Key index identification method, system and equipment for polygene diseases and medium

Abstract

The invention discloses a key index identification method, system and device for a polygene disease and a medium, and the method comprises the steps: obtaining whole exon sequencing original data of a target object, and carrying out the data preprocessing, and obtaining a first processing data set; obtaining an original feature data set according to the first processing data set; according to the first mutation frequency number and the second mutation frequency number, performing preliminary screening and extraction on the original feature data set to obtain a representative mutation gene set and a representative mutation site set; a canonical correlation analysis model is adopted to analyze a first correlation representing the mutation gene set and the mutation type and a second correlation representing the mutation site and the mutation type, and a mutation gene canonical variable group and a mutation site canonical variable group are obtained; and determining key indexes according to the mutation gene typical variable group and the mutation site typical variable group. The key indexes of the polygene diseases can be efficiently and accurately identified, and the method can be widely applied to the technical field of data processing.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, system, device and medium for identifying key indicators of polygenic diseases. Background Art

[0002] Polygenic diseases involve interactions between multiple mutant genes and mutation sites. Traditionally, the diagnosis of such diseases mainly relies on doctors' comprehensive judgment based on clinical symptoms, laboratory test results, and medical history. However, this diagnostic method may be subjective, dependent on doctors' experience, and time-consuming. Based on these problems, key indicators are currently introduced in combination with genetic testing technology: key mutant genes and mutation sites, and test subjects with key mutant genes and mutation sites are judged as belonging to the high-risk population for the disease.

[0003] The commonly used method for detecting key indicators in the existing technology is whole-genome association analysis in the field of bioinformatics. However, whole-genome association analysis mainly focuses on the association between a single gene and a disease or characteristic, and does not directly consider the relationship between multiple genes and multiple sites. It will ignore the complex interactions between multiple genes and multiple sites. In small sample studies, whole-genome association analysis tends to detect common mutations and may not be able to fully explore the impact of low-frequency mutations on the disease. In addition, the whole-genome association analysis process is complex and difficult to implement. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to provide a method, system, device and medium for identifying key indicators of polygenic diseases with high accuracy and high identification efficiency.

[0005] To achieve the above purpose, one aspect of the embodiments of the present application provides a method for identifying key indicators of polygenic diseases, the method comprising:

[0006] Acquire whole exome sequencing raw data of the target object, and perform data preprocessing on the whole exome sequencing raw data to obtain a first processed data set;

[0007] Determine, according to the first processed data set, a first mutation frequency of the target object at each first mutation site of the first mutant gene detected, and a second mutation frequency of the target object under each mutation type, to obtain an original feature data set;

[0008] Preliminarily screening and extracting the original feature data set according to the first mutation frequency and the second mutation frequency to obtain a representative mutation gene set and a representative mutation site set;

[0009] A canonical correlation analysis model is used to analyze the first correlation between the representative mutant gene set and the mutation type and the second correlation between the representative mutation site and the mutation type to obtain a mutant gene typical variable group and a mutation site typical variable group;

[0010] Key indicators are determined based on the typical variable group of mutant genes and the typical variable group of mutation sites; wherein the key indicators include key mutant genes and key mutation sites.

[0011] In some embodiments, the step of obtaining raw data of whole exome sequencing of a target object and performing data preprocessing on the raw data of whole exome sequencing to obtain a first processed data set includes:

[0012] Integrate and deduplicate the whole exome sequencing raw data of the target object to obtain an initial processed data set;

[0013] Determining the mutation type variable value in the initial processing data set according to the mutation type; wherein the mutation type includes one of a missense mutation, a synonymous mutation, a non-stop mutation, a nonsense mutation, and a splice site mutation;

[0014] The mutation type variable value, the first mutation gene and the first mutation site in the initial processed data set are extracted to obtain a first processed data set.

[0015] In some embodiments, the initial screening and extraction of the original feature data set based on the first mutation frequency and the second mutation frequency to obtain a representative mutation gene set and a representative mutation site set includes:

[0016] For the first mutant genes having the first characteristic in the first mutant gene set, an operation of removing and retaining one of the first mutant genes is performed to obtain a second mutant gene set;

[0017] taking a second mutant gene in the second mutant gene set whose correlation with the second mutation frequency is higher than a first preset value as a representative mutant gene, to obtain a representative mutant gene set;

[0018] For the first mutation sites with the second characteristic in the first mutation site set, an operation of removing and retaining one of the first mutation sites is performed to obtain a second mutation site set;

[0019] A second mutation site in the second mutation site set whose correlation with the second mutation frequency is higher than a second preset value is taken as a representative mutation site to obtain a representative mutation site set.

