Multi-center inherited metabolic disease information integration platform

Abstract

The invention discloses a multi-center inherited metabolic disease information integration platform, and relates to the technical field of medical treatment, according to the multi-center inherited metabolic disease information integration platform, the normalization and availability of data are improved through a data standardization module; data from different centers are integrated into a unified database through the data integration module by utilizing a data fusion technology, redundant data are removed, the problem of heterogeneous data integration is effectively solved, and the integrity and consistency of the data are improved; the privacy protection module avoids data leakage and unauthorized access; through the resource calculation management module, the resource utilization efficiency is effectively improved, and the calculation cost is reduced; and secondly, the storage resources are dynamically adjusted and allocated according to the evaluation result of the storage index Cczs, so that the optimal management of the storage resources is realized, the problems of resource waste and resource insufficiency are avoided, and the efficient operation of the system is ensured.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to a multi-center genetic metabolic disease information integration platform. Background Art

[0002] The multi-center genetic metabolic disease information platform aims to integrate data resources from multiple research centers to solve the problem of data dispersion in genetic metabolic disease research. Through standardized data collection, storage and sharing, the platform provides a centralized data warehouse to support comprehensive analysis of genomic, metabolomic and clinical data. Its goal is to improve the quality and consistency of data, promote multidisciplinary collaboration, and advance the development of disease mechanism research and personalized medicine. At the same time, the platform uses advanced encryption and strict access control measures to ensure data privacy and security, providing strong support for drug development and clinical diagnosis.

[0003] However, the existing multi-center genetic metabolic disease information platform often has the following technical shortcomings when applied to drug development:

[0004] 1. Data integration is difficult. Data processing is very complicated because data obtained from different sources may lack consistency and interoperability;

[0005] 2. Difficulty in resource calculation. Since processing and analyzing large-scale genomic data requires powerful computing power and storage resources, existing platforms are unable to meet the demand. Summary of the invention

[0006] Technical issues solved

[0007] In view of the deficiencies of the prior art, the present invention provides a multi-center genetic metabolic disease information integration platform, which solves the technical problems of data integration difficulties and resource calculation difficulties in the background technology.

[0008] Technical Solution

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions: a multi-center genetic metabolic disease information integration platform, including a data standardization module, a data integration module, a privacy protection module, a resource calculation management module, a data analysis module and a collaborative sharing module;

[0010] The data standardization module is used to collect genetic metabolic disease-related data from different centers and pre-process all data, including format conversion and cleaning;

[0011] The data integration module is used to integrate data from different centers into a unified database using data fusion technology; it also manages metadata based on data source, data type, and data quality, and calculates the evaluation data index Sjzs, eliminating redundant data based on the evaluation results;

[0012] The privacy protection module is used to be compatible with encryption technology during data storage and transmission, and to access data in a hierarchical manner by setting strict access rights and authentication mechanisms;

[0013] The resource computing management module uses the elastic computing scheduling computing resources provided by the cloud computing platform to dynamically allocate computing resources according to task requirements; secondly, it calculates and evaluates the storage index Cczs, and dynamically adjusts the allocation of storage resources based on the evaluation results;

[0014] The data analysis module uses machine learning and artificial intelligence algorithms to conduct in-depth mining of managed data to discover potential genetic variations and drug targets; by building prediction models and biomarker recognition models, it assists in drug development and the formulation of personalized treatment plans;

[0015] The collaborative sharing module is used to establish a collaborative platform between researchers and medical institutions to promote the sharing of data and research results; to build a dedicated knowledge base related to genetic metabolic diseases, and to accumulate and share research experience and knowledge.

[0016] Preferably, the data standardization module includes a data acquisition unit, a format conversion unit and a data cleaning unit; the data acquisition unit is connected to multiple data source interfaces through an API interface, and the data sources include genome sequencing centers, hospital clinical databases, laboratory data management systems, public databases and cloud computing platforms, and multi-threaded parallel technology is used to collect relevant data on genetic metabolic diseases in real time; the format conversion unit converts data in different formats into a standardized format; the data cleaning unit is responsible for deduplication, missing value filling and data normalization of the converted data, and after dimensionless processing of all data, a storage resource data set and a genetic variation and drug target data set are constructed respectively.

