JP2020038412A - Onset prediction device and onset prediction system - Google Patents

Abstract

To provide a HDP onset prediction device which facilitates grasping a risk of HDP onset before pregnancy or predicting onset in early stages of pregnancy, and which does not require onset prediction for each pregnancy.SOLUTION: The onset prediction device comprises: a model creation information acquisition unit for acquiring information pertaining to DNA mutation associated with hypertensive disorders of pregnancy (HDP) from information pertaining to DNA mutation in a plurality of pregnant women including a pregnant woman suffering from HDP; a creation unit for a prediction model for predicting the onset of HDP using the information pertaining to DNA mutation acquired by the model creation information acquisition unit; an examinee information acquisition unit for acquiring information pertaining to HDP-related DNA mutation in an examinee for whom prediction is made; and a prediction unit for predicting the onset of HDP in the examinee for whom prediction is made, using the prediction model created by the creation unit and the information pertaining to DNA mutation acquired by the examinee information acquisition unit.SELECTED DRAWING: Figure 1

Description

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

  There is known a technique for predicting the presence or absence of onset of pregnancy-induced hypertension syndrome, the risk of occurrence, and the like. For example, a technique is known that uses sphingosine-1-phosphate as a metabolite biomarker to predict the risk of hypertension disorder in pregnant women at an early stage (for example, see Patent Document 1).

  Also, many studies have been conducted on the prediction of the onset of pregnancy-induced hypertension syndrome.

  For example, the concentration ratio of two compounds in the serum of 1,050 women with singleton pregnancies from 24 weeks 0 days to 36 weeks 6 days of gestation suspected of developing preeclampsia, a kind of pregnancy hypertension syndrome Studies have been conducted to determine whether the (soluble fms-like tyrosine kinase-1 (sFlt-1) / placental growth factor (PlGF) ratio) can predict the onset of subsequent preeclampsia (eg, Non-Patent Document 1). According to this study, if the sFlt-1 / PlGF ratio was less than 38, the negative predictive value to rule out preeclampsia within one week was 99.3%, which exceeded 38. In this case, the positive predictive value for the occurrence of preeclampsia within 4 weeks was 36.7%.

  In addition, a study has been reported in which small ncRNA, which is a kind of a transcript extracted from the blood of 35 normal onset preeclampsia and 40 normal pregnant women, is analyzed (for example, see Non-Patent Document 2). . According to this study, 25 small ncRNAs whose expression levels differed between the affected group and the unaffected group with preeclampsia were found, suggesting that they may be used as predictive markers.

JP 2016-14885A

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) is a dangerous disease that is a major cause of perinatal maternal death, but it is difficult to predict the disease and there is no fundamental treatment other than delivery .

  In addition, it is expected that HDP can prevent the onset of disease and prevent the seriousness of the disease by treating it early. However, in the conventional technology, the onset prediction is performed by using a substance which fluctuates after pregnancy. Has been done.

  Therefore, it has been difficult with the conventional technology to grasp the risk of developing HDP before pregnancy or to predict the development of HDP in the early stage of pregnancy.

  Embodiments of the present invention have been made in view of the above problems, and make it easy to grasp the risk of developing HDP before pregnancy or to predict the onset of pregnancy in the early stages of pregnancy, To provide an HDP onset predicting apparatus that does not need to perform onset prediction.

  In order to solve the above-mentioned problems, the onset predicting apparatus according to one embodiment of the present invention provides information on DNA mutations related to the HDP from information on DNA mutations in a plurality of pregnant women including a pregnant woman suffering from HDP. A model creation information acquisition unit to be acquired, a creation unit to create a prediction model for predicting the onset of HDP using the DNA mutation information acquired by the model creation information acquisition unit, and a subject to be a prediction target, A subject information acquisition unit for acquiring information on the DNA mutation related to the HDP, the prediction model created by the creation unit, and the DNA mutation information acquired by the subject information acquisition unit, the prediction target A prediction unit that predicts the onset of the HDP in the subject.

  ADVANTAGE OF THE INVENTION According to one Embodiment of this invention, while making it easy to grasp | ascertain the onset risk of HDP before pregnancy, or to make prediction in early pregnancy, the onset prediction of HDP which does not need to perform an onset prediction for every pregnancy An apparatus can be provided.

It is a figure showing the example of composition of the onset prediction device concerning one embodiment. FIG. 2 is a diagram illustrating an example of a hardware configuration of a computer according to an embodiment. It is a flow chart which shows the example of the onset prediction processing concerning a 1st embodiment. It is a flow chart which shows the example of the onset prediction processing concerning a 2nd embodiment. It is a flowchart which shows the example of a process of the onset prediction apparatus which concerns on 3rd Embodiment. It is a flowchart which shows the example of a process of the onset prediction apparatus which concerns on 4th Embodiment. It is a figure showing the example of composition of the onset prediction system concerning a 5th embodiment. It is a flow chart which shows an example of narrowing down processing of DNA mutation concerning a 5th embodiment. 15 is a flowchart illustrating an example of a feature amount extraction process according to the fifth embodiment. It is a figure for explaining an example of the characteristic quantity concerning a 5th embodiment. It is a flow chart which shows another example of narrowing down processing of DNA mutation concerning a 5th embodiment. It is a figure (1) which shows the example of the candidate of the single nucleotide polymorphism contained in the candidate list concerning one embodiment. It is a figure (2) which shows the example of the candidate of the single nucleotide polymorphism contained in the candidate list which concerns on one Embodiment. It is a figure (3) which shows the example of the candidate of the single nucleotide polymorphism contained in the candidate list concerning one embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. 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 the onset prediction device>
The configuration of the onset predicting apparatus according to the 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 predicting apparatus 100 has, for example, a hardware configuration of a general computer 200 as shown in FIG.

