JP7141038B2 - Onset prediction device and onset prediction system - Google Patents

Description

The present invention relates to an onset prediction device and an onset prediction system.

Techniques for predicting the presence or absence of the onset of pregnancy-induced hypertension, the risk of onset, and the like are known. For example, a technique for early prediction of the risk of hypertensive disorders in pregnant women using sphingosine-1-phosphate as a metabolite biomarker is known (see, for example, Patent Document 1).

In addition, many studies have been conducted on the prediction of the onset of pregnancy-induced hypertensive syndrome.

For example, 1050 singleton pregnant women at 24 weeks 0 days to 36 weeks 6 days of pregnancy, who are suspected of developing preeclampsia, which is a type of pregnancy hypertension syndrome, were tested. (Soluble fms-like tyrosine kinase-1 (sFlt-1)/ placental growth factor (PlGF) ratio) has been reported to verify whether it can predict the subsequent onset of preeclampsia (e.g., See Non-Patent Document 1). According to this study, when the sFlt-1/PlGF ratio was 38 or less, the negative predictive value for ruling out preeclampsia within 1 week was 99.3%, exceeding 38. In this case, the positive predictive value for developing preeclampsia within 4 weeks was 36.7%.

In addition, a study has been reported in which small ncRNA, which is a type of transcript extracted from the blood of 35 people who developed preeclampsia at an early stage and 40 normal pregnant women, was analyzed (see, for example, Non-Patent Document 2). . According to this study, 25 small ncRNAs whose expression levels differed between the preeclampsia affected group and the non-affected group were found, suggesting their potential as predictive markers.

JP 2016-14685 A

Harald Zeisler, et.al. "Predictive Value of the sFlt-1:PlGF Ratio in Women with Suspected Preeclampsia" N Engl J Med 374;13-22, 2016. Yoffe, L, et al. "Early Detection of Preeclampsia Using Circulating Small non-coding RNA.", Scientific Reports volume 8, Article number: 3401 (2018)

Hypertensive Disorders of Pregnancy (HDP: Hypertensive Disorders of Pregnancy) is a dangerous disease that is the main cause of maternal death in the perinatal period. .

In addition, it is expected that HDP can prevent the onset and aggravation of the disease by treating it at an early stage. is being done.

Therefore, with conventional techniques, it is difficult to grasp the risk of developing HDP before pregnancy or predict the onset of HDP in early pregnancy.

An embodiment of the present invention has been made in view of the above problems, and facilitates grasping the risk of developing HDP before pregnancy or predicting the onset in early pregnancy, and To provide an HDP onset predicting device that does not need to predict the onset of HDP.

In order to solve the above problems, an onset prediction device according to an embodiment of the present invention obtains information on DNA mutations related to HDP from information on DNA mutations in a plurality of pregnant women, including pregnant women suffering from HDP. A prediction model that predicts the onset of HDP using the model creation information acquisition unit to be acquired, the information on the DNA mutation acquired by the model creation information acquisition unit, and the information indicating the presence or absence of the onset of pregnancy-induced hypertension syndrome. a subject information acquisition unit that acquires information on the HDP-related DNA mutation in a subject to be predicted, the prediction model created by the creation unit, and the subject information acquisition unit acquires and a prediction unit that predicts the onset of HDP in the subject subject to be predicted using the information on the DNA mutation obtained, and the information on the DNA mutation acquired by the subject information acquisition unit includes the pregnancy If part of the information on DNA mutations related to hypertension syndrome is not included, the creation unit converts the information on DNA mutations related to pregnancy hypertension syndrome to the information on DNA mutations acquired by the subject information acquisition unit The prediction model is created by excluding information on DNA mutations that are not included.

According to one embodiment of the present invention, it is possible to easily grasp the risk of developing HDP before pregnancy or predict it in early pregnancy, and to predict the onset of HDP without predicting the onset for each pregnancy. Equipment can be provided.

It is a figure which shows the structural example of the onset prediction apparatus which concerns on one Embodiment. It is a figure showing an example of hardware constitutions of a computer concerning one embodiment. 4 is a flowchart showing an example of onset prediction processing according to the first embodiment; 9 is a flowchart showing an example of onset prediction processing according to the second embodiment; FIG. 11 is a flow chart showing an example of processing of the onset prediction device according to the third embodiment; FIG. FIG. 14 is a flow chart showing an example of processing of the onset prediction device according to the fourth embodiment; FIG. It is a figure which shows the structural example of the onset prediction system which concerns on 5th Embodiment. FIG. 12 is a flowchart showing an example of narrowing down processing for DNA mutations according to the fifth embodiment. FIG. FIG. 14 is a flowchart showing an example of feature amount extraction processing according to the fifth embodiment; FIG. FIG. 12 is a diagram for explaining an example of feature amounts according to the fifth embodiment; FIG. FIG. 12 is a flowchart showing another example of narrowing down processing for DNA mutations according to the fifth embodiment; FIG. 1 is a diagram (1) showing examples of single nucleotide polymorphism candidates included in a candidate list according to an embodiment. FIG. FIG. 2 is a diagram (2) showing examples of single nucleotide polymorphism candidates included in a candidate list according to an embodiment. FIG. 3 is a diagram (3) showing examples of single nucleotide polymorphism candidates included in a candidate list according to an embodiment.

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described with reference to the drawings. In addition, the embodiment described below is an example, and the embodiment to which the present invention is applied is not limited to the following embodiment.

<Configuration of onset prediction device>
A configuration of an onset prediction device according to an embodiment will be described with reference to FIGS. The onset prediction device 100 is an information processing device having a computer configuration or a system including a plurality of information processing devices. The onset prediction device 100 has, for example, the hardware configuration of a general computer 200 as shown in FIG.

The onset prediction device 100, for example, predicts onset of hypertensive disorders of pregnancy (HDP: Hypertensive Disorders of Pregnancy) in a subject to be predicted, and outputs a prediction result. The prediction of the onset of HDP includes, for example, whether or not the subject will develop HDP, the risk of the subject developing HDP, and the like.

FIG. 1 is a diagram showing a configuration example of an onset prediction device 100 according to one embodiment. The onset prediction apparatus 100, for example, executes a predetermined program in the processor 201 of FIG. , a DNA sequence identification unit 105, a DNA mutation information extraction unit 106, an onset prediction unit 107, a result output unit 108, a determination unit 109, a storage unit 110, and the like.

It should be noted that at least part of the functional configurations described above may be realized by hardware.

The data acquisition unit 101 acquires information on DNA mutations in a plurality of pregnant women, including a pregnant woman suffering from HDP, as data for creating a prediction model. The data acquired by the data acquisition unit 101 may be, for example, sample data obtained in a cohort study on HDP, or data acquired from an external database or the like. The data acquisition unit 101 may acquire data from an external device such as an external server, or may acquire data stored in advance in the storage unit 110 .

DNA (DeoxyriboNucleic Acid) is a substance that records genetic information, and is composed of about 3 billion pairs of bases. DNA includes genes, which are specific regions (nucleotide sequences) containing genetic information.

DNA mutations are structural (nucleotide sequence) mutations in DNA, and include, for example, single nucleotide polymorphisms (SNPs), copy number variations (CNVs), DNA deletions, insertions, and the like. can be included.

Preferably, the data acquired by the data acquisition unit 101 includes information on single nucleotide polymorphisms in a plurality of pregnant women including pregnant women suffering from HDP.

