KR102371655B1 - Device, Method of Calculating Prostate Cancer Genetic Risk Score Based on Individual Weights for each Genetic Variation and Recording Medium thereof - Google Patents

Abstract

The present invention relates to a calculation device, calculation method, and a recording medium thereof for calculating a risk score for prostate cancer using genetic information. The prostate cancer risk calculation method according to an embodiment of the present invention includes the steps of receiving genetic information of a subject, calculating a genetic risk score for genetic information using a weighted risk model, and identifying a risk group to which the genetic risk score belongs and setting the subject as a subject for intensive management when the risk group to which the genetic risk score for genetic information belongs is a high-risk group.

Description

Device, Method of Calculating Prostate Cancer Genetic Risk Score Based on Individual Weights for each Genetic Variation and Recording Medium thereof

The present invention relates to a calculation device, calculation method, and a recording medium thereof for calculating a risk score for prostate cancer using genetic information.

Prostate cancer is the third most common and fourth most common cancer in men in Korea, and is the leading cause of death in men. Accordingly, studies such as using genetic information to predict prostate cancer have been conducted in the prior art.

On the other hand, the incidence and mortality rates of prostate cancer vary widely worldwide. Men in the United States and Europe have the highest incidence rates, and African Americans have the highest mortality rates, whereas the incidence and mortality rates in Asians are relatively high. It is low. These racial differences suggest that the onset of prostate cancer is likely due to genetic heterogeneity as well as environmental differences. Therefore, there is a need to determine the risk of prostate cancer by reflecting racial differences due to genetic heterogeneity.

In addition, since conventional prostate cancer diagnosis stops at guiding whether there is a cancer risk at the time of diagnosis, efficient management and monitoring for each subject is impossible.

An object of the present invention is to provide an apparatus, method, and recording medium for calculating a genetic risk score in order to predict prostate cancer by race using genetic information.

Another object of the present invention is to provide an apparatus, method, and recording medium for calculating an accurate genetic risk score by assigning different weights to representative genetic mutations that have a significant effect on the occurrence of prostate cancer.

Another object of the present invention is to provide an apparatus, method, and recording medium that provide efficient subject management by sequentially diagnosing the risk of prostate cancer.

However, these problems are exemplary, and the scope of the present invention is not limited thereto.

A method for calculating the risk of prostate cancer according to an embodiment of the present invention includes: receiving genetic information of a subject; calculating a genetic risk score for the genetic information using a weighted risk model; identifying a risk group to which the genetic risk score belongs; and when the risk group to which the genetic risk score for the genetic information belongs is a high-risk group, setting the subject as a subject for intensive management; may include.

In addition, the calculating of the genetic risk score may be characterized in that it is calculated through a weighted risk model corresponding to the genetic information.

In addition, the weighted risk model may be characterized by using 4 SNP (single nucleotide polymorphism) markers or 6 SNP markers.

Meanwhile, the recording medium according to an embodiment of the present invention may be a computer-readable recording medium in which a program for executing the method for calculating the risk of prostate cancer is recorded.

Other aspects, features, and advantages other than those described above will become apparent from the following detailed description, claims and drawings for carrying out the invention.

According to an embodiment of the present invention made as described above, a prostate cancer risk score reflecting the subject's racial specificity may be calculated by applying a different weighting model for each race.

In particular, according to an embodiment of the present invention, it is possible to accurately calculate the risk by assigning a weight to a specific genetic mutation among genetic information.

Of course, the scope of the present invention is not limited by these effects.

1 is a system diagram illustrating a system for calculating a prostate cancer genetic risk score according to an embodiment of the present invention.
2 is a block diagram for explaining the components of a calculation device according to an embodiment of the present invention.
3 is a flowchart illustrating a method of calculating a genetic risk score according to an embodiment of the present invention.
4 is a diagram illustrating general data of Manhattan plots in the discovery GWAS (Genome Wide Association Study) stage.
5 is a diagram illustrating a list of candidate genetic mutations included in the genetic risk score calculation according to an embodiment of the present invention.
6A and 6B are diagrams illustrating a Receiver Operating Characteristic (ROC) curve for comparing predictive power according to the number of genetic variations according to an embodiment of the present invention.
7A to 7G are diagrams for explaining the distribution of a Generic Risk Score (GRS) according to the number of genetic variations in a weighted model according to an embodiment of the present invention.
8A to 8G are diagrams for explaining the distribution of a genetic risk score (GRS) according to the number of genetic variations of a non-weighted model according to an embodiment of the present invention.
9 is a diagram for explaining the odds ratio for prostate cancer for each GRS group according to an embodiment of the present invention.
10 is a diagram for explaining an odds ratio in a GRS group, a middle-high risk group, according to an embodiment of the present invention.
11 is a diagram for explaining genetic variations included for comparison of weighted risk scores of different population groups according to an embodiment of the present invention.
12A and 12B are diagrams illustrating a GRS distribution when a weighted risk model according to an embodiment of the present invention is applied to European data and Korean data.
13A and 13B are diagrams illustrating ROC curves when the weighted risk model according to an embodiment of the present invention is applied to European data and Korean data.
14A and 14B are diagrams for explaining a genetic risk score group according to an embodiment of the present invention.

