KR20230007010A - Method and system for predicting metabolic disease risk - Google Patents

Abstract

Disclosed are a method for predicting a metabolic disease risk and a system for the same. The purpose of the present invention is to provide the method for predicting a metabolic disease by using a methylation thickening area changed in the metabolic disease and predicting a risk of the metabolic disease. According to an embodiment of the present invention, the method for predicting a metabolic disease risk includes: a step of measuring RNA-seq (large capacity transcriptome data) and a methylation degree on a normal person group and a metabolic disease patient group, respectively; a step of selecting a differential expression gene in which the expression is changed only in the metabolic disease patient group in comparison with the normal person group, by using the methylation degree; a step of selecting a differential methylation area in which the methylation is changed only in the metabolic disease patient group in comparison with the normal person group, by using the methylation degree; and a step of determining an epigenetic inheritance index for predicting a metabolic disease patient by modeling the selected differential expression gene and the selected differential methylation area.

Description

Metabolic disease risk prediction method and system {METHOD AND SYSTEM FOR PREDICTING METABOLIC DISEASE RISK}

The present invention relates to a metabolic disease risk prediction method and system for predicting a metabolic disease or predicting its risk by utilizing a methylation epigenetic region that changes in a metabolic disease.

In addition, the present invention provides a metabolic disease risk prediction method and system for predicting metabolic disease patients and determining epigenetic markers (genes) capable of predicting the risk of metabolic disease patients.

Metabolic disease (metabolic syndrome) occurs when three or more of the five risk factors (high blood pressure, high blood sugar, hypertriglyceridemia, low high-density lipoprotein cholesterol, and central obesity) increase the risk of health problems, including heart disease, diabetes, and stroke. means that an individual has

Due to the rapid westernization of lifestyle, the aspect of disease shows a very large change, and obesity-related hypertension, diabetes, hyperlipidemia, cardiovascular and cerebrovascular diseases, etc. are explosively increasing.

The prevalence of metabolic syndrome in adults worldwide is 20-25%, the prevalence in the United States is 35%, and the prevalence in Korea is reported to be up to 30%.

Accordingly, there is an urgent need for a new model that prevents patients from developing metabolic diseases by determining epigenetic markers (genes), which can predict and warn the risk of metabolic diseases in advance.

An object of the present invention is to provide a method and system for predicting metabolic diseases and predicting the risk of metabolic diseases by utilizing methylation epigenetic regions that change in metabolic diseases.

According to one embodiment of the present invention, a metabolic disease risk prediction method includes the steps of measuring the degree of methylation in a methylation region in relation to a group of examiners; performing metabolic disease risk prediction modeling using the measured methylation level; and informing the risk level of the metabolic disease to the examiner group according to a result of performing the metabolic disease risk prediction modeling.

In addition, the metabolic disease risk prediction system according to an embodiment of the present invention, in relation to the tester group, a measurement unit for measuring the degree of methylation of the methylation region; and a decision unit that performs metabolic disease risk prediction modeling using the measured methylation degree and informs the examiner group of the metabolic disease risk according to the results of the metabolic disease risk prediction modeling. there is.

According to one embodiment of the present invention, it is possible to provide a method and system for predicting metabolic diseases and risk of metabolic diseases by utilizing methylation epigenetic regions that change in metabolic diseases.

1 is a block diagram showing the configuration of a metabolic disease risk prediction system according to an embodiment of the present invention.
Figure 2 is a diagram for explaining a method for predicting the risk of metabolic diseases using epigenetic markers.
3 is a diagram showing ROC/AUC results (methylation) using epigenetic markers.
Figure 4 is a flow chart showing a metabolic disease risk prediction method according to an embodiment of the present invention.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes can be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents or substitutes to the embodiments are included within the scope of rights.

Terms used in the examples are used only for descriptive purposes and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

In addition, in the description with reference to the accompanying drawings, the same reference numerals are given to the same components regardless of reference numerals, and overlapping descriptions thereof will be omitted. In describing the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description will be omitted.

1 is a block diagram showing the configuration of a metabolic disease risk prediction system according to an embodiment of the present invention.

Referring to FIG. 1 , a metabolic disease risk prediction system 100 according to an embodiment of the present invention may include a measurement unit 110, a selection unit 120, and a determination unit 130.

