A clinical interpretation system, method, device and medium for tumor diagnosis and treatment

Abstract

The present invention relates to the field of information processing technology, and discloses a clinical interpretation system, method, device and medium for tumor diagnosis and treatment. The clinical interpretation system includes: a data integration module, which is used to collect and integrate multi-dimensional diagnosis and treatment data, and update the multi-dimensional diagnosis and treatment data according to a preset time; a multi-dimensional data knowledge base, which is used to store the multi-dimensional diagnosis and treatment data collected and integrated by the data integration module; and a system for receiving pending cases in user needs, analyzing and processing the pending cases, matching the pending case data obtained after the analysis and processing with the multi-dimensional diagnosis and treatment data of the multi-dimensional data knowledge base to generate an interpretation report, and returning the interpretation report to the user. The present invention solves the problem of single database information and lack of automatic acquisition and update of continuously accumulated new data in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a clinical interpretation system, method, device and medium for tumor diagnosis and treatment. Background Art

[0002] In the early days, the treatment of cancer was mainly limited to surgery, chemotherapy and radiotherapy, but there were disadvantages such as high risk, strong side effects and incurable. With the rapid development of sequencing technology and the significant reduction of sequencing costs in the post-genomic era, sequencing data has grown exponentially, and gene sequencing has also been widely used in the diagnosis and treatment of cancer patients, and precision medicine technology has emerged. Through sequencing analysis of patients, using big data analysis and bioinformatics databases, a personalized medical model of medical and health care is carried out, including medical decision-making, treatment, practice and drugs are planned for the patient's situation, ensuring that the individual treatment of the patient is optimal. As an important means and auxiliary tool for personalized medicine, the tumor drug database has brought great help to medical and scientific researchers. Knowledge bases and tools related to precision medicine are also emerging. However, the existing databases have the following defects:

[0003] 1. It only provides data information on a few dimensions such as gene mutations, drugs, and diseases, without deep extraction and mining of data;

[0004] 2. Lack of rich visualization of data;

[0005] 3. Lack of automatic acquisition and updating of continuously accumulated new data. Summary of the invention

[0006] In view of this, the embodiments of the present invention provide a clinical interpretation system, method, device and medium for tumor diagnosis and treatment to solve the problem of single database information and lack of automatic acquisition and update of continuously accumulated new data in the prior art.

[0007] In a first aspect, an embodiment of the present invention provides a clinical interpretation system for tumor diagnosis and treatment, the clinical interpretation system comprising:

[0008] The data integration module is used to collect and integrate multi-dimensional diagnosis and treatment data, and update the multi-dimensional diagnosis and treatment data according to the preset time;

[0009] Multidimensional data knowledge base, used to store multidimensional diagnosis and treatment data collected and integrated by the data integration module;

[0010] The data processing module is used to receive the pending cases in the user's needs, analyze and process the pending cases, match the pending case data obtained after the analysis and processing with the multi-dimensional diagnosis and treatment data of the multi-dimensional data knowledge base to generate an interpretation report, and return the interpretation report to the user.

[0011] In the clinical interpretation system for tumor diagnosis and treatment provided by the embodiment of the present invention, the diagnosis and treatment data stored in the multidimensional data knowledge base is multidimensional diagnosis and treatment data, the data integration module updates the multidimensional diagnosis and treatment data according to the preset time, the data processing module receives the cases to be processed in the user's needs, and analyzes and processes the cases to be processed, matches the case data to be processed obtained after the analysis and processing with the multidimensional diagnosis and treatment data in the multidimensional data knowledge base to generate an interpretation report, and returns the interpretation report to the user, thereby solving the problem of single database information and lack of automatic acquisition and update of continuously accumulated new data in the prior art.

[0012] In an optional implementation, the data integration module includes:

[0013] A data acquisition unit, used to acquire multi-dimensional diagnosis and treatment data;

[0014] A data integration unit, used for performing data redundancy processing on the multi-dimensional diagnosis and treatment data, and normalizing the multi-dimensional diagnosis and treatment data after the data redundancy processing;

[0015] A data organization unit is used to classify, grade and associate the normalized multi-dimensional diagnosis and treatment data and then transmit them to the multi-dimensional data knowledge base;

[0016] The data updating unit is used to update the acquired multi-dimensional diagnosis and treatment data according to the relationship between the data version of the multi-dimensional data knowledge base and the data source version at a preset time.

[0017] The clinical interpretation system for tumor diagnosis and treatment provided by the embodiment of the present invention acquires multi-dimensional diagnosis and treatment data through a data acquisition unit, and uses a data integration unit to perform data redundancy processing on the multi-dimensional diagnosis and treatment data, and normalizes the multi-dimensional diagnosis and treatment data after data redundancy processing, so as to integrate complex diagnosis and treatment data and unify data management methods, thereby lowering the threshold for users. The data organization unit classifies, grades and associates the normalized multi-dimensional diagnosis and treatment data and transmits them to a multi-dimensional data knowledge base, which greatly improves the coverage and accuracy of the multi-dimensional diagnosis and treatment data. The data update unit updates the acquired multi-dimensional diagnosis and treatment data according to the relationship between the data version of the multi-dimensional data knowledge base and the data source version at a preset time, thereby realizing automatic acquisition and updating of continuously accumulated new data.