Hereinafter, various embodiments of the present disclosure are described in connection with the accompanying drawings. Various embodiments of the present disclosure are capable of various changes and may have various embodiments, and specific embodiments are illustrated in the drawings and the related detailed description is described. However, this is not intended to limit the various embodiments of the present disclosure to specific embodiments, and should be understood to include all modifications and/or equivalents or substitutes included in the spirit and scope of the various embodiments of the present disclosure. In connection with the description of the drawings, like reference numerals have been used for like components.

“Includes” can be used in various embodiments of the present disclosure. or "may include." Expressions such as etc. indicate the existence of the disclosed function, operation, or component, and do not limit one or more additional functions, operations or components. Also, in various embodiments of the present disclosure, "includes." Or "have." The term such as is intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, and is intended to indicate that one or more other features or numbers, steps, operation, component, part or It should be understood that it does not preclude the possibility of the existence or addition of combinations thereof.

In various embodiments of the present disclosure, expressions such as “or” include any and all combinations of words listed together. For example, "A or B" may include A, may include B, or may include both A and B.

Expressions such as “first”, “second”, “first”, or “second” used in various embodiments of the present disclosure may modify various components of various embodiments, but do not limit the components. does not For example, the above expressions do not limit the order and/or importance of corresponding components. The above expressions may be used to distinguish one component from another. For example, both the first user device and the second user device are user devices, and represent different user devices. For example, without departing from the scope of the various embodiments of the present disclosure, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component.

When an element is referred to as being "connected" or "connected" to another element, the element may be directly connected to or connected to the other element, but may be associated with the element. It should be understood that other new components may exist between the other components. On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it will be understood that no new element exists between the element and the other element. should be able to

In an embodiment of the present disclosure, terms such as “module”, “unit”, “part”, etc. are terms for designating a component that performs at least one function or operation, and these components are hardware or software. It may be implemented or implemented as a combination of hardware and software. In addition, a plurality of "modules", "units", "parts", etc. are integrated into at least one module or chip, and are integrated into at least one processor, except when each needs to be implemented in individual specific hardware. can be implemented as

Terms used in various embodiments of the present disclosure are only used to describe one specific embodiment, and are not intended to limit the various embodiments of the present disclosure. The singular expression includes the plural expression unless the context clearly dictates otherwise.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the present disclosure pertain.

Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in various embodiments of the present disclosure, ideal or excessively formal terms not interpreted as meaning

Hereinafter, various embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a system diagram illustrating a system for calculating a prostate cancer genetic risk score according to an embodiment of the present invention.

Referring to FIG. 1 , the calculation system may include a risk score calculation device 100 (hereinafter referred to as calculation device), a server 200 , a terminal 301 , and an external organization 302 .

The calculator 100 may be a desktop computer, but is not limited thereto, and may be any type of electronic device capable of executing a program for performing a method for calculating a risk score for prostate cancer through genetic information. there is.

The user terminal 301 refers to a communication terminal capable of transmitting and receiving data in a wired/wireless communication environment. Here, the user terminal 301 may be a user's personal computer or a user's portable terminal. The user may be a subject, and the subject may directly input genetic information and transmit it to the server 200 .

In FIG. 1, the user terminal 301 is illustrated as a mobile terminal as a smart phone, but the inventive concept is not limited thereto. As described above, a program capable of connecting to a communication network is loaded or includes all kinds of electronic devices connected to a communication module. can do. Specifically, the user terminal 301 is a computer (eg, desktop, laptop, tablet, etc.), a media computing platform (eg, cable, satellite set-top box, digital video recorder), a handheld computing device (eg, PDA, e-mail client, etc.), any type of mobile phone, or any other type of computing or communication platform, but the present invention is not limited thereto.

Although each user terminal 301 is illustrated in the singular in FIG. 1 , according to an embodiment of the present invention, a plurality of user terminals may be directly connected to the calculator 100 and the server 200 .

The institution 302 may be a hospital or a public institution that has obtained genetic information of a plurality of subjects. The institution 302 may transmit a database of genetic information of a plurality of subjects to the server 200 , and the server 200 may determine a weight model for calculating a prostate cancer genetic risk score based on the received database.

The calculator 100 may be a device that receives the subject's genetic information and calculates the subject's prostate cancer risk score by using a weighted risk model. According to an embodiment of the present invention, the calculator 100 may obtain the subject's race information, determine a weighted risk model corresponding to the race information, and calculate the genetic risk score. In this case, the race information may be input to the calculation device 100 by the user, but is not limited thereto, and may be input to the user terminal 301 by the user.

According to another embodiment of the present invention, the calculator 100 may identify a specific SNP (single nucleotide polymorphism) of a nucleotide sequence included in the genetic information. In this case, the specific SNP may include rs16901979, rs1512268, rs4430796 and rs2735739.