  The onset predicting apparatus 100 predicts, for example, the onset of pregnancy-induced hypertension syndrome (HDP: Hypertensive Disorders of Pregnancy) in a subject to be predicted, and outputs a prediction result. The prediction of HDP onset includes, for example, whether or not the subject develops HDP, the risk of the subject developing HDP, and the like.

  FIG. 1 is a diagram illustrating a configuration example of an onset predicting apparatus 100 according to an embodiment. The onset prediction apparatus 100 executes, for example, a predetermined program by 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, and a storage unit 110.

  In addition, at least a part of the above respective functional configurations may be realized by hardware.

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

  DNA (DeoxyriboNucleic Acid) is a substance that records genetic information, and is composed of about 3 billion base pairs. DNA contains a gene that is a specific region (base sequence) containing genetic information.

  A DNA mutation is a mutation in the structure (base sequence) of DNA, and includes, for example, single nucleotide polymorphism (SNP: Single Nucleotide Polymorphism), copy number polymorphism (CNV: Copy Number Variation), deletion and insertion of DNA, and the like. May 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 pregnant women suffering from HDP, acquired by the data acquisition unit 101.

  The DNA mutation related to the 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 information on the DNA mutation related to HDP obtained by the model creation information obtaining unit 102 includes the information on the single nucleotide polymorphism related to HDP described above.

  The prediction model creation unit 103 creates a prediction model for predicting the onset of HDP using the information on the DNA mutation related to HDP acquired by the model creation information acquisition unit 102.

  For example, the prediction model creation unit 103 performs machine learning using the information of the single nucleotide polymorphism associated with HDP acquired by the model creation information acquisition unit 102 as feature amount data, and the presence or absence of HDP as response data, and performs HDP. Create a prediction model that predicts the presence or absence of onset.

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

  As another example, the prediction model creation unit 103 divides the single nucleotide polymorphism information related to HDP acquired by the model creation information acquisition unit 102 into learning data and evaluation data at a predetermined ratio. Further, the prediction model creation unit 103 uses the learning data to select a feature amount in, for example, an elastic net, creates a plurality of prediction models, and applies the evaluation data to the prediction model to improve the accuracy. The best one may be selected.

  There are various methods for creating a prediction model. The prediction model creation unit 103 is not limited to the elastic net, and may create a prediction model by using a method such as lasso, adaptive elastic net, or adaptive lasso.

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

  The DNA sequence identification unit 105 analyzes the sample of the subject or the information of the sample obtained by the DNA sample obtaining unit 104, and specifies DNA sequence information (hereinafter, referred to as DNA information).

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

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

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

  Furthermore, the subject information acquisition unit 120 specifies the DNA sequence information from the DNA sample of the subject to be predicted, and obtains the prediction target from an external device such as a DNA mutation analyzer that acquires information on the DNA mutation of the subject. The information of the DNA mutation of the subject may be obtained. In this case, the DNA mutation information extraction unit 106 extracts the information on the DNA mutation related to HDP from the information on the DNA mutation obtained from the external device.

  As described above, the onset predicting apparatus 100 may not necessarily include the DNA sample obtaining unit 104, the DNA sequence specifying unit 105, and the like.

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

  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 generate a prediction target subject. Predict the onset of HDP.

  For example, the onset predicting unit 107 inputs the DNA mutation information acquired by the DNA mutation information extracting unit 106 (or the subject information acquiring unit 120) to the prediction model created by the prediction model creating unit 103, so that the subject can obtain the HDP. Predict whether to develop.

  Alternatively, the onset predicting unit 107 inputs HDP information by inputting the information on the DNA mutation obtained by the DNA mutation information extracting unit 106 (or the subject information obtaining unit 120) to the prediction model created by the prediction model creating unit 103. A numerical value for determining whether to perform the determination may be obtained.

  In this case, the onset predicting unit 107 determines that the subject develops HDP when the 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 may expect not to. Further, the onset predicting unit 107 may divide this numerical value into a plurality of ranges and predict the risk of the subject developing HDP 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, for example, the output device 205 in FIG.

  The deciding unit 109 decides information on the DNA mutation related to HDP, which is used for predicting the onset. For example, in the storage unit 110, a candidate list 111 that is a list of DNA mutation candidates related to HDP is stored in advance. The determining unit 109 also determines, from among the candidate DNA mutations related to HDP stored in the candidate list 111, information on DNA mutations related to HDP, which is used for predicting the onset.

  As an example, the determination unit 109 causes a list of DNA mutation candidates related to HDP stored in the candidate list 111 to be displayed on the output device 205 or the like, and uses information on the selected DNA mutation for the onset prediction. It may be determined based on information on DNA mutations related to 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 generate DNA relating to HDP used for the onset prediction. The information of the mutation may be determined.

