Prediction method, device and equipment for female early menopause prediction model

Abstract

The invention relates to a prediction method, device and equipment of a female early menopause prediction model. The method comprises the following steps: extracting information in reproductive factors and environmental factors related to early menopause, simultaneously obtaining peripheral blood genome DNA samples of early menopause patients and healthy people, extracting multiple groups of important SNP loci related to early menopause, and screening the multiple groups of important SNP loci through a Logistic regression model, so as to obtain the early menopause related SNP loci. Constructing an early menopause multi-gene risk assessment model according to the screened final SNP sites, adding environmental factors, and finally predicting the female early menopause prediction model according to the early menopause multi-gene and environmental factor risk assessment model. Therefore, healthy crowds are prompted to pay attention to the premenopausal disease risk, crowd layering can be achieved, the risk crowd layering is greatly improved, risk early warning is provided in a targeted mode, and therefore accurate premenopausal risk avoidance of the crowds is achieved.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of application service development, and in particular to a prediction method, device and equipment for a female early menopause prediction model. Background Art

[0002] Menopause refers to the natural and permanent cessation of menstruation and ovulation due to ovarian failure. The average age of natural menopause is about 45-55 years old, which varies from population to population. Studies have found that about 10% of women reach menopause before the age of 45. Menopause before the age of 45 is called premature menopause. About 3.7% of women experience ovarian dysfunction before the age of 40, mainly manifested by abnormal menstruation (amenorrhea, rare or frequent menstruation), increased gonadotropin levels (FSH>25U / L), and fluctuating decreases in estrogen levels. This phenomenon is called premature ovarian insufficiency (POI). Untreated premature menopause increases the risk of cardiovascular disease, type II diabetes, dyslipidemia, obesity, osteoporosis and other diseases in women. In addition, untreated premature menopausal patients are unlikely to conceive naturally, greatly increasing the risk of infertility in women. Ovarian control regulates the occurrence, development and health of women throughout their life cycle until aging. Ovarian aging will lead to reproductive aging, which will lead to the beginning of women's systemic aging. Therefore, early detection, early diagnosis, and early prevention of premature menopause and ovarian dysfunction are related to women’s lifelong health and happiness.

[0003] In the prior art, 290 genetic risk loci associated with natural menopause age were found based on about 200,000 European women, and a polygenic risk prediction model for early menopause in women was constructed, suggesting that a high polygenic risk score (PRS) is clearly associated with early menopause, and women in the top 1% of PRS percentile have the same risk of early menopause as FMR1 carriers. The influencing factors of women's menopause age include not only genetic factors including single genes, chromosomal abnormalities, and genome-wide association (GWAS) research sites (natural menopause age-related SNP sites, menarche age-related SNP sites, reproductive hormone level-related sites, etc.); there are also reproductive factors including menarche age, menstrual cycle, reproductive life span, hormone levels such as anti-Müllerian hormone (AMH), etc.; lifestyle includes smoking, obesity, etc. Therefore, there is an urgent need to develop a multi-dimensional analytical algorithm for the ovarian aging phenotype based on Chinese women, including clinical sub-phenotypes such as genetic factors, environmental factors, and reproductive factors, so as to achieve accurate prediction of early menopause in Chinese women.

[0004] How to discover SNP sites associated with the risk of early menopause through whole-genome association studies and multi-level site screening strategies, construct a comprehensive risk assessment model of early menopause multi-gene + environment, and assist in early screening of early menopause is a technical problem that needs to be solved urgently. Summary of the invention

[0005] In order to solve the problem that it is difficult to construct a female early menopause risk model based on multiple micro-effect sites or genes and environmental factors in the prior art, it is impossible to find more early menopausal people in the early stage, and promote early detection and early treatment of early menopause in women, the embodiment of this specification provides a prediction method, device and equipment for a female early menopause prediction model, through genome-wide association research and multi-level site screening strategy, combined with machine learning algorithm, to find SNP sites associated with early menopause risk; at the same time, combined with reproductive factors and environmental factors related to early menopause, to build a comprehensive risk assessment model of early menopause multi-gene + environment, and issue a risk assessment report. It can effectively remind healthy people to effectively avoid or reduce the risk of early menopause, and achieve the purpose of guiding individual healthy life through gene interpretation.

[0006] The specific technical solutions of the embodiments of this specification are as follows:

[0007] On the one hand, the embodiments of this specification provide a prediction method of a female early menopause prediction model, the method comprising:

[0008] Extract information about reproductive and environmental factors related to early menopause, and obtain peripheral blood genomic DNA samples from early menopausal patients and healthy individuals;

[0009] Based on the peripheral blood genomic DNA samples of the early menopause patients and healthy individuals, a genome-wide association analysis was performed to initially screen out early menopause-related sites; the early menopause-related sites were grouped according to autosomes and integrated into multiple groups of important SNP sites related to early menopause;

[0010] Constructing a Logistic regression model, introducing multiple groups of the important SNP sites into the Logistic regression model one by one to re-screen the important SNP sites, and obtaining the final SNP sites;

[0011] Constructing a polygenic risk assessment model for early menopause according to the final SNP site;

[0012] Adding environmental factors to the early menopause polygenic risk assessment model to construct an early menopause polygenic + environmental factor risk assessment model;

[0013] The female early menopause prediction model is predicted based on the early menopause polygene + environmental factor risk assessment model.