[0017] Preferably, the data integration module includes a data fusion unit and a data sorting unit; the data fusion unit integrates heterogeneous data from different centers through multi-source data fusion technology, including data matching, data cleaning and data merging, to form a unified data set; the data fusion unit also includes a conflict resolution mechanism to resolve data conflict problems through priority rules;

[0018] The data organization unit is used to manage and maintain the metadata of the data. It reads the data information of the genome sequencing center, hospital clinical database, laboratory data management system and public database, and constructs a data information set after dimensionless processing, including data source, data type, data format and data quality; and uses the following formula to calculate the data index Sjzs:

[0019]

[0020] In the formula, Sjy represents the data source evaluation value, Slx represents the data type evaluation value, Sgs represents the data format evaluation value, and Szl represents the data quality evaluation value;

[0021] n represents the number of indicators of data source evaluation value, Ws i is the value of the evaluation value indicator of the i-th data source, s i represents the weight of the data source evaluation value; m is the number of indicators of the data type evaluation value, Wt i is the value of the evaluation value indicator of the i-th data type, t i Indicates the weight of the data type evaluation value;

[0022] p is the number of indicators for data format evaluation, Wf i is the value of the i-th data format evaluation index, f i represents the weight of the data format evaluation value; q is the number of indicators of the data quality evaluation value, Wq i is the value of the i-th data quality assessment indicator, q i Represents the weight of the data quality assessment value;

[0023] The data sorting unit performs the evaluation by presetting the quality threshold Q and the data index Sjzs, and removes redundant data based on the evaluation results. The specific evaluation contents are as follows:

[0024] If the quality threshold Q is less than the data index Sjzs, the data is unqualified and marked and removed;

[0025] If the quality threshold Q ≥ data index Sjz, it means that the data is qualified and the data is stored.

[0026] Preferably, the privacy protection module includes a data encryption unit, an access control unit and an authentication management unit; the data encryption unit uses AES and RSA encryption algorithms to encrypt data; the access control unit controls data access according to user roles and permission levels by establishing a multi-level access permission system, and stipulates that only authorized users can access specific data;

[0027] The authentication management unit adopts a multi-factor authentication mechanism, including password authentication, SMS verification code and fingerprint recognition security; it also sets up dynamic password and two-factor authentication functions.

[0028] Preferably, the resource computing management module includes a computing resource allocation unit and a storage resource computing unit; the resource allocation unit monitors the task load and computing resource usage in real time, and uses a dynamic load balancing algorithm and a predictive scheduling algorithm to automatically adjust and allocate computing resources according to task priority, computing requirements, and resource utilization; at the same time, it is equipped with automatic expansion and reduction computing instance technology to dynamically allocate computing resources according to the increase or decrease in the amount of tasks.

[0029] Preferably, the storage resource calculation unit is used to manage and schedule cloud storage resources, and calculates and obtains the storage index Cczs by extracting the storage resource data set. The specific calculation formula is as follows:

[0030]

[0031] In the formula, Cly represents storage capacity utilization, Cfw represents storage access frequency, Cry represents data redundancy rate, Ccb represents storage cost, and Ckz represents storage scalability;

[0032] e - is an exponential decay function, e -Cry It indicates exponentializing the impact of the data redundancy rate Cry; ln indicates the natural logarithm function;

[0033] The storage resource calculation unit compares the preset storage threshold W with the storage index Cczs to generate the following evaluation results:

[0034] If the storage index Cczs is less than the storage threshold W, a first storage result is generated, indicating that the current storage resource utilization is normal, the system is running normally, and no resource adjustment is performed;

[0035] If the storage index Cczs ≥ storage threshold W, a second storage result is generated, indicating that the current storage resource utilization is abnormal and there is a risk of resource shortage and overload. At this time, resource adjustments are made, including adjusting the storage resource allocation strategy, releasing idle resources, and increasing cloud storage resources.

[0036] Preferably, the data analysis module includes a prediction model building unit, a variation identification unit, and a treatment plan formulation unit;

[0037] The prediction model building unit extracts data features of genetic variation and drug target data sets by selecting convolutional neural networks for deep mining; it analyzes and predicts genetic variation by collecting and training historical data and large-scale genomic data.