  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, and the like, and stores various data and information 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 an 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, a device, a unit, or the like.

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

  Further, the processor 201 reads out a program (program code), a software module, and data from the storage 203 and / or the communication device 206 to the memory 202, and executes various processes in accordance with these. As the program, a program that causes a computer to execute at least a part of the operation of the onset prediction device 100 is used. Various processes executed in the onset predicting apparatus 100 may be executed by one processor 201, or may be executed simultaneously or sequentially by two or more processors 201. Processor 201 may be implemented with one or more chips. Note that the program may be transmitted from a network via a telecommunication line.

  The memory 202 is a computer-readable storage medium and includes at least one of a ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Erasable Programmable ROM), a RAM (Random Access Memory), and the like. May be. The memory 202 may be called a register, a cache, a main memory (main storage device), or the like. The memory 202 can store a program (program code), a software module, and the like that can be executed to execute the DNA mutation narrowing down method according to one embodiment of the present invention.

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

  The input device 204 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, and the like) that receives an external input. The output device 205 is an output device that performs output to the outside (for example, a display, a speaker, an LED lamp, and the like). The input device 204 and the output device 205 may have an integrated configuration (for example, a touch panel display).

  The communication device 206 is hardware (transmission / reception device) for performing communication between computers via a wired and / or wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, or the like. Further, the communication device 206 may have a function of performing direct communication with an external device by short-range wireless communication.

  Each device such as the processor 201 and the memory 202 is connected by a bus 207 for communicating information. The bus 207 may be constituted by a single bus, or may be constituted by different buses between devices.

<Process flow>
Subsequently, a flow of processing of the onset prediction method according to the present embodiment will be described.

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

  In step S301, the determination unit 109 of the onset prediction apparatus 100 determines DNA mutation information to be used for the onset prediction from among the DNA mutation candidates related to HDP stored in the candidate list 111.

  For example, the determination unit 109 displays a list of DNA mutation candidates related to HDP stored in the candidate list 111 on the output device 205 or the like in a selectable manner, and outputs information on the selected DNA mutation to the onset prediction. May be determined.

  Further, the determination unit 109 may determine the DNA mutation candidates (all) related to HDP stored in the candidate list 111 as DNA mutation information used for predicting the onset. Further, 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 on the DNA mutation related to HDP used for the onset prediction. May be determined.

  This process only needs to be performed at least once before starting the process after step S302, and the user can execute or omit this process as necessary.

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

  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 information on the DNA mutation acquired in step S302.

  For example, the prediction model creation unit 103 divides the information on the DNA mutation related to HDP acquired by the model creation information acquisition unit 102 into learning data and evaluation data at a predetermined ratio. Further, the prediction model creation unit 103 uses the learning data, selects a feature amount in an elastic net, creates a plurality of prediction models, applies the evaluation data to the prediction model, and obtains the best accuracy. Choose one.

  Alternatively, the prediction model creation unit 103 performs machine learning using the information of the DNA mutation related to HDP acquired by the model creation information acquisition unit 102 as feature amount data, and uses the presence or absence of HDP as response data to perform the machine learning. A prediction model for predicting the presence / absence may be created.

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

  In step S304, the DNA sequence identification unit 105 of the onset predicting apparatus 100 analyzes the sample of the subject or the information of the sample obtained by the DNA sample obtaining unit 104, and obtains DNA information (DNA sequence information).

  As described above, the onset predicting apparatus 100 specifies the DNA sequence information from the DNA sample of the subject and obtains the information on the DNA mutation of the subject from an external device such as a DNA mutation analyzer that obtains the information on the DNA mutation of the subject. May be used to obtain information on DNA mutations of the above.

  In step S305, the DNA mutation information extraction unit 106 of the onset predicting apparatus 100 obtains information on the HDP-related DNA mutation determined in step S301 from the DNA information obtained in step S304.

  In step S306, the onset prediction unit 107 of the onset prediction apparatus 100 inputs the DNA mutation information of the subject extracted by the DNA mutation information extraction unit 106 to the prediction model created by the prediction model creation unit 103. Thereby, for example, a numerical value for determining whether or not to develop HDP is calculated by a machine learning method.

  In step S307, the onset predicting 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 if the numerical value calculated in step S306 does not exceed the threshold, the subject develops HDP. You may expect not to.

  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 as response data, the prediction model includes the DNA mutation information of the subject. Is input, a prediction result is obtained.

  In step S308, the result output unit 108 of the onset predicting apparatus 100 outputs (for example, displays, saves to a file, or the like) the prediction result of the onset predicting unit 107 using the output device 205.

  According to the present embodiment, the above processing makes it easy to predict whether or not a subject will develop HDP before pregnancy or early in pregnancy, and it is not necessary to predict HDP for each pregnancy. , An onset prediction system, an onset prediction system, and an onset prediction method.

  For example, in the related art, since the onset of HDP is predicted using an in-vivo substance that fluctuates after pregnancy, it is difficult to predict the onset of HDP before pregnancy or early in pregnancy.