[0014] Furthermore, the peripheral blood genomic DNA samples were subjected to genome-wide association analysis and preliminary screening to obtain early menopause-related sites, further including:

[0015] Performing gene chip typing on each of the peripheral blood genomic DNA samples to generate whole genome genotyping data;

[0016] Performing quality control on the whole genome genotyping data according to the default values ​​of the gene chip genotyping data;

[0017] The whole genome genotype data that have passed quality control are subjected to site filtering to obtain genotype data of menopause-related sites.

[0018] Furthermore, information extraction on reproductive factors and environmental factors related to early menopause further includes:

[0019] The reproductive factors related to early menopause include: Basic information of the user

[0020] The basic information of the user includes the user's gender, age, reproductive factors and living habits;

[0021] The environmental factors include: age at menarche, age at first birth, adverse pregnancy and delivery history, history of oral contraceptives, smoking history, drinking frequency and BMI.

[0022] Furthermore, introducing multiple groups of the important SNP sites into the Logistic regression model one by one to re-screen the important SNP sites further includes:

[0023] The early menopause-related loci are divided into 22 groups according to the autosomes, and each group of early menopause-related loci is input into a Logistic regression model in turn;

[0024] Fitting a regression equation containing all the early menopause-related sites, and calculating the influence of the early menopause-related sites on the early menopause;

[0025] Eliminate the early menopause-related site that has the smallest effect on the early menopause, and recalculate and test the effect of the early menopause-related site on the early menopause;

[0026] Repeat the previous step until the effects of all the early menopause-related sites on the early menopause are higher than a preset threshold.

[0027] Furthermore, the early menopause polygenic genetic risk assessment model is expressed as:

[0028] PRS=β1x SNP1+β2x SNP2+…+β n x SNP n ,

[0029] Among them, SNP is the genotype of the SNP site in the sample, 0, 1, and 2 are used to represent homozygous non-risk sites, heterozygous sites, and homozygous risk sites, respectively, and β is the effect of the SNP site on early menopause, that is, the coefficient in the final regression model.

[0030] Furthermore, the prediction of the female early menopause prediction model based on the early menopause polygene + environmental factor risk assessment model and the population stratified baseline of the risk of early menopause further includes:

[0031] Obtaining a peripheral blood genomic DNA sample from the test individual, performing gene chip typing and preprocessing the whole genome genotyping data to obtain the final SNP site of the test individual;

[0032] Acquire the environmental factors of the test individual according to the basic information filled in by the test individual;

[0033] Inputting the final SNP sites and environmental factors of the test individual into the early menopause polygene + environmental factor risk assessment model to obtain the risk assessment result of the test individual;

[0034] The early menopause polygenic + environmental factor risk assessment model IRS is expressed as

[0035] IRS=C+β0x PRS+β1x E1+β2x E2+…+β n x E n ,

[0036] Among them, C is the constant in the regression model, PRS is the PRS value of the individual, E is the reproductive factor or environmental factor related to early extinction, and β is the coefficient of the corresponding factor in the regression model.

[0037] On the other hand, the embodiments of this specification also provide a prediction device for a female early menopause prediction model, the device comprising:

[0038] The sample extraction module is used to extract information about reproductive factors and environmental factors related to early menopause and obtain peripheral blood genomic DNA samples of early menopausal patients and healthy individuals;

[0039] A site screening module, used to perform genome-wide association analysis based on peripheral blood genomic DNA samples of the early menopausal patients and healthy individuals and to screen for early menopausal-related sites;

[0040] A site fine screening module, used to group the early menopause-related sites according to autosomes and integrate them into multiple groups of important SNP sites related to early menopause;

[0041] A site re-screening module is used to construct a Logistic regression model, introduce multiple groups of the important SNP sites into the Logistic regression model one by one to re-screen the important SNP sites, and obtain the final SNP sites;

[0042] An early menopause polygenic risk assessment model construction module is used to construct an early menopause polygenic risk assessment model according to the final SNP site;

[0043] An environmental factor adding module is used to add environmental factors to the early menopause polygenic risk assessment model to construct an early menopause polygenic + environmental factor risk assessment model;

[0044] The early menopause risk assessment module is used to predict the female early menopause prediction model based on the early menopause polygene + environmental factor risk assessment model.

[0045] On the other hand, an embodiment of the present specification further provides a computer device, including a memory, a processor, and a computer program stored in the memory, and the processor implements the above method when executing the computer program.