The model creation information acquisition unit 102 acquires information on DNA mutations related to HDP from the information on DNA mutations in a plurality of pregnant women, including a pregnant woman suffering from HDP, acquired by the data acquisition unit 101 .

For example, the DNA mutation related to HDP may be determined in advance by the determination unit 109 described later, or may be stored in the storage unit 110 in advance.

Preferably, the HDP-related DNA mutation information acquired by the model creation information acquisition unit 102 includes the above-described HDP-related single nucleotide polymorphism information.

The predictive model creation unit 103 creates a predictive model for predicting the onset of HDP using the information on the DNA mutation associated with HDP acquired by the model creation information acquisition unit 102 .

For example, the predictive model creation unit 103 uses the single nucleotide polymorphism information related to HDP acquired by the model creation information acquisition unit 102 as feature amount data, and performs machine learning using the presence or absence of HDP onset as answer data. Create a prediction model to predict the presence or absence of the onset of

In this case, by inputting information on single nucleotide polymorphisms related to HDP in a subject to be predicted into a prediction model, a prediction result of whether or not the subject will develop HDP can be obtained.

As another example, the predictive model creation unit 103 divides the HDP-related single nucleotide polymorphism information acquired by the model creation information acquisition unit 102 into learning data and evaluation data at a predetermined ratio. In addition, the prediction model creation unit 103 uses the learning data to select feature amounts in, for example, an Elastic net, create a plurality of prediction models, apply the evaluation data to the prediction models, and obtain accuracy. The best one may be selected.

Note that there are various methods for creating a prediction model. The predictive model creation unit 103 may create a predictive model using a method such as lasso, adaptive elastic net, or adaptive lasso, without being limited to the elastic net.

The DNA sample acquisition unit 104 acquires a DNA sample of a subject to be predicted or information on the DNA sample. For example, the DNA sample acquisition unit 104 acquires a DNA sample obtained from blood, saliva, hair, or the like of a subject to be predicted, or information on the DNA sample.

The DNA sequence identification unit 105 analyzes the subject's specimen or the information on the specimen acquired by the DNA specimen acquisition unit 104, and identifies DNA sequence information (hereinafter referred to as DNA information).

The DNA mutation information extraction unit 106 extracts, for example, DNA mutation information related to HDP from the DNA sequence information identified by the DNA sequence identification unit 105 .

Note that the DNA sample acquisition unit 104, the DNA sequence identification unit 105, and the DNA mutation information extraction unit 106 are examples of the subject information acquisition unit 120 that acquires information on DNA mutations related to HDP in a subject to be predicted. .

For example, the subject information acquisition unit 120 may acquire information on the DNA sequence of the subject from an external device such as a DNA sequence analyzer that analyzes information on the DNA sequence from the DNA sample of the subject to be predicted. . In this case, the DNA mutation information extraction unit 106 extracts information on DNA mutations related to HDP from the DNA information acquired from the external device.

Furthermore, the subject information acquisition unit 120 identifies DNA sequence information from the DNA sample of the subject to be predicted, and also obtains information on the DNA mutation of the subject from an external device such as a DNA mutation analysis device. It may be one that acquires information on DNA mutations of a subject. In this case, the DNA mutation information extraction unit 106 extracts information on DNA mutations related to HDP from the information on DNA mutations acquired from the external device.

As described above, the onset prediction apparatus 100 does not necessarily have the DNA sample acquisition unit 104, the DNA sequence identification unit 105, and the like.

Preferably, the HDP-related DNA mutation information extracted by the DNA mutation information extraction unit 106 includes HDP-related single nucleotide polymorphism information.

The onset prediction unit 107 uses the prediction model created by the prediction model creation unit 103 and the DNA mutation information acquired by the DNA mutation information extraction unit 106 (or the subject information acquisition unit 120) to predict the occurrence of Predicts development of HDP.

For example, the onset prediction unit 107 inputs the DNA mutation information acquired by the DNA mutation information extraction unit 106 (or the subject information acquisition unit 120) into the prediction model created by the prediction model creation unit 103, so that the subject is HDP Predict whether or not to develop

Alternatively, the onset prediction unit 107 inputs the DNA mutation information acquired by the DNA mutation information extraction unit 106 (or the subject information acquisition unit 120) into the prediction model created by the prediction model creation unit 103, thereby causing HDP to develop. It is also possible to obtain a numerical value for judging whether or not to

In this case, the onset prediction unit 107 determines that the subject develops HDP when this numerical value exceeds (or falls below) the threshold, and when the numerical value does not exceed (or exceeds) the threshold, the subject develops HDP. You can expect not to. Furthermore, the onset prediction unit 107 may classify the numerical value into a plurality of levels, and predict the risk of developing HDP in the subject depending on which range the obtained numerical value belongs to.

The result output unit 108 outputs the prediction result predicted by the onset prediction unit 107 to the output device 205 in FIG. 2, for example.

The determining unit 109 determines information about DNA mutations associated with HDP to be used for onset prediction. For example, the storage unit 110 stores in advance a candidate list 111 that is a list of DNA mutation candidates associated with HDP. Further, the determination unit 109 determines information about a DNA mutation associated with HDP to be used for onset prediction from among the candidates for the DNA mutation associated with HDP stored in the candidate list 111 .

As an example, the determination unit 109 displays a list of HDP-related DNA mutation candidates stored in the candidate list 111 on the output device 205 or the like, and uses information on the selected DNA mutation for onset prediction. It may be determined based on information on DNA mutations associated with HDP.

As another example, the determination unit 109 uses the information of each candidate stored in the candidate list 111 or the information of each candidate obtained from an external device such as an external server to determine the HDP-related DNA used for onset prediction. It may be one that determines mutation information.

The storage unit 110 is realized by, for example, a program executed by the processor 201 in FIG. 2, the storage 203, the memory 202, etc., and stores various data, information, etc. including the candidate list 111 described above.

(Hardware configuration)
FIG. 2 is a diagram illustrating an example of a hardware configuration of a computer according to one embodiment; The onset prediction device 100 may be physically configured as a computer 200 including a processor 201, a memory 202, a storage 203, an input device 204, an output device 205, a communication device 206, a bus 207, and the like. In the following description, the term "apparatus" can be read as a circuit, device, unit, or the like.

The processor 201, for example, operates an operating system to control the entire computer. The processor 201 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic device, a register, and the like.

The processor 201 also reads programs (program codes), software modules and data from the storage 203 and/or the communication device 206 to the memory 202 and executes various processes according to them. As the program, a program that causes a computer to execute at least part of the operation of the onset prediction device 100 is used. Various processes executed in the onset prediction apparatus 100 may be executed by one processor 201, or may be executed by two or more processors 201 simultaneously or sequentially. Processor 201 may be implemented with one or more chips. Note that the program may be transmitted from a network via an electric communication line.

The memory 202 is a computer-readable storage medium, and is composed of at least one of, for example, ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), and the like. May be. The memory 202 may also be called a register, cache, main memory (main storage device), or the like. The memory 202 can store executable programs (program codes), software modules, etc. for carrying out the DNA mutation screening method according to one embodiment of the present invention.

The storage 203 is a computer-readable storage medium, for example, an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disc, a magneto-optical disc (for example, a compact disc, a digital versatile disc, a Blu-ray disk), smart card, flash memory (eg, card, stick, key drive), floppy disk, magnetic strip, and/or the like. The storage 203 may also be called an auxiliary storage device. The storage medium described above may be, for example, a database, server, or other suitable medium including memory 202 and/or storage 203 .