[0038] Preferably, the variation identification unit is used to calculate the variation index Byzs for evaluating genetic variation, and the calculation formula is as follows:

[0039]

[0040] In the formula, Tpl represents the mutation frequency within a fixed period, Tby represents the insertion and deletion variation value, Tkb represents the copy number variation value, Tjg represents the structural variation value, Tcy represents the gene expression difference value, and Tbd represents the gene expression value;

[0041] exp represents exponential function;

[0042] The variation identification unit compares the preset variation threshold R with the variation index Byzs to generate the following evaluation results:

[0043] If the variation threshold R> the variation index Byzs, the first result is generated, indicating that there is an anomaly in the sample, which requires further analysis and attention;

[0044] If the variation threshold R ≤ the variation index Byzs, a second result is generated, indicating that there is no abnormality in the sample and no further intervention is required.

[0045] Preferably, the treatment plan formulation unit analyzes key biomarkers and drug targets related to drug response through established prediction models and biomarker identification models; performs drug screening and adjustment based on the identified drug targets to screen out effective candidate drug molecules; then divides the patients into different subtypes based on their genetic variations and biomarker information, formulates personalized treatment plans, and adjusts the existing treatment plans in combination with the results of the prediction model;

[0046] Finally, the patient's personalized treatment plan will be applied to clinical trials, and clinical trial data will be collected and continuously analyzed. Based on the analysis results of the clinical trial data, the prediction model and treatment plan will be further adjusted, and a special knowledge base related to genetic metabolic diseases will be constructed.

[0047] Preferably, the collaborative sharing module includes a collaborative platform unit, a knowledge base unit and a sharing management unit; the collaborative platform unit provides data upload, download and communication functions by building an online platform, and supports multiple data formats; the knowledge base unit is used to build a special knowledge base related to genetic metabolic diseases, which includes research literature, clinical cases, experimental data and treatment plans, and the knowledge base adopts database technology and natural language processing technology; the sharing management unit is responsible for formulating and implementing data sharing rules and processes, and restricting unauthorized users from accessing and sharing data through access control and permission management; at the same time, the sharing management unit also provides data anonymization and desensitization technology to protect data privacy and comply with relevant regulatory requirements.

[0048] Beneficial Effects

[0049] The present invention provides a communication network fault early warning method and system based on artificial intelligence, which has the following beneficial effects:

[0050] (1) This multi-center genetic metabolic disease information integration platform solves the problems of inconsistent formats and uneven data quality of different data sources through the data standardization module, and improves the standardization and availability of data; through the data integration module, data fusion technology is used to integrate data from different centers into a unified database, and metadata management is performed based on data source, data type and data quality, and the data index Sjzs is calculated and evaluated. Redundant data is eliminated based on the evaluation results, which effectively solves the problem of heterogeneous data integration, improves data integrity and consistency, and ensures high data quality; the privacy protection module is compatible with encryption technology during data storage and transmission, and hierarchical access to data by setting strict access rights and authentication mechanisms ensures data security and privacy, avoids data leakage and unauthorized access, and ensures data compliance and security; through the collaborative work of these three modules, the technical shortcomings of data integration difficulties are effectively solved, and standardized processing, efficient integration and security protection of data are achieved, providing reliable technical support for the multi-center genetic metabolic disease information integration platform.

[0051] (2) This multi-center genetic metabolic disease information integration platform uses the elastic computing provided by the cloud computing platform through the resource computing management module to schedule computing resources and dynamically allocate computing resources according to task requirements, effectively coping with the uncertainty and dynamic changes of computing tasks, improving resource utilization efficiency and reducing computing costs; secondly, by calculating and evaluating the storage index Cczs, dynamically adjusting the allocation of storage resources based on the evaluation results, optimizing the management of storage resources, avoiding resource waste and resource shortage, and ensuring the efficient operation of the system; through the data analysis module, using machine learning and artificial intelligence algorithms, deep mining of managed data is carried out to discover potential genetic variations and drug targets. By constructing prediction models and biomarker identification models, it assists in drug development and personalized treatment plan formulation, improves the accuracy and reliability of data analysis, and accelerates the drug development process and the realization of personalized medicine; through the collaborative sharing module, it is used to establish a collaborative platform between researchers and medical institutions to promote the sharing of data and research results. By building a special knowledge base related to genetic metabolic diseases, it accumulates and shares research experience and knowledge, enhances the efficiency of research cooperation, and promotes the transformation and application of scientific research results; it effectively solves the technical shortcomings of resource calculation difficulties, realizes efficient resource management, in-depth data analysis and extensive sharing of research results, and provides strong technical support for the multi-center genetic metabolic disease information integration platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a schematic diagram of the structure of a multi-center genetic metabolic disease information integration platform of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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.

