Method, device and equipment for predicting hereditary diseases

Abstract

The invention relates to the technical field of medical data analysis, in particular to a hereditary disease prediction method, device and equipment, and the method comprises the steps: obtaining target biological information of a target group; based on the target biological information, adopting a screening model to screen out a target biomarker related to the hereditary disease; based on the target biological information and the target biomarker, adopting multi-omics data analysis to obtain a target correlation result of the target biomarker and the hereditary disease; based on the target biomarker and the target correlation result, adopting a hereditary disease prediction model to predict the hereditary disease risk of the target group, analyzing the correlation result of the biomarker and the hereditary disease, and combining the correlation result with the biomarker so as to accurately predict the hereditary disease risk.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data analysis, and in particular to a method, device and equipment for predicting hereditary diseases. Background Art

[0002] Genetic diseases are a type of disease caused by changes in genetic material, including single-gene genetic diseases, polygenic genetic diseases, and chromosomal abnormalities. The occurrence and development of these diseases involve complex genetic and environmental factors. With the deepening of biomedical research, many biomarkers related to genetic diseases have been discovered, which can be used as a basis for disease diagnosis and prognosis.

[0003] However, these markers are not completely inherited, so the prediction of later genetic diseases cannot be made entirely based on these markers.

[0004] Therefore, how to improve the prediction accuracy of genetic diseases is a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of the above problems, the present invention provides a method, device and apparatus for predicting genetic diseases that overcome the above problems or at least partially solve the above problems.

[0006] In a first aspect, the present invention provides a method for predicting a genetic disease, comprising:

[0007] Obtain target biological information of target groups;

[0008] Based on the target biological information, a screening model is used to screen out target biomarkers related to genetic diseases;

[0009] Based on the target biological information and the target biomarker, multi-omics data analysis is used to obtain a target correlation result between the target biomarker and the genetic disease;

[0010] Based on the target biomarker and the target correlation result, a genetic disease prediction model is used to predict the genetic disease risk of the target population.

[0011] Preferably, the screening model is constructed as follows:

[0012] Collecting first historical biological information of a first historical group, the first historical group including a group of people who suffer from genetic diseases and a group of people who do not suffer from genetic diseases, the first historical biological information being marked with a first historical biomarker related to the genetic disease;

[0013] Based on the first historical biological information, a neural network model is trained to obtain a screening model.

[0014] Preferably, the biological information includes:

[0015] Genome, epigenome, transcriptome, and proteome;

[0016] The multi-omics data analysis includes: genomic data analysis, epigenetic data analysis, transcriptome data analysis, and proteome data analysis.

[0017] Preferably, when genomic data analysis is used, multi-omics data analysis is used based on the target biological information and the target biomarker to obtain the correlation result between the target biomarker and the genetic disease, including:

[0018] Determine the gene location, quantity, structure and function of the DNA sequence of the whole genome sequencing data in the target biological information based on bioinformatics software and database;

[0019] Based on the location, quantity, structure and function of the gene, the expression of the target biomarker in a predetermined tissue or environment is determined by analyzing the transcriptome under different conditions;

[0020] Based on the location, number, structure and function of the genes, the corresponding genomes in the previous and next generation populations are compared to determine the evolutionary relationship of the target biomarkers between the corresponding genomes, the expansion and contraction of gene families, and the innovation and loss of functions;

[0021] Predict new functional elements of the target biomarker based on the location, number, structure and function of the gene, as well as the characteristics of known biological elements of transcription start sites, splicing sites, promoters, enhancers, and miRNA binding sites;

[0022] Based on the location, quantity, structure and function of the gene, by performing enrichment analysis on the first gene where the target biomarker is located, determining whether the target biomarker is involved in a preset biological process or pathway;

[0023] Based on the location, number, structure and function of the gene, determining the effect of the target biomarker on the preset phenotype and the correlation with the preset disease by performing a genetic effect analysis on the second gene where the target biomarker is located;

[0024] Based on the gene location, quantity, structure and function, by simulating protein structure and function, it is predicted whether the target biomarker has an effect on protein structure and function.

[0025] Preferably, when epigenetic data analysis is used, the multi-omics data analysis is used based on the target biological information and the target biomarker to obtain the correlation result between the target biomarker and the genetic disease, including:

[0026] Based on the target biological information and the target biomarker, the epigenetic group is changed by using any one or more of DNA methylation, histone modification, polycomb protein and chromatin remodeling and histone regulation to determine the effect of the target biomarker represented by the change on gene expression, cell differentiation and growth and development process.