[0018] In an optional embodiment, the multidimensional data knowledge base includes a basic medical data storage unit, a clinical application data storage unit, a treatment plan storage unit, and a text interpretation storage unit;

[0019] The basic medical data storage unit is used to store basic medical data including gene variation, somatic variation, germline variation, variation classification, population frequency, gene pathway and disease pathway in multi-dimensional diagnosis and treatment data;

[0020] The clinical application storage unit is used to store clinical application data including drugs, diseases, negative indications, direct action targets, indication targets, drug resistance and clinical evidence level in multi-dimensional diagnosis and treatment data;

[0021] The treatment plan storage unit is used to store the multi-dimensional diagnosis and treatment data including clinical application treatment plans and treatment plan network diagrams;

[0022] The text interpretation storage unit is used to store gene functions and pathogenic mechanisms, related treatment plans, and clinical trial results after summary and organization.

[0023] The clinical interpretation system for tumor diagnosis and treatment provided by the embodiment of the present invention has a multidimensional data knowledge base that stores and provides multidimensional diagnosis and treatment data from the two perspectives of basic medicine and clinical application, and stores the treatment plans for basic medicine and clinical application separately. The multidimensional data knowledge base not only covers comprehensive diagnosis and treatment data, but also stores the data in a classified manner, which is convenient for subsequent matching of user personalized needs.

[0024] In an optional implementation, the data processing module includes:

[0025] The calculation matching unit is used to perform functional analysis, gene feature judgment, gene variation feature analysis and calculation on the cases to be processed to obtain analysis results; match the analysis results with the multidimensional data knowledge base to obtain matching results, and provide clinical annotation information for the matching results;

[0026] Drawing unit: Based on the analysis results and matching results of the calculation matching unit, draw a population frequency bar graph of gene variation and draw a relationship network diagram.

[0027] A generation unit, used to summarize clinical annotation information, generate an interpretation report and transmit it to a central control module;

[0028] The multi-threaded comparison unit is used to compare the analysis results with external resources to provide diagnosis and treatment references for pending cases.

[0029] The clinical interpretation system for tumor diagnosis and treatment provided by the embodiment of the present invention performs functional analysis, gene feature judgment, gene variation feature analysis and calculation on the case to be treated by the calculation matching unit to obtain the analysis result; the analysis result is matched with the multidimensional data knowledge base to obtain the matching result, and clinical annotation information is provided for the matching result. The drawing unit draws the frequency bar graph of the population of gene variation and the relationship network diagram according to the analysis result and the matching result of the calculation matching unit, and provides a visual display to the user, which is conducive to the user's understanding and can meet the needs of personnel in different fields; the generation unit summarizes the clinical annotation information, generates an interpretation report and returns it, and the interpretation report contains rich and comprehensive interpretations, which can better assist clinical decision-making and save labor costs. The analysis results are compared with external resources through a multi-threaded comparison unit to provide diagnosis and treatment references for the case to be treated, and more diagnosis and treatment references are provided to users to ensure that the individual treatment of the case to be treated is optimal.

[0030] In a second aspect, an embodiment of the present invention provides a clinical interpretation method for tumor diagnosis and treatment, which is applied to the clinical interpretation system for tumor diagnosis and treatment of the first aspect or any corresponding embodiment thereof, and the clinical interpretation method includes:

[0031] Receive cases to be processed according to user needs;

[0032] After analyzing and processing the cases to be processed, the data are matched and an interpretation report is generated and returned.

[0033] The clinical interpretation method for tumor diagnosis and treatment provided by the embodiment of the present invention receives the pending cases in the user's needs, analyzes and processes the pending cases in the user's needs, matches the pending case data obtained after the analysis and processing with the multi-dimensional diagnosis and treatment data of the multi-dimensional data knowledge base to generate an interpretation report, the diagnosis and treatment data stored in the multi-dimensional data knowledge base is multi-dimensional diagnosis and treatment data, and the multi-dimensional diagnosis and treatment data is updated according to a preset time, and the interpretation report is returned to the user, which solves the problem of single database information and lack of automatic acquisition and updating of continuously accumulated new data in the prior art.

[0034] In an optional implementation, after analyzing and processing the case to be processed, matching the data, and generating an interpretation report to return includes:

[0035] Perform functional analysis, gene feature judgment, gene variation feature analysis and calculation on the cases to be processed to obtain analysis results, match the gene variation features with the multidimensional data knowledge base to obtain matching results, and provide clinical annotation information for the matching results;

[0036] Draw a population frequency bar graph of gene variation based on the gene variation characteristics in the analysis results; draw a relationship network diagram based on the matching results of gene variation characteristics and multidimensional data knowledge base;

[0037] Summarize clinical annotation information, generate an interpretation report, and send a return instruction for the interpretation report.