[0054] Example 1

[0055] A multi-center genetic metabolic disease information integration platform, please refer to Figure 1 , including data standardization module, data integration module, privacy protection module, resource computing management module, data analysis module and collaborative sharing module;

[0056] The data standardization module is used to collect genetic metabolic disease-related data from different centers and pre-process all data, including format conversion and cleaning;

[0057] The data integration module is used to integrate data from different centers into a unified database using data fusion technology; it also manages metadata based on data source, data type, and data quality, and calculates the evaluation data index Sjzs, eliminating redundant data based on the evaluation results;

[0058] The privacy protection module is used to be compatible with encryption technology during data storage and transmission, and to access data in a hierarchical manner by setting strict access rights and authentication mechanisms;

[0059] The resource computing management module uses the elastic computing scheduling computing resources provided by the cloud computing platform to dynamically allocate computing resources according to task requirements; secondly, it calculates and evaluates the storage index Cczs, and dynamically adjusts the allocation of storage resources based on the evaluation results;

[0060] The data analysis module uses machine learning and artificial intelligence algorithms to conduct in-depth mining of managed data to discover potential genetic variations and drug targets; by building prediction models and biomarker recognition models, it assists in drug development and the formulation of personalized treatment plans;

[0061] The collaborative sharing module is used to establish a collaborative platform between researchers and medical institutions to promote the sharing of data and research results; to build a dedicated knowledge base related to genetic metabolic diseases, and to accumulate and share research experience and knowledge.

[0062] In this embodiment, the data standardization module collects genetic metabolic disease-related data from different centers, converts and cleans the data, and ensures the consistency and availability of the data; the data integration module uses data fusion technology to integrate data from different centers into a unified database, and eliminates redundant data and improves data quality through metadata management and data index evaluation; the privacy protection module uses encryption technology during data storage and transmission, and sets strict access rights and authentication mechanisms to ensure data security; the resource computing management module uses the elastic computing scheduling of the cloud computing platform to dynamically allocate computing resources according to task requirements, and adjusts resources by calculating the storage index Cczs to ensure efficient resource Utilization; the data analysis module uses machine learning and artificial intelligence algorithms to conduct in-depth mining of managed data, discover potential genetic variations and drug targets, and assist in drug development and personalized treatment plan formulation; the collaborative sharing module promotes the sharing of data and research results by establishing a collaborative platform between researchers and medical institutions, and builds a special knowledge base related to genetic metabolic diseases to accumulate and share research experience and knowledge; through the collaborative work of the above modules, the consistency and high quality of data, efficient management of resources, in-depth analysis of data and extensive sharing of research results are achieved, effectively solving the technical problems of data integration and resource calculation, and providing strong support for the research and treatment of genetic metabolic diseases.

[0063] Example 2

[0064] See also Figure 1 The data standardization module includes a data acquisition unit, a format conversion unit and a data cleaning unit; the data acquisition unit is connected to multiple data source interfaces through an API interface, and the data sources include genome sequencing centers, hospital clinical databases, laboratory data management systems, public databases and cloud computing platforms, and multi-threaded parallel technology is used to collect relevant data on genetic metabolic diseases in real time; the format conversion unit converts data in different formats into a standardized format; the data cleaning unit is responsible for deduplication, missing value filling and data normalization of the converted data, and after dimensionless processing of all data, it constructs a storage resource data set and a genetic variation and drug target data set respectively.

[0065] In this embodiment, through the application of multi-threaded parallel technology, the data collection efficiency is greatly improved, and real-time data update and collection are achieved; the format conversion unit ensures the consistency of the data format and solves the problem of inconsistent formats between different data sources; the data cleaning unit improves the integrity and quality of the data through deduplication, missing value filling and data normalization. Ultimately, the data standardization module provides the platform with a high-quality and highly consistent data foundation, ensuring the accuracy and reliability of subsequent data integration, analysis and application, and providing solid data support for the research and treatment of genetic metabolic diseases.