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

  Further, in the related art, the subject test is performed for each pregnancy. However, according to the onset predicting apparatus according to the present embodiment, even if the subject is not tested for each pregnancy, for example, only one test is required. It becomes possible to predict the onset of HDP.

[Second embodiment]
In the first embodiment, an example of the process in which the onset prediction device 100 predicts whether or not the subject to be predicted will develop HDP is described. In the second embodiment, an example of a process in which the onset prediction device 100 predicts the risk (onset risk or the like) of a subject to be predicted developing HDP will be described.

  FIG. 4 is a flowchart illustrating an example of the onset prediction process according to the second embodiment. Note that the processing in steps S301, S302, S304, and S305 shown in FIG. 4 is the same as the processing in steps S301, S302, S304, and S305 in the first embodiment described with reference to FIG. The following description focuses on the differences from FIG. In addition, since the basic processing contents of other processes are the same as those of the first embodiment, a detailed description of the same processes as those of the first embodiment will be omitted.

  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 information on the DNA mutation acquired in step S302.

  For example, similarly to the first embodiment, the prediction model creation unit 103 divides the DNA mutation information related to HDP acquired by the model creation information acquisition unit 102 into learning data and evaluation data at a predetermined ratio. . Further, the prediction model creation unit 103 uses the learning data, selects a feature amount in an elastic net, creates a plurality of prediction models, applies the evaluation data to the prediction model, and obtains the best accuracy. Choose one.

  In step S402, the onset prediction unit 107 of the onset prediction apparatus 100 inputs the DNA mutation information of the subject extracted by the DNA mutation information extraction unit 106 to the prediction model created by the prediction model creation unit 103. Thereby, for example, a numerical value for determining whether or not to develop HDP is calculated by a machine learning method.

  In step S403, the onset predicting unit 107 predicts the risk of the subject developing HDP. For example, the onset predicting unit 107 divides the magnitude of the numerical value calculated in step S402 into a plurality of ranges, and determines the risk (level) at which the subject develops HDP according to which range includes the calculated numerical value. ) May be predicted.

  In step S404, the result output unit 108 of the onset predicting apparatus 100 outputs (for example, displays, saves to a file, or the like) the prediction result of the onset predicting unit 107 using the output device 205.

  According to the present embodiment, according to the present embodiment, it is easy to predict the risk of HDP development before pregnancy or early in pregnancy, and it is not necessary to predict the onset of HDP for each pregnancy. An apparatus, an onset prediction system, and an onset prediction method can be provided.

  Note that the onset prediction device 100 combines the first embodiment and the second embodiment, and a first prediction result indicating whether or not the subject to be predicted develops HDP, The second prediction result indicating the risk of developing may be predicted.

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

  FIG. 5 is a flowchart illustrating an example of the onset prediction process according to the third embodiment. Note that the processing in steps S301, S302, S304, and S305 shown in FIG. 5 is the same as the processing in steps S301, S302, S304, and S305 in the first embodiment described with reference to FIG. The following description focuses on the differences from FIG. In addition, since the basic processing contents of other processes are the same as those of the first embodiment, a detailed description of the same processes as those of the first embodiment will be omitted.

  In step S501, the prediction model creation unit 103 of the onset prediction apparatus 100 determines whether 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 information on DNA mutations that the subject does not have among the information on DNA mutations related to HDP, the prediction model creation unit 103 shifts the processing to step S502. On the other hand, when there is information on DNA mutations that the subject does not have among the information on DNA mutations related to HDP, the prediction model creation unit 103 shifts the processing to step S502.

  In step S502, the prediction model creation unit 103 creates a prediction model that predicts the onset of HDP in the same manner 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, A prediction model for predicting the onset of HDP is created. Note that the method of creating the prediction model may be the same as in the first embodiment or the second embodiment.

  In step S504, the onset predicting apparatus 100 predicts the onset of HDP (whether or not onset 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 predicting apparatus 100 executes the processing shown in steps S306 to S308 in FIG. 3 or the processing shown in steps S402 to S404 in FIG.

  Through the above processing, the onset predicting apparatus 100 can appropriately predict the onset of HDP in the subject even when the subject to be predicted does not have a DNA mutation related to HDP.

[Fourth embodiment]
In the fourth embodiment, the onset predicting apparatus 100 performs filtering by using a numerical value indicating the harmfulness of a DNA mutation among the information on DNA mutations related to HDP, and predicts the onset of HDP in a subject to be predicted. An example of the processing in the case of performing will be described.

  FIG. 6 is a flowchart illustrating an example of the onset prediction process according to the fourth embodiment. Note that the processing in steps S301, S302, S304, and S305 shown in FIG. 6 is the same as the processing in steps S301, S302, S304, and S305 in the first embodiment described with reference to FIG. The following description focuses on the differences from FIG. In addition, since the basic processing contents of other processes are the same as those of the first embodiment, a detailed description of the same processes as those of the first embodiment will be omitted.

  In step S601, the prediction model creation unit 103 of the onset prediction apparatus 100 extracts, from the information on the DNA mutations related to HDP obtained in step S302, information on the DNA mutations whose numerical values indicating the risk of DNA mutations are equal to or greater than a threshold value. I do.

  As the 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 prediction model creation unit 103 extracts, from the information on the DNA mutations related to HDP acquired in step S302, the information on the DNA mutations whose CADD scores are equal to or larger than the threshold.