First of all, the measurement unit 110 may measure the methylation degree of the methylation region in relation to the tester group.

The determiner 130 may perform metabolic disease risk prediction modeling using the measured methylation level, and inform the examiner group of the metabolic disease risk according to the results of the metabolic disease risk prediction modeling.

The measurement unit 110 may analyze methylation information of the normal group and the metabolic disease patient group.

In addition, the measurement unit 110 may measure RNA-seq (large transcript data) for each of the normal group and the metabolic disorder group.

The selection unit 120 may select the methylation region through verification of the methylation information by RNA-seq. Here, the methylation region for measuring the degree of methylation can be selected by analyzing 800,000 methylation information of normal people and patients with metabolic diseases and verifying RNA-seq (gene expression) information.

In addition, the measurement unit 110 measures RNA-seq (large-capacity transcript data) and methylation levels for each of the normal group and the metabolic disorder group. That is, the measurement unit 110 may play a role of acquiring information/data related to genes that can distinguish a difference between a normal person and a person with a metabolic disease.

Here, RNA-Seq (RNA-sequencing) may refer to sequencing RNA strands made into a library suitable for NGS. By RNA-Seq, the expression of messenger RNA (mRNA) that synthesizes proteins and some mutations can be confirmed, and non-coding RNAs that do not synthesize proteins can also be examined. there is.

The degree of methylation may refer to the level of DNA methylation for each subject belonging to the normal group and the metabolic disorder group. DNA methylation is the process of forming 5-methylcytosine (5-mC) by adding one methyl group to the 5th carbon position (C5) of cytosine, regulating gene expression, silencing transposon, stabilizing genome It may be a very important epigenetic mechanism related to X-chromosome inactivation, genomic imprinting, etc.

In the embodiment, RNA-seq (large-scale transcriptome data) and methylation levels are measured for each of the group of 9 healthy people and the group of 11 people with metabolic disease, thereby obtaining gene-related information/data of each subject.

The selection unit 120 selects differentially expressed genes whose expression changes only in the metabolic disease patient group compared to the normal group using the RNA-seq. That is, the selection unit 120 may play a role of identifying genes that are characteristically expressed only in subjects belonging to the metabolic disease patient group based on the measured RNA-seq, and selecting them as differentially expressed genes.

In the above-described embodiment, the selection unit 120 identifies a gene that is not expressed in 9 people belonging to the normal group but commonly expressed in 11 people belonging to the metabolic disease group through RNA-seq, and selects it as a differentially expressed gene. can do.

In the selection of differentially expressed genes, the selection unit 120 checks the expression level for each gene in association with the sequencing read of the nucleotide sequence produced in the RNA-seq, and fold change (FC according to the identified expression level) ) with a difference of more than 2 times and a P-value of 0.05 or less, which indicates significance, can be selected as a differentially expressed gene.

That is, the selection unit 120 removes adapters among sequencing reads of Q30 or higher of the nucleotide sequence produced by RNA-seq in order to select genes whose expression changes in patients with metabolic diseases compared to normal people, removes overlapping reads, and then By mapping to the genome, the expression level of each gene can be measured. Thereafter, the selection unit 120 may select a gene with a P-value of 0.05 or less, which indicates significance with a difference of expression fold change (FC) by more than two times, and select a differentially expressed gene.

In addition, the selection unit 120 may select a differential methylation region in which methylation changes only in the metabolic disease patient group compared to the normal group by using the methylation degree. That is, the selection unit 120 identifies a region in which the methylation value changes, which is characteristic only for subjects belonging to the metabolic disease patient group, based on the measured degree of methylation, and selects it as a differential methylation region. there is.

In the above-described embodiment, the selection unit 120 identifies a region where the methylation value, which did not change in 9 people belonging to the normal group, changes commonly in 11 people belonging to the metabolic disease group through the degree of methylation, and differentiates It can be selected as a methylation region.

In the selection of differentially expressed genes, the selection unit 120 selects regions in which the P-value value indicating significance is 0.05 or less, from the image file of the methylation chip (Human Methylation 850K BeadChip) obtained through the measurement of the degree of methylation. can be selected as the differential methylation region.

