GWAS-based social isolation and neuroplasm analysis system

Abstract

The present invention relates to the field of computational biology, and discloses a GWAS-based social isolation and neuroplasm analysis system, which comprises: a data collection and processing module, which comprises a database interface for extracting single nucleotide polymorphism from a whole genome association research database and a data processing unit; the tool variable selection module comprises an SNP (Single Nucleotide Polymorphism) screening algorithm; the causal analysis module comprises a calculation unit used for executing double-sample Mendel randomization analysis; the heterogeneity and multi-effect test module comprises a heterogeneity detection unit and a multi-effect detection unit; and the result display and interpretation module comprises a visual interface and a report generator. According to the method, the correlation in the GWAS data can be effectively converted into causal inference by integrating a double-sample Mendel randomization (TSMR) method, and the system can identify the potential causal relationship between social isolation and neuroplasm by selecting SNP sites meeting strict tool variable standards and combining multiple robustness analysis methods such as inverse variance weighting (IVW).

Description

Technical Field

[0001] The present invention relates to the field of computational biology, and in particular to a social isolation and neuroticism analysis system based on GWAS. Background Art

[0002] Genome-wide association study (GWAS) is one of the most widely used techniques in genetic research. It aims to identify genetic variants associated with specific phenotypes by analyzing the association of millions of single nucleotide polymorphisms (SNPs). GWAS has been widely used to study the genetic basis of many diseases and psychological traits, such as neuroticism, depression, anxiety, etc. However, existing GWAS studies still have some technical bottlenecks and shortcomings when exploring the causal relationship between complex behaviors and psychological traits (such as social isolation and neuroticism) and their genetic basis.

[0003] Existing GWAS studies mainly use association analysis to identify the relationship between specific SNP sites and a certain phenotype, but these associations cannot directly prove the causal relationship between the two. The correlation may be affected by confounding factors or multiple genetic effects, and cannot accurately explain the causal chain between complex social behaviors such as social isolation and psychological traits (such as neuroticism). This makes it difficult to use existing GWAS studies to design targeted interventions or predict individual mental health risks. Summary of the invention

[0004] In order to make up for the above shortcomings, the present invention provides a social isolation and neuroticism analysis system based on GWAS, aiming to improve the problem that existing GWAS studies mainly identify the relationship between specific SNP sites and a certain phenotype through association analysis, but these associations cannot directly prove the causal relationship between the two.

[0005] In a first aspect, the present invention provides the following technical solution, a social isolation and neuroticism analysis system based on GWAS, comprising:

[0006] A data collection and processing module, including a database interface and a data processing unit for extracting single nucleotide polymorphisms from a genome-wide association study database, wherein the data processing unit cleans, fills in missing values, and converts the extracted data using a standardized algorithm to generate a genetic data set suitable for subsequent analysis;

[0007] An instrumental variable selection module, including a SNP screening algorithm, wherein the screening algorithm is based on filtering SNP loci significantly associated with social isolation, social interaction, and neuroticism, and uses a preset p-value threshold and linkage disequilibrium elimination criteria to select instrumental variables that meet the requirements of Mendelian randomization analysis from the cleaned data set;

[0008] A causal analysis module, including a computing unit for performing a two-sample Mendelian randomization analysis, wherein the computing unit calculates the causal relationship between social isolation, social interaction and neuroticism by an inverse variance weighted method, and integrates weighted median, weighted mode and MREgger methods for robustness testing;

[0009] The heterogeneity and pleiotropy test module includes a heterogeneity test unit and a pleiotropy test unit. The heterogeneity test unit identifies differences in different dimensions of social isolation through Cochran's Q test, and the pleiotropy test unit detects potential pleiotropy of instrumental variables through MREgger regression and global pleiotropy test methods.

[0010] The result display and interpretation module includes a visualization interface and a report generator. The visualization interface is used to display the causal relationship between social isolation and neuroticism in the form of a chart. The report generator automatically generates a personalized neuroticism risk prediction report based on the analysis results.