According to another embodiment of the present invention, the calculator 100 receives the first genetic information of a subject and calculates a first genetic risk score for the first genetic information by using a first weighted risk model corresponding thereto. can do.

The calculator 100 determines a group to which the first genetic risk score belongs among a plurality of genetic risk score groups, and when the first genetic risk score is determined to be a high risk group, calculates a second genetic risk score using a second weighted risk model can do. On the other hand, when it is determined that the first genetic risk score is a low-risk group, the first genetic risk score may be determined as a genetic risk score for the first genetic information.

In this case, the plurality of genetic risk score groups may be groups according to a preset GRS distribution. For example, it may be classified into a high-risk group, a medium-risk group, and a low-risk group based on a GRS score previously calculated based on a database for a plurality of subjects, but is not limited thereto.

The first weighted risk model may be a weighted risk model determined in consideration of the subject's race information. The second weighted risk model may be a weighted model determined in consideration of race information and life information of a subject. However, race information and/or life information of a subject are only examples, and a weight model may be determined using various information about the subject.

In addition, the determination of the weighted risk model through the information on the subject is only an exemplary embodiment, and criteria for determining the first weighted risk model and the second weighted risk model may vary. For example, the first weighted risk model may be a standardized weighted risk model using 5 SNP markers, and the second weighted risk model may be a higher performance model using 4 SNP markers.

Through the above-described embodiment, it is possible to primarily diagnose the genetic risk to the subject, and perform a more precise genetic risk diagnosis if necessary.

According to another embodiment of the present invention, when the calculating device 100 receives the second genetic information of the subject at a point later than the first genetic information, the group to which the genetic risk score for the second genetic information belongs is the first 1 In case of a change to a high-risk group compared to the genetic risk score for genetic information, the subject may be set as a subject for intensive management.

That is, when the risk score for prostate cancer of the subject increases, it has the effect of setting the subject as a subject for intensive management and presenting guidelines. Specifically, when the subject is set as the subject of intensive management, the calculator 100 may provide guidelines for the subject's lifestyle, eating habits, and the like, and guide the next prostate cancer examination schedule.

In addition, according to an embodiment of the present invention, the calculator 100 may determine the intensive management target grade according to the degree of increase in the risk score. For example, if the level of risk score is level 4, if the level is changed to a high-risk group by level 1, it is determined as a lower-level subject for intensive management, and a subject who is changed to a high-risk group by level 2 or higher may be determined as a higher-level subject for intensive care. , this is only an example, and the grade of the risk score and the grade of the subject for intensive management may vary.

On the other hand, the calculation device 100 according to the above-described example may provide additional guiding for the subject determined to be a subject for senior intensive management. For example, the calculator 100 may transmit a periodic test guide text or test guide mail to the subject by using personal information such as contact information of the higher-level centralized management target.

Meanwhile, the weighted risk model may be received from the server 200 . That is, the server 200 may determine a weighted risk model for predicting prostate cancer based on the database received from the terminal 301 and the external organ 302 , and transmit it to the calculator 100 .

Specifically, the server 200 may search for prostate cancer-related genetic mutations. Specifically, the server 200 can compare prostate cancer patients (998 people)-normal controls (2,641 people) in the discovery set for 60,276 genetic mutations. Also, the server 200 may extract 17 genetic mutations for replication. The server 200 may determine a weighted risk model based on the database and genetic variation.

According to an embodiment of the present invention, the server 200 extracts 9 representative mutations out of 17 mutations and weighted inheritance as a new independent data source (replication set: prostate cancer patients (514 patients) + normal controls (548 people))) A risk score can be calculated. In this case, the server 200 may calculate a genetic risk score related to prostate cancer through a specific genetic mutation. In this case, in the process of extracting the representative mutation, the genetic mutation divided by race may be considered.

The server 200 may give weight to the number of occurrences of the genetic mutation, but is not limited thereto. According to an embodiment of the present invention, the server 200 may assign weights according to the importance (or degree of contribution to disease) of the genetic mutation. That is, the server 200 may use a value obtained by taking a logarithm of an odds ratio indicating the degree of association with the genetic variation as a weight.

According to an embodiment of the present invention, the server 200 may learn a weighted risk model using an artificial intelligence model. At this time, the artificial intelligence model may be various deep learning algorithms including CNN, RNN, BNN, etc., but is not limited thereto.

In addition, in the weighted risk model, according to the number of risk alleles for each SNP included in the genetic information, homozygous of non-risk alleles is 0, heterozygous alleles (heterozygous of alleles) may be a model in which a detailed score of 1 and homozygous of the risk alleles is given, and a weight corresponding to each SNP is given to the detailed score, but is not limited thereto . This will be described in detail later.

The calculator 100 according to an embodiment of the present invention may be implemented in the form of a calculator. That is, the calculator 100 may receive a genetic information value related to the genetic mutation, and output the prostate cancer risk and/or guideline calculated from the input values through the display.