[0020] In some embodiments, in the step of using a canonical correlation analysis model to analyze the first correlation between the representative mutant gene set and the mutation type and the second correlation between the representative mutation site and the mutation type to obtain a mutant gene typical variable group and a mutation site typical variable group, the working steps of the canonical correlation analysis model include:

[0021] Calculating the degree of linear relationship of the representative data set to obtain a covariance matrix; wherein the representative data set is a representative mutant gene set or a representative mutation site set;

[0022] Performing an inverse operation on the covariance matrix to obtain an inverse matrix;

[0023] Calculating the generalized eigenvalues ​​of the inverse matrix;

[0024] The eigenvector with the largest eigenvalue is used as the target typical variable; wherein the target typical variable is a mutant gene typical variable or a mutation site typical variable;

[0025] Calculate the first coefficient of the target typical variable on the original variable;

[0026] According to the generalized eigenvalue and the first coefficient, the typical correlation coefficient between the target typical variables is calculated to obtain a target typical variable group; wherein the target typical variable group includes a mutant gene typical variable group and a mutation site typical variable group.

[0027] In some embodiments, determining key indicators based on the mutant gene typical variable group and the mutation site typical variable group includes:

[0028] The Wilkes statistic test method is used to evaluate whether the correlation between the target typical variables of the target typical variable group is significant, and the test results are obtained;

[0029] Based on the canonical correlation coefficient between the test result and the target canonical variable, determine the target canonical variable with the highest correlation significance and correlation as the selected canonical variable;

[0030] calculating a first correlation coefficient between the selected canonical variable and a representative data set;

[0031] Determining important mutation genes or important mutation sites according to the first correlation coefficient;

[0032] Calculate the second correlation between the important mutation gene and the mutation type, and determine the key mutation gene according to the second correlation; or calculate the third correlation between the important mutation site and the mutation type, and determine the key mutation site according to the third correlation.

[0033] In some embodiments, the method further comprises:

[0034] The key indicator identification results are displayed through the front-end display page.

[0035] In some embodiments, the method further comprises:

[0036] The whole exome sequencing raw data and the key indicator identification results are stored in a database.

[0037] To achieve the above purpose, another aspect of the embodiment of the present application provides a key indicator identification system for polygenic diseases, the system comprising:

[0038] The first module is used to obtain the original data of whole exome sequencing of the target object, and perform data preprocessing on the original data of whole exome sequencing to obtain a first processed data set;

[0039] A second module is used to determine, according to the first processed data set, a first mutation frequency of the target object at each first mutation site of the first mutant gene detected, and a second mutation frequency of the target object under each mutation type, to obtain an original feature data set;

[0040] A third module is used to preliminarily screen and extract the original feature data set according to the first mutation frequency and the second mutation frequency to obtain a representative mutation gene set and a representative mutation site set;

[0041] The fourth module is used to analyze the first correlation between the representative mutant gene set and the mutation type and the second correlation between the representative mutation site and the mutation type using a typical correlation analysis model to obtain a mutant gene typical variable group and a mutation site typical variable group;

[0042] The fifth module is used to determine key indicators based on the typical variable group of the mutant gene and the typical variable group of the mutation site; wherein the key indicators include key mutant genes and key mutation sites.

[0043] It should be noted that, in some embodiments, the system may further include at least one of the following modules:

[0044] The sixth module is used to display the key indicator identification results through the front-end display page.

[0045] The seventh module is used to store the whole exome sequencing raw data and the key indicator identification results through a database.

[0046] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above-mentioned method when executing the computer program.

[0047] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0048] The embodiments of the present application include at least the following beneficial effects: The present application provides a method, system, device and medium for identifying key indicators of polygenic diseases. The scheme can find out the correlation between mutant genes and the mutual relationship between mutation sites by preliminary screening and typical correlation analysis of the original data of whole exome sequencing of the target object, and then efficiently and accurately identify the key indicators of polygenic diseases. It is suitable for small samples and has low implementation difficulty, which helps to provide doctors with immediate and objective diagnostic auxiliary information and improve the quality of auxiliary diagnosis and treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide further understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0050] Figure 1 This is a flow chart of a method for identifying key indicators of a polygenic disease provided in an embodiment of the present application;

[0051] Figure 2 It is a schematic diagram of the process of screening representative mutant genes or representative mutation sites provided in the embodiments of the present application;

[0052] Figure 3 It is a schematic diagram of the steps of a typical correlation analysis calculation provided in an embodiment of the present application;

[0053] Figure 4 This is a schematic diagram of the steps for screening key mutant genes or key mutation sites provided in the embodiments of the present application;

[0054] Figure 5 It is a hierarchical flow chart for automatic identification of key indicators of hyperthyroidism based on canonical correlation analysis provided in an embodiment of the present application;

[0055] Figure 6 is a schematic diagram of a front-end user interface provided in an embodiment of the present application;

[0056] Figure 7 It is a ROC curve diagram of the experimental result classification verification provided in the embodiment of the present application;

[0057] Figure 8 This is a schematic diagram of the structure of a key indicator identification system for polygenic diseases provided in an embodiment of the present application;

[0058] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0060] Although the functional modules are divided in the system schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first / S100", "second / S200", etc. in the specification, claims and the above drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0061] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0062] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0063] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0065] In related technologies, a commonly used method for detecting key indicators is whole-genome association analysis in the field of biological information. However, whole-genome association analysis mainly focuses on the association between a single gene and a disease or characteristic, and does not directly consider the relationship between multiple genes and multiple sites, and ignores the complex interactions between multiple genes and multiple sites. In small sample studies, whole-genome association analysis tends to detect common mutations and may not be able to fully explore the impact of low-frequency mutations on the disease. In addition, the process of whole-genome association analysis is complex and difficult to implement.