[0011] Preferably, the data collection and processing module also includes a multi-source data integration unit, which is used to extract SNP data from different whole-genome association study databases and perform data integration and normalization processing on data from different sources through a consistency verification algorithm.

[0012] Preferably, the instrumental variable selection module also includes a machine learning model for optimizing the SNP selection process, wherein the machine learning model automatically adjusts the p-value threshold and LD elimination criteria through historical data in the training set.

[0013] Preferably, the causal analysis module further comprises a dynamic adjustment unit, which automatically adjusts the SNP selection parameters and the weight coefficient of the TSMR model according to the preliminary analysis results to optimize the accuracy of causal inference.

[0014] Preferably, the heterogeneity and pleiotropy testing module also includes an automated alarm unit, which monitors the heterogeneity and pleiotropy indicators of the instrumental variables, automatically generates an alarm when significant heterogeneity or pleiotropy is identified, and prompts the user to perform manual intervention or adjust analysis parameters.

[0015] Preferably, the result display and interpretation module further comprises an interactive visualization interface, which allows the user to select a specific social isolation dimension and dynamically updates a chart to display the causal relationship between different dimensions and neuroticism.

[0016] Preferably, the report generator includes a natural language generation engine, which automatically generates a detailed report including neuroticism risk prediction, significant SNP site interpretation and individualized suggestions based on the analysis results.

[0017] In a second aspect, the present invention provides the following technical solution, a social isolation and neuroticism analysis method based on GWAS, comprising the following steps:

[0018] S1: Data Collection and Processing

[0019] Single nucleotide polymorphism data associated with social isolation, social interaction, and neuroticism were extracted from the Genome-Wide Association Study database;

[0020] Use the data processing module to clean the extracted data, including missing value filling, abnormal data removal and data format standardization;

[0021] S2: Instrumental variable selection

[0022] The cleaned data were screened using a screening algorithm to select candidate instrumental variables based on SNP loci significantly associated with social isolation and neuroticism. The screening criteria included setting a p-value threshold and using a linkage disequilibrium elimination strategy to exclude SNPs significantly associated with other characteristics.

[0023] After the screening is completed, a set of instrumental variables that meet the requirements of Mendelian randomization is generated;

[0024] S3: Causal Analysis

[0025] The inverse variance weighting method was used to conduct causal inference analysis on instrumental variables to explore the causal relationship between social isolation, social interaction and neuroticism.

[0026] At the same time, the results of IVW analysis were robustly tested by weighted median, weighted mode and MREgger methods;

[0027] S4: Heterogeneity and Pleiotropy Tests

[0028] Using the heterogeneity test tool, the Cochran's Q test was used to identify the differences in the effects of different types of social isolation on the risk of neuroticism and to assess the heterogeneity between different dimensions;

[0029] The MREgger regression method and global pleiotropy test were used to detect the potential pleiotropy of instrumental variables, so that the selected SNPs instrumental variables would not affect the results of causal analysis through other pathways;

[0030] S5: Results presentation and interpretation

[0031] In the result display module, a visualization chart of the causal relationship between social isolation, social interaction and neuroticism is generated, showing the causal association, odds ratio and confidence interval of each dimension;

[0032] Based on the analysis results, an individualized neuroticism risk prediction report is automatically generated, which explains the significant SNP sites and mental health risks in detail and provides corresponding suggestions.

[0033] In a third aspect, the invention provides the following technical solution: a computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the above-mentioned GWAS-based social isolation and neuroticism analysis method when executing the computer program.

[0034] In a fourth aspect, the present invention provides the following technical solution: a readable storage medium having a computer program stored thereon, and the computer program, when executed by a processor, implements the above-mentioned GWAS-based social isolation and neuroticism analysis method.

[0035] The present invention has the following beneficial effects:

[0036] 1. By integrating the two-sample Mendelian randomization (TSMR) method, the present invention can effectively transform the correlation in GWAS data into causal inference and eliminate the influence of confounding factors. By selecting SNP sites that meet strict instrumental variable standards and combining multiple robustness analysis methods such as inverse variance weighting (IVW), the system can identify the potential causal relationship between social isolation and neuroticism, which not only helps to better understand the genetic mechanism behind it, but also provides a clear direction for formulating intervention measures.