[0046] On the other hand, an embodiment of the present specification further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0047] Finally, the embodiments of this specification also provide a computer program product, wherein the computer program product includes a computer program, and the computer program implements the above method when executed by a processor.

[0048] Using the embodiments of this specification, firstly, information on reproductive factors and environmental factors related to early menopause is extracted, and peripheral blood genomic DNA samples of patients with early menopause and healthy people are obtained at the same time; the peripheral blood genomic DNA samples are subjected to genome-wide association analysis and preliminary screening to obtain sites that may be related to early menopause; after obtaining the positions of the related points, they are grouped according to the autosomes and integrated into multiple groups of important SNP sites related to early menopause, and the multiple groups of the important SNP sites are rescreened by the Logistic regression model, and the final SNP sites are obtained by introducing the important SNP sites one by one into the Logistic regression model to complete the multi-level SNP risk site screening, so that technicians in this field can use a variety of appropriate statistics as screening criteria for SNP sites, thereby constructing an early menopause polygenic risk assessment model based on the final SNP sites screened; further, in order to take into account more factors leading to early menopause, environmental factors are added to the early menopause polygenic risk assessment model to construct an early menopause polygenic + environmental factor risk assessment model, and finally the risk of early menopause in women can be assessed based on the early menopause polygenic + environmental factor risk assessment model. This can remind healthy people to pay attention to the risk of early menopause, and can also achieve population stratification, greatly improve the differentiation and stratification of risk groups, and provide targeted risk warnings, thereby achieving more accurate risk avoidance of early menopause in the population. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 It is a schematic diagram of an implementation system of a prediction method of a female early menopause prediction model in the embodiments of this specification;

[0051] Figure 2 It is a schematic flow chart of a prediction method of a female early menopause prediction model according to an embodiment of this specification;

[0052] Figure 3 It is a schematic diagram of the process of performing genome-wide association analysis on the peripheral blood genomic DNA sample and preliminarily screening for early menopause-related sites in the embodiments of this specification;

[0053] Figure 4 It is a schematic diagram of the process of introducing multiple groups of the important SNP sites into the Logistic regression model one by one to perform re-screening of the important SNP sites in the embodiment of this specification;

[0054] Figure 5 It is a schematic diagram of the process of predicting the female early menopause prediction model in the embodiment of this specification;

[0055] Figure 6 The figure shows a schematic diagram of the structure of the multi-gene loci combined early menopause risk analysis and assessment platform in the embodiments of this specification;

[0056] Figure 7 Shown is a ROC curve diagram drawn according to the early menopause polygenic genetic risk value of the training set samples in the embodiments of this specification;

[0057] Figure 8 Shown is a ROC curve diagram of the early menopause polygene + environmental factor risk assessment model in the embodiments of this specification;

[0058] Fig. 9 It is a schematic diagram of the structure of a prediction device of a female early menopause prediction model in the embodiment of this specification;

[0059] Fig.10 The figure is a schematic diagram of the structure of a computer device in an embodiment of the present specification.

[0060]

Description of the accompanying drawings

[0061] 101. Terminal;

[0062] 102. Server;

[0063] 901. Sample extraction module;

[0064] 902. Site screening module;

[0065] 903, site fine screening module;

[0066] 904. Site rescreening module;

[0067] 905. Module for constructing a polygenic risk assessment model for early menopause;

[0068] 906. Environmental factors added module;

[0069] 907. Early menopause risk assessment module;

[0070] 1002. Computer equipment;

[0071] 1004. Processing equipment;

[0072] 1006. Storage resources;

[0073] 1008. Drive system;

[0074] 1010, input / output module;

[0075] 1012. Input device;

[0076] 1014. Output device;

[0077] 1016. Presentation equipment;

[0078] 1018. Graphical user interface;

[0079] 1020. Network interface;

[0080] 1022. Communication link;

[0081] 1024. Communication bus. DETAILED DESCRIPTION

[0082] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the embodiments of this specification.

[0083] It should be noted that the terms "first", "second", etc. in the description and claims of the embodiments of this specification 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 interchanged where appropriate, so that the embodiments of the embodiments of this specification described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes 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 equipment.

[0084] It should be noted that the acquisition, storage, use, and processing of data in the technical solutions of the embodiments of this specification comply with the relevant provisions of national laws and regulations.

[0085] It should be noted that in the embodiments of this specification, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0086] like Figure 1The diagram shows a system diagram of an implementation method of a prediction model for early menopause in women in an embodiment of the specification, including a terminal 101 and a server 102. The terminal 101 and the server 102 can communicate with each other through a network, and the network can include a local area network (LAN), a wide area network (WAN), the Internet, or a combination thereof, and is connected to a website, a user device (such as a computing device), and a back-end system.