[0066] In view of this, a method, system, device and medium for identifying key indicators of polygenic diseases are provided in the embodiments of the present application. The scheme can find out the correlation between mutant genes and the mutual relationship between mutation sites by preliminary screening and typical correlation analysis of the original data of whole exome sequencing of the target object, and then efficiently and accurately identify the key indicators of polygenic diseases. It is suitable for small samples and has low implementation difficulty, which helps to provide doctors with immediate and objective diagnostic auxiliary information and improve the quality of auxiliary diagnosis and treatment.

[0067] A method for identifying a key indicator of a polygenic disease provided in an embodiment of the present application relates to the field of data processing technology. A method for identifying a key indicator of a polygenic disease provided in an embodiment of the present application can be applied to a terminal, can be applied to a server, or can be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured to provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and cloud servers for basic cloud computing services such as big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements a method for identifying a key indicator of a polygenic disease, etc., but is not limited to the above forms.

[0068] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0069] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on user information, user behavior data, user historical data, user location information, user genetic information and other data related to user identity or characteristics, the user's permission or consent will be obtained first, and the collection, use and processing of these data will comply with relevant laws, regulations and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or jump to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0070] Figure 1This is an optional flow chart of a key indicator identification method for a polygenic disease provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S100 to S500.

[0071] Step S100, obtaining whole exome sequencing raw data of a target object, and performing data preprocessing on the whole exome sequencing raw data to obtain a first processed data set;

[0072] Step S200, determining, according to the first processed data set, a first mutation frequency of the target object at each first mutation site of a first mutant gene detected, and a second mutation frequency of the target object under each mutation type, to obtain an original feature data set;

[0073] Step S300, preliminarily screening and extracting the original feature data set according to the first mutation frequency and the second mutation frequency to obtain a representative mutation gene set and a representative mutation site set;

[0074] Step S400, using a canonical correlation analysis model to analyze the first correlation between the representative mutant gene set and the mutation type and the second correlation between the representative mutation site and the mutation type, to obtain a mutant gene typical variable group and a mutation site typical variable group;

[0075] Step S500, determining key indicators according to the typical variable group of the mutant gene and the typical variable group of the mutation site; wherein the key indicators include key mutant genes and key mutation sites.

[0076] Steps S100 to S500 shown in the embodiment of the present application, by combining the patient's genetic data and utilizing the principle that different mutation types have different degrees of impact on patients, use the method of canonical correlation analysis to find out the correlation between mutant genes and the mutual relationship between mutation sites, thereby efficiently and accurately identifying the key indicators of polygenic diseases. This method is suitable for small samples and has low implementation difficulty, which helps to provide doctors with immediate and objective diagnostic auxiliary information and improve the quality of auxiliary diagnosis and treatment.

[0077] In some embodiments, step S100 may include but is not limited to steps S110 to S130:

[0078] Step S110 , integrating and deduplicating the original data of whole exome sequencing of the target object to obtain an initial processed data set.

[0079] Step S120, determining the mutation type variable value in the initial processing data set according to the mutation type; wherein the mutation type includes one of a missense mutation, a synonymous mutation, a non-stop mutation, a nonsense mutation, and a splice site mutation.

[0080] Step S130, extracting the mutation type variable value, the first mutation gene and the first mutation site in the initial processing data set to obtain a first processing data set.

[0081] In some embodiments, step S300 may include but is not limited to the following steps S310 to S340:

[0082] Step S310, for the first mutant genes with the first characteristic in the first mutant gene set, an operation of removing and retaining one of the first mutant genes is performed to obtain a second mutant gene set;

[0083] Step S320, taking the second mutant gene in the second mutant gene set whose correlation with the second mutation frequency is higher than the first preset value as a representative mutant gene, to obtain a representative mutant gene set;

[0084] Step S330, for the first mutation sites with the second characteristic in the first mutation site set, an operation of removing and retaining one of the first mutation sites is performed to obtain a second mutation site set;

[0085] Step S340: taking the second mutation site in the second mutation site set whose correlation with the second mutation frequency is higher than the second preset value as a representative mutation site to obtain a representative mutation site set.

[0086] Through the above steps S310 to S340, the original feature data set can be analyzed and screened to obtain a set of representative mutant genes and representative mutation sites for further canonical correlation analysis.