The input device 204 is an input device (for example, keyboard, mouse, microphone, switch, button, sensor, etc.) that receives input from the outside. The output device 205 is an output device (for example, display, speaker, LED lamp, etc.) that outputs to the outside. Note that the input device 204 and the output device 205 may be integrated (for example, a touch panel display).

The communication device 206 is hardware (transmitting/receiving device) for communicating between computers via a wired and/or wireless network, and is also called a network device, network controller, network card, communication module, or the like. Also, the communication device 206 may have a function of directly communicating with an external device by short-range wireless communication.

Devices such as the processor 201 and the memory 202 are connected by a bus 207 for communicating information. The bus 207 may be composed of a single bus, or may be composed of different buses between devices.

<Process flow>
Next, the flow of processing of the onset prediction method according to this embodiment will be described.

[First Embodiment]
FIG. 3 is a flowchart illustrating an example of onset prediction processing according to the first embodiment. This process is an example of an onset prediction process in which the onset prediction device 100 predicts whether or not a subject to be predicted will develop HDP.

In step S<b>301 , the determination unit 109 of the onset prediction apparatus 100 determines DNA mutation information to be used for onset prediction from among HDP-related DNA mutation candidates stored in the candidate list 111 .

For example, the determination unit 109 selectably displays a list of HDP-related DNA mutation candidates stored in the candidate list 111 on the output device 205 or the like, and information on the selected DNA mutation is used as onset prediction. You may determine the information of the DNA mutation used for.

Further, the determination unit 109 may determine (all) DNA mutation candidates associated with HDP stored in the candidate list 111 as DNA mutation information to be used for onset prediction. Furthermore, the determination unit 109 uses the information of each candidate stored in the candidate list 111 or the information of each candidate obtained from an external device such as an external server to obtain information about DNA mutations related to HDP used for onset prediction. may be determined.

Note that this process has only to be executed at least once before starting the processes after step S302, and the user can execute or omit this process as necessary.

In step S302, the onset prediction apparatus 100 acquires information on DNA mutations related to HDP from information on DNA mutations in a plurality of pregnant women, including a pregnant woman suffering from HDP. For example, the data acquisition unit 101 acquires information on DNA mutations in a plurality of pregnant women including pregnant women suffering from HDP. In addition, the model creation information acquisition unit 102 acquires (extracts) information on DNA mutations related to HDP to be used for predicting the onset determined in step S301 from the information on DNA mutations acquired by the data acquisition unit 101 .

In step S303, the prediction model creation unit 103 of the onset prediction apparatus 100 creates a prediction model for predicting the onset of HDP using the DNA mutation information acquired in step S302.

For example, the predictive model creation unit 103 divides the information on DNA mutations associated with HDP acquired by the model creation information acquisition unit 102 into learning data and evaluation data at a predetermined ratio. In addition, the prediction model creation unit 103 uses the learning data to select feature amounts in the elastic net, create a plurality of prediction models, apply the evaluation data to the prediction models, and obtain the best accuracy. choose things.

Alternatively, the predictive model creation unit 103 performs machine learning using the information on the DNA mutation related to HDP acquired by the model creation information acquisition unit 102 as feature amount data and the presence or absence of the onset of HDP as response data. You may create a prediction model that predicts the presence or absence of

Further, the onset prediction apparatus 100 executes the processes of steps S304 and S305, for example, in parallel with the processes of steps S302 and S303, or before and after the processes of steps S302 and S303.

In step S304, the DNA sequence identification unit 105 of the onset prediction apparatus 100 analyzes the subject's sample or the information on the sample acquired by the DNA sample acquisition unit 104, and acquires DNA information (DNA sequence information).

As described above, the onset prediction apparatus 100 specifies DNA sequence information from a DNA sample of a subject, and obtains DNA mutation information of the subject from an external device such as a DNA mutation analysis device. DNA mutation information may be acquired.

In step S305, the DNA mutation information extraction unit 106 of the onset prediction apparatus 100 acquires information on the DNA mutation associated with HDP determined in step S301 from the DNA information acquired in step S304.

In step S<b>306 , the onset prediction unit 107 of the onset prediction apparatus 100 inputs the subject's DNA mutation information extracted by the DNA mutation information extraction unit 106 to the prediction model created by the prediction model creation unit 103 . As a result, for example, a numerical value for determining whether HDP develops is calculated by a machine learning technique.

In step S307, the onset prediction unit 107 predicts whether or not the subject will develop HDP. For example, the onset prediction unit 107 predicts that the subject will develop HDP if the numerical value calculated in step S306 exceeds the threshold, and that the subject will develop HDP if the numerical value calculated in step S306 does not exceed the threshold. You can expect not to.

Note that the processing shown in steps S306 and S307 is an example. For example, if the prediction model is a prediction model created by machine learning using the information on the DNA mutation acquired in step S302 as feature amount data and the presence or absence of HDP onset as response data, the prediction model contains the DNA mutation information of the subject. to get the prediction result.

In step S<b>308 , the result output unit 108 of the onset prediction device 100 uses the output device 205 to output (for example, display, save in a file, etc.) the prediction result by the onset prediction unit 107 .

With the above-described processing, according to the present embodiment, it is possible to easily predict whether or not a subject will develop HDP before pregnancy or in early pregnancy, and at the same time, it is possible to eliminate the need to predict the onset of HDP for each pregnancy. Onset prediction device, onset prediction system, and onset prediction method can be provided.

For example, in conventional techniques, the onset of HDP is predicted using substances in the body that fluctuate after pregnancy, so it is difficult to predict the onset of HDP before pregnancy or in the early stages of pregnancy.

On the other hand, according to the onset prediction apparatus according to the present embodiment, it is possible to predict whether or not a subject to be predicted will develop HDP even before pregnancy.

In addition, in the conventional technology, the subject was tested for each pregnancy, but according to the onset prediction device according to the present embodiment, even if the subject is not tested for each pregnancy, for example, a single test It becomes possible to predict the onset of HDP.

[Second embodiment]
In the first embodiment, an example of processing in which the onset prediction apparatus 100 predicts whether or not a subject to be predicted will develop HDP has been described. In the second embodiment, an example of processing when the onset prediction apparatus 100 predicts the degree of risk (onset risk, etc.) of developing HDP in a subject to be predicted will be described.

FIG. 4 is a flowchart illustrating an example of onset prediction processing according to the second embodiment. Note that the processing of steps S301, S302, S304, and S305 shown in FIG. 4 is the same as the processing of steps S301, S302, S304, and S305 in the first embodiment described with reference to FIG. The explanation will focus on the differences between the Further, since the basic processing contents of other processes are similar to those of the first embodiment, detailed descriptions of the processes similar to those of the first embodiment will be omitted here.

In step S401, the prediction model creation unit 103 of the onset prediction apparatus 100 creates a prediction model for predicting the risk of developing HDP using the DNA mutation information acquired in step S302.

For example, as in the first embodiment, the predictive model creation unit 103 divides the HDP-related DNA mutation information acquired by the model creation information acquisition unit 102 into learning data and evaluation data at a predetermined ratio. . In addition, the prediction model creation unit 103 uses the learning data to select feature amounts in the elastic net, create a plurality of prediction models, apply the evaluation data to the prediction models, and obtain the best accuracy. choose things.

In step S<b>402 , the onset prediction unit 107 of the onset prediction apparatus 100 inputs the subject's DNA mutation information extracted by the DNA mutation information extraction unit 106 to the prediction model created by the prediction model creation unit 103 . As a result, for example, a numerical value for determining whether HDP develops is calculated by a machine learning technique.