[0027] Preferably, when transcriptome data analysis is used, multi-omics data analysis is used based on the target biological information and the target biomarker to obtain the correlation results between the target biomarker and the genetic disease, including:

[0028] Based on the target biological information and the target biomarker, a preset process of transcriptome data analysis is used to obtain differentially expressed genes;

[0029] The differentially expressed genes are subjected to enrichment analysis to determine the relevant biological processes and pathways regulated by the target biomarkers.

[0030] Preferably, when protein data analysis is used, the multi-omics data analysis is used based on the target biological information and the target biomarker to obtain the correlation result between the target biomarker and the genetic disease, including:

[0031] By comparing the expression of the proteome in different individuals of the same group, differentially expressed proteins were identified;

[0032] Performing network analysis on the differentially expressed proteins to determine the correlations between the differentially expressed proteins in different individuals;

[0033] Based on the differentially expressed proteins, key nodes are determined through functional annotation and enrichment analysis;

[0034] Based on the relevant associations and the key nodes, the key proteins, biological functions and signaling pathways of the target biomarkers are determined.

[0035] Preferably, the method for constructing the genetic disease prediction model comprises:

[0036] collecting a second historical biomarker for a second historical population and historical correlation results of the second historical biomarker with a genetic disease;

[0037] The second historical biomarker and the historical correlation result are input into a machine learning model for training to obtain a genetic disease prediction model, wherein the machine learning model is specifically any one of the following:

[0038] Logistic regression model, random forest model, and support vector machine model.

[0039] In a second aspect, the present invention further provides a prediction device for hereditary diseases, comprising:

[0040] An acquisition module, used to acquire target biological information of a target group;

[0041] A screening module, for screening biomarkers related to genetic diseases using a screening model based on the target biological information;

[0042] An analysis module, for obtaining a target correlation result between the target biomarker and the genetic disease by using multi-omics data analysis based on the target biological information and the target biomarker;

[0043] A prediction module is used to predict the genetic disease risk of a target population based on the target biomarker and the target correlation result using a genetic disease prediction model.

[0044] In a third aspect, the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the program.

[0045] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:

[0046] The present invention provides a method for predicting genetic diseases, comprising: obtaining target biological information of a target group; based on the target biological information, using a screening model to screen out target biomarkers related to genetic diseases, based on the target biological information and the target biomarkers, using multi-omics data analysis to obtain target correlation results between the target biomarkers and genetic diseases; based on the target biomarkers and the target correlation results, using a genetic disease prediction model to predict the genetic disease risk of the target group, by analyzing the biomarkers and their correlation results with the genetic diseases, and combining the correlation results with the biomarkers, thereby accurately predicting the risk of genetic diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Also, throughout the accompanying drawings, the same reference figures are used to represent the same components. In the drawings:

[0048] Figure 1 A schematic flow chart showing the steps of a method for predicting a genetic disease in an embodiment of the present invention is shown;

[0049] Figure 2 A schematic diagram of a code for predicting and annotating a gene for repeated sequences in an embodiment of the present invention is shown;

[0050] Figure 3 A schematic diagram showing the structure of a prediction device for hereditary diseases in an embodiment of the present invention is shown;

[0051] Figure 4 A schematic diagram of the structure of a computer device for implementing a method for predicting genetic diseases in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0052] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0053] Embodiment 1:

[0054] An embodiment of the present invention provides a method for predicting a genetic disease, comprising:

[0055] S101, obtaining target biological information of a target group;

[0056] S102, based on the target biological information, a screening model is used to screen out target biomarkers related to genetic diseases;

[0057] S103, based on the target biological information and target biomarkers, multi-omics data analysis is used to obtain the target correlation results between the target biomarkers and genetic diseases;

[0058] S104, based on the target biomarkers and target correlation results, a genetic disease prediction model is used to predict the genetic disease risk of the target population.

[0059] First of all, biomarkers are indicators of key events related to pathogenesis that occur in organisms. They are any measurable changes in the physiological, biochemical, immune and genetic aspects of organs, cells and sub-cells of the body caused by exposure to various environmental factors. They can be used for disease diagnosis, disease staging or to evaluate the safety and effectiveness of new drugs or new therapies in a preset population.

[0060] The biological information here includes: genome, epigenome, transcriptome and proteome.

[0061] There are many types of biomarkers, such as proteins, nucleic acids, lipids, metabolites, etc.