[0038] The clinical interpretation method for tumor diagnosis and treatment provided by the embodiment of the present invention performs functional analysis, gene feature judgment, gene variation feature analysis and calculation on the case to be treated to obtain the analysis result, matches the gene variation feature with the multidimensional data knowledge base to obtain the matching result, and provides clinical annotation information for the matching result; draws a population frequency bar chart of gene variation according to the gene variation feature analysis in the analysis result; draws a relationship network diagram according to the matching result of the gene variation feature and the multidimensional data knowledge base, and provides a visual display to the user, which is conducive to user understanding and can meet the needs of personnel in different fields; summarizes the clinical annotation information of the matching result, generates an interpretation report and returns it to the user; the interpretation report contains rich and comprehensive interpretations that can better assist clinical decision-making and save labor costs. Through the multi-threaded comparison unit, the analysis results are compared with external resources to provide diagnosis and treatment references for the case to be treated, and more diagnosis and treatment references are provided to the user, ensuring that the individual treatment of the case to be treated is optimal.

[0039] In an optional implementation, drawing a relationship network diagram based on the matching results of the gene variation characteristics and the multidimensional data knowledge base includes:

[0040] The disease type of the case to be treated is obtained according to the matching results of the gene variation characteristics and the multidimensional data knowledge base, and all genes related to it are obtained from the multidimensional data knowledge base and sorted;

[0041] Select a preset number of genes and match the relevant drugs corresponding to the preset number of genes;

[0042] The disease types, genes and drugs in the cases to be processed are taken as nodes, the first correlation between the disease types and genes, and the second correlation between genes and drugs are calculated from the gene variation data, and the first correlation and the second correlation are taken as the edge lengths;

[0043] Draw a relationship network diagram based on nodes and edge lengths.

[0044] The clinical interpretation method for tumor diagnosis and treatment provided by the embodiment of the present invention provides a relationship network diagram to provide a user with a visual display, which is conducive to user understanding and can meet the needs of people in different fields.

[0045] In a third aspect, an embodiment of the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the clinical interpretation method for tumor diagnosis and treatment of the above-mentioned second aspect or any corresponding embodiment thereof by executing the computer instructions.

[0046] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the clinical interpretation method for tumor diagnosis and treatment of the above-mentioned second aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 is a structural block diagram of a clinical interpretation system for tumor diagnosis and treatment according to an embodiment of the present invention;

[0049] Figure 2 is a structural block diagram of another clinical interpretation system for tumor diagnosis and treatment according to an embodiment of the present invention;

[0050] Figure 3 is a flow chart of a clinical interpretation method for tumor diagnosis and treatment according to an embodiment of the present invention;

[0051] Figure 4 is a flow chart of another clinical interpretation method for tumor diagnosis and treatment according to an embodiment of the present invention;

[0052] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0054] According to an embodiment of the present invention, a clinical interpretation system for tumor diagnosis and treatment is provided. Figure 1 is a structural block diagram of a clinical interpretation system for tumor diagnosis and treatment according to an embodiment of the present invention, such as Figure 1 As shown, including:

[0055] The data integration module 11 is used to collect and integrate multi-dimensional diagnosis and treatment data, and update the multi-dimensional diagnosis and treatment data according to the preset time; specifically, the preset time is not specifically limited, and can be one week, one month, or the required time. The data integration module 11 collects multi-dimensional diagnosis and treatment data from public data sources in a variety of ways, organizes the multi-dimensional diagnosis and treatment data, and updates the multi-dimensional diagnosis and treatment data according to the preset time. Multi-dimensional diagnosis and treatment data include but are not limited to genetic information, treatment plans, disease types, drug resistance, cases, samples, clinical trials, text interpretations, disease pathways, gene mutation population frequencies, gene domains, three-dimensional structures of drug molecules, and references, etc. These data can be associated with genes, treatment plans, and diseases as the center.

[0056] The multidimensional data knowledge base 12 is used to store the multidimensional diagnosis and treatment data collected and integrated by the data integration module 11; specifically, the multidimensional data knowledge base 12 stores the multidimensional diagnosis and treatment data sorted by the data integration module.

[0057] The data processing module 14 is used to receive the pending cases in the user's needs, analyze and process the pending cases, match the pending case data obtained after the analysis and processing with the multi-dimensional diagnosis and treatment data of the multi-dimensional data knowledge base to generate an interpretation report, and return the interpretation report to the user. Specifically, user needs include: user registration and login, page retrieval and query, data visualization; user data upload, interpretation report acquisition. The data processing module 14 calculates, analyzes, matches, interprets and automatically generates an interpretation report for the pending cases in the user's needs, and returns the interpretation report to the user.

[0058] In the clinical interpretation system for tumor diagnosis and treatment provided by the embodiment of the present invention, the diagnosis and treatment data stored in the multidimensional data knowledge base is multidimensional diagnosis and treatment data, the data integration module updates the multidimensional diagnosis and treatment data according to the preset time, the data processing module receives the cases to be processed in the user's needs, and analyzes and processes the cases to be processed, matches the case data to be processed obtained after the analysis and processing with the multidimensional diagnosis and treatment data in the multidimensional data knowledge base to generate an interpretation report, and returns the interpretation report to the user, thereby solving the problem of single database information and lack of automatic acquisition and update of continuously accumulated new data in the prior art.