[0087] Terminal 101 may be a device with input function, which may record reproductive factors and environmental factors related to premature menopause as well as peripheral blood genomic DNA samples of premature menopausal patients and healthy individuals; server 102 may be a platform for running a premature menopause polygenic risk assessment model, which may send data to terminal 101 for display and receive input from developers through terminal 101.

[0088] Alternatively, the server 102 may be a node of a cloud computing system (not shown), or each server may be a separate cloud computing system including a plurality of computers interconnected by a network and operating as a distributed processing system.

[0089] In addition, it should be noted that Figure 1 What is shown is only one application environment provided by the embodiment of this specification. In actual application, other application environments may also be included, and this specification does not limit it.

[0090] In view of the problems existing in the prior art, the embodiments of this specification provide a prediction method for a female early menopause prediction model, by obtaining the reproductive factors related to early menopause and the environmental factors of the sample in the sample information, and obtaining a peripheral blood genomic DNA sample. Thus, the genomic DNA sample is screened, the early menopause-related sites are confirmed, and then a model is constructed, so as to predict the female early menopause prediction model. Figure 2 The flowchart of the prediction method of the female early menopause prediction model in the embodiment of this specification is shown. The process of constructing the early menopause polygene + environmental factor risk assessment model is described in this figure. The order of steps listed in the embodiment is only one way of executing the order of many steps and does not represent the only execution order. When the system or device product is executed in practice, it can be executed in the order of the method shown in the embodiment or the accompanying drawings or in parallel.

[0091] Specific as Figure 2 As shown, the method may include:

[0092] Step 201: extracting information on reproductive factors and environmental factors related to early menopause, and obtaining peripheral blood genomic DNA samples of early menopausal patients and healthy individuals;

[0093] Step 202: performing genome-wide association analysis based on peripheral blood genomic DNA samples of the premature menopausal patients and healthy individuals and preliminarily screening for premature menopausal-related loci;

[0094] Step 203: grouping the early menopause-related loci according to autosomes and integrating them into multiple groups of important SNP loci related to early menopause;

[0095] Step 204: constructing a Logistic regression model, introducing multiple groups of the important SNP sites into the Logistic regression model one by one to re-screen the important SNP sites, and obtaining the final SNP sites;

[0096] Step 205: constructing an early menopause polygenic risk assessment model based on the final SNP site;

[0097] Step 206: adding environmental factors to the early menopause polygenic risk assessment model to construct an early menopause polygenic + environmental factor risk assessment model;

[0098] Step 207: Predicting a female early menopause prediction model based on the early menopause polygene + environmental factor risk assessment model.

[0099] Using the embodiments of the present specification, firstly, information on reproductive factors and environmental factors related to early menopause is extracted, and peripheral blood genomic DNA samples of patients with early menopause and healthy people are obtained at the same time; the peripheral blood genomic DNA samples are subjected to genome-wide association analysis and preliminary screening to obtain sites related to early menopause; after obtaining the positions of the related points, they are grouped according to the autosomes and integrated into multiple groups of important SNP sites related to early menopause, and the multiple groups of the important SNP sites are rescreened by the Logistic regression model, and the final SNP sites are obtained by introducing the important SNP sites one by one into the Logistic regression model to complete the multi-level SNP risk site screening, so that technicians in this field can use a variety of appropriate statistics as screening criteria for SNP sites, thereby constructing an early menopause polygenic risk assessment model based on the final SNP sites screened; further, in order to take into account more factors leading to early menopause, environmental factors are added to the early menopause polygenic risk assessment model to construct an early menopause polygenic + environmental factor risk assessment model, and finally the risk of early menopause in women can be assessed based on the early menopause polygenic + environmental factor risk assessment model. This can remind healthy people to pay attention to the risk of early menopause, and can also achieve population stratification, greatly improve the differentiation and stratification of risk groups, and provide targeted risk warnings, thereby achieving more accurate risk avoidance of early menopause in the population.

[0100] In the embodiments of this specification, a multi-level SNP risk site screening is performed, which includes at least: primary screening, fine screening and rescreening, so as to ensure that the final SNP site is indeed related to early menopausal diseases. At the same time, in the primary screening, fine screening and rescreening process, suitable statistics known to those skilled in the art can be used as screening criteria for SNP sites, including, but not limited to, chi-square test p value, Pearson correlation coefficient, and / or information gain (KLIC). Alternatively, the model can be iteratively trained, and the model can be iteratively trained by selecting part of the features each time, and the retention of features can be selected by scoring according to the model prediction effect; or the retention of features can be selected by the weight coefficients of each SNP site in the obtained model according to the ranking of the weight coefficients.

[0101] In another embodiment of the present specification, since diseases with polygenic factors are usually caused by the combined effects of multiple micro-effect polygenics / locus and environmental factors, it is necessary to add environmental factors after obtaining the polygenic risk assessment model for premature menopause to construct a polygenic + environmental factor risk assessment model for premature menopause for more accurate risk assessment.