[0062] In order to accurately screen biomarkers, a screening model needs to be built first. The present invention is based on generative artificial intelligence biomarker screening, specifically using generative artificial algorithms to conduct deep learning and pattern recognition on the biological information of a large population to screen out new biomarkers that are closely related to genetic diseases. This method can greatly improve the efficiency and accuracy of biomarker screening.

[0063] Among them, the construction method of the screening model is as follows:

[0064] The first historical biological information of the first historical group is collected, where the first historical group includes some groups with genetic diseases and some groups without genetic diseases, and the first historical biological information is marked with historical biomarkers related to genetic diseases; based on the first historical biological information, a neural network model is trained to obtain a screening model.

[0065] Examples of biomarkers associated with genetic diseases include: Tumor markers for lymphoma:

[0066] Lactate dehydrogenase (LD or LDH) is an intracellular enzyme that is released into the blood when cells are damaged or destroyed. Therefore, LDH levels may be elevated in patients with lymphoma.

[0067] Serum β2-microglobulin (β2-MG), a plasma protein normally filtered by the kidneys and excreted in the urine, may be elevated in patients with lymphoid neoplasms.

[0068] Serum fetal collagen (AFP), AFP is a protein produced during fetal development. It is sometimes elevated in malignant tumors such as lymphoma, but its increase is not specific and is often used to diagnose other types of tumors.

[0069] Antinuclear antibodies (ANA), a type of autoimmune antibody, may be positive in some patients with lymphoma.

[0070] Serum beta-2-globulin may also be elevated in some patients with lymphoma.

[0071] Leukocyte alkaline phosphatase (WBC-AP) is an enzyme that is normally present in white blood cells, but levels may be elevated in some people with lymphoma.

[0072] During the model training process, the training data used include: some groups with genetic diseases who carry biomarkers of the disease; some groups with genetic diseases who do not carry biomarkers of the disease; some groups who do not suffer from genetic diseases who carry biomarkers of the disease; and some groups who do not suffer from genetic diseases who do not carry biomarkers of the disease.

[0073] These training data are input into a neural network model for training, thereby obtaining a screening model that can screen out biomarkers related to genetic diseases from biological information.

[0074] Although these biomarkers can mark patients with lymphoma, some markers do not necessarily cause the disease or be inherited, so further analysis is needed.

[0075] Since biological information contains a lot of private information, before training the screening model, the security of biological information collection and storage needs to be ensured for the collected training data, that is, the sample data. Therefore, a federated learning blockchain network is used to integrate the central and decentralized big data management and collaborative analysis platform, which uses an enterprise-level blockchain solution (Hyperledger Fabric) as the underlying blockchain platform. The encryption technology used by the platform can effectively ensure the security and privacy of the data and ensure that the biological data is not tampered with or leaked.

[0076] After the screening model is obtained, next, S101 is executed to obtain target biological information of the target population.

[0077] Specifically, the target group may be sick users or healthy users. The target biological information obtained may be obtained by analyzing the genome, epigenetic group, transcriptome and proteome in a blood test.

[0078] Among them, by using high-throughput sequencing technology, such as second-generation sequencing (NGS) and third-generation sequencing technology, DNA is sequenced to obtain the genome. Analysis of epigenetic markers such as DNA methylation and histone modification is used to analyze the distribution of markers in the genome and obtain the epigenetic group. By extracting RNA from cells and performing sequencing analysis, the expression of genes under specific conditions can be obtained to obtain the transcriptome. The proteome is obtained by testing and analyzing the plasma in the blood.

[0079] Then, S102 is performed to screen out target biomarkers related to genetic diseases using a screening model based on the target biological information, wherein the screening model is used to screen out biomarkers related to genetic diseases from the biological information.

[0080] This step is the application of the screening model. The biological information obtained in S101 is first input into the screening model. Then, the screening model outputs the target biomarkers related to genetic diseases.

[0081] Next, in order to accurately predict the genetic diseases of the target group, S103 is executed to obtain the target correlation results between the target biomarkers and the genetic diseases by using multi-omics data analysis based on the target biological information and the target biomarkers.

[0082] After obtaining the target biomarkers for the target population, multi-omics analysis is used to obtain the target correlation results between the biomarkers and genetic diseases.

[0083] Among them, multi-omics analysis includes: genomic data analysis, epigenetic data analysis, transcriptome data analysis and proteome data analysis.