[0037] 2. This invention uses advanced SNP screening algorithms and machine learning techniques to not only consider the significant associations with social isolation and neuroticism when selecting instrumental variables, but also combines linkage disequilibrium (LD) elimination strategies to automatically exclude SNPs with strong pleiotropic effects. The MREgger method further corrects possible pleiotropic effects to ensure the accuracy and robustness of causal inference results.

[0038] 3. The present invention provides the ability to perform hierarchical analysis on different dimensions of social isolation (such as loneliness, social frequency, etc.). The system can detect the differential impact of different dimensions on neuroticism risk through heterogeneity test tools (such as Cochran's Q test). This multi-dimensional analysis capability can reveal more subtle causal mechanisms behind complex behaviors and provide guidance for future precision interventions. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is the architecture diagram of the social isolation and neuroticism analysis system based on GWAS proposed in the present invention;

[0040] Figure 2 This is a flow chart of the social isolation and neuroticism analysis method based on GWAS proposed in the present invention. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] Embodiment 1

[0043] Reference Figure 1 In a first embodiment of the present invention, the present invention provides a social isolation and neuroticism analysis system based on GWAS, comprising:

[0044] A data collection and processing module, including a database interface and a data processing unit for extracting single nucleotide polymorphisms from a genome-wide association study database. The data processing unit cleans, fills in missing values, and converts the extracted data using standardized algorithms to generate a genetic data set suitable for subsequent analysis;

[0045] The instrumental variable selection module includes a SNP screening algorithm, which filters SNP loci that are significantly associated with social isolation, social interaction, and neuroticism, and selects instrumental variables that meet the requirements of Mendelian randomization analysis from the cleaned data set using a preset p-value threshold and linkage disequilibrium elimination criteria;

[0046] Causal analysis module, including a computing unit for performing two-sample Mendelian randomization analysis, which calculates the causal relationship between social isolation, social interaction and neuroticism through the inverse variance weighting method, and integrates weighted median, weighted mode and MREgger methods for robustness testing;

[0047] Heterogeneity and pleiotropy testing module, including heterogeneity test unit and pleiotropy test unit. The heterogeneity test unit identifies the differences in different dimensions of social isolation through Cochran's Q test, and the pleiotropy test unit detects the potential pleiotropy of instrumental variables through MREgger regression and global pleiotropy test methods.

[0048] The result display and interpretation module includes a visualization interface and a report generator. The visualization interface is used to display the causal relationship between social isolation and neuroticism in the form of a chart. The report generator automatically generates a personalized neuroticism risk prediction report based on the analysis results.

[0049] Specifically, the data collection and processing module extracts genetic data related to social isolation, social interaction, and neuroticism from multiple GWAS databases through a database interface. This module includes data preprocessing functions, and the processing steps include data cleaning, standardized transformation (such as missing value filling, outlier removal), etc., to ensure the high quality and consistency of the data, which is suitable for subsequent causal analysis.

[0050] Instrumental variable selection module: used to select SNPs suitable as instrumental variables for causal analysis. The system screens out SNPs that are significantly associated with the target variable (social isolation, social interaction) through preset statistical thresholds (such as p-values) and linkage disequilibrium (LD) elimination criteria. This ensures that the selected instrumental variables will not affect the results of causal analysis through other channels.

[0051] Causal analysis module: The system uses the two-sample Mendelian randomization (TSMR) method for causal inference. The core method is inverse variance weighting (IVW), supplemented by weighted median and weighted mode methods for result verification. The MREgger method is used to detect and correct possible pleiotropic problems.

[0052] Heterogeneity and pleiotropy testing module: This module can ensure that the differences in the impact of different social isolation dimensions on neuroticism are not ignored through heterogeneity and pleiotropy detection tools, and at the same time detect the pleiotropy of SNPs to prevent the selected instrumental variables from having non-causal effects on the analysis results.