[0059] In an optional embodiment, if Figure 1 and Figure 2 As shown, the data integration module 11 includes:

[0060] The data acquisition unit 110 is used to acquire multi-dimensional diagnosis and treatment data; specifically, acquiring multi-dimensional diagnosis and treatment data includes but is not limited to collecting multi-dimensional diagnosis and treatment data by means of web crawling, downloading, API calling, and literature acquisition. Multi-dimensional diagnosis and treatment data includes but is not limited to gene information, treatment plans, disease types, drug resistance, cases, samples, clinical trials, text interpretations, disease pathways, gene mutation population frequencies, gene domains, drug molecule three-dimensional structures, and references, etc. These data can be associated based on genes, treatment plans, and diseases. Figure 2 In the example, DB represents data transmission.

[0061] Specifically, the multi-dimensional diagnosis and treatment data collection methods include:

[0062] 1) Obtain the relationship between drug, mutation and disease from the information on targets, indications, dosage, clinical trials, etc. of targeted drugs, immune drugs and gene therapy released by authoritative organizations such as FDA (Food and Drug Administration) and NMPA (National Medical Products Administration).

[0063] 2) Extract multi-cancer mutation information of the human population from multiple public databases including the GENIE project (American Association for Cancer Research project), COSMIC (Catalogue of Cancer Somatic Mutations), NCBIgene (database for retrieving gene structure), and HGMD (Human Gene Mutation Database).

[0064] 3) Obtain cancer-related information from databases such as NCIt (National Cancer Institute), OncoTree (Cancer Classification System for Precision Oncology), and COSMIC (Catalogue of Somatic Mutations in Cancer).

[0065] 4) Obtain drug structural information from PubChem and PDB structural databases

[0066] 5) Use relevant literature from Pubmed (a biomedical literature database) to provide scientific evidence support for each drug-variant-disease association.

[0067] The data integration unit 111 is used to perform data redundancy processing on the multi-dimensional diagnosis and treatment data, and normalize the multi-dimensional diagnosis and treatment data after the data redundancy processing; specifically, the multi-dimensional diagnosis and treatment data acquired by the data acquisition unit is filtered, merged and then normalized. The specific operations are: deleting duplicate, redundant or inaccurate data, merging data from different sources but essentially the same, normalizing the names of data with different names but essentially the same, and converting them into data with a unified format to facilitate subsequent applications.

[0068] The data organization unit 112 is used to classify, grade and associate the normalized multi-dimensional diagnosis and treatment data and then transmit it to the multi-dimensional data knowledge base; specifically, the data organization unit 112 classifies, grades and associates the multi-dimensional diagnosis and treatment data, and divides gene mutations into five categories according to clinical importance: Pathogenic (disease causing), Likely Pathogenic (likely to cause disease), Likely Benign (suspected benign mutation), Benign (benign), and Uncertain (uncertain), and divides tumor case types into 84 subcategories according to the two systems of NCIt (National Cancer Institute of the United States) and OncoTree (cancer classification system for precision oncology), and associates the relationship between the three types of information: gene mutation, tumor case type, and treatment plan, and divides them into three levels of evidence: Level-1, Level-2, and Level-3 according to the approval of FDA (Food and Drug Administration) / EMA (European Medicines Agency) / NMPA (National Medical Products Administration), NCCN (National Comprehensive Cancer Network) guidelines, and clinical trial outcomes.

[0069] The data updating unit 113 is used to update the acquired multidimensional diagnosis and treatment data according to the relationship between the data version of the multidimensional data knowledge base and the data source version according to the preset time. Specifically, the data updating unit 113 updates the multidimensional diagnosis and treatment data according to the preset time, and the specific process is as follows: a. The multidimensional data knowledge base regularly sends a request to the data updating unit to determine whether the existing data version of the multidimensional data knowledge base and the data source version (the data source version refers to the data version acquired last time) are the same. If they are not the same, the update program is started. b. Based on the different restrictions and requirements of each ontology and knowledge base, the latest data version is obtained by API call and download, and then different scripts are used for conversion and loading according to the characteristics of different data sources, and Snakemake (a tool based on Python) encapsulated in the data updating unit is automatically constructed. c. According to the pre-designed rules, it is determined whether the extracted data meets the requirement standards. If it meets the requirements, it is directly passed to the data integration unit and the data organization unit for processing to update the multidimensional diagnosis and treatment data. Otherwise, a request is sent for manual verification, and it is passed to the data integration unit for distribution after being submitted to the expert for discussion, otherwise it is discarded. d. According to the type, the passed data are sent to the multidimensional data knowledge base for storage.