The calculator 100 according to an embodiment of the present invention may change the type of genetic mutation associated with prostate cancer. The calculator 100 may change the type of genetic variation to be reflected in the weight model according to user information, for example, information on age, gender, race, and the like.

In this case, the calculator 100 may determine a weight model corresponding to user information from among various weight models set in the server 200 in cooperation with the server 200 . For example, if it is determined that the input subject's race is European, the calculator 100 receives a weighted model in which weights are given to genetic variations corresponding to Europeans from the server 200, and calculates the subject's prostate cancer risk score. can do.

The calculator 100 according to another embodiment of the present invention may set a weight model by inferring a relationship between the user's or subject's body information, life information, and a prostate cancer risk score. For example, when the subject is a smoker, the calculator 100 may calculate a risk score for prostate cancer by using a weighted model in which a weight is assigned to a genetic variation corresponding to the living information. Even in this case, the calculator 100 may use various weight models in conjunction with the server 200 .

2 is a block diagram for explaining the components of a calculation device according to an embodiment of the present invention.

Referring to FIG. 2 , the calculator 100 may include a communication unit 110 , an input unit 120 , a memory 130 , a display 140 , and a processor 150 .

The communication unit 110 is configured to transmit and receive data to and from external organizations and devices including the server 200 , the user terminal 301 , and the organization 302 . The communication unit 100 includes a Bluetooth communication unit, a BLE (Bluetooth Low Energy) communication unit, a near field communication unit, a WLAN (Wi-Fi) communication unit, a Zigbee communication unit, an infrared (IrDA, infrared Data Association) communication unit, a WFD ( It may include a Wi-Fi Direct) communication unit, an ultra wideband (UWB) communication unit, a short-distance communication unit such as an Ant+ communication unit, and a mobile communication network.

The input unit 120 may include a user interface for inputting various types of information into the calculation device 100 . In this case, the various information input to the calculation device 100 may include, but is not limited to, genetic information of the subject, information on the age, sex, race, etc. of the subject, and lifestyle information of the subject.

The memory 130 may store various data for the overall operation of the calculation device 100 , such as a program for processing or controlling the processor 150 . The memory 130 may store a plurality of application programs (or applications) driven by the calculation device 100 , data for operation of the calculation device 100 , and commands. At least some of these application programs may be downloaded from an external server through wireless communication. In addition, at least some of these application programs may exist on the calculation device 100 from the time of shipment for a basic function of the calculation device 100 . The application program is stored in the memory 130 and may be driven by the processor 150 to perform an operation (or function) of the calculation device 100 .

The display 140 may display the prostate cancer risk score of the subject calculated by the calculator 100 through the weighted risk model. According to an embodiment of the present invention, the display 140 may display a prostate cancer risk score calculated from information input through the input unit 120, and through this, guidelines for the subject's lifestyle, etc. can be displayed on the display. can be printed through

The display 140 may be implemented with various types of display panels. For example, the display panel is a liquid crystal display (LCD), organic light emitting diode (OLED), active-matrix organic light-emitting diode (AM-OLED), liquid crystal on silicon (LcoS), digital light processing (DLP), etc. It can be implemented with various display technologies. Also, the display 140 may be coupled to at least one of a front area, a side area, and a rear area of the display apparatus 140 in the form of a flexible display.

The display 140 may be implemented as a touch screen having a layer structure. The touch screen may have a function of detecting not only a display function but also a touch input position and a touched area, as well as a touch input pressure, and also has a function of detecting a proximity touch as well as a real-touch. can

The processor 150 is configured to control the calculation device 100 as a whole. Specifically, the processor 150 controls the overall operation of the calculation device 100 by using various programs stored in the memory 130 of the calculation device 100 . For example, the processor 150 may include a CPU, a RAM, a ROM, and a system bus. Here, the ROM is a configuration in which an instruction set for system booting is stored, and the CPU copies the operating system stored in the memory of the calculation device 100 to the RAM according to the instructions stored in the ROM, and executes O/S to boot the system. . Upon completion of booting, the CPU may perform various operations by copying various applications stored in the memory 130 to the RAM and executing them. Although it has been described above that the processor 150 includes only one CPU, it may be implemented with a plurality of CPUs (or DSPs, SoCs, etc.).

According to an embodiment of the present invention, the processor 150 may be implemented as a digital signal processor (DSP), a microprocessor, or a time controller (TCON) for processing a digital signal. Without limitation, a central processing unit (CPU), a micro controller unit (MCU), a micro processing unit (MPU), a controller, an application processor (AP), or a communication processor ( communication processor (CP)), may include one or more of an ARM processor, or may be defined as a corresponding term In addition, the processor 150 may include a system on chip (SoC), large scale integration (LSI) in which a processing algorithm is embedded. ) or implemented in the form of a field programmable gate array (FPGA).

According to an embodiment of the present invention, the processor 150 may include a genetic risk score calculating unit 151 and a risk class determining unit 152 .