That is, the selection unit 120 uses the image file of the methylation chip to select a region in which methylation changes in patients with metabolic disease compared to normal people, and CpG showing a statistical difference (P value < 0.05) in patients with metabolic disease compared to normal people. The region can be selected as a differential methylation region.

The determination unit 130 determines an epigenetic index for predicting a patient with a metabolic disease through modeling of the selected differential expression gene and the differential methylation region. That is, the determination unit 130 may play a role of determining an epigenetic index used for predicting a metabolic disease risk by extracting selected differentially expressed genes within the selected differential methylation region.

In determining the epigenetic index, the determination unit 130 identifies a plurality of genetic indexes belonging to the differential methylation region and being the differentially expressed genes, and among the plurality of genetic indexes, an area under the curve (AUC) value is Relatively high n (n is a natural number of 3 or more) genetic indexes can be determined as the epigenetic index.

Here, AUC may refer to a subregion of a Receiver Operating Characteristics (ROC) curve that is useful when evaluating model performance in an imbalanced dataset. The ROC curve is a tool widely used to visually show the classification, layer probability estimation, and scoring performance of a model, and it allows us to know the fundamental strengths and weaknesses of each model because it expresses the model performance itself regardless of various application conditions. AUC corresponds to the area under the ROC curve, which briefly tells important information, and can be the area under the classifier curve within the unit square, with values ranging from 0 to 1.

In an exemplary embodiment, the determination unit 130 may include at least indices 'cg23248424', 'cg02891314', and 'cg03849834' as the n genetic indices.

After determining the indices 'cg23248424', 'cg02891314', and 'cg03849834', the metabolic disease risk prediction system 100 of the present invention can predict metabolic disease patients and predict their risk using these epigenetic indicators.

According to the present invention, it is possible to provide a method and system for predicting metabolic diseases and predicting the risk of metabolic diseases by utilizing methylation epigenetic regions that change in metabolic diseases.

DNA methylation refers to an epigenetic mutation that occurs on DNA. It refers to a chemical change in which the DNA sequence inherited from parents does not change and the methyl group (CH3) attaches to DNA.

DNA methylation has the advantage of being widely used in diagnosis due to its high measurability even when a relatively small amount of biomarker is present.

The present invention is a predictive model capable of diagnosing metabolic diseases by calculating epigenetic influence scores (DNA methylation scores) using epigenetic markers with high predictive accuracy that can predict metabolic diseases and showing the accuracy of prediction. It is about.

According to the present invention, a metabolic disease can be predicted through an epigenetic influence score (DNA methylation score), and an epigenetic diagnostic marker prediction system capable of diagnosing with a small amount of sample can be supported.

Metabolic diseases are caused by various factors, and symptoms such as hypertension, diabetes, and hyperlipidemia simultaneously have risk factors that lead to cardiovascular and cerebrovascular diseases. A system capable of predicting epigenetic diagnostic markers is required.

In the present invention, by measuring the epigenetic influence score (DNA methylation score) and calculating the predictive value of metabolic diseases, an epigenetic index with high accuracy is presented.

The method for selecting epigenetic markers used in the present invention is as follows.

1. Collection of study samples

The metabolic disease risk prediction system 100 may collect (blood) samples of normal (n=9)/metabolic disease (n=11).

The metabolic disease risk prediction system 100 may collect samples from normal people (9 people) and metabolic disease patients (11 people) among the OO citizen cohort.

2. Production of transcriptome (bulk RNA seq) and methylation chip (HM850k chip) data for each sample (Paired)

The metabolic disease risk prediction system 100 derives gene expression across the genome for the collected samples, normal people (9 people) and metabolic disease patients (11 people), and RNA-seq (large-scale transcriptome data) and To measure the degree of methylation, a methylation chip can be performed.

Methylation indicates that cytosine (C) is methylated at a specific CpG in a specific gene and changes to methylcytosine (mC). there is.

3. Indicators that change significantly in metabolic diseases compared to normal are selected through gene expression analysis (|FC| >2, P-value < 0.05) and methylation (P-value <0.05) analysis

- Selection of differentially expressed genes (|FC|>2 and P-value<0.05)

Metabolic disease risk prediction system 100, in order to select genes whose expression changes in metabolic disease patients compared to normal people, among sequencing reads of Q30 or higher of the nucleotide sequence produced by RNA-seq, adapters are removed and overlapping leads are removed Then, the expression level of each gene can be measured by mapping to the human genome.