[0070] The data integration module 11 also includes: a data review unit 114, which corrects, checks and consults external experts on the multidimensional diagnosis and treatment data that is processed by the data organization unit and is ready to be transmitted to the multidimensional data knowledge base, including: 1) Data cleaning, retaining the main data such as drugs, mutations, diseases, clinical trials, samples, etc., and removing irrelevant data. 2) Data conversion, unifying data from different platforms and sources according to rules to facilitate comparison and screening. 3) Reviewing each piece of data, discussing rationality and correctness, and supplementing, correcting and classifying according to specifications. 4) Inviting external translational medicine experts to conduct review and correction processing, etc., can improve the accuracy and reliability of the multidimensional diagnosis and treatment data stored in the multidimensional data knowledge base.

[0071] In an optional embodiment, if Figure 1 and Figure 2 As shown, the multidimensional data knowledge base 12 includes a basic medical data storage unit 120, a clinical application data storage unit 121, a treatment plan storage unit 122 and a text interpretation storage unit 123; specifically, the multidimensional data knowledge base 12 provides multidimensional diagnosis and treatment data from the two perspectives of basic medicine and clinical application. The multidimensional diagnosis and treatment data not only includes conventional basic medical data such as gene variation, variation classification, population frequency, gene pathway, disease pathway disease, drug resistance, cases, samples, etc., but also establishes clinical application data of drugs, diseases, negative indications, direct action targets, indication targets, drug resistance, clinical evidence level, summary text interpretation, and automatic literature capture, and also includes basic medical treatment plans and clinical application treatment plans contained in the multidimensional diagnosis and treatment data. The above data are stored in the basic medical data storage unit, the clinical application data storage unit, and the treatment plan storage unit according to the basic medical data, clinical application data, and diagnosis and treatment plan.

[0072] Specifically, the basic medical data storage unit is used to store basic medical data including gene variation, variation classification, population frequency, gene pathway and disease pathway in multi-dimensional diagnosis and treatment data;

[0073] The clinical application storage unit is used to store clinical application data including drugs, diseases, negative indications, direct action targets, indication targets, drug resistance and clinical evidence level in multi-dimensional diagnosis and treatment data;

[0074] The treatment plan storage unit is used to store the clinical application treatment plan and the treatment plan network diagram included in the multi-dimensional diagnosis and treatment data;

[0075] The text interpretation storage unit is used to summarize and store gene functions and pathogenic mechanisms, related treatment plans, and clinical trial results. Specifically, the text interpretation storage unit manually summarizes and organizes gene functions and pathogenic mechanisms, related treatment plans, and clinical trial results, and forms a comprehensive and general text explanation, including: screening genes with recorded data, selecting high-frequency mutations, and hotspot driver genes; conducting a large amount of literature research on the above genes, summarizing the latest functional descriptions and published clinically treatable plans; discussing and reviewing the summary content to decide whether to pass or modify it. The content is entered into the interpretation report as supporting text for user understanding.

[0076] In an optional embodiment, if Figure 1 and Figure 2 As shown, the data processing module 14 includes:

[0077] The calculation matching unit 140 is used to perform functional analysis, gene feature judgment, gene variation feature analysis and calculation on the case to be processed to obtain the analysis result; match the analysis result with the multidimensional data knowledge base to obtain the matching result, and provide clinical annotation information for the matching result; draw a population frequency bar chart of gene variation and a relationship network diagram according to the analysis result, and draw a relationship network diagram according to the matching result; specifically, match the entity of gene variation, gene variation feature, disease, or treatment plan with the multidimensional data knowledge base, and provide the matched entity with various clinical annotation information in the multidimensional data knowledge base, including gene variation, treatment plan, tumor subtype, drug resistance, clinical trial, disease pathway, gene variation population frequency, references, and text interpretation information. The analysis matching result refers to the disease type, gene and matching therapeutic drug in the case to be processed obtained after performing functional analysis, gene feature judgment, gene variation feature analysis and calculation on the case to be processed, as well as the correlation between the disease type and gene, and between the gene and drug.

[0078] Drawing unit 141 is used to draw a population frequency bar chart of gene mutation according to the gene mutation feature analysis in the analysis results, and draw a relationship network diagram according to the drug and disease information in the matching results. Specifically, the disease types of the cases to be treated are obtained according to the results of functional analysis, gene feature judgment, and gene mutation feature analysis, and all genes related to them are obtained from the multidimensional data knowledge base and sorted; a preset number of genes are selected, and the relevant drugs corresponding to the preset number of genes are matched; the disease types, genes, and drugs in the cases to be treated are used as nodes, and the first correlation between the disease types and genes and the second correlation between genes and drugs are calculated from the gene mutation data, and the first correlation and the second correlation are used as the edge length; a relationship network diagram is drawn according to the nodes and the edge lengths. The drug-gene-disease interaction network is displayed using the interactive network modeling method. The tumor classification structure is displayed using the hierarchical tree method. According to the tumor classification and grading data of oncoTree, the superior-subordinate relationship of each tumor type is recursively obtained, and this relationship is modeled as a tree structure, and a hierarchical tree is drawn for display. The three-dimensional structure of the drug is displayed using the Molstar software module), and online operation and preliminary structural analysis can be performed. The text and serialization information of the drug 3D structure is obtained from the PDB database using the API application program interface or direct download, stored in the MySQL (relational database management system) database, and then transmitted to the front-end Molstar to display the 3D structure.