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

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

  By the above processing, the onset predicting apparatus 100 can more effectively predict the onset of HDP in the subject using the information on the DNA mutation having a higher risk of DNA mutation.

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

<System configuration of the onset prediction system>
FIG. 7 is a diagram illustrating an example of a system configuration of the onset prediction system according to the fifth embodiment. As illustrated in FIG. 7, the onset prediction system 700 includes the onset prediction device 100 described in the first to fourth embodiments and the DNA mutation of the HDP-related DNA mutation included in the candidate list 111 used by the onset prediction device 100. A DNA mutation narrowing down apparatus 710 for narrowing down 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 the DNA mutations related to HDP based on the DNA mutation data of a plurality of subjects including the subject suffering from HDP and the continuous quantitative trait data, and narrows down. The candidate of the DNA mutation related to the HDP is output to the candidate list 111 and the like.

  Although a guideline for diagnosis is set for HDP, symptoms such as HDP may actually appear even if they do not correspond to the guideline. As described above, the DNA mutation narrowing-down device 710 is configured to easily narrow down information on DNA mutations related to HDP even when the definition of a disease is ambiguous.

  7, the DNA mutation narrowing-down device 710 executes, for example, a predetermined program by the processor 201 of FIG. 714, a DNA mutation extraction unit 715, a storage unit 716, a result output unit 717, and the like. At least a part of the input receiving unit 711, the feature amount extracting unit 712, the DNA mutation information acquiring unit 713, the association analyzing unit 714, the DNA mutation extracting unit 715, the storage unit 716, and the result output unit 717 is hardware. It may be realized by.

  The input receiving unit 711 receives, for example, input data, an input operation, and the like input from the input device 204, the communication device 206, and the like in FIG. For example, the input receiving unit 711 receives an input of a continuous measurement value of a quantitative trait related to HDP collected from a plurality of subjects including a subject having HDP (or having HDP). .

  Here, quantitative traits related to HDP include, for example, continuous, blood pressure, body weight, BMI (Body Mass Index), pulse, heart rate, body fat percentage, activity, calorie consumption, sleep time, and the like. Includes quantitatively varying traits.

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

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

  For example, the feature amount extraction unit 712 fits a continuous measurement value of a quantitative trait related to HDP to a predetermined polynomial, and uses a polynomial coefficient, a polynomial intercept, or a polynomial coefficient and intercept to obtain a feature. Determine the amount. Note that a specific example of a feature amount extraction method 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 subjects suffering from HDP. For example, the DNA mutation information obtaining unit 713 analyzes the DNA information received by the input receiving unit 711 and extracts information on the DNA mutation.

  Alternatively, the DNA mutation information obtaining unit 713 obtains information on DNA mutations in a plurality of subjects from an external device that obtains information on DNA mutations from DNA information on a plurality of subjects including a subject suffering from HDP. It may be. Further, the DNA mutation information obtaining unit 713 obtains 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 a subject suffering from HDP are registered. Is also good.

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

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

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

  In addition, linear regression, logistic regression, Fisher's exact test, Chi-square test, Cochran-Amitage test, t-test, and the like can be applied to the association analysis (test), but the present invention is not limited thereto.

  The association analysis unit 714 labels the feature amounts extracted by the feature amount extraction unit 712 into an affected group and an unaffected group of HDP using a predetermined reference value, as described later, and May be calculated as a value of a statistical index indicating the significance of.

  The DNA mutation extraction unit 715 extracts a DNA mutation related to HDP based on the analysis result of the association analysis unit 714. For example, the DNA mutation extraction unit 715 extracts a DNA mutation related to HDP based on the value of the statistical index 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 and the storage 203, the memory 202, and the like, 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 DNA mutation candidate related to HDP extracted by the DNA mutation extraction unit 715 to the onset prediction device 100 or 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 receiving unit 711 is a continuous measurement of blood pressure measured from a plurality of subjects including a subject suffering from HDP every day at the same time. Accept the information of.

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

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

  The association analysis unit 714 uses the feature amount (eg, the slope of the polynomial) extracted by the feature amount extraction unit 712 as the target variable, and all the single nucleotide polymorphisms included in the single nucleotide polymorphism information acquired by the DNA mutation information acquisition unit 713. Perform an association analysis (test) using the type as an explanatory variable. For example, the association analysis unit 714 determines, by linear regression, a p-value (an example of a value of a statistical index) indicating a significant probability of the extracted feature quantity and all single nucleotide polymorphisms included in the single nucleotide polymorphism information. Is calculated.

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

Here, the significance level is a value indicating a level at which the p-value can be considered statistically significant, and 0.05 (5%) is used in general analysis. However, in genomic analysis, since thousands to tens of thousands of parameters are tested at once, the number of tests increases, and the possibility that a significant difference occurs by chance is increased. Therefore, it is general 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 (for example, 5 × 10 ⁻¹⁰ , 5 × 10 ^−12, etc.) may be used if necessary. May be used.

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

<Process flow>
FIG. 8 is a flowchart illustrating an example of a DNA mutation narrowing down process according to the fifth embodiment. Here, as an example, the following description will be given assuming that the DNA mutation narrowing down apparatus 710 narrows down candidates for single nucleotide polymorphism (an example of DNA mutation) related to HDP.