[0053] Result display and interpretation module: The causal association analysis results of social isolation, social interaction and neuroticism are displayed through a visual interface, and a specific genetic analysis report is provided to individuals through a report generation function to explain the potential impact of their genes on social isolation and neuroticism.

[0054] The data collection and processing module also includes a multi-source data integration unit, which is used to extract SNP data from different whole-genome association study databases and integrate and normalize data from different sources through a consistency verification algorithm.

[0055] Specifically, in order to ensure the diversity and robustness of the analysis results, this module integrates SNP data from different GWAS databases. Through the consistency verification algorithm, data from different sources are processed and standardized to reduce data bias and avoid problems caused by heterogeneity. This module specifically implements batch extraction of relevant data from multiple data sources, and cleans and merges these data to ensure the uniformity of the analysis data.

[0056] The system batch extracts SNP data related to social isolation, social interaction and neuroticism from multiple GWAS databases (such as UKBiobank, 23andMe, etc.).

[0057] These data are calibrated through algorithms to ensure standardized processing of data from different sources and the uniformity of data fields, so as to eliminate heterogeneous interference between different data sets.

[0058] The instrumental variable selection module also includes a machine learning model for optimizing the SNP selection process. The machine learning model automatically adjusts the p-value threshold and LD elimination criteria using historical data in the training set.

[0059] Specifically, this module introduces machine learning technology to dynamically adjust the p-value threshold and LD elimination criteria used in the SNP selection process by training historical data sets to improve the accuracy and effectiveness of instrumental variable selection. The system will screen SNPs based on given thresholds and criteria in the initial analysis, but then automatically adjust the screening criteria by learning effective causal inference results in historical analysis.

[0060] Specific implementations may include:

[0061] When the system is initialized, a fixed p-value threshold (such as p<5×10 -8 )Screening of SNPs.

[0062] Through machine learning algorithms, we learn effective SNPs that have been verified by causal analysis, and use this information to optimize future screening processes, dynamically adjusting the p-value threshold and LD elimination criteria to improve accuracy.

[0063] The causal analysis module also includes a dynamic adjustment unit, which automatically adjusts the SNP selection parameters and the weight coefficients of the TSMR model according to the preliminary analysis results to optimize the accuracy of causal inference.

[0064] Specifically, during the causal inference analysis, this module automatically adjusts SNP selection parameters (such as p-value threshold, LD elimination criteria, etc.) and model weights based on the preliminary analysis results to optimize the final causal inference accuracy. The system can identify abnormal results or inconsistent causal associations in the initial analysis and dynamically reselect appropriate instrumental variables or adjust the model weight coefficients. Specific implementation method:

[0066] When performing causal analysis, if the system detects abnormal results (such as the confidence interval of the causal association is too wide or the analysis results are not significant), it will automatically adjust the p-value threshold for SNP selection and the weight of the model.

[0067] Based on multiple iterative analyses, the optimal causal inference result is finally determined by adjusting the weight coefficients and parameters.

[0068] The heterogeneity and pleiotropy testing module also includes an automated alarm unit, which monitors the heterogeneity and pleiotropy indicators of instrumental variables, automatically generates an alarm when significant heterogeneity or pleiotropy is identified, and prompts the user to perform manual intervention or adjust analysis parameters.

[0069] Specifically, the system has a built-in automatic alarm system that can monitor the heterogeneity and pleiotropy test results of instrumental variables. If significant heterogeneity or pleiotropy of instrumental variables is detected (such as abnormal results through Cochran's Q test or MREgger test), the system will generate an automatic alarm and prompt the user to adjust parameters or replace SNP variables. Specific implementation method:

[0071] The system continuously monitors heterogeneity indicators (such as Cochran's Q test value) and pleiotropy indicators (MREgger slope) and automatically generates alerts when significant heterogeneity or pleiotropy is detected.

[0072] The system prompts users to reselect instrumental variables or adjust existing causal analysis parameters to ensure the reliability of the final results.

[0073] The results presentation and interpretation module also includes an interactive visualization interface that allows users to select specific dimensions of social isolation and dynamically updates charts to demonstrate the causal relationships between different dimensions and neuroticism.