The genetic risk score calculation unit 151 is configured to calculate the genetic risk score of the subject through the inputted subject information, and the risk grade determination unit 152 determines the risk score grade through the subject's weighted risk model. configuration to do

Each of the genetic risk score calculating unit 151 and the risk grade determining unit 152 may be implemented by a processor 150 and the like required to execute a program on a computing device. As such, the genetic risk score calculating unit 151 and the risk grade determining unit 152 may be implemented by physically independent components, or may be implemented in a form that is functionally divided within one processor.

Meanwhile, in FIGS. 1 and 2 , it is illustrated that the server 200 is implemented as a separate configuration from the calculation device 100 , but according to an embodiment of the present invention, the server 200 is configured with the calculation device 100 and one It can be implemented as a configuration.

For example, a series of processes executed in the server 200 may be executed in the calculation device 100 . That is, the calculator 100 may receive data directly from the hospital 301 , the user terminal 302 , and the like, and determine a weight risk model that applies different weights to correspond to subject information based on the data.

Hereinafter, for convenience of description, an embodiment in which all processes performed in the server 200 are performed in the calculation device 100 will be described.

3 is a flowchart illustrating a method of calculating a genetic risk score according to an embodiment of the present invention.

The calculator 100 may receive genetic information about the subject (S300). In this case, the genetic information may include a single nucleotide polymorphism (SNP) associated with prostate cancer and a continuous nucleotide sequence including the SNP. In addition, the genetic information may include various information such as race information and lifestyle information about the subject.

The calculator 100 may determine the first weighted risk model based on the subject's genetic information. In this case, the calculator 100 may determine a first weighted risk model corresponding thereto by comparing the genetic ratio difference between races. For example, when the subject's race information is European, the calculator 100 may determine a first weighted risk model in which a weight is assigned to a specific genetic mutation highly correlated with a European prostate cancer risk. To compare the gene ratio between races, the method of 'A Draft Sequence of the Neandertal Genome' published in Science in 2010 may be used, but is not limited thereto.

The calculator 100 may calculate a first genetic risk score through the first weighted risk model ( S310 ). Meanwhile, the calculator 100 may determine whether the calculated first genetic risk score is a high-risk group (S320). As a result of the determination, if the first genetic risk score is not the high-risk group (S320-N), the corresponding score may be determined as the final genetic risk score.

However, if it is determined that the first genetic risk score is a high risk group (S320-Y), the calculator 100 may determine a second weighted risk model to calculate a second genetic risk score (S340). Specifically, the calculator 100 may determine the second weighted risk model through additional information about the subject. For example, based on the information that the subject is a European and an elderly person, the calculator 100 may determine a second weighted risk model in which a weight is given to a specific genetic mutation highly related to the risk of prostate cancer of not only Europeans but also elderly people.

Thereafter, the calculator 100 may determine the second genetic risk score through the second weighted risk model as the final genetic risk score ( S330 ).

According to an embodiment of the present invention, the calculator 100 verifies the calculated genetic risk score through Receiver Operating Characteristics (ROC), and as a result of the verification, the genetic risk exceeding a preset Area under the curve (AUC) value. A risk score may be determined as the genetic risk score.

4 is a diagram illustrating general data of Manhattan plots in the discovery GWAS (Genome Wide Association Study) stage.

In general, GWAS compares the genetic information of two groups: Case (group with the trait of interest, patient group) and Control (group without the trait, normal group), and compares them to find a higher frequency, that is, association in the case. This is the step to find the gene that you have. In other words, GWAS is not a causal relationship, but a process of finding candidates for genes that appear by chance. Therefore, in general, research proceeds as a process of finding candidate genes through GWAS, and then confirming (replication cohort) in more patient groups or examining the results of biological verification in experiments, and finally revealing the gene-trait relationship.

In linkage disequilibrium (LD), genotypes that are close to each other do not mix with each other in the process of rearrangement of genotypes, but move together in a mosaic pattern, forming an LD block. When association analysis is performed on positions included in the same LD block, similar association strength and statistical significance (p-value) are shown. This is the reason why the signals all around are high in the Manhattan plot commonly used in GWAS as shown in FIG. 4 .

5 is a diagram illustrating a list of candidate genetic mutations included in the calculation of the genetic risk score according to an embodiment of the present invention.

The calculator 100 may extract nine major SNP genetic mutations related to prostate cancer. Referring to Figure 5, it can be confirmed that the major genetic variation SNPs are rs1456315, rs7837688, rs1512268, rs7501939, rs2735839, rs339331, rs2016588, rs11147922, rs57006764.

In the weighted risk model according to an embodiment of the present invention, weights may be assigned to each SNP based on an odds ratio (OR) associated with prostate cancer. For example, since the odds ratio of rs1456315 for prostate cancer among the SNPs is 1.797, 0.586, which is the result of log(OR), can be given as a weight to rs1456315.