In step S403, the onset prediction unit 107 predicts the risk of the subject developing HDP. For example, the onset prediction unit 107 divides the magnitude of the numerical value calculated in step S402 into a plurality of ranges, and depending on which range the calculated numerical value falls within, the degree of risk (level ) can be predicted.

In step S<b>404 , the result output unit 108 of the onset prediction device 100 uses the output device 205 to output (for example, display, save in a file, etc.) the prediction result by the onset prediction unit 107 .

With the above processing, according to the present embodiment, it is possible to easily predict the risk of developing HDP before pregnancy or in early pregnancy, and to predict the onset of HDP without predicting the onset for each pregnancy. An apparatus, an onset prediction system, and an onset prediction method can be provided.

Note that the onset prediction apparatus 100 combines the first embodiment and the second embodiment to obtain a first prediction result indicating whether or not the subject to be predicted will develop HDP, and A second prediction result indicating the risk of developing the disease may also be predicted.

[Third Embodiment]
In the third embodiment, an example of processing in the case where the information on the DNA mutation of the subject to be predicted does not include part of the information on the DNA mutation related to HDP will be described.

FIG. 5 is a flowchart showing an example of onset prediction processing according to the third embodiment. Note that the processing of steps S301, S302, S304, and S305 shown in FIG. 5 is the same as the processing of steps S301, S302, S304, and S305 in the first embodiment described with reference to FIG. The explanation will focus on the differences between the Further, since the basic processing contents of other processes are similar to those of the first embodiment, detailed descriptions of the processes similar to those of the first embodiment will be omitted here.

In step S501, the prediction model creation unit 103 of the onset prediction apparatus 100 determines whether or not there is information on DNA mutations that the subject does not have among the information on DNA mutations related to HDP.

If there is no DNA mutation information that the subject does not have among the information on DNA mutations related to HDP, the predictive model creation unit 103 shifts the process to step S502. On the other hand, if there is information on DNA mutations that the subject does not have among the information on DNA mutations related to HDP, the predictive model creation unit 103 shifts the process to step S502.

After moving to step S502, the predictive model creation unit 103 creates a predictive model for predicting the onset of HDP, as in the first embodiment or the second embodiment.

On the other hand, when the process proceeds to step S503, the prediction model creation unit 103 excludes DNA mutation information that the subject does not have from the DNA mutation information related to HDP in a plurality of pregnant women acquired in step S302, Create a predictive model that predicts the development of HDP. Note that the prediction model creation method may be the same as in the first embodiment or the second embodiment.

In step S504, the onset prediction device 100 predicts the onset of HDP (whether it will develop or the risk of onset) in the subject to be predicted using the prediction model created in step S502 or step S503. . For example, the onset prediction device 100 executes the processes shown in steps S306 to S308 in FIG. 3 or the processes shown in steps S402 to S404 in FIG.

With the above processing, the onset prediction apparatus 100 can appropriately predict the onset of HDP in a subject even if the subject to be predicted does not have an HDP-related DNA mutation.

[Fourth embodiment]
In the fourth embodiment, the onset prediction device 100 performs filtering using numerical values indicating the degree of harm of DNA mutations among the information on DNA mutations related to HDP, and predicts the onset of HDP in subjects to be predicted. An example of processing in the case of doing so will be described.

FIG. 6 is a flowchart showing an example of onset prediction processing according to the fourth embodiment. Note that the processing of steps S301, S302, S304, and S305 shown in FIG. 6 is the same as the processing of steps S301, S302, S304, and S305 in the first embodiment described with reference to FIG. The explanation will focus on the differences between the Further, since the basic processing contents of other processes are similar to those of the first embodiment, detailed descriptions of the processes similar to those of the first embodiment will be omitted here.

In step S601, the prediction model creation unit 103 of the onset prediction apparatus 100 extracts DNA mutation information whose numerical value indicating the degree of risk of DNA mutation is equal to or greater than a threshold from the information on DNA mutation associated with HDP acquired in step S302. do.

As a numerical value indicating the risk of DNA mutation, for example, a CADD score obtained from CADD (Combined Annotation Dependent Depletion), which is a database in which the harmfulness of gene mutation is scored as numerical data, can be applied. The numerical value indicating the risk of DNA mutation may be a numerical value obtained from another database different from CADD, or may be a numerical value calculated independently.

As an example, the predictive model creation unit 103 extracts information on DNA mutations with a CADD score equal to or higher than a threshold from the information on DNA mutations associated with HDP acquired in step S302.

In step S602, the prediction model creation unit 103 uses the DNA mutation information acquired in step S601 to create a prediction model that predicts the onset of HDP by the same method as in the first embodiment or the second embodiment. create.

In step S603, the onset prediction apparatus 100 predicts the onset of HDP (whether or not it will develop, or the risk of onset) in the subject to be predicted using the prediction model created in step S602. For example, the onset prediction device 100 executes the processes shown in steps S306 to S308 in FIG. 3 or the processes shown in steps S402 to S404 in FIG.

By the above-described processing, the onset prediction device 100 can more effectively predict the onset of HDP in a subject using information about DNA mutations that have a higher risk of DNA mutations.

[Fifth embodiment]
Preferably, the candidate list 111 stored in the storage unit 110 of the onset prediction device 100 includes, for example, DNA mutation information narrowed down by the DNA mutation narrowing down device 710 shown in FIG. In the fifth embodiment, a DNA mutation narrowing down device 710 will be described.

<System configuration of onset prediction system>
FIG. 7 is a diagram showing an example of the system configuration of an onset prediction system according to the fifth embodiment. As shown in FIG. 7, the onset prediction system 700 includes the onset prediction device 100 described in the first to fourth embodiments, and the candidate list 111 used by the onset prediction device 100 for HDP-related DNA mutations. and a DNA mutation screening device 710 for narrowing down the candidates.

The DNA mutation narrowing down device 710 is, for example, an information processing device having the configuration of the computer 200 as shown in FIG. 2, or a system including a plurality of information processing devices. The DNA mutation narrowing-down device 710 narrows down DNA mutations related to HDP based on the DNA mutation data of a plurality of subjects including a subject with HDP and continuous quantitative trait data, and narrows down the DNA mutations. DNA mutation candidates related to HDP are output to the candidate list 111 or the like.

There are guidelines for diagnosing HDP, but in reality, symptoms like HDP may appear even if the guidelines do not apply. The DNA mutation narrowing-down device 710 is thus configured to easily narrow down information on DNA mutations associated with HDP even when the definition of the disease is ambiguous.

In FIG. 7, the DNA mutation narrowing down device 710 includes, for example, an input reception unit 711, a feature amount extraction unit 712, a DNA mutation information acquisition unit 713, and a related analysis unit by executing a predetermined program in the processor 201 of FIG. 714, a DNA mutation extraction unit 715, a storage unit 716, a result output unit 717, and the like. Note that at least some of the input reception unit 711, the feature amount extraction unit 712, the DNA mutation information acquisition unit 713, the association analysis unit 714, the DNA mutation extraction unit 715, the storage unit 716, and the result output unit 717 are implemented by hardware. It may be realized by

The input reception unit 711 receives input data, input operations, and the like input from the input device 204, the communication device 206, and the like in FIG. 3, for example. For example, the input receiving unit 711 receives input of continuous measurements of HDP-related quantitative traits collected from a plurality of subjects, including subjects suffering from (or developing) HDP. .