[0102] In the present embodiment, in order to obtain sites associated with premature menopause in peripheral blood genomic DNA samples, such as Figure 3 As shown, the peripheral blood genomic DNA samples were subjected to genome-wide association analysis and preliminary screening to obtain early menopause-related sites, further including:

[0103] Step 301: performing gene chip typing on each of the peripheral blood genomic DNA samples to generate whole genome genotyping data;

[0104] Step 302: performing quality control on the whole genome genotyping data according to the default value of the gene chip genotyping data;

[0105] Step 303: Perform site filtering on the whole genome genotype data that has passed quality control to obtain genotype data of menopause-related sites.

[0106] In one embodiment of the present specification, each sample is first subjected to gene chip typing and the whole genome typing data is preprocessed to obtain genotype data of menopause-related sites, and the preprocessing includes using the default values ​​of the chip typing data to perform quality control on the sequencing data to ensure that the default values ​​can produce valid data, re-sequencing if unqualified, subsequent processing of qualified samples, and finally site filtering of the VCF file to extract disease risk sites.

[0107] In the embodiment of this specification, extracting information about reproductive factors and environmental factors related to early menopause further includes:

[0108] The reproductive factors related to early menopause include: Basic information of the user

[0109] The basic information of the user includes the user's gender, age, reproductive factors and living habits;

[0110] The environmental factors include: age at menarche, age at first birth, adverse pregnancy and delivery history, history of oral contraceptives, smoking history, drinking frequency and BMI.

[0111] Specifically, genome association analysis was performed on multiple known early menopausal patients (case, menopausal age less than 45 years old) and normal menopausal individuals (control, menopausal age between 48-52 years old). Peripheral blood genomic DNA was extracted according to conventional methods, and genotyping was performed on the Infinium Asian Screening Array chip. The differences in each genotype in early menopausal cases and healthy female controls were compared, and a multi-level site screening strategy was combined to discover risk SNP sites associated with menopause.

[0112] In the examples of this specification, in order to obtain important SNP sites related to early menopause, such as Figure 4 As shown, introducing multiple groups of the important SNP sites one by one into the Logistic regression model to re-screen the important SNP sites further includes:

[0113] Step 401: Divide the early menopause-related loci into 22 groups according to the autosomes, and input each group of early menopause-related loci into a Logistic regression model in turn;

[0114] Step 402: Fitting a regression equation including all the early menopause-related sites, and calculating the influence of the early menopause-related sites on the early menopause;

[0115] Step 403: Eliminate the early menopause-related site with the smallest influence on the early menopause, and recalculate and test the influence of the early menopause-related site on the early menopause;

[0116] Step 404: Repeat the previous step until the influence of all the early menopause-related sites on the early menopause is higher than a preset threshold.

[0117] In one embodiment of the present specification, the risk SNP sites associated with early menopause are divided into 22 groups according to the autosomes through preliminary screening, and each group uses a Logistic regression model and a stepwise regression method to screen the sites. Specifically, a regression equation containing all SNP sites is first fitted, and then the contribution of the SNP site corresponding to the variable to the occurrence of early menopause is tested from small to large, and the SNP sites that are not statistically significant are eliminated in turn. Each time a SNP site is eliminated, the contribution of the variable corresponding to the SNP site that has not been eliminated to the occurrence of early menopause must be recalculated and tested, and it is decided whether to eliminate the SNP site with the smallest contribution to the model. Repeat the above process until the SNP sites in the regression equation meet the given criteria for remaining in the model and no SNP sites can be eliminated. In the entire process, only the elimination of SNP sites is considered. Once the SNP site is eliminated, it is no longer considered to be introduced into the regression model.

[0118] In the embodiment of this specification, after the final SNP site is obtained, an early menopause polygenic risk assessment model is constructed according to the final SNP site, wherein the early menopause polygenic genetic risk assessment model is expressed as:

[0119] PRS=β1x SNP1+β2x SNP2+…+β n x SNP n ,

[0120] Among them, SNP is the genotype of the SNP site in the sample, 0, 1, and 2 are used to represent homozygous non-risk sites, heterozygous sites, and homozygous risk sites, respectively, and β is the effect of the SNP site on early menopause, that is, the coefficient in the final regression model.

[0121] In the embodiments of this specification, in order to combine the environment, the risk of premature menopause in women is assessed according to the premature menopause polygene + environmental factor risk assessment model, such as Figure 5 As shown, further comprising,

[0122] Step 501: Obtain a peripheral blood genomic DNA sample of a test individual, perform gene chip typing and pre-process the whole genome genotyping data to obtain the final SNP site of the test individual;

[0123] Step 502: Acquire the environmental factors of the test individual according to the basic information filled in by the test individual;

[0124] Step 503: inputting the final SNP site and environmental factors of the test individual into the early menopause polygenic + environmental factor risk assessment model to obtain the risk assessment result of the test individual;

[0125] The early menopause polygenic + environmental factor risk assessment model IRS is expressed as