[0074] Specifically, the system provides an interactive visualization interface that allows users to select different dimensions of social isolation (such as loneliness, social frequency, etc.) for causal analysis according to their needs. Users can dynamically switch analysis dimensions through the interface to view the impact of each dimension on neuroticism, and the interface updates the result charts and statistics in real time. Specific implementation method:

[0076] The system displays preliminary causal analysis results through a visual interface, including statistical data such as odds ratio (OR), confidence interval (CI) and p-value.

[0077] Users can select specific dimensions of social isolation (such as loneliness, social support, etc.) in the interface. The interface will dynamically update the causal analysis results of the corresponding dimensions and display the correlation in the form of a chart.

[0078] The report generator includes a natural language generation engine that automatically generates a detailed report based on the analysis results, including neuroticism risk prediction, significant SNP site interpretation, and personalized recommendations.

[0079] Specifically, the system integrates a report generator based on natural language generation (NLG) technology, which can automatically analyze the results of causal analysis and generate a detailed neuroticism risk report. The report not only includes the explanation of significant SNP sites, but also provides personalized genetic risk prediction and mental health advice. The NLG engine generates reports suitable for academic or personal use by interpreting statistical data and describing the analysis results in human-friendly language. Specific implementation method:

[0081] Based on the final causal analysis results, the system calls the NLG engine to automatically generate a report, including the statistical significance of each SNP site, causal association explanation and genetic risk assessment.

[0082] Reports can be personalized based on user input, for example, to add mental health advice or relevant preventive measures.

[0083] Embodiment 2:

[0084] Reference Figure 2 In a second embodiment of the present invention, the present invention provides a social isolation and neuroticism analysis method based on GWAS, comprising the following steps:

[0085] S1: Data Collection and Processing

[0086] This step describes the process of extracting single nucleotide polymorphism (SNPs) data related to social isolation, social interaction, and neuroticism from the public genome-wide association study (GWAS) database. After extracting the data, the data processing module preprocesses the data. The preprocessing steps include:

[0087] Missing value imputation: The system automatically identifies missing gene loci and fills them in through interpolation algorithms or using similar features from other samples in the genetic data.

[0088] Outlier removal: Outliers are automatically removed through a detection mechanism that deviates from the normal statistical range (such as z-values ​​exceeding 3 times the standard deviation).

[0089] Data standardization: Through normalization or Z-score conversion, all sample data are made to conform to unified analysis standards to ensure the comparability and consistency of genetic data in different databases.

[0090] S2: Instrumental variable selection

[0091] The screening of instrumental variables is a crucial step, which is implemented as follows:

[0092] Screening algorithm: A built-in screening algorithm is used, which will filter the samples by the set p-value threshold (e.g. p<5×10 -8) to screen SNPs significantly associated with social isolation and neuroticism. The system automatically calculates the correlation between SNPs and various phenotypes and selects significantly associated sites.

[0093] Linkage disequilibrium (LD) elimination strategy: The LD elimination module is used to automatically detect linkage disequilibrium, eliminate redundant SNPs caused by co-inheritance, and ensure that the selected SNP instrument variables are independent of each other.

[0094] Ultimately, a set of instrumental variables that meet the requirements of Mendelian randomization is generated, which will be automatically stored by the system and used in subsequent causal analysis steps.

[0095] S3: Causal Analysis

[0096] When conducting a causal analysis, the specific steps are as follows:

[0097] Inverse Variance Weighted (IVW) Analysis: The system calculates the causal effect of each instrumental variable on neuroticism using the IVW method. The IVW method takes a weighted average of the effect estimates for each SNP to produce an overall causal effect value.

[0098] Robustness test: The system further verifies the IVW analysis results through weighted median, weighted mode and MREgger method. MREgger method is particularly critical in detecting the potential multi-effect of instrumental variables and can effectively correct the bias in causal estimation.

[0099] These steps ensure that the results of the causal analysis are robust and can exclude possible confounding effects in the data.