Here, the quantitative traits related to HDP include, for example, subject's blood pressure, weight, BMI (Body Mass Index), pulse rate, heart rate, body fat percentage, amount of activity, calorie consumption, sleep time, continuous, Quantitatively variable traits are included.

The input reception unit 711 can also receive inputs such as DNA information (DNA sequence information) collected from a plurality of subjects including subjects suffering from a predetermined disease, DNA mutation information, and the like.

The feature amount extraction unit 712 extracts feature amounts from the continuous measurement values of the HDP-related quantitative traits received by the input reception unit 711 .

For example, the feature extractor 712 may fit a continuous measure of a quantitative trait associated with HDP to a predetermined polynomial, and use the polynomial coefficients, polynomial intercepts, or polynomial coefficients and intercepts to obtain feature Determine quantity. A specific example of the method of extracting the feature amount by the feature amount extraction unit 712 will be described later with reference to FIGS.

The DNA mutation information acquisition unit 713 acquires information on DNA mutations in a plurality of subjects including a subject suffering from HDP. For example, the DNA mutation information acquisition unit 713 analyzes the DNA information received by the input reception unit 711 and extracts DNA mutation information.

Alternatively, the DNA mutation information acquisition unit 713 acquires information on DNA mutations in a plurality of subjects from an external device that acquires information on DNA mutations from DNA information on a plurality of subjects including subjects suffering from HDP. can be Furthermore, the DNA mutation information acquisition unit 713 acquires information on DNA mutations in a plurality of subjects from an external database or the like in which DNA mutations of a plurality of subjects, including subjects suffering from HDP, are registered. Also good.

Preferably, the DNA mutation information acquired by the DNA mutation information acquisition unit 713 includes information on all single nucleotide polymorphisms (SNPs) extracted from the DNA information.

The relation analysis unit (analysis unit) 714 analyzes the relation between the feature amount extracted by the feature amount extraction unit 712 and the DNA mutation included in the DNA mutation information acquired by the DNA mutation information acquisition unit 713 . For example, the association analysis unit 714 performs association analysis (testing) using the feature amount extracted by the feature amount extraction unit 712 as the objective variable and the DNA mutation included in the DNA mutation information acquired by the DNA mutation information acquisition unit 713 as the explanatory variable. Then, a statistical index value indicating the degree of association between the feature quantity and the DNA mutation is calculated.

Here, the value of the statistical index indicating the degree of association between the feature quantity and the DNA mutation is the significant difference between the feature quantity extracted by the feature quantity extraction unit 712 and each DNA mutation acquired by the DNA mutation information acquisition unit 713. (eg, p-value, f-value, odds ratio, etc.) are included.

For the association analysis (test), linear regression, logistic regression, Fisher's exact test, chi-square test, Cochran-Amitage test, t-test, etc. can be applied, but not limited thereto.

Note that, as will be described later, the association analysis unit 714 uses a predetermined reference value to label the feature amount extracted by the feature amount extraction unit 712 into an HDP affected group and a non-affected group. It is also possible to calculate the value of a statistical index that indicates the significance of

A DNA mutation extraction unit 715 extracts DNA mutations related to HDP based on the analysis result of the association analysis unit 714 . For example, the DNA mutation extraction unit 715 extracts DNA mutations related to HDP based on the statistical index values calculated by the association analysis unit 714 .

The storage unit 716 is realized by, for example, the program executed by the processor 201 in FIG. 2, the storage 203, the memory 202, etc., and stores information received by the input receiving unit 711, information obtained by the DNA mutation information obtaining unit 713, and the like. Remember.

The result output unit 717 outputs the HDP-related DNA mutation candidates extracted by the DNA mutation extraction unit 715 to the onset prediction device 100, the candidate list 111, or the like.

(Example of specific configuration)
As an example of a specific configuration of the DNA mutation narrowing down device 710, the input reception unit 711 receives continuous blood pressure measurement values from a plurality of subjects, including subjects suffering from HDP, measured at the same time every day. receive information about

The feature quantity extraction unit 712 fits the continuous blood pressure measurement values received by the input reception unit 711 to a polynomial (for example, a linear expression) to calculate the slope, intercept, and the like of the polynomial. Here, as an example, the slope of a polynomial can be used as a feature amount.

The DNA mutation information acquisition unit 713 acquires information on all single nucleotide polymorphisms (an example of DNA mutations) from the DNA information of a plurality of subjects including, for example, subjects suffering from HDP.

The association analysis unit 714 uses the feature amount (for example, the slope of the polynomial) extracted by the feature amount extraction unit 712 as an objective variable, An association analysis (test) is performed using the type as an explanatory variable. For example, the association analysis unit 714 uses linear regression to obtain a p-value (an example of a statistical index value) representing the significance probability between the extracted feature amount and all single nucleotide polymorphisms included in the single nucleotide polymorphism information. Calculate

The DNA mutation extraction unit 715 determines that the p-value of all the single nucleotide polymorphisms included in the nucleotide polymorphism information is below (or less than) a predetermined significance level (for example, 5×10 ⁻⁸ ). Extract single nucleotide polymorphisms.

Here, the significance level is a value indicating the level at which the p-value can be regarded as statistically significant, and 0.05 (5%) is used in general analysis. However, since thousands to tens of thousands of parameters are tested at once in genome analysis, the number of tests increases and the possibility of significant differences occurring by chance increases, so it is common to correct the significance level. 5 × 10-8 (0.000005%) is often used as the level of the p-value after correction, but other values (e.g., 5 × ^10-10 , 5 × ^10-12 , etc.) can be used as necessary. You can use it.

The result output unit 717 outputs the single nucleotide polymorphism information extracted by the DNA mutation extraction unit 715 to the candidate list 111 or the like as a candidate for DNA mutation associated with HDP.

<Process flow>
FIG. 8 is a flowchart showing an example of DNA mutation screening processing according to the fifth embodiment. Here, as an example, the DNA mutation screening device 710 narrows down candidates for single nucleotide polymorphism (an example of DNA mutation) associated with HDP.

In step S801, the input reception unit 711 of the DNA mutation narrowing down device 710 acquires continuous quantitative trait information including blood pressure measurement results for a plurality of subjects including a subject suffering from HDP, and stores the information. 716 or the like.

In step S<b>802 , the feature quantity extraction unit 712 of the DNA mutation narrowing down device 710 extracts the feature quantity related to HDP from the temporal changes in quantitative traits stored in the storage unit 716 . For example, the feature quantity extraction unit 712 executes a feature quantity extraction process as shown in FIG.

FIG. 9 is a flowchart illustrating an example of feature amount extraction processing according to the fifth embodiment. This process shows an example of the feature amount extraction process executed in step S802 of FIG. 8, for example.

In step S901, the feature quantity extraction unit 712 fits the continuous quantitative trait measurement values acquired by the input reception unit 711 to a polynomial, for example, as shown in FIG.

FIG. 10 is a diagram for explaining an example of feature amounts according to the fifth embodiment. Here, as an example, the continuous quantitative trait is the measured value of the blood pressure of a pregnant woman (an example of a subject) measured at predetermined time intervals (eg, every day, the same time zone, etc.), and the polynomial is a linear expression shall be

In FIG. 10, the feature quantity extraction unit 712 fits the blood pressure measurement value 1001 of the pregnant woman A to a linear expression "y=ax+b" by, for example, linear regression. Note that the linear expression "y=ax+b" is an example of a predetermined polynomial.