[0126] IRS=C+β0x PRS+β1x E1+β2x E2+…+β n x E n ,

[0127] Wherein, C is a constant in the regression model, PRS is the PRS value of an individual, E is a reproductive factor or environmental factor related to premature menopause, and β is the coefficient of the corresponding factor in the regression model. This illustrative embodiment uses a whole genome association study and a multi-level site screening strategy, combined with a machine learning algorithm, to discover SNP sites associated with the risk of premature menopause; at the same time, combined with reproductive factors and environmental factors related to premature menopause, a comprehensive risk assessment model of premature menopause polygene + environment is constructed to assess the risk of premature menopause for individuals and issue a report. The present invention can effectively remind healthy people to effectively avoid or reduce the risk of premature menopause, and achieve the purpose of guiding individuals to live a healthy life through gene interpretation.

[0128] In another embodiment of the present specification, a multi-gene locus combined early menopause risk analysis and assessment platform is also provided, such as Figure 6 As shown, including:

[0129] The sample preprocessing module 601 is used to perform gene chip typing on each sample and preprocess the whole genome genotyping data to obtain genotype data of menopause-related loci;

[0130] The polygenic risk assessment module 602 is used to locate the risk sites of early menopause for the target project and conduct preliminary assessment, and to conduct subsequent data learning and optimization assessment on the preliminary assessment results based on the data fed back by the data processing module;

[0131] The polygenic + environmental comprehensive risk assessment module 603 is used to extract information on reproductive factors and environmental factors related to early menopause for the target project, and to conduct preliminary risk assessment in combination with polygenic factors, and to conduct subsequent data learning and optimization assessment of the preliminary assessment results based on the data fed back by the data processing module;

[0132] Report presentation and user feedback module 604, used to present the evaluation report, collect user feedback and transmit it to the data processing module;

[0133] The data processing module 605 is used to manage user data and feed back to the polygenic risk assessment module.

[0134] Specifically, the polygenic risk assessment module obtains a preliminary assessment report through preliminary assessment and presents it in a report presentation and user feedback module; the early menopause risk assessment module obtains a later optimization assessment report through later optimization assessment and presents it in a report presentation and user feedback module.

[0135] Exemplarily, firstly, information on reproductive factors and environmental factors related to early menopause is extracted to obtain peripheral blood genomic DNA samples of early menopausal patients and healthy individuals. The sample selection of the training set includes: selecting 21,137 early menopausal patients (cases), requiring the menopausal age to be less than 45 years old; at the same time, selecting 74,690 normal menopausal women with a menopausal age of 48-52 years old as controls (control); then extracting the sample DNA for Infinium Asian Screening Array chip typing; at the same time, performing early menopause GWAS association analysis on the above-mentioned 95,827 samples of the training set, and finally obtaining 286 risk SNP sites, calculating the effect value of each SNP site, and constructing an early menopause risk prediction model for 286 sites; specifically, calculating the early menopause polygenic genetic risk (PRS) value of the training set samples based on the effect value and genotype of the 286 sites, and drawing the ROC curve, such as Figure 7 As shown, the AUC of the PRS model for the training set samples is 0.575.

[0136] Seven environmental factors, including age at menarche, age at first birth, adverse pregnancy and childbirth history, history of oral contraceptives, smoking history, drinking frequency, and BMI, were added to the training set samples, and together with PRS, a polygenic + environmental factor risk assessment model for early menopause was constructed. Figure 8 As shown, the ROC curve of the early menopause polygenic + environmental factor risk assessment model IRS was drawn, and AUC = 0.623 was obtained. Compared with the PRS model, the accuracy was improved by 8.3%. According to the ROC curve, when the IRS of an individual is greater than 0.211, the individual is considered to be at high risk of early menopause.

[0137] 104 Chinese patients with early menopause were selected as the test set; the 104 test set samples were typed with the Infinium Asian Screening Array chip to obtain detailed genotypes of 286 risk SNP sites, and combined with their age at menarche, age at first birth, adverse pregnancy and childbirth history, oral contraceptive history, smoking history, drinking frequency, and BMI, these seven environmental factors were brought into the early menopause polygenic + environmental factor risk assessment model IRS to calculate IRS. Based on the IRS greater than 0.211 as the threshold for high risk of early menopause, 37 cases were predicted to be at high risk of early menopause, accounting for 35.6%.

[0138] The evaluation method given in this embodiment is not suitable for diagnosis, because the conclusion of the evaluation is not whether the subject has a disease, and the score does not represent whether the subject will definitely get sick in the future; therefore, it is only used for disease risk assessment, and it is only to assess the risk or probability of individual future disease occurrence. The level of the evaluation can reflect the risk of illness compared with normal people, but the result of whether the disease will occur in the future is still uncertain. Therefore, there is no necessary relationship between the evaluation result and the individual's future result, but its reliability will be greatly improved when it comes to the evaluation of population samples, so the conclusion of the evaluation only provides a future reminder and reference for the individual. Through the embodiments of this specification, healthy people can be reminded to pay attention to the risk of early menopause, population stratification can be achieved, and risk warnings can be provided in a targeted manner, thereby achieving more accurate risk avoidance of early menopause in the population.