[0087] In some embodiments, step S400 may include but is not limited to the following steps S410 to S460:

[0088] Step S410, calculating the degree of linear relationship of the representative data set to obtain a covariance matrix; wherein the representative data set is a representative mutant gene set or a representative mutation site set;

[0089] Step S420, performing an inverse operation on the covariance matrix to obtain an inverse matrix;

[0090] Step S430, calculating the generalized eigenvalues ​​of the inverse matrix;

[0091] Step S440, taking the eigenvector with the largest eigenvalue as the target typical variable; wherein the target typical variable is the mutant gene typical variable or the mutation site typical variable;

[0092] Step S450, calculating the first coefficient of the target typical variable on the original variable;

[0093] Step S460, calculating the typical correlation coefficient between the target typical variables according to the generalized eigenvalue and the first coefficient, and obtaining the target typical variable group; wherein the target typical variable group includes the mutant gene typical variable group and the mutation site typical variable group.

[0094] Through the above steps S410 to S460, the target typical variable obtained has the greatest correlation and can be used to study the relationship between the mutant gene and the mutation type and the relationship between the mutation site and the mutation type.

[0095] In some embodiments, step S500 may include but is not limited to the following steps S510 to S550:

[0096] Step S510, using the Wilkes statistic test method to evaluate whether the correlation between the target typical variables of the target typical variable group is significant, and obtaining a test result.

[0097] Specifically, the Wilk's Lambda test method is used to calculate the proportion of intra-group variation in the total variation, and to evaluate whether the correlation between the target typical variables of the target typical variable group is significant. The smaller the value of the statistic, the smaller the corresponding p-value. When the p-value corresponding to the statistic is less than 0.05, it means that the correlation is significant, and the test result is obtained.

[0098] Step S520, based on the canonical correlation coefficient between the test result and the target canonical variable, determine the target canonical variable with the highest correlation significance and correlation as the selected canonical variable.

[0099] Step S530, calculating a first correlation coefficient between the selected typical variable and the representative data set.

[0100] Step S540, determining important mutation genes or important mutation sites according to the first correlation coefficient.

[0101] Step S550, calculating the second correlation between the important mutation gene and the mutation type, and determining the key mutation gene according to the second correlation; or calculating the third correlation between the important mutation site and the mutation type, and determining the key mutation site according to the third correlation.

[0102] Through the above steps S510 to S550, the key indicators can be effectively determined by utilizing the results of the canonical correlation analysis in combination with the correlation test and the canonical structure analysis.

[0103] In some embodiments, the following steps S600 to S700 may also be included:

[0104] Step S600, obtaining the whole exome sequencing raw data through the front-end display page; and displaying the key indicator identification result through the front-end display page.

[0105] Displaying the page on the front end facilitates the acquisition and presentation of data and improves the user experience.

[0106] Step S700, storing the whole exome sequencing raw data and key indicator identification results in a database.

[0107] Storing data in a database helps ensure the security and availability of data.

[0108] Below, in conjunction with a specific application example of identifying key indicators of polygenic diseases, the solution of the embodiment of the present invention is described in detail and explained:

[0109] In an embodiment of the present application, a method for identifying key indicators of polygenic diseases is provided. The method can be applied to identifying key indicators of polygenic diseases. Taking hyperthyroidism as an example, hyperthyroidism is a polygenic disease involving interactions between multiple mutant genes and mutation sites.

[0110] In identifying key indicators of a polygenic disease such as hyperthyroidism, the application may include the following steps:

[0111] (1) Obtaining raw data of whole exome sequencing of hyperthyroidism patients and performing a series of preprocessing on the raw data to obtain a first processed data set.

[0112] Specifically, whole exome sequencing is performed on samples related to hyperthyroidism patients to obtain the raw data of whole exome sequencing, which can also be imported or input by doctors from the front-end display page. The raw data files of whole exome sequencing of each hyperthyroidism patient are integrated into the same data set, and the mutation type variable values ​​in the data set are converted into one of missense mutations, synonymous mutations, non-stop mutations, nonsense mutations, and splice site mutations. The mutation type, mutant gene, mutation site characteristics and other data in the data are extracted as the first processing data set. In most cases, nonsense mutations have the greatest impact on patients, followed by non-stop mutations, splice site mutations, missense mutations and synonymous mutations.

[0113] (2) Determine, based on the first processed data set, the first mutation frequency of the hyperthyroidism patient at the first mutation site of each detected first mutant gene, and the second mutation frequency of the hyperthyroidism patient under each mutation type, to obtain an original feature data set.

[0114] Based on the first processed data set, the occurrence frequency of each mutation type, each mutant gene and mutation site is calculated for each patient as the original feature data set.

[0115] (3) Based on the first mutation frequency and the second mutation frequency, the original feature data set is preliminarily screened and extracted to obtain a representative mutant gene set and a representative mutation site set.

[0116] Reference Figure 2 , mainly to preliminarily screen and extract mutant genes and mutation sites. In order to ensure the operation of typical correlation analysis and retain the most meaningful mutant genes and mutation sites, mutant genes with the following characteristics are eliminated and one is retained:

[0117] ① Mutated genes whose frequencies of occurrence in patients are completely linearly correlated.