In step S902, the feature quantity extraction unit 712 calculates coefficients and intercepts of the fitted polynomial. For example, the feature quantity extraction unit 712 calculates the slope a1 and the intercept b1 of the straight line represented by a linear expression.

In step S903, the feature quantity extraction unit 712 extracts the calculated coefficient, intercept, or coefficient and intercept as a feature quantity.

For example, it is assumed that the slope a2 and the intercept b2 are further calculated by performing fitting to the linear expression "y=ax+b" using the measured values of another pregnant woman B. In this case, as an example, the slopes a1 and a2 of the linear expressions can be used as feature amounts.

For example, as shown in FIG. 10, it is assumed that blood pressure increases with time (pregnancy progress). When each pregnant woman measures blood pressure at each timing, for example, as shown in FIG. 10, there is a blood pressure measurement value 1001 of pregnant woman A at time t1, but there is no blood pressure measurement value 1003 of pregnant woman B. . When the blood pressures of pregnant women A and B are compared at different time points, the difference includes the influence of the difference in the time points of measurement.

On the other hand, as shown in FIG. 10, for example, the measured blood pressure values of pregnant woman A and pregnant woman B are fitted to a linear expression, and the regression line 1002 for the blood pressure value of pregnancy A and the slope of the measured blood pressure value of pregnant woman B are regressed. Suppose that line 1004 is calculated. By also using the regression lines 1002 and 1004, it is possible to compare the difference in blood pressure transition between pregnancies A and B from the slopes of both. In addition, by using the predicted value of blood pressure at a predetermined time (t), it is possible to perform a comparison that eliminates the influence of the difference in measurement time points.

Similarly, for example, as shown in FIG. 10, a regression line 1006 for the blood pressure value of the pregnant woman C is calculated using the blood pressure measurement value 1005 of the pregnant woman C after time t2. In this case, the period t1 to t2 does not include the blood pressure measurement value 1005 of the pregnant woman C. Differences in C blood pressure transitions can be compared.

As another example, in FIG. 6, it is assumed that time t0 is the first day of pregnancy of the pregnant woman. It is also assumed that the presence or absence of the onset of a certain disease is related to the blood pressure value on the first day of pregnancy. In this case, even if there is no record of blood pressure values on the first day of pregnancy, such as pregnant women A, pregnant women B, and pregnant women C, by fitting the blood pressure values of each pregnant woman to the linear equation, the intercept b1 of the linear equation and the intercept b2 and an intercept b3 can be obtained and used as feature amounts.

Similarly, for example, the blood pressure of each pregnant woman at the time when a predetermined number of days have passed since the first day of pregnancy can be calculated using a fitted linear expression and used as a feature amount.

In this way, the feature amount extraction unit 712 extracts a feature amount related to a predetermined disease from temporal changes in quantitative traits collected from a plurality of subjects.

Note that the slopes a1, a2, a3 and the intercepts b1, b2, b3 described above are examples of feature amounts extracted by the feature amount extraction unit 712. FIG. Also, the linear expression shown in FIG. 10 is an example of a predetermined polynomial, and the predetermined polynomial may be a polynomial of degree 2 or higher.

Here, returning to FIG. 8, the description of the flowchart showing an example of narrowing down processing for DNA mutations will be continued.

In step S803, the DNA mutation information acquisition unit 713 of the DNA mutation narrowing down device 710, for example, in parallel with the processing of steps S801 and S802, obtains DNA mutation information of a plurality of subjects including a subject suffering from HDP. get.

For example, the DNA mutation information acquisition unit 713 analyzes DNA information of a plurality of subjects including a subject suffering from HDP, which is received by the input reception unit 711, and acquires information on all single nucleotide polymorphisms. In addition, as described above, the DNA mutation information acquisition unit 713 acquires DNA information from a plurality of subjects from an external device that acquires DNA information from the DNA information of a plurality of subjects, or from an external database in which the DNA information of a plurality of subjects is registered. DNA mutation information may be obtained.

Preferably, the plurality of subjects from whom continuous quantitative trait information is obtained in step S801 and the plurality of subjects from which single nucleotide polymorphism information is obtained in step S803 are the same subjects.

In step S804, the association analysis unit 714 of the DNA mutation narrowing down device 710 uses the feature amount extracted in step S802 as an objective variable and the single nucleotide polymorphism included in the single nucleotide polymorphism information acquired in step S803 as an explanatory variable. Perform an association analysis (test).

For example, the association analysis unit 714 uses the p-value calculated from the Wald statistic of the coefficient of each DNA mutation as the value of the statistical index in a regression equation in which the feature amount is the objective variable and the DNA mutation is the explanatory variable. can be done.

The test (association analysis) when the association analysis unit 714 calculates the value of the statistical index includes, for example, linear regression, logistic regression, Fisher's exact test, chi-square test, Cochran-Amitage test, and t-test. etc. are used, but are not limited to these. The value of the statistical index calculated by the association analysis unit 714 may be, for example, a p-value, an f-value, or an odds ratio, but is not limited thereto.

In addition, the association analysis unit 714 may further consider dominant gene action, recessive gene action, genotype, etc. to calculate the value of the statistical index, or use information such as age, weight, BMI, etc. as the amount of co-editing. It can be anything.

In step S805, the DNA mutation extraction unit 715 of the DNA mutation narrowing down device 710 extracts single nucleotide polymorphism candidates related to HDP based on the analysis results of the association analysis unit 714. FIG. For example, the DNA mutation extraction unit 715 determines that the p-value calculated in step S804 from among the single nucleotide polymorphisms included in the single nucleotide polymorphism information acquired in step S803 is at a predetermined significance level (for example, 0.05) to extract single nucleotide polymorphisms smaller than In addition, the DNA mutation extraction unit 715 outputs the extracted single nucleotide polymorphisms to the candidate list 111 or the like, for example, as single nucleotide polymorphism candidates related to HDP.

With the above processing, the DNA mutation narrowing down device 710 can easily narrow down information on DNA mutations related to HDP even when the definition of the disease is ambiguous like HDP.

Note that the narrowing down process for DNA mutations shown in FIG. 8 is an example. For example, as shown in FIG. 11, the association analysis unit 714 of the DNA mutation narrowing down device 710 compares the feature amount extracted by the feature amount extraction unit 712 to the HDP affected group and non-affected group using a predetermined reference value. , and a p-value indicating the significance of each single nucleotide polymorphism may be calculated.

FIG. 11 shows another example of narrowing down processing for DNA mutations according to the fifth embodiment. A detailed description of the same processing as the processing shown in FIG. 8 will be omitted here.

In step S1101, the input reception unit 711 of the onset prediction apparatus 100 acquires continuous quantitative trait information including blood pressure measurement values of a plurality of subjects, and stores the acquired continuous quantitative trait measurement values. Save (store) in unit 716 .

In step S1102, the feature quantity extraction unit 712 of the DNA mutation narrowing down device 710 extracts, for example, a feature quantity related to HDP (for example, , the slope of the linear expression).

In step S1103, the association analysis unit 714 of the DNA mutation narrowing down device 710 classifies (labels) the feature amount extracted by the feature amount extraction unit 712 into a diseased group and a non-diseased group using a predetermined reference value. do.

For example, assume that the slope of blood pressure measurements in pregnant women with HDP tends to be greater than the slope of blood pressure measurements in pregnant women without HDP. In this case, features greater than a predetermined slope can be labeled as the diseased group, and features less than or equal to the predetermined slope can be labeled as the non-diseased group.