[0079] The generation unit 142 is used to summarize the clinical annotation information, generate an interpretation report and transmit it to the central control module; specifically, the clinical annotation information of various gene variations (including but not limited to SNV (single nucleic acid variation), CNV (copy number variation), SV (structural variation), TMB (tumor mutation burden), MSI (microsatellite instability), mutation signature (mutation fingerprint), MMR (mismatch repair) gene variation, HRR (homologous recombination repair) of each case to be processed) is summarized and an interpretation report is automatically generated.

[0080] The multi-threaded comparison unit 143 is used to compare the analysis results with external resources to provide diagnosis and treatment references for pending cases. Specifically, the treatment plans and indications corresponding to the gene mutations in the analysis results are compared with external resources to provide users with more references. For example: through multi-threaded calls to the APIs of other knowledge bases or downloading corresponding data to the data integration module, the background program is used to process the data downloaded from external resources and compare them with the same dimensions of the multidimensional data knowledge base, and the data downloaded from external resources are output together to the central control module, and the comparison results will be included in the output interpretation report. External resources include links to external public resources for entities such as genes, diseases, drugs, and pathways and lists of related literature retrievals.

[0081] In an optional embodiment, if Figure 1 and Figure 2 As shown, the clinical interpretation system for tumor diagnosis and treatment further includes: a central control module 13 and a client service module 15 , and the central control module 13 is communicatively connected with the client service module 15 .

[0082] The client service module 15 is used to receive and return user needs. User needs include: user registration and login, page retrieval and query, data visualization; user data upload, interpretation report acquisition. User registration and login, page retrieval and query, and data visualization are implemented using Web applications, including: user identity authentication and authority allocation; receiving user queries and responding; user data collection, return data output and graphic output; log management. When the user retrieves data, the corresponding multi-dimensional diagnosis and treatment data is obtained from the multi-dimensional data knowledge base for calculation, modeling or visualization, and the output is returned to the client service module in the form of text, tables, charts, files, etc. for display.

[0083] When the user wants to obtain the interpretation report of the pending case in the user's needs, the client service module transmits the user's needs to the central control module and sends a control instruction to the data processing module. After automatically processing, calculating and analyzing the pending cases in the user's needs, the first-level and second-level characteristics of the genome of the pending cases are comprehensively analyzed to provide the most reasonable treatment plan and medication explanation. Specifically: extract the gene variation information in the pending cases and annotate them, and compare and screen them with the variations in the multidimensional data knowledge base. Comprehensively evaluate tumor markers based on the variation characteristics, screen the treatment information that meets the requirements, and transmit it to the multi-threaded comparison unit to obtain similar case information from other external resources. Statistical similar disease group data, draw the drug-gene-disease relationship network diagram and population frequency bar chart through the drawing unit of the data processing module, and generate an interpretation report and return it to the customer service module for users.

[0084] The central control module 13 is used to schedule and process user needs, and send control instructions to the data processing module according to user needs; specifically, the central control module 13 is used to communicate with users, effectively schedule the acquisition, distribution, packaging, and storage tasks of user needs, and send control instructions to the data processing module according to user needs. The control instructions can be analysis and processing of cases to be processed, etc., to improve the communication efficiency with the data processing module 14 and the user's response speed.

[0085] This embodiment also provides a clinical interpretation method for tumor diagnosis and treatment, which is applied to a clinical interpretation system for tumor diagnosis and treatment. Figure 3 is a flow chart of a clinical interpretation method for tumor diagnosis and treatment according to an embodiment of the present invention, such as Figure 3As shown, the process includes the following steps:

[0086] Step S101, receiving the pending cases in user needs; specifically, when the user wants to obtain the interpretation report of the pending cases in user needs, the client service module transmits the user needs to the central control module and sends a control instruction to the data processing module, so that the pending cases in user needs can be obtained.

[0087] Step S102, after analyzing and processing the case to be processed, the data is matched and an interpretation report is generated and returned.

[0088] Specifically, the calculation and matching unit performs functional analysis, gene feature judgment, gene variation feature analysis and calculation on the cases to be processed to obtain the analysis results, matches the gene variation features with the multidimensional data knowledge base to obtain the matching results, and provides clinical annotation information for the matching results; the drawing unit draws a population frequency bar chart of gene variation according to the gene variation feature analysis in the analysis results, and draws a relationship network diagram according to the drug and disease information in the matching results, providing users with a visual display, which is conducive to user understanding and can meet the needs of people in different fields; the generation unit summarizes the clinical annotation information, generates an interpretation report and transmits it to the central control module, and returns it to the user through the central control module; the interpretation report contains rich and comprehensive interpretations that can better assist clinical decision-making and save labor costs.

[0089] The clinical interpretation method for tumor diagnosis and treatment provided by the embodiment of the present invention receives the pending cases in the user's needs, analyzes and processes the pending cases in the user's needs, matches the pending case data obtained after the analysis and processing with the multi-dimensional diagnosis and treatment data of the multi-dimensional data knowledge base to generate an interpretation report, the diagnosis and treatment data stored in the multi-dimensional data knowledge base is multi-dimensional diagnosis and treatment data, and the multi-dimensional diagnosis and treatment data is updated according to a preset time, and the interpretation report is returned to the user, which solves the problem of single database information and lack of automatic acquisition and updating of continuously accumulated new data in the prior art.