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

  In step S802, the feature amount extraction unit 712 of the DNA mutation narrowing device 710 extracts a feature amount related to HDP from the temporal change of the quantitative trait stored in the storage unit 716. For example, the feature amount extraction unit 712 executes a feature amount extraction process as shown in FIG.

  FIG. 9 is a flowchart illustrating an example of a feature amount extraction process according to the fifth embodiment. This process shows an example of the feature amount extraction process executed in step S802 in 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 describing an example of a feature amount according to the fifth embodiment. Here, as an example, the continuous quantitative trait is a measured value of the blood pressure of a pregnant woman (an example of a subject) measured at predetermined time intervals (for example, every day, the same time zone, etc.), and the polynomial is a linear expression. It is assumed that

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

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

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

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

  For example, as shown in FIG. 10, it is assumed that the blood pressure increases with time (elapse of pregnancy). When each pregnant woman measures the blood pressure at each timing, for example, as shown in FIG. 10, the measured value 1001 of the blood pressure of pregnant woman A at time t1 exists, but the measured value 1003 of the blood pressure of pregnant woman B does not exist. . When the blood pressures at different time points are compared between pregnant women A and B, it is difficult to truly compare the difference between the blood pressure values of pregnant women A and B because the difference includes the influence of the measurement time point difference.

  On the other hand, as shown in FIG. 10, for example, the measured values of the blood pressure 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 pregnant woman A and the regression of the slope of the measured value of the blood pressure of pregnant woman B are determined. It is assumed that the line 1004 has been calculated. By using the regression lines 1002 and 1004, it is possible to compare the difference in blood pressure transition between pregnancy A and pregnancy B from the slope of both. In addition, by using the predicted value of the blood pressure at the predetermined time (t), it is possible to perform the comparison excluding the influence of the measurement time difference.

  Similarly, for example, as shown in FIG. 10, it is assumed that the regression line 1006 for the blood pressure value of the pregnant woman C is calculated using the measured value 1005 of the blood pressure of the pregnant woman C after time t2. In this case, the measurement values 1005 of the blood pressure of the pregnant woman C are not included in the periods t1 to t2, but in the present embodiment, the regression lines 1002, 1004, and 1006 are used, and the pregnant women A to The difference in blood pressure transition of C can be compared.

  As another example, in FIG. 6, it is assumed that time t0 is the first day of pregnancy of a pregnant woman. It is also assumed that the occurrence of a certain disease is related to the blood pressure value on the first day of pregnancy. In this case, even when there is no record of the blood pressure value on the first day of pregnancy, such as pregnant woman A, pregnant woman B, and pregnant woman C, the blood pressure value of each pregnant woman is fitted to the linear expression to obtain the intercept b1 of the primary expression and the intercept b2 and the intercept b3 can be obtained, and can be used as a feature amount.

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

  As described above, the feature amount extraction unit 712 extracts feature amounts related to a predetermined disease from temporal changes in quantitative traits collected from a plurality of subjects.

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

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

  In step S803, the DNA mutation information acquiring unit 713 of the DNA mutation narrowing device 710, for example, obtains information on DNA mutations in a plurality of subjects including HDP-affected subjects in parallel with the processing in steps S801 and S802. get.

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

  Preferably, in step S801, the plurality of subjects who obtain continuous quantitative trait information and the plurality of subjects who obtain single nucleotide polymorphism information in step S803 are the same subject.

  In step S804, the association analysis unit 714 of the DNA mutation narrowing apparatus 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 sets the p-value calculated from the Wald statistic of the coefficient of each DNA mutation as the value of the statistical index in the regression equation using the feature amount as the target variable and the DNA mutation as the explanatory variable. Can be.

  Note that the tests (association analysis) when the association analysis unit 714 calculates the value of the statistical index include, for example, linear regression, logistic regression, Fisher's exact test, chi-square test, Cochran-Amitage test, t-test Etc. are used, but the present invention is not limited to this. Further, as the value of the statistical index calculated by the association analysis unit 714, for example, a p value, an f value, an odds ratio, or the like is used, but is not limited thereto.

  In addition, the association analysis unit 714 may calculate the value of the statistical index by further considering the dominant gene action, recessive gene action, genotype, and the like, or use information such as age, weight, and BMI as the co-knitting amount. It may be something.

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

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

  Note that the process of narrowing down 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 apparatus 710 converts the feature amounts extracted by the feature amount extraction unit 712 into an affected group and an unaffected group of HDP using a predetermined reference value. And calculating a p-value indicating the significance of each single nucleotide polymorphism.

  FIG. 11 shows another example of the process of narrowing down DNA mutations according to the fifth embodiment. Note that a detailed description of the same processing as the processing illustrated in FIG. 8 is omitted here.

  In step S1101, the input receiving unit 711 of the onset predicting 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. The information is stored (stored) in the unit 716.

  In step S1102, the feature amount extraction unit 712 of the DNA mutation narrowing-down device 710 performs, for example, a feature amount related to HDP (for example, based on a temporal change in the measured value of blood pressure) in the same manner as the process of step S802 in FIG. , A linear equation).