In step S1104, the DNA mutation information acquiring unit 713 of the DNA mutation narrowing down device 710 acquires information on DNA mutations in a plurality of subjects including a subject suffering from HDP, for example, in the same manner as in the process of step S803 in FIG. to get

In step S<b>1105 , the association analysis unit 714 of the DNA mutation narrowing down device 710 analyzes each single nucleotide polymorphism included in the single nucleotide polymorphism information acquired by the DNA mutation information acquisition unit 713 for the affected group and the non-affected group. Calculate the value of a statistical index that indicates whether there is a difference in the number of carriers in the groups. For example, the association analysis unit 714 performs Fisher's exact test or chi-square test to calculate the p-value.

In step S1106, the DNA mutation extraction unit 715 of the DNA mutation narrowing down device 710 extracts DNA mutations for which the value of the statistical index calculated by the association analysis unit 714 is equal to or greater than the reference value or equal to or less than the reference value. For example, the DNA mutation extraction unit 715 extracts DNA mutations whose p-value is equal to or less than a predetermined reference value (eg, 0.05). In addition, the DNA mutation extraction unit 715 outputs the extracted single nucleotide polymorphisms to the candidate list 111 or the like, for example, as single nucleotide polymorphism candidates related to HDP.

With the above processing, the DNA mutation narrowing down device 710 can easily narrow down information on DNA mutations related to HDP even when the definition of the disease is ambiguous like HDP.

As described above, according to the DNA mutation narrowing down device 710 according to the present embodiment, even when the definition of a disease is ambiguous like HDP, candidates for single nucleotide polymorphisms related to HDP can be easily identified. It becomes possible to narrow down and create a candidate list 111 .

Note that the system configuration of the onset prediction system 700 shown in FIG. 7 is an example. For example, at least part of the functional configuration included in the DNA mutation narrowing down device 710 may be included in the onset prediction device 100 .

<Example of candidate list>
The candidate list 111 used by the onset prediction device 100 to predict the onset of HDP includes, for example, HDP-related single nucleotide polymorphism candidates narrowed down by the DNA mutation screening device 710 described in the fifth embodiment. be

However, this is only an example, and the candidate list 111 includes one or more single nucleotide polymorphism candidates selected from HDP-related single nucleotide polymorphism candidates narrowed down by the DNA mutation narrowing down device 710. Candidates may be stored. Thus, the candidate list 111 includes some or all of the HDP-related single nucleotide polymorphism candidates narrowed down by the DNA mutation narrowing down device 710 .

FIG. 12 is a diagram (1) showing examples of single nucleotide polymorphism candidates included in a candidate list according to an embodiment. This figure shows that among the candidates of single nucleotide polymorphisms related to HDP narrowed down by the DNA mutation narrowing down device 710, association with HDP has been reported in the vicinity, or they are thought to contribute to the onset of HDP. 1200 shows a list 1200 of single nucleotide polymorphism candidates in which a gene that is associated with a

In other words, this list 1200 includes single nucleotide polymorphism candidates for which a gene reported to be related to HDP was found in the vicinity of the single nucleotide polymorphism candidates related to HDP narrowed down by the DNA mutation narrowing down device 710. showing candidates.

If the single nucleotide polymorphism narrowed down by the DNA mutation narrowing down device 710 does not exist on the gene, it is generally considered that the single nucleotide polymorphism is involved in the function of neighboring genes. Here, as the neighborhood, a range of 400,000 bases to 1,000,000 bases (400 kbp to 1 Mbp) before and after the single nucleotide polymorphism is used. The range of this neighborhood is, for example, a paper investigating how much range should be searched for as a neighborhood (Non-Patent Document 3: Aharon Brondie, et al., Nucleic Acids Research, 2016, 44(13): 6046-6054), etc.

In FIG. 12, for example, the single nucleotide polymorphism (SNP) with rs number rs3997995 is located at position 31321587 on chromosome 6, and the base is changed to T. In addition, the single nucleotide polymorphism with rs number rs3997995 is closely related to genes MUC21 and MUC22, which are reported to be related to HDP, and phenotypes related to HDP (e.g., diastolic blood pressure). It has been shown that there is a reported gene BAG6.

FIG. 13 is a diagram (2) showing examples of single nucleotide polymorphism candidates included in the candidate list according to one embodiment. This figure also shows that among the candidates for single nucleotide polymorphisms related to HDP narrowed down by the DNA mutation narrowing down device 710, association with HDP has been reported in the vicinity, or it is thought that they contribute to the onset of HDP. 1300 shows a list 1300 of single nucleotide polymorphism candidates in which a gene that has

In other words, in this list 1300, among the candidates for HDP-related single nucleotide polymorphisms narrowed down by the DNA mutation narrowing down device 710, vascular endothelial growth factor levels and Candidate single nucleotide polymorphisms found in genes involved in hypertension are shown.

FIG. 14 is a diagram (3) showing examples of single nucleotide polymorphism candidates included in the candidate list according to one embodiment. This figure shows a list 1400 of single nucleotide polymorphisms that are particularly useful for prediction, out of known single nucleotide polymorphisms existing on HDP-related genes that have already been registered in databases of research institutions. .

In this list 1400, among the single nucleotide polymorphisms existing on genes related to HDP, among the single nucleotide polymorphisms having a high numerical value indicating the risk of DNA mutation used in the fourth embodiment, prediction is performed. Candidates for single nucleotide polymorphisms that particularly contributed to the analysis are shown.

The candidate list 111 used by the onset prediction device 100 for onset prediction includes, for example, the single nucleotide polymorphism shown in FIG. may include candidates for

Similarly, the candidate list 111 used by the onset prediction device 100 for onset prediction includes, for example, the single nucleotide polymorphism candidate shown in FIG. Candidates for nucleotide polymorphisms may be included.

Similarly, in the candidate list 111 used by the onset prediction device 100 for onset prediction, instead of the HDP-related single nucleotide polymorphism candidates narrowed down by the DNA mutation screening device 710, for example, Candidates for nucleotide polymorphisms may be included.

As a result, the onset prediction apparatus 100 can more effectively predict the onset of HDP in a subject to be predicted, using the single nucleotide polymorphism candidates that are more closely related to the onset of HDP.

As described above, according to each embodiment of the present invention, it is possible to easily grasp the risk of developing HDP before pregnancy or to predict the onset in early pregnancy, and it is not necessary to predict the onset for each pregnancy. A device for predicting the onset of HDP can be provided.

For example, in the prior art, onset prediction was performed using substances in the body that fluctuate after pregnancy. be able to In addition, in the prior art, an examination was performed for each pregnancy to predict the onset, but according to each embodiment of the present invention, it is possible to predict the onset of HDP in subsequent pregnancies with a single examination. become able to.

In addition, the DNA mutation narrowing down apparatus 710 according to the fifth embodiment narrows down single nucleotide polymorphism candidates related to HDP even in HDP, for which the definition of a disease is ambiguous, and selects a candidate list to be used for onset prediction. 111 can be created easily.

Furthermore, from among the single nucleotide polymorphism candidates narrowed down by the DNA mutation narrowing down device 710, single nucleotide polymorphism candidates in the vicinity of the HDP-related gene are extracted to create a candidate list 111. , it becomes possible to predict the onset of HDP more efficiently.