The metabolic disease risk prediction system 100 can select a gene whose expression fold change (FC) has a difference of 2 or more times and a P-value value of 0.05 or less, which indicates significance.

- Selection of differential methylation area (P value <0.05)

In addition, the metabolic disease risk prediction system 100 uses an image file of a methylation chip (Human Methylation 850K BeadChip) to select a region in which methylation changes in patients with metabolic disease compared to normal people, so that the detection P value is 0.05 or less and Bayesian t-test can be performed for data with a CpG area of 99% or more (P-value<= 0.05).

4. Discovery of final epigenetic markers to the degree of significance through correlation analysis to select genes whose expression changes due to methylation (P-value <0.05): Expression of a total of 47 probes is controlled by methylation in metabolic diseases confirm to be

- Selection of epigenetic markers

The metabolic disease risk prediction system 100 may select differentially expressed genes in which gene expression changes and differential methylation regions in which methylation values change by using the pearson correlation (r) method (47).

Epigenetic markers represent CpG regions included in genes whose expression changes due to methylation changes in metabolic diseases compared to normal subjects.

- Metabolic disease prediction

Metabolic disease risk prediction system 100 models the methylation values of the extracted candidates and distinguishes between metabolic disease patients and normal people. As a result, 3 out of 47 epigenetic markers (cg23248424, cg02891314, cg03849834) are used as individual indicators can do.

In the case of cg23248424, the AUC value may be 0.828, in the case of cg02891314, the AUC value may be 0.878, and in the case of cg03849834, the AUC value may be 0.767.

Figure 2 is a diagram for explaining a method for predicting the risk of metabolic diseases using epigenetic markers.

In step 210, the metabolic disease risk prediction system 100 receives an epigenetic indicator.

The metabolic disease risk prediction system 100 may receive an input of epigenetic markers within 36 genes including epigenetic markers associated with metabolic diseases of the subject.

The value of the epigenetic index can be newly created through experimentation or a previously known value can be entered.

In step 220, the metabolic disease risk prediction system 100 may calculate the degree of significance of the epigenetic index.

The metabolic disease risk prediction system 100 may use a combination including at least one of three epigenetic markers (cg23248424, cg02891314, and cg03849834) among 47 epigenetic markers as variables of the prediction algorithm.

Prediction algorithms can use various machine learning methods such as simple linear regression methods and SVMs.

In step 230, the metabolic disease risk prediction system 100, as a result provided, may determine the presence or absence of a disease according to the degree of significance and provide the result.

The metabolic disease risk prediction system 100 may use each of the three epigenetic indicators (cg23248424, cg02891314, and cg03849834) as one variable to provide a metabolic disease prediction result.

3 is a diagram showing ROC/AUC results (methylation) using epigenetic markers.

3 illustrates the results of predicting metabolic diseases. Through FIG. 3, it can be seen that AUC can be used for prediction alone as 0.77 to 0.88.

Genetic markers used for epigenetic index calculation are exemplified in [Table 1].

The metabolic disease risk prediction system 100 may derive a candidate group of final epigenetic markers selected to a degree of significance through analysis of correlation between methylation and gene expression.

In FIG. 3, ROC/AUC results for 3 probes (2 genes) for determining the predictive power of epigenetic markers are exemplified.

The metabolic disease risk prediction system 100 utilizes the epigenetic index with high predictive power presented in Table 1 in addition to the epigenetic index as an index to determine metabolic disease, thereby facilitating personalized treatment and management of metabolic disease patients. It can be used as a predictive system.

The index cg23248424 has an AUC value of 0.828 obtained from the methylation value, which can increase the predictive power of metabolic diseases.

Accordingly, when the methylation value of the index cg23248424 is used as an input value, the metabolic disease risk prediction system 100 is 10% (beta value) of the total methylation value range (0 to 1) than the average methylation value of 0.368 in normal people. : 0.1), patients with a methylation value of 0.468 or higher can be classified as having a metabolic disease.

Table 2 exemplifies the methylation criteria of cg23248424.

The index cg02891314 (GFPT2) has an AUC value of 0.878 obtained from the methylation value, which can increase the predictive power of metabolic diseases.