[0084] Specifically, when genome data analysis is used, it is implemented in the following ways:

[0085] Determine the gene location, quantity, structure and function of the DNA sequence of the whole genome sequencing data in the target biological information based on bioinformatics software and database;

[0086] Based on the location, number, structure and function of genes, the expression of target biomarkers in preset tissues or environments is determined by analyzing the transcriptome under different conditions, including high expression and low expression. This is an analysis based on the gene expression spectrum, which can obtain rich expression information in a short time. The frequency of occurrence of the target biomarker represents the expression level of the gene, and the expression level also represents the degree of correlation between the target biomarker and the genetic disease.

[0087] Based on the location, number, structure and function of genes, the corresponding genomes in the previous and next generation groups are compared to determine the evolutionary relationship between the target biomarkers in the corresponding genomes, the expansion and contraction of the gene family, and the innovation and loss of functions. This is an analysis from the genome comparison. This genome comparison analysis can reveal gene functions and molecular mechanisms of diseases, clarify the evolutionary relationship of species and the intrinsic structure of the genome. Through such analysis, it is possible to determine the probability of biomarkers being inherited, whether they are dominant or recessive, or whether they are cured or restored to a recessive state, etc.

[0088] Based on the location, number, structure and function of genes, as well as the characteristics of biological elements such as known transcription start sites, splicing sites, promoters, enhancers, and miRNA binding sites, new functional elements of target biomarkers are predicted. This is prediction from functional elements, which can predict the response of elements to different environmental signals, such as living temperature, light, etc., and thus affect gene expression, which has an important impact on individual growth and development, metabolic processes, and the occurrence and development of diseases.

[0089] Based on the location, number, structure and function of genes, the first gene where the target biomarker is located is enriched to determine whether the target biomarker is involved in the preset biological process or pathway. This is functional enrichment analysis. Its essence is cluster analysis, which interprets the biological knowledge represented by the first gene where the target biomarker is located, thereby revealing its role inside or outside the cell.

[0090] Based on the location, number, structure and function of the gene, the genetic effect analysis of the second gene where the target biomarker is located is performed to determine the impact of the target biomarker on the preset phenotype and the correlation with the preset disease; this is the analysis of the genetic effect of the mutation. Through the impact of the target biomarker on the morphological structure, physiological function and genetic information of the biological individual, the impact on the evolution of the biological population and the stability of the ecosystem is analyzed, and the correlation of the target biomarker with the preset phenotype and the preset disease is obtained.

[0091] Based on the location, number, structure and function of genes, by simulating protein structure and function, we can predict whether the target biomarker has an impact on protein structure and function. This is prediction and analysis from the protein structure. Since the structure of the protein determines the biological function, for target biomarkers of protein type, we can predict their biological function by predicting the protein structure, that is, predict whether there are related diseases such as protein folding disease.

[0092] When determining the location, number, structure and function of a gene, RepeatMasker (a common tool for detecting repetitive sequences) can be used to predict and annotate the repetitive sequences of the gene. This includes statistical information such as the proportion of repetitive sequences, the type and number of repetitive sequences, etc. Figure 2 The code is shown in the following figure.

[0093] When epigenetic data analysis is used, it is specifically achieved through the following methods:

[0094] Based on the target biological information and target biomarkers, the epigenetic group is changed by using any one or more of DNA methylation, histone modification, polycomb protein and chromatin remodeling and histone regulation to determine the effect of the target biomarker represented by the change on gene expression, cell differentiation and growth and development process.

[0095] DNA methylation can silence gene expression or activate transcription, while histone modification can regulate the structure and function of chromatin, thereby affecting gene accessibility. Therefore, epigenetic data analysis analyzes how these changes participate in regulating cell functions and characteristics, as well as their role in the occurrence and development of diseases.

[0096] For example, hepatocellular carcinoma (HCC) is a highly aggressive malignant disease. Epigenomic analysis regulates gene expression without changing the DNA sequence. Abnormal epigenetic changes can alter the expression of oncogenes or tumor suppressor genes, leading to tumorigenesis. Abnormal epigenetic changes may lead to phenotypic changes in tumor cell growth, immune escape, metastasis, heterogeneity, and chemoresistance. A comprehensive review of genomic data was performed to determine the role of epigenetics in the tumor microenvironment (TME), immune cell infiltration characteristics, and inflammatory response in HCC.