[0090] In this embodiment, a clinical interpretation method for tumor diagnosis and treatment is provided, which can be used in the above-mentioned mobile terminals, such as mobile phones, tablet computers, etc. Figure 4 is a flow chart of a clinical interpretation method for tumor diagnosis and treatment according to an embodiment of the present invention, such as Figure 4 As shown, the process includes the following steps:

[0091] Step S201: Receive cases to be processed in user requirements. Figure 3 Step S101 of the illustrated embodiment will not be described in detail here.

[0092] Step S202, after analyzing and processing the case to be processed, the data is matched and an interpretation report is generated and returned.

[0093] Specifically, the above step S202 includes:

[0094] Step S2021, perform functional analysis, gene feature judgment, gene variation feature analysis and calculation on the case to be processed, obtain analysis results, match the gene variation features with the multidimensional data knowledge base, obtain matching results, and provide clinical annotation information for the matching results. Specifically, the clinical annotation information includes gene variation, treatment plan, tumor subtype, drug resistance, clinical trials, disease pathways, gene variation population frequency, references, text interpretation information, etc.

[0095] Step S2022, draw a population frequency bar graph of gene variation according to the gene variation feature analysis in the analysis results; draw a relationship network diagram according to the matching results of the gene variation feature and the multidimensional data knowledge base. Specifically, draw a population frequency bar graph of gene variation and a relationship network diagram according to the analysis results and the matching results, and provide a visual display to the user, which is conducive to the user's understanding and can meet the needs of people in different fields.

[0096] In some optional embodiments, the above step S2022 includes:

[0097] Step a1, obtaining the disease type of the case to be processed based on the matching results of the gene variation characteristics and the multidimensional data knowledge base, and obtaining all genes related to it from the multidimensional data knowledge base and sorting them.

[0098] Step a2, select a preset number of genes, and match the relevant drugs corresponding to the preset number of genes. Specifically, the preset number of genes can be set to the first fifteen genes, and all the relevant drugs of the first fifteen genes are matched in the multidimensional data knowledge base.

[0099] Step a3, taking the disease types, genes and drugs in the cases to be processed as nodes, calculating the first correlation between the disease types and genes, and the second correlation between genes and drugs from the gene variation data, and taking the first correlation and the second correlation as the edge length. Specifically, the size of the node is regarded as the importance of the node, and the thickness of the edge is regarded as the size of the correlation with the node.

[0100] Step a4, draw a relationship network diagram based on the nodes and edge lengths. Specifically, the nodes of disease type, gene and drug, as well as the edge lengths of the first correlation between disease type and gene, and the second correlation between gene and drug are input into the drawing software, and a relationship network diagram reflecting the relationship between drug-gene-disease is automatically drawn.

[0101] Step S2023, summarize the clinical annotation information, generate an interpretation report, and send a return instruction for the interpretation report. Specifically, the generation unit summarizes the clinical annotation information, generates an interpretation report and transmits it to the central control module, and returns it to the user through the central control module; the interpretation report contains rich and comprehensive interpretations that can better assist clinical decision-making and save labor costs.

[0102] The clinical interpretation method for tumor diagnosis and treatment provided by the embodiment of the present invention provides a relationship network diagram to provide a user with a visual display, which is conducive to user understanding and can meet the needs of people in different fields.