[0118] ② Mutated genes that occur at the same frequency in every patient.

[0119] Then, among the remaining mutant genes, the mutant genes with a higher correlation with the frequency of occurrence of the mutation type are selected as representative mutant genes. At the same time, the mutation sites with the following characteristics are eliminated and one of them is retained:

[0120] ① Mutation sites whose frequencies of occurrence in patients are completely linearly correlated.

[0121] ② Mutation sites that occur at the same frequency in every patient.

[0122] Then, the mutation sites with a higher correlation with the frequency of occurrence of the mutation type among the remaining mutation sites are selected as representative mutation sites.

[0123] Specifically, the implementation method of determining the representative mutant gene or representative mutation site may be:

[0124] For the convenience of description, the format of "mutant gene / mutation site" is used to indicate the corresponding identification process of the mutant gene or mutation site, and " / " can be understood as "or".

[0125] First, the Pearson correlation coefficient is used to calculate the correlation between every two mutant genes / mutation sites, and the mutant genome / mutation site group with a correlation of 1 is selected from the correlation matrix. For the group with a correlation of 1, one of the mutant genes / mutation sites is retained, and the other mutant genes / mutation sites with a correlation of 1 are deleted from the mutant gene set / mutation site set of the original feature data set to ensure no repeated calculations.

[0126] For each mutant gene / mutation site, there is a mutation frequency in other different patient samples. If the mutation frequency of a mutant gene / mutation site is the same in all samples, it means that it is too common among different patient samples, so it will be deleted;

[0127] The Pearson correlation coefficient is used to calculate the correlation between each mutant gene / mutation site and each mutation type, and the mutant gene / mutation site with higher correlation is selected as the representative. At this time, the higher correlation can determine the threshold or standard according to actual needs.

[0128] (4) A typical correlation analysis model is used to analyze the first correlation between the representative mutant gene set and the mutation type and the second correlation between the representative mutation site and the mutation type to obtain a typical variable group of mutant genes and a typical variable group of mutation sites.

[0129] A set of correlation coefficients is selected as the correlation index between the representative mutation site set and the mutation type set. For the typical variables representing the mutation site set, the weight of each representative mutation site in the typical variable is calculated. The weight reflects the contribution of each representative mutation site to the typical variable, thereby reflecting the importance of the mutation site in the representative mutation site set.

[0130] Specifically, the data representing the mutant gene set and its corresponding mutation type are input into the canonical correlation analysis model. The model outputs several typical variable groups representing the mutant gene set and mutation type. The group with the highest significance and correlation is selected as the typical variable group of the mutant gene. Similarly, the typical variable group of the mutation site can be obtained.

[0131] Reference Figure 3 , the specific steps include:

[0132] For the datasets representing mutant genes / mutation sites and the datasets representing mutation types, their covariance matrices are calculated respectively. The covariance matrix describes the degree of linear relationship between variables.

[0133] Perform an inverse operation on the calculated covariance matrix to obtain the inverse matrix. The inverse matrix will be used in subsequent calculations.

[0134] For the inverse matrices of the two covariance matrices, the generalized eigenvalue problem is calculated. This involves solving the generalized eigenvalues ​​and generalized eigenvectors, which describe the maximum correlation between the mutant gene dataset / mutation site dataset and the mutation type dataset.

[0135] Based on the size of the generalized eigenvalues, the eigenvector corresponding to the largest generalized eigenvalue is selected as the typical variable. These typical variables are linear combinations of the above two data sets, maximizing the correlation between them.

[0136] The coefficients of the typical variables on the original variables (mutated genes / mutation sites and mutation types) are calculated, and these coefficients describe how to linearly combine the original variables into typical variables. It should be noted that in the embodiments of the present application, the typical variables calculated based on the mutant genes and mutation types can be called mutant gene typical variables; the typical variables calculated based on the mutation sites and mutation types can be called mutation site typical variables.

[0137] The canonical correlation coefficient between typical variables is calculated through the generalized eigenvalue to measure the correlation between two data sets on the canonical variables.

[0138] Ultimately, a set of typical variables representing mutant genes / mutation sites and mutation types are obtained. These typical variables have the greatest correlation and can be used to determine the relationship between mutant genes / mutation sites and mutation types, thereby helping to obtain key mutant genes and key mutation sites.

[0139] In the embodiment of the present application, the calculation process of the canonical correlation analysis is as follows:

[0140] Let the representative mutant gene / mutation site be X = (x1, x2…x n ), the mutation type is Y=(y1,y2…y m ), X and Y are two sets of zero-mean random variables.

[0141] First, we need to find a pair of projection directions a1, b1 so that the linear combination of X Linear combination of Y The correlation is the largest. Similarly, find the second pair of projections a2, b2 so that and The correlation is the largest, and u2, v2 are unrelated to u1, v1, where the superscript T represents the vector transpose, so:

[0142] var(u1)=var(v1)=1

[0143] cov(u1,u2)=cov(v1,v2)=0

[0144] The second, third, and other pairs of canonical variables proceed in the same way.

