis key factor to a neuron apoptosis risk under a current expression level; calculating an initial risk assessment value based on the expression level of each of the neuron apoptosis key factors in the neuron apoptosis key factor expression level and the corresponding final risk coefficient; wherein the initial risk assessment value is obtained by multiplying the expression level of each of the neuron apoptosis key factors by the corresponding final risk coefficient and summing the results; inputting the initial risk assessment value into a preset risk assessment value normalization model to obtain the normalized neuron apoptosis risk assessment value.

8. The oxidative stress signaling axis-based neuronal apoptosis risk assessment system according to claim 7, wherein: In the S400, based on the neuron apoptosis key factor expression level, the base risk coefficient and the risk adjustment factor of each neuron apoptosis key factor are obtained, specifically including the steps of: based on the type of each of the neuron apoptosis key factors in the neuron apoptosis key factor expression level, obtaining the corresponding base risk coefficient from a preset risk coefficient database; wherein the risk coefficient database stores base risk coefficients corresponding to different neuron apoptosis key factors, the base risk coefficients are determined based on the correlation between each of the neuron apoptosis key factors and the neuron apoptosis risk in historical data, and the historical data includes the neuron apoptosis key factor expression level and the corresponding neuron apoptosis incidence statistical value of an in vitro neuron culture model or an animal model under different oxidative stress conditions; inputting the expression level of each of the neuron apoptosis key factors in the neuron apoptosis key factor expression level into a preset risk adjustment model to obtain the corresponding risk adjustment factor of each of the neuron apoptosis key factors; wherein the risk adjustment model is used to dynamically adjust the base risk coefficient according to the deviation degree of the neuron apoptosis key factor expression level, and the risk adjustment model is trained based on a machine learning algorithm or a statistical regression method.

9. The oxidative stress signaling axis-based neuronal apoptosis risk assessment system according to claim 8, wherein: comprising the following modules: an oxidative stress biomarker measurement data acquisition module configured to acquire oxidative stress biomarker measurement data; an oxidative stress signaling axis activation index calculation module connected to the oxidative stress biomarker measurement data acquisition module and configured to calculate an oxidative stress signaling axis activation index based on the oxidative stress biomarker measurement data; a neuron apoptosis key factor expression level determination module connected to the oxidative stress signaling axis activation index calculation module and configured to determine a neuron apoptosis key factor expression level based on the oxidative stress signaling axis activation index; a neuron apoptosis risk assessment value calculation module connected to the neuron apoptosis key factor expression level determination module and configured to calculate a neuron apoptosis risk assessment value based on the neuron apoptosis key factor expression level; a neuron apoptosis risk assessment value output module connected to the neuron apoptosis risk assessment value calculation module and configured to output the neuron apoptosis risk assessment value.

Images