[0139] Based on the same inventive concept, the embodiment of this specification also provides a prediction device for a female early menopause prediction model, such as Fig. 9 As shown, the device comprises:

[0140] The sample extraction module 901 is used to extract information about reproductive factors and environmental factors related to early menopause, and obtain peripheral blood genomic DNA samples of early menopausal patients and healthy individuals;

[0141] A site screening module 902 is used to perform genome-wide association analysis based on peripheral blood genomic DNA samples of the early menopausal patients and healthy individuals and to screen out early menopausal-related sites;

[0142] A site fine screening module 903 is used to group the early menopause-related sites according to autosomes and integrate them into multiple groups of important SNP sites related to early menopause;

[0143] The site re-screening module 904 is used to construct a Logistic regression model, introduce multiple groups of the important SNP sites into the Logistic regression model one by one to re-screen the important SNP sites, and obtain the final SNP sites;

[0144] An early menopause polygenic risk assessment model construction module 905 is used to construct an early menopause polygenic risk assessment model according to the final SNP site;

[0145] An environmental factor adding module 906 is used to add environmental factors to the early menopause polygenic risk assessment model to construct an early menopause polygenic + environmental factor risk assessment model;

[0146] The early menopause risk assessment module 907 is used to predict the female early menopause prediction model based on the early menopause polygene + environmental factor risk assessment model.

[0147] Since the principle of solving the problem by the above device is similar to that of the above method, the implementation of the above system can refer to the implementation of the above method, and the repeated parts will not be repeated.

[0148] like Fig.10 The figure is a schematic diagram of the structure of the computer device in the embodiment of this specification. The method in the embodiment of this specification can be applied to the computer device in this embodiment.

[0149] Specifically, Fig.10 As shown, the computer device 1002 may include one or more processing devices 1004, such as one or more central processing units (CPUs), each of which may implement one or more hardware threads. The computer device 1002 may also include any storage resources 1006 for storing any type of information such as code, settings, data, etc. Without limitation, for example, the storage resource 1006 may include any one or more combinations of the following: any type of RAM, any type of ROM, a flash memory device, a hard disk, an optical disk, etc. More generally, any storage resource may use any technology to store information.

[0150] Further, any storage resource may provide volatile or non-volatile retention of information.

[0151] Further, any storage resource may represent a fixed or removable component of the computer device 1002. In one case, when the processing device 1004 executes the associated instructions stored in any storage resource or combination of storage resources, the computer device 1002 may perform any operation of the associated instructions. The computer device 1002 also includes one or more drive systems 1008 for interacting with any storage resource, such as a hard disk drive system, an optical disk drive system, etc.

[0152] The computer device 1002 may also include an input / output module 1010 (I / O) for receiving various inputs (via input device 1010) and for providing various outputs (via output device 1014). A specific output mechanism may include a presentation device 1016 and an associated graphical user interface (GUI) 1018. In other embodiments, the input / output module 1010 (I / O), input device 1010, and output device 1014 may not be included, and the computer device 1002 may be used as a computer device in a network. The computer device 1002 may also include one or more network interfaces 1020 for exchanging data with other devices via one or more communication links 1022. One or more communication buses 1024 couple the components described above together.

[0153] The communication link 1022 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 1022 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.

[0154] The embodiments of the present specification also provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0155] The embodiments of the present specification also provide a computer-readable instruction, wherein when a processor executes the instruction, the program therein causes the processor to execute the above method.

[0156] It should be understood that in the various embodiments of the present specification, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present specification.

[0157] It should also be understood that in the embodiments of this specification, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the embodiments of this specification generally indicates that the associated objects before and after are in an "or" relationship.

[0158] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the embodiments of this specification can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiments of this specification.

[0159] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0160] In the several embodiments provided in the embodiments of this specification, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the 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. In addition, 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, or it can be an electrical, mechanical or other form of connection.

[0161] The units described 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 embodiments of this specification.

[0162] In addition, each functional unit in each embodiment of the present specification can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0163] 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 embodiment of this specification is essentially 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 a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the embodiment of this specification. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), disk or optical disk and other media that can store program code.

[0164] The embodiments of this specification use specific embodiments to illustrate the principles and implementation methods of the embodiments of this specification. The description of the above embodiments is only used to help understand the methods and core ideas of the embodiments of this specification. At the same time, for those skilled in the art, according to the ideas of the embodiments of this specification, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the embodiments of this specification.