[0066] Example 3

[0067] See also Figure 1 ,The data integration module includes a data fusion unit and a data ,collation unit; the data fusion unit integrates heterogeneous data from different ,centers through multi-source data fusion technology, including data matching, ,data cleaning and data merging, to form a unified data set; the data fusion unit also includes a ,conflict resolution mechanism to resolve data conflict problems through priority ,rules;

[0068] The data organization unit is used to manage and maintain the metadata of the data. It reads the data information of the genome sequencing center, hospital clinical database, laboratory data management system and public database, and constructs a data information set after dimensionless processing, including data source, data type, data format and data quality; and uses the following formula to calculate the data index Sjzs:

[0069]

[0070] In the formula, Sjy represents the data source evaluation value, Slx represents the data type evaluation value, Sgs represents the data format evaluation value, and Szl represents the data quality evaluation value;

[0071] n represents the number of indicators of data source evaluation value, Ws i is the value of the evaluation value indicator of the i-th data source, s i represents the weight of the data source evaluation value; m is the number of indicators of the data type evaluation value, Wt i is the value of the evaluation value indicator of the i-th data type, t i Indicates the weight of the data type evaluation value;

[0072] p is the number of indicators for data format evaluation, Wf i is the value of the i-th data format evaluation index, f i represents the weight of the data format evaluation value; q is the number of indicators of the data quality evaluation value, Wq i is the value of the i-th data quality assessment indicator, q i Represents the weight of the data quality assessment value;

[0073] The data sorting unit performs the evaluation by presetting the quality threshold Q and the data index Sjzs, and removes redundant data based on the evaluation results. The specific evaluation contents are as follows:

[0074] If the quality threshold Q is less than the data index Sjzs, the data is unqualified and marked and removed;

[0075] If the quality threshold Q ≥ data index Sjz, it means that the data is qualified and the data is stored.

[0076] Example 4

[0077] See also Figure 1 The privacy protection module includes a data encryption unit, an access control unit, and an authentication management unit; the data encryption unit uses the AES and RSA encryption algorithms to encrypt data; the access control unit establishes a multi-level access authority system to control data access according to user roles and authority levels, and stipulates that only authorized users can access specific data;

[0078] The authentication management unit adopts a multi-factor authentication mechanism, including password authentication, SMS verification code and fingerprint recognition security; it also sets up dynamic password and two-factor authentication functions.

[0079] In this embodiment, the reliability and diversity of the data source Sjy directly affect the credibility and coverage of the data. The data provided by different data sources may come from different backgrounds and environments, and can comprehensively reflect information from more dimensions; the diversity of data types Slx reflects the comprehensiveness and richness of the data, including different types of data such as structured data, semi-structured data, and unstructured data, which can provide a more comprehensive information perspective; the uniformity and standardization of the data format Sgs determine the processability and compatibility of the data. When integrating and processing data in different formats, additional conversion and normalization work is performed; data quality Szl refers to the accuracy, completeness, timeliness, and consistency of the data. High-quality data can ensure the accuracy and reliability of the analysis results.

[0080] Example 5

[0081] See also Figure 1 The resource computing management module includes a computing resource allocation unit and a storage resource computing unit; the resource allocation unit monitors the task load and computing resource usage in real time, and uses dynamic load balancing algorithm and predictive scheduling algorithm to automatically adjust and allocate computing resources according to task priority, computing requirements and resource utilization; at the same time, it is equipped with automatic expansion and reduction of computing instance technology to dynamically allocate computing resources according to the increase or decrease of task volume.

[0082] The storage resource calculation unit is used to manage and schedule cloud storage resources. It extracts the storage resource data set and calculates the storage index Cczs. The specific calculation formula is as follows:

[0083]

[0084] In the formula, Cly represents storage capacity utilization, Cfw represents storage access frequency, Cry represents data redundancy rate, Ccb represents storage cost, and Ckz represents storage scalability;

[0085] e- is an exponential decay function, e -Cry It indicates exponentializing the impact of the data redundancy rate Cry; ln indicates the natural logarithm function;

[0086] The storage resource calculation unit compares the preset storage threshold W with the storage index Cczs to generate the following evaluation results:

[0087] If the storage index Cczs is less than the storage threshold W, a first storage result is generated, indicating that the current storage resource utilization is normal, the system is running normally, and no resource adjustment is performed;

[0088] If the storage index Cczs ≥ storage threshold W, a second storage result is generated, indicating that the current storage resource utilization is abnormal and there is a risk of resource shortage and overload. At this time, resource adjustments are made, including adjusting the storage resource allocation strategy, releasing idle resources, and increasing cloud storage resources.