A genetic risk score (GRS) in consideration of nine genetic variations according to an embodiment of the present invention based on the above-described weights may be as follows.

weighted genetic risk score (wGRS) =

In this case, X ₁ to X ₉ correspond to the number of risk alleles for each SNP (rs1456315, rs7837688, rs1512268, rs7501939, rs2735839, rs339331, rs2016588, rs11147922, rs57006764). Specifically, the calculation device 100 determines that, according to the number of risk alleles for each SNP included in the genetic information, the homozygous of non-risk alleles is X _n = 0 , a sub-score of X _n = 1 for heterozygous alleles and X _n = 2 for homozygous of the risk alleles. That is, the weighted risk model can be set to give a weight proportional to the number of each allele.

However, this is only an exemplary embodiment, and the calculator 100 of the present invention may determine the GRS equation using various numbers of genetic mutations. For example, while the above-described weight model is a GRS for all nine genetic mutations, the calculator 100 may determine the GRS expression according to a combination of optimal SNPs with high relevance according to the subject's information.

For example, the calculator 100 may assign weights using only the SNP marker set corresponding to the subject's race information, and may assign weights using only the SNP marker set corresponding to the subject's lifestyle information. .

The above-described optimal SNP marker set may be determined through an artificial intelligence model using a database, but this is only an example and may be determined through various methods.

6A and 6B are diagrams illustrating a Receiver Operating Characteristic (ROC) curve for comparing predictive power according to the number of genetic variations according to an embodiment of the present invention.

ROC (Receiver Operating Characteristics) curve is a graph visualized to evaluate prediction performance. The prediction performance is evaluated by the area under the curve (AUC). ROC indicates specificity and sensitivity according to each evaluation criterion in X and Y coordinates, respectively, and is connected with a line.

In this case, specificity is defined as the ratio of predicting disease-free patients without disease, and sensitivity is defined as the probability of predicting the presence of disease when the disease is present. The two indicators show a trade-off relationship with each other. The X, Y coordinates of the curve have values from (0,0) to (1,1), and the better the predictive power, the closer the AUC value is to 1.

According to an embodiment of the present invention, the calculator 100 can visualize how the sensitivity and specificity of the ROC vary according to the threshold of the genetic risk score, and calculate the AUC of the curve to evaluate the model's performance. can be evaluated In addition, the calculation device 100 of the present invention may indicate and compare how well the prostate cancer patient group and the normal group are distinguished according to the number of genetic mutations included according to the statistical significance level.

Referring to FIG. 6A , the weighted risk model shows the highest predictive performance while having the largest AUC value (0.680) when the number of genetic variations is 4 and 6. Also, referring to FIG. 6B , the weighted risk model shows the second highest predictive performance at 0.679 when the number of included genetic variations is 5 and 9.

7A to 7G are diagrams for explaining the distribution of a Generic Risk Score (GRS) according to the number of genetic variations in a weighted model according to an embodiment of the present invention.

7A is a table showing the GRS and AUC for each number of upper SNPs according to the p value (statistical significance) according to an embodiment of the present invention.

7b to 7g are graphs showing the GRS distribution for cases (group with the trait of interest, patient group) and control (group without the trait of interest, normal group) sequentially from 4 to 9 SNP markers, respectively. am.

Referring to FIGS. 7A to 7G , when there are 4 and 6 markers, the GRS value is large and the accuracy is high.

8A to 8G are diagrams for explaining the distribution of a Generic Risk Score (GRS) according to the number of genetic variations in a non-weighted model according to an embodiment of the present invention.

8A is a table showing GRS and AUC for each number of upper SNPs according to p-value (statistical significance) according to an embodiment of the present invention.

8b to 8g are graphs showing the GRS distribution for cases (group with the trait of interest, patient group) and control (group without the trait of interest, normal group) sequentially from 4 to 9 SNP markers, respectively. am.

7A to 8G , it can be confirmed that the weighted risk model has a high GRS value and high accuracy in all types of the number of markers.

9 is a diagram for explaining the odds ratio for prostate cancer for each GRS group according to an embodiment of the present invention.

The odds ratio is to determine the causal relationship between the input variable (independent variable or explanatory variable) with respect to the dependent variable. If this value is lower than 1, it is an index indicating a negative correlation.

That is, the ratio of disease in people with a specific allele (odds) to the ratio of disease in people without the allele (ratio), and the disease between groups with and without a specific allele to compare the risk of

Prostate cancer group (Cases) Healthy controls risk allele A B Protective allele C D

Odds Ratio =

The x-axis of FIG. 9 is an arrangement of GRS groups in quartiles from the upper to the frequency distribution in the GRS distribution of FIGS. 7B to 7G according to an embodiment of the present invention, and the y-axis is prostate cancer for each GRS group It is about the odds ratio for .

Referring to FIG. 9 , Q4 (the highest group of quartiles) has a GRS range of 0.26 to 0.45, and an odds ratio (OR, Odds Ratio) of 6, which is highly correlated with prostate cancer. For the other groups, Q3 had a GRS range of 0.19 to 0.26 and an odds ratio of 3.1, Q2 had a GRS range of 0.12 to 0.19 with an odds ratio of 1.72, and Q1 had a GRS range of 0-0.12, and an odds ratio of 1 was used as a reference group for comparison with other groups. see.