[0097] Transcriptome data analysis is performed in the following ways:

[0098] Based on the target biological information and target biomarkers, the preset process of transcriptome data analysis was used to obtain differentially expressed genes;

[0099] Enrichment analysis of differentially expressed genes was performed to identify relevant biological processes and pathways regulated by the target biomarkers.

[0100] Among them, the preset processes include: quality control, data preprocessing, and differential analysis. Quality control mainly involves quality control of sequencing data, evaluating data quality and excluding low-quality data. Commonly used quality control tools include FastQC and MultiQC. Data preprocessing is to remove sequence adapters (trimming) and filtering (filtering) from the original sequencing data to ensure the accuracy and reliability of subsequent differential analysis. Differential analysis is to identify genes with significantly different expression levels in different samples, and DESeq2 and edgeR are often used. The specific code is as follows:

[0101] #Import raw count file

[0102] countData<-read.table(" / path / to expression data", header=TRUE, row.names=1)

[0103] #Create sample information

[0104] colData<-data.frame(condition=c(rep("Control",3),rep("Treatment",3)),row.names=colnames(countData))

[0105] #Create a DESeq object

[0106] dds<-DESeqDataSetFromMatrix(countData=countData,colData=colData,design=~condition)

[0107] #Perform quality control and filtering

[0108] dds<-dds[rowSums(counts(dds))>=10,]

[0109] dds<-DESeq(dds)

[0110] #Perform differential analysis

[0111] res<-results(dds)

[0112] # Output differential expression matrix

[0113] write.table(res,file="deseq2_results.txt",sep="\t",quote="FALSE)

[0114] Finally, enrichment analysis was performed on differentially expressed genes to determine the relevant biological processes and pathways regulated by the target biomarkers. The code of the Goseq enrichment analysis tool is as follows:

[0115] # Initialize the GSEABase package

[0116] library(GSEABase)

[0117] setwd(" / path / to / your / gene / ids")

[0118] # Load gene ids

[0119] gene.ids.common<-read.csv("geneID2Symbol.txt",header=F,sep="\t")[,1]

[0120] #Run goseq function

[0121] over.list<-goseq(de,"hsa","canonical",gene.ids=gene.ids.common)

[0122] print(over.list)

[0123] When protein data analysis is used, it is specifically achieved in the following ways:

[0124] By comparing the expression of different proteins in different individuals of the same group, differentially expressed proteins were identified;

[0125] Conduct network analysis on differentially expressed proteins to determine the correlation between differentially expressed proteins in different individuals;

[0126] Based on the differentially expressed proteins, key nodes were identified through functional annotation and enrichment analysis;

[0127] Based on the interrelationships and key nodes, the key proteins, biological functions, and signaling pathways of the target biomarkers were identified.

[0128] By using PCA analysis (principal component analysis) on the preprocessed data, the degree of data convergence is obtained, thereby obtaining the separation effect between different groups, removing individual values, and then screening differentially expressed proteins. Pathway analysis is performed based on the differentially expressed proteins, thereby determining the correlation results between the target biomarkers and genetic diseases.

[0129] The analysis of each correlation result analyzes the correlation between the biomarker and the genetic disease from different aspects. Taking into account the diversity of various components in the biological body of the group, various omics data such as genomics, metabolomics and proteomics are analyzed from multiple angles, thereby obtaining the target correlation result between the target biomarker and the genetic disease of the target group. The target correlation result shows the degree of correlation between each target biomarker and the corresponding genetic disease.

[0130] The above-mentioned analysis methods of correlation results can be used alone or in combination, and are not limited here.

[0131] These target correlation results can serve as an effective basis for the later prediction of genetic diseases.

[0132] Therefore, S104 is executed to predict the risk of genetic diseases using a genetic disease prediction model based on the target biomarker and the target correlation result.

[0133] Prior to this, a genetic disease prediction model needs to be built, including:

[0134] collecting a second historical biomarker for a second historical population and historical correlation results of the second historical biomarker with the genetic disease;

[0135] The second historical biomarker and the historical correlation result are input into the machine learning model for training to obtain a genetic disease prediction model, wherein the machine learning model is specifically any one of the following:

[0136] Logistic regression model, random forest model, and support vector machine model.

[0137] The historical correlation result between the second historical biomarker of the second historical population and the genetic disease can be obtained according to S103, and the second historical biomarker of the second historical population can be obtained according to the way of marking the first historical biomarker in the first historical population.

[0138] After obtaining the second historical biomarker of the second historical population and the historical correlation results of the second historical biomarker with the genetic disease, the second historical biomarker and the historical correlation results are input into the machine learning model for training to obtain a genetic disease prediction model.