[0103] The embodiment of the present invention also provides a computer device. Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0104] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0105] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0106] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0107] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0108] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0109] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0110] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A clinical interpretation system for tumor diagnosis and treatment, characterized in that: The clinical interpretation system comprises: The data integration module is used to collect and integrate multi-dimensional diagnosis and treatment data, and update the multi-dimensional diagnosis and treatment data according to the preset time; Multidimensional data knowledge base, used to store multidimensional diagnosis and treatment data collected and integrated by the data integration module; The data processing module is used to receive the cases to be processed in the user's needs, analyze and process the cases to be processed, match the case data to be processed obtained after the analysis and processing with the multi-dimensional diagnosis and treatment data of the multi-dimensional data knowledge base to generate an interpretation report, and return the interpretation report to the user; The data processing module comprises: The calculation matching unit is used to perform functional analysis, gene feature judgment, gene variation feature analysis and calculation on the cases to be processed to obtain analysis results; match the analysis results with the multidimensional data knowledge base to obtain matching results, and provide clinical annotation information for the matching results; Drawing unit: draw a population frequency bar graph of gene variation and a relationship network diagram according to the analysis result and the matching result of the calculation and matching unit; wherein, draw a population frequency bar graph of gene variation according to the gene variation feature analysis in the analysis result, and draw a relationship network diagram according to the drug and disease information in the matching result; obtain the disease type of the case to be processed according to the functional analysis, gene feature judgment, and gene variation feature analysis results, and obtain all genes related thereto from the multidimensional data knowledge base and sort them; select a preset number of genes, and match the relevant drugs corresponding to the preset number of genes; use the disease type, gene, and drug in the case to be processed as nodes, calculate the first correlation between the disease type and the gene, and the second correlation between the gene and the drug from the gene variation data, and connect the first correlation and the second correlation degree as the edge length; draw a relationship network diagram based on nodes and edge lengths; the size of the node is regarded as the importance of the node, and the thickness of the edge length is regarded as the size of the node correlation; use the interaction network modeling method to display the drug-gene-disease interaction network; use the hierarchical tree method to display the tumor classification structure; according to the tumor classification and grading data of oncoTree, recursively obtain the superior-subordinate relationship of each tumor type, model the superior-subordinate relationship as a tree structure, and draw a hierarchical tree to display it; use the Molstar software module to display the three-dimensional structure of the drug, and perform online operation and preliminary structural analysis; use the API application interface or directly download to obtain the text and serialization information of the drug 3D structure from the PDB database and store it in the mysql database, and then transmit it to the front-end Molstar to display the 3D structure; A generating unit, used to summarize the clinical annotation information, generate an interpretation report and transmit it to a central control module; The multi-threaded comparison unit is used to compare the analysis results with external resources to provide diagnosis and treatment references for pending cases; through multi-threaded calls to the APIs of other knowledge bases or downloading corresponding data to the data integration module, the background program is used to process the data downloaded from external resources and compare them with the same dimensions of the multidimensional data knowledge base, and the data downloaded from external resources are output to the central control module. The comparison results will be included in the output interpretation report; external resources include links to external public resources for entities such as genes, diseases, drugs, and pathways and lists of related literature retrieval.

2. The system according to claim 1, characterized in that The data integration module includes: A data acquisition unit, used to acquire multi-dimensional diagnosis and treatment data; A data integration unit, used for performing data redundancy processing on the multi-dimensional diagnosis and treatment data, and normalizing the multi-dimensional diagnosis and treatment data after the data redundancy processing; A data organization unit, used for classifying, grading and associating the normalized multi-dimensional diagnosis and treatment data and then transmitting the data to the multi-dimensional data knowledge base; The data updating unit is used to update the acquired multi-dimensional diagnosis and treatment data according to the relationship between the data version of the multi-dimensional data knowledge base and the data source version at a preset time.

3. The system according to claim 1, characterized in that The multidimensional data knowledge base includes a basic medical data storage unit, a clinical application data storage unit, a treatment plan storage unit and a text interpretation storage unit; The basic medical data storage unit is used to store basic medical data including gene variation, somatic variation, germline variation, variation classification, population frequency, gene pathway and disease pathway in multi-dimensional diagnosis and treatment data; The clinical application data storage unit is used to store clinical application data including drugs, diseases, negative indications, direct action targets, indication targets, drug resistance and clinical evidence levels in multi-dimensional diagnosis and treatment data; The treatment plan storage unit is used to store the multi-dimensional diagnosis and treatment data including clinical application treatment plans and treatment plan network diagrams; The text interpretation storage unit is used to store the gene functions and pathogenic mechanisms, the associated treatment plans, and the clinical trial results after being summarized and sorted.

4. A clinical interpretation method for tumor diagnosis and treatment, characterized in that: A clinical interpretation system for tumor diagnosis and treatment applied to any one of claims 1 to 3, the method comprising: Receive cases to be processed according to user needs; After analyzing and processing the cases to be processed, the data are matched and an interpretation report is generated and returned.

5. The method according to claim 4, characterized in that After analyzing and processing the cases to be processed, the data is matched and an interpretation report is generated and returned including: Perform functional analysis, gene feature judgment, gene variation feature analysis and calculation on the cases to be processed to obtain analysis results; match the gene variation features with the multidimensional data knowledge base to obtain matching results, and provide clinical annotation information for the matching results; Draw a population frequency bar graph of gene variation based on the gene variation characteristics in the analysis results; draw a relationship network diagram based on the matching results of gene variation characteristics and multidimensional data knowledge base; The clinical annotation information is summarized, an interpretation report is generated, and a return instruction for the interpretation report is sent.

6. The method according to claim 5, characterized in that Drawing a relationship network diagram based on the matching results of gene variation characteristics and multidimensional data knowledge base includes: The disease type of the case to be treated is obtained according to the matching results of the gene variation characteristics and the multidimensional data knowledge base, and all genes related to the disease are obtained from the multidimensional data knowledge base and sorted; Select a preset number of genes and match the relevant drugs corresponding to the preset number of genes; The disease types, genes and drugs in the cases to be processed are taken as nodes, the first correlation between the disease types and genes, and the second correlation between genes and drugs are calculated from the gene variation data, and the first correlation and the second correlation are taken as the edge lengths; Draw a relationship network diagram based on the nodes and edge lengths.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the clinical interpretation method for tumor diagnosis and treatment according to any one of claims 4 to 6 by executing the computer instructions.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the clinical interpretation method for tumor diagnosis and treatment according to any one of claims 4 to 6.

Images