[0089] In this embodiment, the storage capacity utilization Cly reflects the actual use of storage resources, which can help identify the waste of storage resources and potential optimization space; the storage access frequency Cfw measures the frequency of data access, which helps to optimize storage performance and response speed; the data redundancy rate Cry evaluates the degree of data duplication, which affects the utilization efficiency of storage space and the complexity of data management; the storage cost Ccb is directly related to the economic benefits of the storage solution, ensuring that cost-effectiveness is maximized while meeting the needs; the storage scalability Ckz reflects the ability of the storage system to cope with data growth and changes, ensuring that the system can be flexibly expanded to meet future needs; by comprehensively evaluating these parameters, the storage index Cczs fully reflects the overall performance and efficiency of the storage system, provides a scientific basis for the optimization and management of storage resources, and thus improves the reliability, economy and scalability of data storage.

[0090] Example 6

[0091] See also Figure 1 ,The data analysis module includes a prediction model building unit, a variant identification unit, and a treatment plan formulation unit;

[0092] The prediction model building unit extracts data features of genetic variation and drug target data sets by selecting convolutional neural networks for deep mining; it analyzes and predicts genetic variation by collecting and training historical data and large-scale genomic data.

[0093] The variation identification unit is used to calculate the variation index Byzs for evaluating genetic variation, and its calculation formula is as follows:

[0094]

[0095] In the formula, Tpl represents the mutation frequency within a fixed period, Tby represents the insertion and deletion variation value, Tkb represents the copy number variation value, Tjg represents the structural variation value, Tcy represents the gene expression difference value, and Tbd represents the gene expression value;

[0096] exp represents exponential function;

[0097] The variation identification unit compares the preset variation threshold R with the variation index Byzs to generate the following evaluation results:

[0098] If the variation threshold R> the variation index Byzs, the first result is generated, indicating that there is an anomaly in the sample, which requires further analysis and attention;

[0099] If the variation threshold R ≤ the variation index Byzs, a second result is generated, indicating that there is no abnormality in the sample and no further intervention is required.

[0100] The treatment plan formulation unit analyzes key biomarkers and drug targets related to drug response through established prediction models and biomarker identification models; screens and adjusts drugs based on the identified drug targets to screen out effective candidate drug molecules; then divides patients into different subtypes based on their genetic variations and biomarker information, formulates personalized treatment plans, and adjusts existing treatment plans based on the results of the prediction model;

[0101] Finally, the patient's personalized treatment plan will be applied to clinical trials, and clinical trial data will be collected and continuously analyzed. Based on the analysis results of the clinical trial data, the prediction model and treatment plan will be further adjusted, and a special knowledge base related to genetic metabolic diseases will be constructed.

[0102] In this embodiment, the mutation frequency Tpl within a fixed period reflects the mutation activity of the genome within a certain period of time, helping to identify high mutation risk areas; the insertion and deletion mutation value Tby evaluates the impact of inserted or deleted fragments in the genome, revealing potential functional changes; the copy number mutation value Tkb measures the change in the copy number of a specific region in the genome, providing important information about gene amplification or deletion; the structural variation value Tjg evaluates the situation of genome rearrangement and structural changes, which is crucial to understanding complex genome variations; the gene expression difference value Tcy reflects the changes in gene expression levels under different conditions, which helps to understand gene function and regulatory mechanisms; the gene expression value Tbd provides the expression amount of the gene under specific conditions, providing basic data for studying the relationship between genes and phenotypes; through the comprehensive evaluation of these parameters, the variation index Byzs comprehensively reflects the variation of the genome, provides a scientific basis for genetic research and drug development, and promotes the development of personalized medicine and precision treatment.

[0103] Example 7

[0104] See also Figure 1 The collaborative sharing module includes a collaborative platform unit, a knowledge base unit and a sharing management unit; the collaborative platform unit provides data upload, download and communication functions by building an online platform, and supports multiple data formats; the knowledge base unit is used to build a special knowledge base related to genetic metabolic diseases, which includes research literature, clinical cases, experimental data and treatment plans. The knowledge base uses database technology and natural language processing technology; the sharing management unit is responsible for formulating and implementing data sharing rules and processes, and restricting unauthorized users from accessing and sharing data through access control and permission management; at the same time, the sharing management unit also provides data anonymization and desensitization technology to protect data privacy and comply with relevant regulatory requirements.

[0105] In this embodiment, the design of the collaborative sharing module helps to break down data silos and promote collaboration and sharing in genetic metabolic disease research; by providing a multi-functional online platform, researchers and medical institutions can easily upload, download and exchange data, thereby improving research efficiency; the establishment of a dedicated knowledge base provides researchers with a wealth of data resources to support deeper research and discovery; at the same time, through strict access control and data protection measures, the security and compliance of data sharing are ensured, enhancing users' confidence in data security; overall, the collaborative sharing module not only improves data utilization and sharing efficiency, but also promotes progress and innovation in genetic metabolic disease research.