Accordingly, when the methylation value of the indicator cg02891314 (GFPT2) is used as an input value, the metabolic disease risk prediction system 100 compares the average methylation value of 0.337 in normal people to 10 of the entire methylation range (0 to 1). Patients with a methylation of 0.4337 or more, which differs by more than % (beta value: 0.1), can be classified as having a metabolic disease.

Table 3 exemplifies the methylation criteria of the index cg02891314 (GFPT2).

The index cg03849834 (TREML4) has an AUC value of 0.767 obtained from the methylation value, which can increase the predictive power of metabolic diseases.

Accordingly, when the methylation value of the indicator cg03849834 (TREML4) is used as an input value, the metabolic disease risk prediction system 100 compares the average methylation value of 0.825 in normal people with the full range of methylation values (0 to 1). Patients with a methylation of 0.925 or more, which is a difference of 10% (beta value: 0.1) or more, can be classified as having a metabolic disease.

Table 4 exemplifies the methylation criteria of the index cg03849834 (TREML4).

Hereinafter, in FIG. 4, the workflow of the metabolic disease risk prediction system 100 according to embodiments of the present invention will be described in detail.

Figure 4 is a flow chart showing a metabolic disease risk prediction method according to an embodiment of the present invention.

The metabolic disease risk prediction method according to this embodiment may be performed by the metabolic disease risk prediction system 100 .

First, the metabolic disease risk prediction system 100 may measure the degree of methylation in the methylation region in relation to the tester group.

In addition, the metabolic disease risk prediction system 100 performs metabolic disease risk prediction modeling using the measured methylation level, and according to the results of the metabolic disease risk prediction modeling, the metabolic disease risk for the examiner group can tell you

The metabolic disease risk prediction system 100 may analyze methylation information of a normal group and a metabolic disease patient group.

In addition, the metabolic disease risk prediction system 100 may measure RNA-seq (large transcript data) for each of the normal group and the metabolic disease patient group.

In addition, the metabolic disease risk prediction system 100 may select the methylation region by verifying the methylation information by RNA-seq. Here, the methylation region for measuring the degree of methylation can be selected by analyzing 800,000 methylation information of normal people and patients with metabolic diseases and verifying RNA-seq (gene expression) information.

In addition, the metabolic disease risk prediction system 100 measures RNA-seq (large-capacity transcriptome data) and methylation levels for each of the normal group and the metabolic disease patient group (410). Step 410 may be a process of obtaining information/data related to genes that can distinguish a normal person from a person with a metabolic disease.

Here, RNA-Seq (RNA-sequencing) may refer to sequencing RNA strands made into a library suitable for NGS. By RNA-Seq, the expression of messenger RNA (mRNA) that synthesizes proteins and some mutations can be confirmed, and non-coding RNAs that do not synthesize proteins can also be examined. there is.

The degree of methylation may refer to the level of DNA methylation for each subject belonging to the normal group and the metabolic disorder group. DNA methylation is the process of forming 5-methylcytosine (5-mC) by adding one methyl group to the 5th carbon position (C5) of cytosine, regulating gene expression, silencing transposon, stabilizing genome It may be a very important epigenetic mechanism related to X-chromosome inactivation, genomic imprinting, etc.

In the embodiment, RNA-seq (large-scale transcriptome data) and methylation levels are measured for each of the group of 9 healthy people and the group of 11 people with metabolic disease, thereby obtaining gene-related information/data of each subject.

In addition, the metabolic disease risk prediction system 100 uses the RNA-seq to select differentially expressed genes whose expression changes only in the metabolic disease patient group compared to the normal group (420). Step 420 may be a process of identifying a gene that is characteristically expressed only in a subject belonging to a metabolic disease patient group based on the measured RNA-seq, and selecting it as a differentially expressed gene.

In the above-described embodiment, the metabolic disease risk prediction system 100 identifies genes that are not expressed in 9 people belonging to the normal group but are commonly expressed in 11 people belonging to the metabolic disease group through RNA-seq, and differentially expressed. It can be selected as a gene.

In the selection of differentially expressed genes, the metabolic disease risk prediction system 100 checks the expression level for each gene in association with the sequencing read of the nucleotide sequence produced in the RNA-seq, and folds according to the identified expression level. A gene with a difference in change (FC) of more than 2 times and a P-value of 0.05 or less, which indicates significance, can be selected as a differentially expressed gene.