[0139] Specifically, historical biomarkers and historical correlation results, as well as corresponding historical disease states, are input into any one of a logistic regression model, a random forest model, and a support vector machine model for training, thereby obtaining a genetic disease prediction model.

[0140] By combining the second historical biomarker and the historical correlation results of the second historical biomarker with the genetic disease, the risk of the genetic disease can be effectively predicted, avoiding the problem of low prediction accuracy caused by prediction based solely on biomarkers.

[0141] The result output by the genetic disease prediction model is the prediction confidence of the genetic disease, that is, the probability of suffering from the genetic disease, including the prediction confidence of various genetic diseases. The prediction confidence of various genetic diseases is output according to the confidence ranking.

[0142] Finally, after obtaining the genetic disease prediction model, the target biomarkers and target correlation results of the target group collected by S102 and S103 are input into the genetic disease prediction model, thereby outputting the risk level of genetic diseases in the target group, that is, the prediction confidence of various genetic diseases.

[0143] The technical solution of the present invention can greatly improve the screening and prediction efficiency of genetic diseases, help to achieve early detection and early intervention of genetic diseases, thereby improving the prevention and treatment level of genetic diseases. Secondly, the present invention can effectively process high-dimensional and complex biological data, help to discover more biomarkers related to genetic diseases, thereby improving the accuracy of disease diagnosis and prognosis. Finally, it can also provide sufficient generalization ability and interpretability, which helps to improve the practicality and reliability of genetic disease screening and prediction models. The present invention has broad market demand and good application prospects.

[0144] For example, if the parent has a genetic disease that is currently in the late stage, the offspring may not necessarily have the genetic disease and will also be in the late stage. On the one hand, the target biomarker of the offspring can be obtained through screening, and on the other hand, the target correlation result with the genetic disease can be obtained based on the analysis of the target biomarker. Then, the target biomarker and the target correlation result are input into the genetic disease prediction model, and finally the genetic disease risk of the offspring is output, including: the heritability of various genetic diseases.

[0145] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:

[0146] The present invention provides a method for predicting genetic diseases, comprising: obtaining target biological information of a target group; based on the target biological information, using a screening model to screen out target biomarkers related to genetic diseases, based on the target biological information and the target biomarkers, using multi-omics data analysis to obtain target correlation results between the target biomarkers and genetic diseases; based on the target biomarkers and the target correlation results, using a genetic disease prediction model to predict the genetic disease risk of the target group, by analyzing the biomarkers and their correlation results with the genetic diseases, and combining the correlation results with the biomarkers, thereby accurately predicting the risk of genetic diseases.

[0147] Embodiment 2:

[0148] Based on the same inventive concept, the present invention also provides a prediction device for hereditary diseases, such as Figure 3 As shown, including:

[0149] An acquisition module 301 is used to acquire target biological information of a target group;

[0150] A screening module 302 is used to screen out target biomarkers related to genetic diseases based on the target biological information and using a screening model;

[0151] An analysis module 303 is used to obtain a target correlation result between the target biomarker and the genetic disease by using multi-omics data analysis based on the target biological information and the target biomarker;

[0152] The prediction module 304 is used to predict the genetic disease risk of the target population based on the target biomarker and the target correlation result using a genetic disease prediction model.

[0153] In an optional embodiment, the method for constructing the screening model is as follows:

[0154] Collecting first historical biological information of a first historical group, the first historical group including a group of people who suffer from genetic diseases and a group of people who do not suffer from genetic diseases, the first historical biological information being marked with a first historical biomarker related to the genetic disease;

[0155] Based on the first historical biological information, a neural network model is trained to obtain a screening model.

[0156] In an optional implementation, the biological information includes:

[0157] Genome, epigenome, transcriptome, and proteome;

[0158] The multi-omics data analysis includes: genomic data analysis, epigenetic data analysis, transcriptome data analysis, and proteome data analysis.