[0106] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-center genetic metabolic disease information integration platform, Features: It includes data standardization module, data integration module, privacy protection module, resource computing management module, data analysis module and collaborative sharing module; The data standardization module is used to collect genetic metabolic disease-related data from different centers and pre-process all data, including format conversion and cleaning; The data integration module is used to integrate data from different centers into a unified database using data fusion technology; at the same time, metadata management is performed based on data source, data type and data quality, and the evaluation data index Sjzs is calculated and redundant data is eliminated based on the evaluation results; The privacy protection module is used to be compatible with encryption technology during data storage and transmission, and to access data in a hierarchical manner by setting strict access rights and authentication mechanisms; The resource computing management module dynamically allocates computing resources according to task requirements by utilizing the elastic computing scheduling computing resources provided by the cloud computing platform; Secondly, the storage index Cczs is calculated and evaluated, and storage resources are dynamically adjusted and allocated based on the evaluation results; The data analysis module uses machine learning and artificial intelligence algorithms to conduct in-depth mining of managed data to discover potential genetic variations and drug targets; by building prediction models and biomarker recognition models, it assists in drug development and the formulation of personalized treatment plans; The collaborative sharing module is used to establish a collaborative platform between researchers and medical institutions to promote the sharing of data and research results; to build a dedicated knowledge base related to genetic metabolic diseases, and to accumulate and share research experience and knowledge.

2. A multi-center genetic metabolic disease information integration platform according to claim 1, Features: The data standardization module includes a data acquisition unit, a format conversion unit and a data cleaning unit; the data acquisition unit is connected to multiple data source interfaces through an API interface, and the data sources include a genome sequencing center, a hospital clinical database, a laboratory data management system, a public database and a cloud computing platform, and multi-threaded parallel technology is used to collect relevant data of genetic metabolic diseases in real time; the format conversion unit converts data in different formats into a standardized format; the data cleaning unit is responsible for deduplication, missing value filling and data normalization of the converted data, and after dimensionless processing of all data, a storage resource data set and a genetic variation and drug target data set are constructed respectively.

3. A multi-center genetic metabolic disease information integration platform according to claim 1, Features: The data integration module includes a data fusion unit and a data sorting unit; the data fusion unit integrates heterogeneous data from different centers through multi-source data fusion technology, including data matching, data cleaning and data merging, to form a unified data set; The data fusion unit also includes a conflict resolution mechanism to resolve data conflicts through priority rules; The data sorting unit is used to manage and maintain the metadata of the data. It reads the data information of the genome sequencing center, the hospital clinical database, the laboratory data management system and the public database, and constructs a data information set after dimensionless processing, including the data source, data type, data format and data quality; and uses the following formula to calculate the data index Sjzs: In the formula, Sjy represents the data source evaluation value, Slx represents the data type evaluation value, Sgs represents the data format evaluation value, and Szl represents the data quality evaluation value; n represents the number of indicators of data source evaluation value, Ws i is the value of the evaluation value indicator of the i-th data source, s i Indicates the weight of the data source evaluation value; m is the number of indicators of the data type evaluation value, Wt i is the value of the evaluation value indicator of the i-th data type, t i Indicates the weight of the data type evaluation value; p is the number of indicators for data format evaluation, Wf i is the value of the i-th data format evaluation index, f i The weight representing the data format evaluation value; q is the number of indicators for data quality assessment, Wq i is the value of the i-th data quality assessment indicator, q i Represents the weight of the data quality assessment value; The data sorting unit performs the evaluation by presetting the quality threshold Q and the data index Sjzs, and removes redundant data according to the evaluation results. The specific evaluation contents are as follows: If the quality threshold Q is less than the data index Sjzs, the data is unqualified and marked and removed; If the quality threshold Q ≥ data index Sjz, it means that the data is qualified and the data is stored.

4. A multi-center genetic metabolic disease information integration platform according to claim 1, Features: The privacy protection module includes a data encryption unit, an access control unit and an authentication management unit; the data encryption unit uses AES and RSA encryption algorithms to encrypt data; the access control unit establishes a multi-level access authority system to control data access according to user roles and authority levels, and stipulates that only authorized users can access specific data; The authentication management unit adopts a multi-factor authentication mechanism, including password authentication, SMS verification code and fingerprint recognition security; and also sets up dynamic password and two-factor authentication functions.