[0100] S4: Heterogeneity and Pleiotropy Tests

[0101] In order to ensure that the influence of instrumental variables on neuroticism risk is through social isolation or social interaction dimensions rather than other channels, the system provides two test methods:

[0102] Heterogeneity test: The system uses Cochran's Q test to detect the difference in the impact of different social isolation dimensions on neuroticism risk. Through this test, it is possible to identify which dimensions have a more significant impact and help adjust the analysis strategy.

[0103] Pleiotropy detection: The system uses MREgger regression and global pleiotropy test methods to ensure that the selected SNPs will not affect the analysis results through other gene pathways or complex mechanisms. Any significant pleiotropy detected will be automatically marked and the user will be reminded to make corrections.

[0104] S5: Results presentation and interpretation

[0105] The system presents the results of causal analysis in the form of visual charts, including:

[0106] Visualization chart: Based on the analysis results, the system generates a causal relationship diagram between social isolation and neuroticism, showing the odds ratio (OR), confidence interval (CI) and statistical significance of each SNP. Users can dynamically select and view causal analysis results of different dimensions through an interactive interface.

[0107] Personalized report generation: Based on the analysis results, the system will automatically generate a personalized neuroticism risk prediction report using the natural language generation (NLG) engine. The report explains in detail the significant SNP sites and their potential impact on individual mental health, and provides personalized health management suggestions.

[0108] Specifically, single nucleotide polymorphisms (SNPs) associated with social isolation and social interaction were extracted from genome-wide association study (GWAS) datasets. Instrumental variables that met the predetermined criteria were selected. The main TSMR analysis was performed using the inverse variance weighting (IVW) method, and robustness checks were performed using weighted median, weighted mode, and MR Egger methods. Heterogeneity and pleiotropy tests as well as sensitivity analyses were performed to improve the accuracy and robustness of the results.

[0109] Among the five social engagement types analyzed, loneliness (IVW) (odds ratio per standard deviation change: 4.230; 95% confidence interval: 2.081-8.599; p<0.001) and loneliness (MTAG) (odds ratio per standard deviation change in IVW: 1.670; 95% confidence interval: 1.314-2.122; p<0.001) showed statistically significant associations with increased risk of neuroticism. The remaining three social engagement types were not significantly associated with risk of neuroticism.

[0110] Conclusion: Our results suggest a causal relationship between loneliness and loneliness (MTAG) and increased risk of neuroticism, which warrants further investigation to understand the underlying mechanisms.

[0111] Embodiment 3

[0112] The third embodiment of the present invention is based on the same inventive concept and proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the GWAS-based social isolation and neuroticism analysis method of the above embodiment.

[0113] Embodiment 4

[0114] The fourth embodiment of the present invention is based on the same inventive concept. The present invention proposes a terminal, which includes: a processor and a memory; the processor and the memory communicate with each other; the memory is used to store instructions; the processor is used to execute the instructions in the memory to execute the social isolation and neuroticism analysis method based on GWAS of the above embodiment.

[0115] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0116] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A GWAS-based social isolation and neuroticism analysis system, characterized by: include: A data collection and processing module, including a database interface and a data processing unit for extracting single nucleotide polymorphisms from a genome-wide association study database, wherein the data processing unit cleans, fills in missing values, and converts the extracted data using a standardized algorithm to generate a genetic data set suitable for subsequent analysis; An instrumental variable selection module, including a SNP screening algorithm, wherein the screening algorithm is based on filtering SNP loci significantly associated with social isolation, social interaction, and neuroticism, and uses a preset p-value threshold and linkage disequilibrium elimination criteria to select instrumental variables that meet the requirements of Mendelian randomization analysis from the cleaned data set; A causal analysis module, including a computing unit for performing a two-sample Mendelian randomization analysis, wherein the computing unit calculates the causal relationship between social isolation, social interaction and neuroticism by an inverse variance weighted method, and integrates weighted median, weighted mode and MREgger methods for robustness testing; The heterogeneity and pleiotropy test module includes a heterogeneity test unit and a pleiotropy test unit. The heterogeneity test unit identifies differences in different dimensions of social isolation through Cochran's Q test, and the pleiotropy test unit detects potential pleiotropy of instrumental variables through MREgger regression and global pleiotropy test methods. The result display and interpretation module includes a visualization interface and a report generator. The visualization interface is used to display the causal relationship between social isolation and neuroticism in the form of a chart. The report generator automatically generates a personalized neuroticism risk prediction report based on the analysis results.