<Supplement>
1 and 7 show blocks for each function. These functional blocks are realized by any combination of hardware and/or software. Further, means for realizing each functional block is not particularly limited. That is, each functional block may be implemented by one device physically and/or logically coupled, or may be implemented by two or more physically and/or logically separated devices directly and/or indirectly. These multiple devices may be connected together (eg, wired and/or wirelessly).

Further, the hardware configuration of the computer 200 shown in FIG. 2 may be configured to include one or more of each device shown in the drawing, or may be configured without including some of the devices. The computer 200 includes hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array). A part or all of each functional block may be implemented by the hardware. For example, processor 201 may be implemented with at least one of these hardware.

The processing procedures, sequences, flowcharts, etc. of each aspect/embodiment described herein may be interchanged in order as long as there is no contradiction. For example, the methods described herein present elements of the various steps in a sample order, and are not limited to the specific order presented.

Input/output information and the like may be stored in a specific location (for example, memory), or may be managed in a management table. Input/output information and the like can be overwritten, updated, or appended. The output information and the like may be deleted. The entered information and the like may be transmitted to another device.

The determination may be made by a value represented by 1 bit (0 or 1), by a true/false value (Boolean: true or false), or by numerical comparison (for example, a predetermined value).

Each aspect/embodiment described herein may be used alone, may be used in combination, or may be used by switching between implementations. In addition, the notification of predetermined information (for example, notification of “being X”) is not limited to being performed explicitly, but may be performed implicitly (for example, not notifying the predetermined information). Also good.

Software, whether referred to as software, firmware, middleware, microcode, hardware description language or otherwise, includes instructions, instruction sets, code, code segments, program code, programs, subprograms, and software modules. , applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, and the like.

Software, instructions, etc. may also be transmitted and received over a transmission medium. For example, the software can be used to access websites, servers, or other When transmitted from a remote source, these wired and/or wireless technologies are included within the definition of transmission media.

Information, signals, etc. described herein may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may refer to voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any of these. may be represented by a combination of

The terms explained in this specification and/or terms necessary for understanding this specification may be replaced with terms having the same or similar meanings.

In addition, the information, parameters, and the like described in this specification may be represented by absolute values, may be represented by relative values from a predetermined value, or may be represented by corresponding other information. . For example, radio resources may be indexed.

As used herein, the phrase "based on" does not mean "based only on," unless expressly specified otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

To the extent that "including," "comprising," and variations thereof are used herein or in the claims, these terms, as well as the term "comprising," It is intended to be inclusive. Furthermore, the term "or" as used in this specification or the claims is not intended to be an exclusive OR.

Throughout this disclosure, where articles have been added by translation, e.g., a, an, and the in English, these articles are used unless the context clearly indicates otherwise. It shall include plural things.

Although the present invention has been described in detail above, it will be apparent to those skilled in the art that the present invention is not limited to the embodiments described herein. The present invention can be implemented with modifications and variations without departing from the spirit and scope of the invention defined by the claims. Accordingly, the descriptions herein are for illustrative purposes only and are not meant to be limiting of the present invention.

100 onset prediction device 102 model creation information acquisition unit 103 prediction model creation unit (creation unit)
107 onset prediction unit 111 candidate list 120 subject information acquisition unit 710 DNA mutation screening device 712 feature amount extraction unit 713 DNA mutation information acquisition unit 714 association analysis unit (analysis unit)
715 DNA Mutation Extractor (Extractor)

Claims (9)

A model creation information acquisition unit that acquires information on DNA mutations related to pregnancy-induced hypertension from information on DNA mutations in a plurality of pregnant women including pregnant women suffering from pregnancy-induced hypertension;
Information on the DNA mutation acquired by the model creation information acquisition unitand information indicating the presence or absence of the onset of gestational hypertension syndrome;A creation unit that creates a prediction model that predicts the onset of pregnancy-induced hypertension using
A subject information acquisition unit that acquires information on DNA mutations related to the hypertension of pregnancy in a subject to be predicted;
A prediction unit that predicts the onset of pregnancy-induced hypertension in the subject to be predicted using the prediction model created by the creation unit and the information on the DNA mutation acquired by the subject information acquisition unit;
havedeath,
If the DNA mutation information acquired by the subject information acquisition unit does not include part of the information on the DNA mutation related to the hypertension of pregnancy,
The creation unit creates the prediction model by excluding information on DNA mutations not included in the information on DNA mutations acquired by the subject information acquisition unit from the information on DNA mutations related to pregnancy-induced hypertension. ,
departureDisease prediction device. The information of the DNA mutation associated with the hypertension of pregnancy includes information of one or more single nucleotide polymorphisms stored in the candidate list of single nucleotide polymorphisms associated with the hypertension of pregnancy, according to claim 1 Onset prediction device. The candidate list includes some or all of the single nucleotide polymorphism candidates related to the pregnancy hypertension narrowed down by the DNA mutation narrowing down device,
The DNA mutation screening device
A feature quantity extraction unit for extracting a feature quantity from continuous measured values of quantitative traits related to the gestational hypertension collected from a plurality of subjects including the subject suffering from the gestational hypertension;
a DNA mutation information acquisition unit that acquires information on single nucleotide polymorphisms in the plurality of subjects;
an analysis unit that analyzes the relationship between the feature quantity and the single nucleotide polymorphism contained in the information on the single nucleotide polymorphism;
A DNA mutation extraction unit that extracts a single nucleotide polymorphism candidate related to pregnancy hypertension syndrome based on the analysis result of the analysis unit;
The onset prediction device according to claim 2, comprising: In the candidate list, among the single nucleotide polymorphism candidates related to pregnancy hypertension narrowed down by the DNA mutation narrowing down device, a gene related to pregnancy hypertension or one present in the vicinity of the gene 4. The onset prediction device according to claim 3, comprising information on the above single nucleotide polymorphisms. 5. The onset predicting device according to any one of claims 2 to 4, wherein said candidate list includes information on single nucleotide polymorphisms specified by rs numbers described in FIG. 12, FIG. 13 or FIG. The creation unit uses information on one or more single nucleotide polymorphism candidates whose single nucleotide polymorphism toxicity level is equal to or greater than a threshold among the single nucleotide polymorphism candidates included in the candidate list, The onset prediction device according to any one of claims 2 to 5, which creates a prediction model. The creation unit creates a prediction model that predicts whether the pregnancy hypertensive syndrome will develop,
The onset prediction device according to any one of claims 1 to 6 , wherein the prediction unit predicts whether or not the subject will develop the pregnancy-induced hypertension. The creation unit creates a prediction model that predicts the risk of developing pregnancy-induced hypertension,
The onset prediction device according to any one of claims 1 to 7 , wherein the prediction unit predicts the risk of the subject developing the pregnancy hypertension syndrome. The onset prediction device according to claim 1;
a DNA mutation narrowing-down device that creates a candidate list of DNA mutations related to pregnancy-induced hypertension used in the onset prediction device;
An onset prediction system comprising
The DNA mutation screening device
A feature quantity extraction unit for extracting a feature quantity from continuous measured values of quantitative traits related to the gestational hypertension collected from a plurality of subjects including the subject suffering from the gestational hypertension;
a DNA mutation information acquisition unit that acquires information on single nucleotide polymorphisms in the plurality of subjects;
an analysis unit that analyzes the relationship between the feature quantity and the single nucleotide polymorphism contained in the information on the single nucleotide polymorphism;
a DNA mutation extraction unit that extracts candidates for DNA mutations related to pregnancy-induced hypertension based on the analysis results of the analysis unit;
An onset prediction system.

Images