[0145] The Pearson correlation coefficient is used to measure correlation. The formula for correlation is as follows:

[0146]

[0147] Finally, we can obtain the typical variable group U of X=(u1,u2…u n ), the typical variable group V of Y=(v1,v2…v m), calculate the correlation coefficient between each group of typical variables to get ρ1, ρ2…ρ min(n,m) , calculate the indicators p1, p2…p describing the significance of the correlation coefficient min(n,m) .

[0148] (5) Determine key indicators based on typical variable groups of mutant genes and typical variable groups of mutation sites; among which, key indicators include key mutant genes and key mutation sites.

[0149] The typical structure of the typical variable group of mutant genes was analyzed, and the mutant genes with the greatest correlation with the typical variables and the greatest correlation with the severe mutation type were selected as the key mutation genes; the typical structure of the typical variable group of mutation sites was analyzed, and the mutation sites with the greatest correlation with the typical variables and the greatest correlation with the severe mutation type were selected as the key mutation sites.

[0150] Reference Figure 4 , specifically including the following steps:

[0151] Wilk's Lambda statistical test was used to evaluate whether the similarity between the canonical variables was significant and to verify whether the canonical variables established a significant linear relationship between the two sets of variables.

[0152] Based on the results of the Wilks' Lambda test and the correlation coefficients of typical variables, a group of typical variables representing mutant genes / mutation sites and mutation types with significant and high correlations were selected. These variables can better explain the relationship between the two sets of variables.

[0153] Perform canonical structure analysis: Use the selected canonical variables to calculate the correlation coefficient between them and the representative mutant gene / mutation site data set, i.e., the canonical structure. This step helps understand the linear relationship between each canonical variable and the original variable, as well as the contribution of the canonical variable in explaining the original variable.

[0154] Select important mutant genes / mutation sites: According to the correlation coefficient between the typical variables representing the mutant genes / mutation sites and each representative mutant gene / mutation site, select the important mutant genes / mutation sites with high correlation. These mutant genes / mutation sites are of great significance for the interpretation of the representative mutant gene / mutation site set;

[0155] For the selected important mutant genes / mutation sites, calculate their correlation with each mutation type. According to the impact of the mutation type on the patient, select the mutant genes / mutation sites with a higher correlation with the mutation type that seriously affects the patient. Use this as a standard to screen out the key mutant genes / mutation sites, which may play an important role in the disease or specific biological process.

[0156] Through the above steps, the key mutation genes / mutation sites were selected by using the results of canonical correlation analysis combined with correlation test and canonical structure analysis.

[0157] In addition, refer to Figure 5 , when implementing the above method of the embodiment of the present application, a database layer, a basic data processing layer, a core model operation layer and a front-end user layer can be designed. In the database layer, the original whole exome sequencing data of hyperthyroidism patients and the key indicator data obtained after the model is run are stored to ensure the security and availability of the data; in the basic data processing layer, the whole exome sequencing data of hyperthyroidism patients are integrated, deduplicated and other pre-processing work is performed to obtain the original all mutant genes, all mutation site characteristics and corresponding mutation types; in the core operation layer of the model, it mainly includes feature extraction, typical correlation analysis and key mutation-based or key mutation site screening processes; refer to Figure 6 At the front-end user level, doctors can upload whole exome sequencing data through this interface and obtain key indicator results automatically identified by the system. The front-end interface can support interactive operations and provide charts and data table displays. The embodiment of the present application can process the original data input by the doctor through basic data, and then use the key indicator results to compare with the processed doctor input data, and output the key mutation genes and key mutation sites carried by the patient as key indicators.

[0158] The embodiments of the present application have at least the following beneficial effects:

[0159] (1) Through preliminary screening and canonical correlation analysis of the original data of whole exome sequencing of the target object, the correlation between mutant genes and the relationship between mutation sites can be found, and then the key indicators of polygenic diseases can be identified efficiently and accurately. It is suitable for small samples and has low implementation difficulty. It helps to provide doctors with immediate and objective diagnostic auxiliary information and improve the quality of auxiliary diagnosis and treatment.

[0160] (3) Improve diagnostic accuracy: The system can more easily and effectively identify key indicators related to hyperthyroidism from a large amount of data through canonical correlation analysis methods, and assist doctors in making more accurate diagnoses. This will help reduce the possibility of misdiagnosis and missed diagnosis, and improve the quality of diagnosis and treatment for patients. Improve diagnostic efficiency: The system can automatically identify key indicators and provide doctors with instant and objective diagnostic information. This will save doctors' diagnosis time and speed up the diagnosis and treatment process for patients.

[0161] (4) Facilitates personalized treatment and monitoring: The key indicators identified help to better understand the patient's hyperthyroidism condition, thereby providing support for personalized treatment. Doctors can develop more precise treatment plans based on the patient's specific indicators and conduct more detailed monitoring to improve treatment outcomes.