[0159] In an optional implementation, the analysis module 303 is used to:

[0160] Determine the gene location, quantity, structure and function of the DNA sequence of the whole genome sequencing data in the target biological information based on bioinformatics software and database;

[0161] Based on the location, quantity, structure and function of the gene, the expression of the target biomarker in a predetermined tissue or environment is determined by analyzing the transcriptome under different conditions;

[0162] Based on the location, number, structure and function of the genes, the corresponding genomes in the previous and next generation populations are compared to determine the evolutionary relationship of the target biomarkers between the corresponding genomes, the expansion and contraction of gene families, and the innovation and loss of functions;

[0163] Predict new functional elements of the target biomarker based on the location, number, structure and function of the gene, as well as the characteristics of known biological elements of transcription start sites, splicing sites, promoters, enhancers, and miRNA binding sites;

[0164] Based on the location, quantity, structure and function of the gene, by performing enrichment analysis on the first gene where the target biomarker is located, determining whether the target biomarker is involved in a preset biological process or pathway;

[0165] Based on the location, number, structure and function of the gene, determining the effect of the target biomarker on the preset phenotype and the correlation with the preset disease by performing a genetic effect analysis on the second gene where the target biomarker is located;

[0166] Based on the gene location, quantity, structure and function, by simulating protein structure and function, it is predicted whether the target biomarker has an effect on protein structure and function.

[0167] In an optional implementation, the analysis module 303 is used to:

[0168] Based on the target biological information and the target biomarker, the epigenetic group is changed by using any one or more of DNA methylation, histone modification, polycomb protein and chromatin remodeling and histone regulation to determine the effect of the target biomarker represented by the change on gene expression, cell differentiation and growth and development process.

[0169] In an optional implementation, the analysis module 303 is used to:

[0170] Based on the target biological information and the target biomarker, a preset process of transcriptome data analysis is used to obtain differentially expressed genes;

[0171] The differentially expressed genes are subjected to enrichment analysis to determine the relevant biological processes and pathways regulated by the target biomarkers.

[0172] In an optional implementation, the analysis module 303 is used to:

[0173] By comparing the expression of different proteins in different individuals from different groups, differentially expressed proteins were identified;

[0174] Performing network analysis on the differentially expressed proteins to determine the correlations between the differentially expressed proteins in different individuals;

[0175] Based on the differentially expressed proteins, key nodes are determined through functional annotation and enrichment analysis;

[0176] Based on the relevant associations and the key nodes, the key proteins, biological functions and signaling pathways of the target biomarkers are determined.

[0177] In an optional embodiment, the method for constructing the genetic disease prediction model comprises:

[0178] collecting a second historical biomarker for a second historical population and historical correlation results of the second historical biomarker with a genetic disease;

[0179] The second historical biomarker and the historical correlation result are input into a machine learning model for training to obtain a genetic disease prediction model, wherein the machine learning model is specifically any one of the following:

[0180] Logistic regression model, random forest model, and support vector machine model.

[0181] In an optional implementation, the prediction module 304 is used to:

[0182] The target biomarker and the target correlation result are input into the genetic disease prediction model, and the risk level of the genetic disease of the target population is output.

[0183] Embodiment three:

[0184] Based on the same inventive concept, an embodiment of the present invention provides a computer device, such as Figure 4 As shown, it includes a memory 404, a processor 402, and a computer program stored in the memory 404 and executable on the processor 402. When the processor 402 executes the program, the steps of the above-mentioned method for predicting genetic diseases are implemented.

[0185] Among them, Figure 4 In the embodiment of the present invention, a bus architecture (represented by bus 400) is shown, which may include any number of interconnected buses and bridges, and bus 400 links various circuits including one or more processors represented by processor 402 and memory represented by memory 404. Bus 400 may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 406 provides an interface between bus 400 and receiver 401 and transmitter 403. Receiver 401 and transmitter 403 may be the same element, namely a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 402 is responsible for managing bus 400 and general processing, while memory 404 may be used to store data used by processor 402 when performing operations.

[0186] Embodiment 4:

[0187] Based on the same inventive concept, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above-mentioned method for predicting genetic diseases when executed by a processor.

[0188] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0189] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0190] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recorded in each embodiment. More specifically, as reflected in each embodiment, the inventive aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0191] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0192] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in a specific embodiment, any one of the claimed embodiments may be used in any combination.

[0193] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in the prediction device for hereditary diseases and computer equipment according to an embodiment of the present invention. The present invention can also be implemented as a device or device program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0194] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

Claims

1. A method for predicting a genetic disease, characterized in that: include: Obtain target biological information of target groups; Based on the target biological information, a screening model is used to screen out target biomarkers related to genetic diseases; Based on the target biological information and the target biomarker, multi-omics data analysis is used to obtain a target correlation result between the target biomarker and the genetic disease; Based on the target biomarker and the target correlation result, a genetic disease prediction model is used to predict the genetic disease risk of the target population.