10 is a diagram for explaining the odds ratio in the middle and high risk group of the GRS group according to an embodiment of the present invention. Referring to FIG. 10 , even within the Q4 group, when the GRS cut-off is 0.35 and the top 2.5% is the highest, the odds ratio is 4.65.

11 is a diagram for explaining genetic variations included for comparison of weighted risk scores of different population groups according to an embodiment of the present invention.

Xu, Jianfeng, et al. “Genome-wide association study in Chinese men identifies two new prostate cancer risk loci at 9q31. 2 and 19q13. 4." Nature genetics 44.11 (2012): 1231. Reference is made to the OR values of Europeans among the results of the literature (Supplementary Table 2).

Referring to FIG. 11 , it can be seen that, in particular, in the case of SNP rs4430796 of the risk allele A, the GRS for Koreans (KOR) is 0.292 and the GRS for Europeans (EUR) is 0.086, which is significantly different.

For example, when it is determined that the subject's race information is Korean, the calculator 100 may calculate the risk by including SNPs such as rs16901979, rs1512268, rs4430796, and rs2735839 in the weight model.

12A and 12B are diagrams illustrating a GRS distribution when a weighted risk model according to an embodiment of the present invention is applied to European data and Korean data.

12A shows the GRS distribution when weights derived from European data are applied, and FIG. 12B shows the GRS distribution when weights derived from Korean data are applied.

Referring to Figure 12a, as a result of applying European data to a weight model including SNPs such as rs1512268, rs4430796 and rs2735839, both control and case show low GRS. On the other hand, when Korean data is applied, a relatively high GRS distribution is shown as shown in FIG. 12B.

13A and 13B are diagrams illustrating ROC curves when the weighted risk model according to an embodiment of the present invention is applied to European data and Korean data.

Specifically, FIG. 13A shows the ROC when the weights derived from the European data are applied, and FIG. 13B shows the ROC when the weights derived from the Korean data are applied.

12a and 12b, the Korean data has an AUC of 0.604, which is higher than that of the European data, AUC of 0.591. That is, it can be seen that there is a need to use different weighting models for each race.

Accordingly, the calculator 100 of the present invention may calculate a risk score with high accuracy by differently changing the weighted risk model for each race.

14A and 14B are diagrams for explaining a genetic risk score group according to an embodiment of the present invention.

Figure 14a is an x-axis grouping the GRS from the top to the quintile in the frequency distribution in the GRS distribution, and the y-axis shows the number of cases (patient group) and control (normal group).

14B is an arrangement in which the x-axis is grouped into quartiles from the upper to the frequency distribution of GRS in the GRS distribution, and the y-axis represents the number of cases (patient group) and control (normal group).

That is, the calculator 100 of the present invention may variously group the quartiles or the fifth quartiles based on the GRS according to embodiments. When calculating the genetic risk score for the subject through the weighted risk model, the calculator 100 may determine to which group the score belongs.

According to an embodiment of the present invention, the calculation device 100 may receive the second genetic information of the subject at a point later than the first genetic information. In this case, when the group to which the genetic risk score for the second genetic information belongs is changed to a high-risk group compared to the genetic risk score for the first genetic information, the calculator 100 may set the subject as a subject for intensive management. The calculator 100 may present various guidelines, such as lifestyle improvement, periodic prostate cancer diagnosis, and the like to a subject set as a subject for intensive management.

According to another embodiment of the present invention, when the genetic risk score for the third genetic information that follows the second genetic information is changed to a low-risk group, the calculation device 100 may release the subject from the subject of intensive management. can

Meanwhile, the above-described methods according to various embodiments of the present disclosure may be implemented in the form of an application that can be installed in an existing electronic device.

In addition, the above-described methods according to various embodiments of the present disclosure may be implemented only by software upgrade or hardware upgrade of an existing electronic device.

In addition, various embodiments of the present invention described above may be performed through an embedded server provided in the electronic device or an external server of the electronic device.

On the other hand, according to an embodiment of the present invention, the various embodiments described above are a recording medium (readable by a computer or a similar device) using software, hardware, or a combination thereof. It may be implemented as software including instructions stored in a computer readable recording medium). In some cases, the embodiments described herein may be implemented by the processor itself. According to the software implementation, embodiments such as the procedures and functions described in this specification may be implemented as separate software modules. Each of the software modules may perform one or more functions and operations described herein.

Meanwhile, a computer or a similar device is a device capable of calling a stored command from a storage medium and operating according to the called command, and may include the device according to the disclosed embodiments. When the instruction is executed by the processor, the processor may directly or use other components under the control of the processor to perform a function corresponding to the instruction. Instructions may include code generated or executed by a compiler or interpreter.