5. A multi-center genetic metabolic disease information integration platform according to claim 1, Features: The resource computing management module includes a computing resource allocation unit and a storage resource computing unit; the resource allocation unit automatically adjusts and allocates computing resources according to task priority, computing requirements and resource utilization by using a dynamic load balancing algorithm and a predictive scheduling algorithm through real-time monitoring of task load and computing resource usage; and is equipped with automatic expansion and reduction of computing instance technology to dynamically allocate computing resources according to the increase or decrease in the amount of tasks.

6. A multi-center genetic metabolic disease information integration platform according to claim 5, Features: The storage resource calculation unit is used to manage and schedule cloud storage resources. By extracting the storage resource data set, the storage index Cczs is calculated. The specific calculation formula is as follows: In the formula, Cly represents storage capacity utilization, Cfw represents storage access frequency, Cry represents data redundancy rate, Ccb represents storage cost, and Ckz represents storage scalability; e - is an exponential decay function, e -Cry It indicates exponentializing the impact of the data redundancy rate Cry; ln indicates the natural logarithm function; The storage resource calculation unit compares the preset storage threshold W with the storage index Cczs to generate the following evaluation result: If the storage index Cczs is less than the storage threshold W, a first storage result is generated, indicating that the current storage resource utilization is normal, the system is running normally, and no resource adjustment is performed; If the storage index Cczs ≥ storage threshold W, a second storage result is generated, indicating that the current storage resource utilization is abnormal and there is a risk of resource shortage and overload. At this time, resource adjustments are made, including adjusting the storage resource allocation strategy, releasing idle resources, and increasing cloud storage resources.

7. A multi-center genetic metabolic disease information integration platform according to claim 1, Features: The data analysis module includes a prediction model building unit, a variation identification unit, and a treatment plan formulation unit; The prediction model building unit extracts data features of genetic variation and drug target data sets by selecting a convolutional neural network, and performs deep mining; and analyzes and predicts genetic variation by collecting and training historical data and large-scale genome data.

8. A multi-center genetic metabolic disease information integration platform according to claim 7, Features: The variation identification unit is used to calculate the variation index Byzs for evaluating genetic variation, and the calculation formula is as follows: In the formula, Tpl represents the mutation frequency within a fixed period, Tby represents the insertion and deletion variation value, Tkb represents the copy number variation value, Tjg represents the structural variation value, Tcy represents the gene expression difference value, and Tbd represents the gene expression value; exp represents exponential function; The variation identification unit compares the preset variation threshold R with the variation index Byzs to generate the following evaluation results: If the variation threshold R> the variation index Byzs, the first result is generated, indicating that there is an anomaly in the sample, which requires further analysis and attention; If the variation threshold R ≤ the variation index Byzs, a second result is generated, indicating that there is no abnormality in the sample and no further intervention is required.

9. A multi-center genetic metabolic disease information integration platform according to claim 8, Features: The treatment plan formulation unit analyzes key biomarkers and drug targets related to drug response through established prediction models and biomarker identification models; performs drug screening and adjustment based on the identified drug targets to screen out effective candidate drug molecules; then divides the patients into different subtypes based on their genetic variations and biomarker information, formulates personalized treatment plans, and adjusts existing treatment plans in combination with the results of the prediction model; Finally, the patient's personalized treatment plan will be applied to clinical trials, and clinical trial data will be collected and continuously analyzed. Based on the analysis results of the clinical trial data, the prediction model and treatment plan will be further adjusted, and a special knowledge base related to genetic metabolic diseases will be constructed.

10. A multi-center genetic metabolic disease information integration platform according to claim 1, Features: The collaborative sharing module includes a collaborative platform unit, a knowledge base unit and a sharing management unit; the collaborative platform unit provides data upload, download and communication functions by building an online platform, and supports multiple data formats; the knowledge base unit is used to build a special knowledge base related to genetic metabolic diseases, which includes research literature, clinical cases, experimental data and treatment plans. The knowledge base adopts database technology and natural language processing technology; the sharing management unit is responsible for formulating and implementing data sharing rules and processes, and restricting unauthorized users from accessing and sharing data through access control and permission management; at the same time, the sharing management unit also provides data anonymization and desensitization technology to protect data privacy and comply with relevant regulatory requirements.

Images