[0162] In summary, the embodiments of the present application will provide a new auxiliary tool for the clinical diagnosis and treatment of polygenic diseases, improve the accuracy and efficiency of diagnosis, and bring multiple beneficial effects to medical practice and patients.

[0163] The following are some experimental data and experimental results provided by this application:

[0164] When obtaining experimental data, DNA samples from 39 hyperthyroidism patients were collected with the approval of the central ethics committee and the informed consent of the patients, and the DNA samples were whole genome sequenced to obtain whole exome sequencing data of hyperthyroidism patients.

[0165] The whole exome sequencing data were processed and screened according to the scheme described above in the embodiment of the present application, and finally, through electrical correlation analysis, the mutant gene CGA, mutation site KANK1 and mutation site g.44651599T>C, which have a greater impact on hyperthyroidism, were obtained.

[0166] Verification of experimental results: Sequencing data from 39 patients and 39 healthy controls were used to verify the results (the above sequencing data were obtained with the informed consent of the participants). The mutations of gene CGA, gene KANK1, and site g.44651599T>C were used as classification features, and mutations were marked as 1 and no mutations were marked as 0. Simple logistic regression was selected as the classification algorithm, and the data was randomly divided into 70% as a training set and 30% as a test set. The diseased and non-diseased were classified, and the classification accuracy reached 87.5%, of which the classification precision reached 82.35%. Figure 7 The area under the ROC curve is large, which can explain that the key indicators identified by the scheme of the embodiment of the present application can be used as classification features and can be used to find most patients. That is, the key indicator identification method for polygenic diseases in the embodiment of the present application has high recognition accuracy and can identify key indicators with certain specificity and sensitivity to polygenic diseases.

[0167] See also Figure 8 The embodiment of the present application also provides a key indicator identification system 100 for polygenic diseases, which can implement the above-mentioned key indicator identification method for polygenic diseases. The system includes:

[0168] The first module 101 is used to obtain the original data of whole exome sequencing of the target object, and perform data preprocessing on the original data of whole exome sequencing to obtain a first processed data set;

[0169] The second module 102 is used to determine the first mutation frequency of the target object at each first mutation site of the first mutant gene detected, and the second mutation frequency of the target object under each mutation type according to the first processed data set, to obtain an original feature data set;

[0170] The third module 103 is used to preliminarily screen and extract the original feature data set according to the first mutation frequency and the second mutation frequency to obtain a representative mutation gene set and a representative mutation site set;

[0171] The fourth module 104 is used to analyze the first correlation between the representative mutant gene set and the mutation type and the second correlation between the representative mutation site and the mutation type using a typical correlation analysis model to obtain a mutant gene typical variable group and a mutation site typical variable group;

[0172] The fifth module 105 is used to determine key indicators based on the typical variable group of mutant genes and the typical variable group of mutation sites; wherein the key indicators include key mutant genes and key mutation sites.

[0173] It should be noted that, in some embodiments, the system may further include at least one of the following modules:

[0174] The sixth module is used to display the key indicator identification results through the front-end display page.

[0175] The seventh module is used to store the whole exome sequencing raw data and key indicator identification results through the database.

[0176] The above modules can be divided into various layers according to the functions they implement. In some embodiments, the process of building the system may include: working with medical experts, data scientists and clinicians to collect and define the functional requirements of the system. The system design includes four parts: database, basic data processing, core model operation and front-end users. Use MySQL database to store raw data, use Python programming language, use Scikit-learn and NumPy and other libraries for data processing and model development, and use HTML, CSS and JavaScript to build front-end pages. The above is only an implementation example of an embodiment of the present application, and appropriate technology can be used for system development according to actual needs.

[0177] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0178] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned key indicator identification method of a polygenic disease when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0179] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0180] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0181] The processor 201 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0182] The memory 202 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 202 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 202, and the processor 201 calls and executes a key indicator identification method for a polygenic disease in the embodiment of this application;

[0183] Input / output interface 203, used to implement information input and output;

[0184] The communication interface 204 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0185] Bus 205 , which transmits information between various components of the device (e.g., processor 201 , memory 202 , input / output interface 203 , and communication interface 204 );

[0186] The processor 201 , the memory 202 , the input / output interface 203 and the communication interface 204 are connected to each other in communication within the device via the bus 205 .

[0187] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned key indicator identification method for a polygenic disease.

[0188] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0189] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory 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 embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor 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.

[0190] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0191] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0192] The system embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0193] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0194] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0195] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0196] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0197] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0198] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0199] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0200] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for identifying key indicators of polygenic diseases, characterized in that: include: Acquire whole exome sequencing raw data of the target object, and perform data preprocessing on the whole exome sequencing raw data to obtain a first processed data set; Determine, according to the first processed data set, a first mutation frequency of the target object at each first mutation site of the first mutant gene detected, and a second mutation frequency of the target object under each mutation type, to obtain an original feature data set; Preliminarily screening and extracting the original feature data set according to the first mutation frequency and the second mutation frequency to obtain a representative mutation gene set and a representative mutation site set; A canonical correlation analysis model is used to analyze the first correlation between the representative mutant gene set and the mutation type and the second correlation between the representative mutation site and the mutation type to obtain a mutant gene typical variable group and a mutation site typical variable group; Key indicators are determined based on the typical variable group of mutant genes and the typical variable group of mutation sites; wherein the key indicators include key mutant genes and key mutation sites.