The device-readable recording medium may be provided in the form of a non-transitory computer readable recording medium. Here, 'non-transitory' means that the storage medium does not include a signal and is tangible, and does not distinguish that data is semi-permanently or temporarily stored in the storage medium. In this case, the non-transitory computer-readable medium refers to a medium that stores data semi-permanently, rather than a medium that stores data for a short moment, such as a register, cache, memory, etc., and can be read by a device. Specific examples of the non-transitory computer-readable medium may include a CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, and the like.

As such, the present invention has been described with reference to the embodiments shown in the drawings, which are merely exemplary, and those skilled in the art will understand that various modifications and equivalent other embodiments are possible therefrom. . Therefore, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

100: risk score calculation device
110: communication department
120: input unit
130: memory
140: display
150: processor
151: Genetic risk score calculation unit
152: risk grading unit
200: server
301: user terminal
302: agency

Claims (6)

an input unit receiving a Korean input as the subject's race information, and receiving the first genetic information of the subject and the second genetic information of the subject at a point later than the first genetic information; and
calculating a first genetic risk score for the first genetic information and a second genetic risk score for the second genetic information by using the first weighted risk model;
When the group to which the second genetic risk score belongs rises by more than a preset grade as a high-risk group compared to the first genetic risk score, the subject is set as a subject for senior intensive management, and the group to which the second genetic risk score belongs is the A processor for setting the subject as a lower-level intensive care subject when the higher-risk group rises less than the preset grade compared to the first genetic risk score; and
The weighted risk model is

ego,
W1 is a weight value corresponding to the rs1456315 marker, W2 is a weight value corresponding to the rs7837688 marker, W3 is a weight value corresponding to the rs1512268 marker, and W4 is a weight value corresponding to the rs7501939 marker;
wherein X1 is the number of risk alleles corresponding to the rs1456315 marker, X2 is the number of risk alleles corresponding to the rs7837688 marker, X3 is the number of risk alleles corresponding to the rs1512268 marker, and X4 is the number of risk alleles corresponding to the rs7501939 marker, and X1 to X4 are one of 0 to 2, prostate cancer risk calculating device. The method of claim 1,
the processor
It is calculated through the weighted risk model,
W1 is a value obtained by taking the logarithm of an odds ratio associated with prostate cancer corresponding to the rs1456315 marker, W2 is a value obtained by taking the logarithm of an odds ratio associated with prostate cancer corresponding to the rs7837688 marker, and W3 is a value obtained by taking the logarithm of an odds ratio associated with prostate cancer corresponding to the rs7837688 marker. is a value obtained by taking the logarithm of an odds ratio associated with prostate cancer, and W4 is a value obtained by taking the logarithm of an odds ratio associated with prostate cancer corresponding to the rs7501939 marker, a prostate cancer risk calculator. The method of claim 1,
The weighted risk model is
A prostate cancer risk calculation device that trains using an artificial intelligence model. In the risk score calculation method of the prostate cancer risk calculation device including an input unit and a processor,
receiving, by the input unit, a Korean as the subject's race information;
receiving, by the input unit, the first genetic information of the subject and the second genetic information of the subject at a later time point than the first genetic information;
calculating, by the processor, a first genetic risk score for the first genetic information and a second genetic risk score for the second genetic information using a first weighted risk model;
When, by the processor, the group to which the second genetic risk score belongs rises by more than a preset grade as a high-risk group compared to the first genetic risk score, the subject is set as a higher-level intensive care subject, and the second genetic risk score setting the subject as a lower-level intensive care subject when the group to which the aggravation belongs rises by less than the preset grade as a high-risk group compared to the first genetic risk score; including,
The weighted risk model is

ego,
W1 is a weight value corresponding to the rs1456315 marker, W2 is a weight value corresponding to the rs7837688 marker, W3 is a weight value corresponding to the rs1512268 marker, and W4 is a weight value corresponding to the rs7501939 marker;
wherein X1 is the number of risk alleles corresponding to the rs1456315 marker, X2 is the number of risk alleles corresponding to the rs7837688 marker, X3 is the number of risk alleles corresponding to the rs1512268 marker, and X4 is the number of risk alleles corresponding to the rs7501939 marker, and X1 to X4 are one of 0 to 2. 5. The method of claim 4,
The step of calculating the genetic risk score is calculating through the weighted risk model,
W1 is a value obtained by taking the logarithm of an odds ratio associated with prostate cancer corresponding to the rs1456315 marker, W2 is a value obtained by taking the logarithm of an odds ratio associated with prostate cancer corresponding to the rs7837688 marker, and W3 is a value obtained by taking the logarithm of an odds ratio associated with prostate cancer corresponding to the rs7837688 marker. is a value obtained by taking the logarithm of an odds ratio associated with prostate cancer, and W4 is a value obtained by taking the logarithm of an odds ratio associated with prostate cancer corresponding to the rs7501939 marker. 6. according to any one of claims 4 and 5,
A computer-readable recording medium recording a program for executing the method for calculating the risk of prostate cancer.

Images