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

  For example, it is assumed that the slope of the measured value of blood pressure in a pregnant woman suffering from HDP tends to be larger than the slope of the measured value of blood pressure in a pregnant woman not suffering from HDP. In this case, a feature amount larger than a predetermined slope can be labeled as an affected group, and a feature amount less than or equal to a predetermined slope can be labeled as an unaffected group.

  In step S1104, the DNA mutation information acquiring unit 713 of the DNA mutation narrowing-down apparatus 710, for example, similarly to the process of step S803 in FIG. 8, obtains information on DNA mutations in a plurality of subjects including HDP-affected subjects. To get.

  In step S1105, the association analysis unit 714 of the DNA mutation narrowing-down apparatus 710 determines whether each of the single nucleotide polymorphisms included in the single nucleotide polymorphism information obtained by the DNA mutation information obtaining unit 713 is an affected group and an unaffected group. Calculate the value of the statistical index indicating whether there is a difference in the number of holdings in the group. For example, the association analysis unit 714 performs Fisher's exact test or Chi-square test to calculate a p-value.

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

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

  As described above, according to the DNA mutation narrowing-down apparatus 710 according to the present embodiment, even when the definition of a disease is ambiguous as in HDP, single nucleotide polymorphism candidates related to HDP can be easily identified. It becomes possible to narrow down and create the 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 a part of the functional components 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 predicting apparatus 100 for predicting the onset of HDP includes, for example, single nucleotide polymorphism candidates related to HDP, which are narrowed down by the DNA mutation narrowing down apparatus 710 described in the fifth embodiment. It is.

  However, this is an example, and the candidate list 111 includes one or more single nucleotide polymorphisms selected from among the single nucleotide polymorphism candidates related to HDP narrowed down by the DNA mutation narrowing apparatus 710. Candidates may be stored. As described above, the candidate list 111 includes some or all of single nucleotide polymorphism candidates related to HDP narrowed down by the DNA mutation narrowing device 710.

  FIG. 12 is a diagram (1) illustrating an example of single nucleotide polymorphism candidates included in a candidate list according to an embodiment. This figure shows that among the single nucleotide polymorphism candidates related to HDP narrowed down by the DNA mutation narrowing device 710, the association with HDP is reported in the vicinity, or it seems to contribute to the development of HDP. A list 1200 of single nucleotide polymorphism candidates in which the gene to be found was found is shown.

  In other words, the list 1200 includes, among candidates for single nucleotide polymorphisms related to HDP narrowed down by the DNA mutation narrowing device 710, single nucleotide polymorphisms in which a gene whose association with HDP is reported is found nearby. Shows candidates.

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

  FIG. 12 shows that, for example, a single nucleotide polymorphism (SNP) having an rs number of rs39979795 is a single nucleotide polymorphism located at position 31321587 on chromosome 6, and the base is changed to T. In addition, a single nucleotide polymorphism having an rs number of rs3997975 is closely related to genes MUC21 and MUC22, which are reported to be associated with HDP, and a phenotype associated with HDP (eg, diastolic blood pressure). It has been shown that there is a reported gene, BAG6.

  FIG. 13 is a diagram (2) illustrating an example of single nucleotide polymorphism candidates included in the candidate list according to the embodiment. This figure also shows that among the candidates for the single nucleotide polymorphisms related to HDP narrowed down by the DNA mutation narrowing device 710, the association with HDP is reported in the vicinity, or it seems to contribute to the development of HDP. 1300 shows a list of single nucleotide polymorphism candidates in which the gene to be found was found.

  That is, the list 1300 includes, among the candidates for the single nucleotide polymorphisms related to HDP narrowed down by the DNA mutation narrowing device 710, the vascular endothelial growth factor level, which is considered to be involved in the development of HDP, and Single nucleotide polymorphism candidates in which genes related to hypertension were found are shown.

  FIG. 14 is a diagram (3) illustrating an example of single nucleotide polymorphism candidates included in the candidate list according to the embodiment. This figure shows a list 1400 of single nucleotide polymorphisms that are particularly useful for prediction among single nucleotide polymorphisms existing on genes related to known HDPs already registered in a research institution database or the like. .

  The list 1400 includes predictions among single nucleotide polymorphisms present on genes related to HDP, among single nucleotide polymorphisms having a high numerical value indicating the risk of DNA mutation used in the fourth embodiment. Candidates for single nucleotide polymorphisms that have contributed particularly in performing are shown.

  In the candidate list 111 used for the onset prediction by the onset prediction apparatus 100, in place of the single nucleotide polymorphism candidate related to HDP narrowed down by the DNA mutation narrowing apparatus 710, for example, the single nucleotide polymorphism shown in FIG. May be included.

  Similarly, the candidate list 111 used for the onset prediction by the onset prediction apparatus 100 includes, for example, a single nucleotide polymorphism candidate shown in FIG. 13 instead of the single nucleotide polymorphism candidate related to HDP narrowed down by the DNA mutation narrowing down apparatus 710. Nucleotide polymorphism candidates may be included.

  Similarly, in the candidate list 111 used for the onset prediction by the onset prediction apparatus 100, in place of the single nucleotide polymorphism candidate related to HDP narrowed down by the DNA mutation narrowing down apparatus 710, for example, the candidate list shown in FIG. Nucleotide polymorphism candidates may be included.