2. The social isolation and neuroticism analysis system based on GWAS according to claim 1, characterized in that: The data collection and processing module also includes a multi-source data integration unit, which is used to extract SNP data from different whole genome association study databases and perform data integration and normalization processing on data from different sources through a consistency verification algorithm.

3. The social isolation and neuroticism analysis system based on GWAS according to claim 1, characterized in that: The instrumental variable selection module also includes a machine learning model for optimizing the SNP selection process, wherein the machine learning model automatically adjusts the p-value threshold and LD elimination criteria through historical data in the training set.

4. The social isolation and neuroticism analysis system based on GWAS according to claim 1, characterized in that: The causal analysis module also includes a dynamic adjustment unit, which automatically adjusts the SNP selection parameters and the weight coefficient of the TSMR model according to the preliminary analysis results to optimize the accuracy of causal inference.

5. The social isolation and neuroticism analysis system based on GWAS according to claim 1, characterized in that: The heterogeneity and pleiotropy testing module also includes an automated alarm unit, which automatically generates an alarm when significant heterogeneity or pleiotropy is identified by monitoring the heterogeneity and pleiotropy indicators of the instrumental variables, and prompts the user to perform manual intervention or adjust the analysis parameters.

6. The social isolation and neuroticism analysis system based on GWAS according to claim 1, characterized in that: The result display and interpretation module also includes an interactive visualization interface that allows users to select specific social isolation dimensions and dynamically updates charts to display the causal relationships between different dimensions and neuroticism.

7. The social isolation and neuroticism analysis system based on GWAS according to claim 1, characterized in that: The report generator includes a natural language generation engine, which automatically generates a detailed report containing neuroticism risk prediction, significant SNP site interpretation and personalized suggestions based on the analysis results.

8. The social isolation and neuroticism analysis method based on GWAS is characterized by: The GWAS-based social isolation and neuroticism analysis system for any one of claims 1 to 7 comprises the following steps: S1: Data Collection and Processing Single nucleotide polymorphism data associated with social isolation, social interaction, and neuroticism were extracted from the Genome-Wide Association Study database; Use the data processing module to clean the extracted data, including missing value filling, abnormal data removal and data format standardization; S2: Instrumental variable selection The cleaned data were screened using a screening algorithm to select candidate instrumental variables based on SNP loci significantly associated with social isolation and neuroticism. The screening criteria included setting a p-value threshold and using a linkage disequilibrium elimination strategy to exclude SNPs significantly associated with other characteristics. After the screening is completed, a set of instrumental variables that meet the requirements of Mendelian randomization is generated; S3: Causal Analysis The inverse variance weighting method was used to conduct causal inference analysis on instrumental variables to explore the causal relationship between social isolation, social interaction and neuroticism. At the same time, the results of IVW analysis were robustly tested by weighted median, weighted mode and MREgger methods; S4: Heterogeneity and Pleiotropy Tests Using the heterogeneity test tool, the Cochran's Q test was used to identify the differences in the effects of different types of social isolation on the risk of neuroticism and to assess the heterogeneity between different dimensions; The MREgger regression method and global pleiotropy test were used to detect the potential pleiotropy of instrumental variables, so that the selected SNPs instrumental variables would not affect the results of causal analysis through other pathways; S5: Results presentation and interpretation In the result display module, a visualization chart of the causal relationship between social isolation, social interaction and neuroticism is generated, showing the causal association, odds ratio and confidence interval of each dimension; Based on the analysis results, an individualized neuroticism risk prediction report is automatically generated, which explains the significant SNP sites and mental health risks in detail and provides corresponding suggestions.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the social isolation and neuroticism analysis method based on GWAS as claimed in claim 8 is implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the social isolation and neuroticism analysis method based on GWAS as claimed in claim 8 is implemented.

Images