That is, the metabolic disease risk prediction system 100 removes adapters and removes overlapping reads among sequencing reads of Q30 or higher of the nucleotide sequence produced by RNA-seq in order to select genes whose expression changes in metabolic disease patients compared to normal people. After that, the expression level of each gene can be measured by mapping the human genome. Thereafter, the metabolic disease risk prediction system 100 selects a gene with a P-value value of 0.05 or less that indicates significance while the expression fold change (FC) is more than twice as different, and selects a differentially expressed gene.

Subsequently, the metabolic disease risk prediction system 100 may select a differential methylation region in which methylation changes only in the metabolic disease patient group compared to the normal group using the methylation degree (430). Step 430 may be a process of identifying a region in which a methylation value characteristically changes only in a subject belonging to a metabolic disease patient group is identified and selected as a differential methylation region, based on the measured methylation degree.

In the above embodiment, the metabolic disease risk prediction system 100, through the degree of methylation, the methylation value, which did not change in 9 people belonging to the normal group, changes in common in 11 people belonging to the metabolic disease patient group. It can be identified and selected as a differential methylation region.

In the selection of differential expression genes, the metabolic disease risk prediction system 100, from the image file of the methylation chip (Human Methylation 850K BeadChip) obtained through the measurement of the degree of methylation, the P-value value indicating significance A region of 0.05 or less may be selected as the differential methylation region.

That is, the metabolic disease risk prediction system 100 uses the image file of the methylation chip to select a region in which methylation changes in metabolic disease patients compared to normal individuals. Statistical difference in metabolic disease patients compared to normal individuals (P value < 0.05) CpG regions that show can be selected as differential methylation regions.

In addition, the metabolic disease risk prediction system 100 determines an epigenetic index for predicting a patient with a metabolic disease through modeling of the selected differential expression gene and the differential methylation region (440). Step 440 may be a process of extracting selected differentially expressed genes within the selected differential methylation region and determining epigenetic markers used for predicting risk of metabolic diseases.

In determining the epigenetic index, the metabolic disease risk prediction system 100 identifies a plurality of genetic indexes that belong to the differential methylation region and are the differentially expressed genes, and among the plurality of genetic indexes, AUC (Area Under the Curve) ), n genetic indexes having relatively high values (where n is a natural number of 3 or more) can be determined as the epigenetic index.

Here, AUC may refer to a subregion of a Receiver Operating Characteristics (ROC) curve that is useful when evaluating model performance in an imbalanced dataset. The ROC curve is a tool widely used to visually show the classification, layer probability estimation, and scoring performance of a model, and it allows us to know the fundamental strengths and weaknesses of each model because it expresses the model performance itself regardless of various application conditions. AUC corresponds to the area under the ROC curve, which briefly tells important information, and can be the area under the classifier curve within the unit square, with values ranging from 0 to 1.

In one embodiment, the metabolic disease risk prediction system 100 may determine including at least indicators 'cg23248424', 'cg02891314', and 'cg03849834' as the n genetic indicators.

After determining the indices 'cg23248424', 'cg02891314', and 'cg03849834', the metabolic disease risk prediction system 100 of the present invention can predict metabolic disease patients and predict their risk using these epigenetic indicators.

According to the present invention, it is possible to provide a method and system for predicting metabolic diseases and predicting the risk of metabolic diseases by utilizing methylation epigenetic regions that change in metabolic diseases.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

100: metabolic disease risk prediction system
110: measuring unit
120: selection unit
130: decision unit

Claims (15)