2. The method according to claim 1, characterized in that The step of obtaining raw data of whole exome sequencing of a target object and performing data preprocessing on the raw data of whole exome sequencing to obtain a first processed data set includes: Integrate and deduplicate the whole exome sequencing raw data of the target object to obtain an initial processed data set; Determining the mutation type variable value in the initial processing data set according to the mutation type; wherein the mutation type includes one of a missense mutation, a synonymous mutation, a non-stop mutation, a nonsense mutation, and a splice site mutation; The mutation type variable value, the first mutation gene and the first mutation site in the initial processed data set are extracted to obtain a first processed data set.

3. The method according to claim 1, characterized in that: The method of preliminarily screening and extracting the original feature data set according to the first mutation frequency and the second mutation frequency to obtain a representative mutation gene set and a representative mutation site set includes: For the first mutant genes having the first characteristic in the first mutant gene set, an operation of removing and retaining one of the first mutant genes is performed to obtain a second mutant gene set; taking a second mutant gene in the second mutant gene set whose correlation with the second mutation frequency is higher than a first preset value as a representative mutant gene, to obtain a representative mutant gene set; For the first mutation sites with the second characteristic in the first mutation site set, an operation of removing and retaining one of the first mutation sites is performed to obtain a second mutation site set; A second mutation site in the second mutation site set whose correlation with the second mutation frequency is higher than a second preset value is taken as a representative mutation site to obtain a representative mutation site set.

4. The method according to claim 1, characterized in that: In the step of using a canonical correlation analysis model to analyze the first correlation between the representative mutant gene set and the mutation type and the second correlation between the representative mutation site and the mutation type to obtain a mutant gene typical variable group and a mutation site typical variable group, the working steps of the canonical correlation analysis model include: Calculating the degree of linear relationship of the representative data set to obtain a covariance matrix; wherein the representative data set is a representative mutant gene set or a representative mutation site set; Performing an inverse operation on the covariance matrix to obtain an inverse matrix; Calculating the generalized eigenvalues ​​of the inverse matrix; The eigenvector with the largest eigenvalue is used as the target typical variable; wherein the target typical variable is a mutant gene typical variable or a mutation site typical variable; Calculate the first coefficient of the target typical variable on the original variable; According to the generalized eigenvalue and the first coefficient, the typical correlation coefficient between the target typical variables is calculated to obtain a target typical variable group; wherein the target typical variable group includes a mutant gene typical variable group and a mutation site typical variable group.

5. The method according to claim 1, characterized in that Determining key indicators according to the typical variable group of the mutant gene and the typical variable group of the mutation site includes: The Wilkes statistic test method is used to evaluate whether the correlation between the target typical variables of the target typical variable group is significant, and the test results are obtained; Based on the canonical correlation coefficient between the test result and the target canonical variable, determine the target canonical variable with the highest correlation significance and correlation as the selected canonical variable; calculating a first correlation coefficient between the selected canonical variable and a representative data set; Determining important mutation genes or important mutation sites according to the first correlation coefficient; Calculate the second correlation between the important mutation gene and the mutation type, and determine the key mutation gene according to the second correlation; or calculate the third correlation between the important mutation site and the mutation type, and determine the key mutation site according to the third correlation.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining the whole exome sequencing raw data through a front-end display page; The key indicator identification results are displayed through the front-end display page.

7. The method according to claim 1, characterized in that The method further comprises: The whole exome sequencing raw data and the key indicator identification results are stored in a database.

8. A key indicator identification system for polygenic diseases, characterized in that: include: The first module is used to obtain the original data of whole exome sequencing of the target object, and perform data preprocessing on the original data of whole exome sequencing to obtain a first processed data set; A second module is used to determine, according to the first processed data set, a first mutation frequency of the target object at each first mutation site of the first mutant gene detected, and a second mutation frequency of the target object under each mutation type, to obtain an original feature data set; A third module is used to preliminarily screen and extract the original feature data set according to the first mutation frequency and the second mutation frequency to obtain a representative mutation gene set and a representative mutation site set; The fourth module is used to analyze the first correlation between the representative mutant gene set and the mutation type and the second correlation between the representative mutation site and the mutation type using a typical correlation analysis model to obtain a mutant gene typical variable group and a mutation site typical variable group; The fifth module is used to determine key indicators based on the typical variable group of the mutant gene and the typical variable group of the mutation site; wherein the key indicators include key mutant genes and key mutation sites.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 7.

10. A computer storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the method according to any one of claims 1 to 7 when executed by the processor.

Images