2. The method according to claim 1, characterized in that The method for constructing the screening model is as follows: Collecting first historical biological information of a first historical group, the first historical group including a group of people who suffer from genetic diseases and a group of people who do not suffer from genetic diseases, the first historical biological information being marked with a first historical biomarker related to the genetic disease; Based on the first historical biological information, a neural network model is trained to obtain a screening model.

3. The method according to claim 1, characterized in that The biological information includes: Genome, epigenome, transcriptome, and proteome; The multi-omics data analysis includes: genomic data analysis, epigenetic data analysis, transcriptome data analysis, and proteome data analysis.

4. The method according to claim 3, characterized in that When genomic data analysis is used, the target correlation results between the target biomarker and the genetic disease are obtained by using multi-omics data analysis based on the target biological information and the target biomarker, including: Determine the gene location, quantity, structure and function of the DNA sequence of the whole genome sequencing data in the target biological information based on bioinformatics software and database; Based on the location, quantity, structure and function of the gene, the expression of the target biomarker in a predetermined tissue or environment is determined by analyzing the transcriptome under different conditions; Based on the location, number, structure and function of the genes, the corresponding genomes in the previous and next generation populations are compared to determine the evolutionary relationship of the target biomarkers between the corresponding genomes, the expansion and contraction of gene families, and the innovation and loss of functions; Predict new functional elements of the target biomarker based on the location, number, structure and function of the gene, as well as the characteristics of known biological elements of transcription start sites, splicing sites, promoters, enhancers, and miRNA binding sites; Based on the location, quantity, structure and function of the gene, by performing enrichment analysis on the first gene where the target biomarker is located, determining whether the target biomarker is involved in a preset biological process or pathway; Based on the location, number, structure and function of the gene, determining the effect of the target biomarker on the preset phenotype and the correlation with the preset disease by performing a genetic effect analysis on the second gene where the target biomarker is located; Based on the gene location, quantity, structure and function, by simulating protein structure and function, it is predicted whether the target biomarker has an effect on protein structure and function.

5. The method according to claim 3, characterized in that When epigenetic data analysis is used, the target correlation results between the target biomarker and the genetic disease are obtained by using multi-omics data analysis based on the target biological information and the target biomarker, including: Based on the target biological information and the target biomarker, the epigenetic group is changed by using any one or more of DNA methylation, histone modification, polycomb protein and chromatin remodeling and histone regulation to determine the effect of the target biomarker represented by the change on gene expression, cell differentiation and growth and development process.

6. The method according to claim 3, characterized in that When transcriptome data analysis is used, multi-omics data analysis is used based on the target biological information and the target biomarker to obtain the target correlation result between the target biomarker and the genetic disease, including: Based on the target biological information and the target biomarker, a preset process of transcriptome data analysis is used to obtain differentially expressed genes; The differentially expressed genes are subjected to enrichment analysis to determine the relevant biological processes and pathways regulated by the target biomarkers.

7. The method according to claim 3, characterized in that When protein data analysis is used, the target correlation results between the target biomarker and the genetic disease are obtained by using multi-omics data analysis based on the target biological information and the target biomarker, including: By comparing the expression of the proteome in different individuals of the same group, differentially expressed proteins were identified; Performing network analysis on the differentially expressed proteins to determine the correlations between the differentially expressed proteins in different individuals; Based on the differentially expressed proteins, key nodes are determined through functional annotation and enrichment analysis; Based on the mutual correlations and the key nodes, the key proteins, biological functions and signaling pathways of the target biomarkers are determined.

8. The method according to claim 1, characterized in that The method for constructing the genetic disease prediction model comprises: collecting a second historical biomarker for a second historical population and historical correlation results of the second historical biomarker with a genetic disease; The second historical biomarker and the historical correlation result are input into a machine learning model for training to obtain a genetic disease prediction model, wherein the machine learning model is specifically any one of the following: Logistic regression model, random forest model, and support vector machine model.

9. A prediction device for genetic diseases, characterized in that: include: An acquisition module, used to acquire target biological information of a target group; A screening module, for screening biomarkers related to genetic diseases using a screening model based on the target biological information; An analysis module, for obtaining a target correlation result between the target biomarker and the genetic disease by using multi-omics data analysis based on the target biological information and the target biomarker; A prediction module is used to predict the genetic disease risk of a target population based on the target biomarker and the target correlation result using a genetic disease prediction model.

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

Images