Measuring a degree of methylation in a methylation region with respect to a group of testers;
performing metabolic disease risk prediction modeling using the measured methylation level; and
Notifying the risk of metabolic disease for the tester group according to the results of the metabolic disease risk prediction modeling
Metabolic disease risk prediction method comprising a. According to claim 1,
Analyzing methylation information of a normal group and a metabolic disorder group;
measuring RNA-seq (large-capacity transcriptome data) for each of the normal group and the metabolic disease patient group;
Selecting the methylation region through verification by the RNA-seq for the methylation information
Metabolic disease risk prediction method further comprising a. According to claim 1,
Measuring RNA-seq (large-capacity transcriptome data) and methylation levels for each of the normal group and the metabolic disease patient group;
Selecting a differentially expressed gene whose expression changes only in the metabolic disease patient group compared to the normal group by using the RNA-seq;
selecting a differential methylation region in which methylation changes only in the metabolic disease patient group compared to the normal group by using the degree of methylation; and
Determining epigenetic markers for predicting patients with metabolic diseases through modeling of the selected differentially expressed genes and the differential methylation region
Metabolic disease risk prediction method further comprising a. According to claim 3,
The step of selecting the differential expression gene,
Checking the expression level of each gene in association with the sequencing read of the nucleotide sequence produced in the RNA-seq; and
Selecting, as the differentially expressed gene, a gene having a P-value value of 0.05 or less, which indicates significance, while the fold change (FC) according to the confirmed expression level is more than twice as different.
Metabolic disease risk prediction method comprising a. According to claim 3,
In the step of selecting the differential methylation region,
Selecting a region having a P-value of 0.05 or less indicating significance as the differential methylation region from the image file of the methylation chip (Human Methylation 850K BeadChip) obtained through the measurement of the degree of methylation.
Metabolic disease risk prediction method comprising a. According to claim 3,
The step of determining the epigenetic marker,
identifying a plurality of genetic markers that belong to the differential methylation region and are the differentially expressed genes; and
Determining, among the plurality of genetic indices, n genetic indices having relatively high AUC (Area Under the Curve) values (where n is a natural number of 3 or more) as the epigenetic indices;
Metabolic disease risk prediction method comprising a. According to claim 6,
The step of determining the n genetic markers as the epigenetic markers,
Determining including at least indicators 'cg23248424', 'cg02891314', and 'cg03849834' as the n genetic indicators
Metabolic disease risk prediction method comprising a. a measurement unit for measuring a degree of methylation in a methylation region in relation to a group of testers; and
A determination unit that performs metabolic disease risk prediction modeling using the measured methylation degree and informs the metabolic disease risk for the tester group according to the results of the metabolic disease risk prediction modeling
Metabolic disease risk prediction system comprising a. According to claim 8,
In the measuring unit, as the methylation information of the normal group and the metabolic disease patient group is analyzed, and RNA-seq (large transcript data) is measured for each of the normal group and the metabolic disease patient group,
Selection unit for selecting the methylation region through verification by the RNA-seq for the methylation information
Metabolic disease risk prediction system further comprising a. According to claim 8,
In the measurement unit, as the RNA-seq (large-capacity transcript data) and the degree of methylation were measured for each of the normal group and the metabolic disease patient group,
Using the RNA-seq, select differentially expressed genes whose expression changes only in the metabolic disease patient group compared to the normal group, and using the methylation degree, methylation only in the metabolic disease patient group compared to the normal group Selection unit that selects this changing differential methylation region
Including more,
The decision section,
Determining epigenetic markers for predicting patients with metabolic diseases through modeling of the selected differential expression genes and the differential methylation region
Metabolic disease risk prediction system. According to claim 10,
The selection department,
In connection with the sequencing read of the nucleotide sequence produced in the RNA-seq, the expression level for each gene was confirmed, and the fold change (FC) according to the identified expression level was more than twice as different, indicating significance. Selecting a gene of 0.05 or less as the differential expression gene
Metabolic disease risk prediction system. According to claim 10,
The selection department,
From the image file of the methylation chip (Human Methylation 850K BeadChip) obtained through the measurement of the degree of methylation, a region having a P-value value of 0.05 or less indicating significance is selected as the differential methylation region.
Metabolic disease risk prediction system. According to claim 10,
The decision section,
A plurality of genetic markers that belong to the differential methylation region and are the differential expression genes are identified, and among the plurality of genetic markers, n genetic markers having a relatively high AUC value (n is a natural number of 3 or more) are selected as the epigenetic genes. determined by indicators
Metabolic disease risk prediction system. According to claim 13,
The decision section,
As the n genetic indicators, to determine including at least indicators 'cg23248424', 'cg02891314', 'cg03849834'
Metabolic disease risk prediction system. A computer-readable recording medium recording a program for executing the method of any one of claims 1 to 7.

Images