Claims

1. A prediction method for a female early menopause prediction model, characterized in that: The method comprises: Extract information on reproductive and environmental factors related to early menopause, and obtain peripheral blood genomic DNA samples from early menopausal patients and healthy individuals; Based on the peripheral blood genomic DNA samples of the early menopause patients and healthy individuals, a genome-wide association analysis was performed to initially screen out early menopause-related sites; the early menopause-related sites were grouped according to autosomes and integrated into multiple groups of important SNP sites related to early menopause; Constructing a Logistic regression model, introducing multiple groups of the important SNP sites into the Logistic regression model one by one to re-screen the important SNP sites, and obtaining the final SNP sites; Constructing a polygenic risk assessment model for early menopause according to the final SNP site; Adding environmental factors to the early menopause polygenic risk assessment model to construct an early menopause polygenic + environmental factor risk assessment model; The female early menopause prediction model is predicted based on the early menopause polygene + environmental factor risk assessment model.

2. The prediction method of the female early menopause prediction model according to claim 1, characterized in that: The peripheral blood genomic DNA samples were subjected to genome-wide association analysis and preliminary screening to obtain early menopause-related sites, further including: Performing gene chip typing on each of the peripheral blood genomic DNA samples to generate whole genome genotyping data; Performing quality control on the whole genome genotyping data according to the default values ​​of the gene chip genotyping data; The whole genome genotyping data that passed quality control were subjected to site filtering to obtain genotype data of menopause-related sites.

3. The prediction method of the female early menopause prediction model according to claim 2, characterized in that: Information extraction on reproductive and environmental factors associated with early menopause further included: The reproductive factors related to early menopause include: basic information of the user; The basic information of the user includes the user's gender, age, reproductive factors and living habits; The environmental factors include: age at menarche, age at first birth, adverse pregnancy and delivery history, history of oral contraceptives, smoking history, drinking frequency and BMI.

4. The prediction method of the female early menopause prediction model according to claim 2, characterized in that: Introducing multiple groups of the important SNP sites one by one into the Logistic regression model to re-screen the important SNP sites further includes: The early menopause-related loci are divided into 22 groups according to the autosomes, and each group of early menopause-related loci is input into a Logistic regression model in turn; Fitting a regression equation containing all the sites associated with early menopause, and calculating the influence of the sites associated with early menopause on the early menopause; Eliminate the early menopause-related site that has the smallest effect on the early menopause, and recalculate and test the effect of the early menopause-related site on the early menopause; Repeat the previous step until the effects of all the early menopause-related sites on the early menopause are higher than a preset threshold.

5. The prediction method of the female early menopause prediction model according to claim 1, characterized in that: The early menopause polygenic genetic risk assessment model is expressed as: PRS=β1x SNP1+β2x SNP2+...+β n x SNP n , Among them, SNP is the genotype of the SNP site in the sample, 0, 1, and 2 are used to represent homozygous non-risk sites, heterozygous sites, and homozygous risk sites, respectively, and β is the effect of the SNP site on early menopause, that is, the coefficient in the final regression model.

6. The prediction method of the female early menopause prediction model according to claim 1, characterized in that: The prediction of the female early menopause prediction model based on the early menopause polygene + environmental factor risk assessment model and the population stratification baseline of the early menopause risk further includes: Obtaining a peripheral blood genomic DNA sample from the test individual, performing gene chip typing and preprocessing the whole genome genotyping data to obtain the final SNP site of the test individual; Acquire the environmental factors of the test individual according to the basic information filled in by the test individual; Inputting the final SNP sites and environmental factors of the test individual into the early menopause polygene + environmental factor risk assessment model to obtain the risk assessment result of the test individual; The early menopause polygenic + environmental factor risk assessment model IRS is expressed as IRS=C+β0x PRS+β1xE1+β2x E2+…+β n x E n , Among them, C is the constant in the regression model, PRS is the PRS value of the individual, E is the reproductive factor or environmental factor related to early extinction, and β is the coefficient of the corresponding factor in the regression model.

7. A prediction device for a female early menopause prediction model, characterized in that: The device comprises: The sample extraction module is used to extract information about reproductive factors and environmental factors related to early menopause and obtain peripheral blood genomic DNA samples of early menopausal patients and healthy individuals; A site screening module, used to perform genome-wide association analysis based on peripheral blood genomic DNA samples of the early menopausal patients and healthy individuals and to screen for early menopausal-related sites; A site fine screening module, used to group the early menopause-related sites according to autosomes and integrate them into multiple groups of important SNP sites related to early menopause; A site re-screening module is used to construct a Logistic regression model, introduce multiple groups of the important SNP sites into the Logistic regression model one by one to re-screen the important SNP sites, and obtain the final SNP sites; An early menopause polygenic risk assessment model construction module is used to construct an early menopause polygenic risk assessment model according to the final SNP site; An environmental factor adding module is used to add environmental factors to the early menopause polygenic risk assessment model to construct an early menopause polygenic + environmental factor risk assessment model; The early menopause risk assessment module is used to predict the female early menopause prediction model based on the early menopause polygene + environmental factor risk assessment model.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images