  Thus, the onset predicting apparatus 100 can more effectively predict the onset of HDP in the subject to be predicted using the single nucleotide polymorphism candidate more closely related to the onset of HDP.

  As described above, according to each embodiment of the present invention, it is easy to grasp the onset risk of HDP before pregnancy, or to make it easy to predict the onset at the beginning of pregnancy, and it is not necessary to make the onset prediction every pregnancy. An apparatus for predicting the onset of HDP can be provided.

  For example, in the prior art, the onset was predicted using an intracorporeal substance that fluctuates after pregnancy. However, according to each embodiment of the present invention, the onset of HDP is predicted even before the subject becomes pregnant. Will be able to In the conventional technology, a test is performed for each pregnancy to predict the onset. However, according to each embodiment of the present invention, it is possible to predict the onset of HDP in a subsequent pregnancy by one test. become able to.

  Further, even in HDP where the definition of the disease is ambiguous, candidates for single nucleotide polymorphisms related to HDP are narrowed down by the DNA mutation narrowing-down apparatus 710 according to the fifth embodiment, and a candidate list used for the onset prediction is narrowed down. 111 can be easily created.

  Further, from among the single nucleotide polymorphism candidates narrowed down by the DNA mutation narrowing apparatus 710, single nucleotide polymorphism candidates near the genes related to HDP are extracted, and a candidate list 111 is created. Thus, the onset of HDP can be predicted more efficiently.

<Supplement>
1 and 7 show functional blocks. These functional blocks are realized by any combination of hardware and / or software. The means for implementing each functional block is not particularly limited. That is, each functional block may be realized by one device physically and / or logically coupled, or two or more devices physically and / or logically separated from each other directly and / or indirectly. (For example, wired and / or wireless), and may be realized by the plurality of devices.

  Further, the hardware configuration of the computer 200 illustrated in FIG. 2 may be configured to include one or more devices illustrated in the drawing, or may be configured not including some 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). Alternatively, some or all of the functional blocks may be implemented by the hardware. For example, the processor 201 may be implemented by at least one of these hardware.

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

  The input and output information and the like may be stored in a specific place (for example, a memory) or may be managed by a management table. Information that is input and output can be overwritten, updated, or added. The output information or the like may be deleted. The input information or the like may be transmitted to another device.

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

  Each aspect / embodiment described in the present specification may be used alone, may be used in combination, or may be used by switching with execution. In addition, the notification of the predetermined information (for example, the notification of “X”) is not limited to explicitly performed, and is performed implicitly (for example, not performing the notification of the predetermined information). Is also good.

  Software, regardless of whether it is called software, firmware, middleware, microcode, a hardware description language, or any other name, instructions, instruction sets, codes, code segments, program codes, programs, subprograms, software modules , Applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, and the like.

  In addition, software, instructions, and the like may be transmitted and received via a transmission medium. For example, if the software uses a wired technology such as coaxial cable, fiber optic cable, twisted pair and digital subscriber line (DSL) and / or a wireless technology such as infrared, wireless and microwave, the website, server, or other When transmitted from a remote source, these wired and / or wireless technologies are included within the definition of transmission medium.

  The 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 can be referred to throughout the above description are not limited to voltages, currents, electromagnetic waves, magnetic or magnetic particles, optical or photons, or any of these. May be represented by a combination of

  Note that terms described in this specification and / or terms necessary for understanding this specification may be replaced with terms having the same or similar meaning.

  Further, the information, parameters, and the like described in this specification may be represented by an absolute value, may be represented by a relative value from a predetermined value, or may be represented by other corresponding information. . For example, the radio resource may be indicated by an index.

  The phrase "based on" as used herein does not mean "based solely on" unless stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

  As long as “including”, “comprising”, and variations thereof, are used herein or in the claims, these terms are used as well as the term “comprising” It is intended to be comprehensive. Further, the term "or" as used in the present specification and claims is not intended to be the exclusive OR.

  Throughout this disclosure, when articles are added by translation, e.g., a, an, and the in English, unless the context clearly indicates otherwise, It shall include a plurality.

  Although the present invention has been described in detail, it will be apparent to those skilled in the art that the present invention is not limited to the embodiments described in this specification. The present invention can be implemented as modified and changed aspects without departing from the spirit and scope of the present invention defined by the description of the claims. Therefore, the description in the present specification is for the purpose of illustrative explanation, and does not have any restrictive meaning to 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 narrowing-down device 712 Feature extraction unit 713 DNA mutation information acquisition unit 714 Related analysis unit (analysis unit)
715 DNA mutation extraction unit (extraction unit)

Claims (10)

From the information of DNA mutations in a plurality of pregnant women, including pregnant women suffering from pregnancy-hypertension syndrome, a model creation information acquisition unit for obtaining information on DNA mutations related to the pregnancy-hypertension syndrome,
Using the information of the DNA mutation obtained by the model creation information acquisition unit, a creation unit that creates a prediction model for predicting the onset of the pregnancy hypertension syndrome,
In a subject to be predicted, a subject information obtaining unit for obtaining information on a DNA mutation related to the pregnancy-induced hypertension syndrome,
The prediction model created by the creation unit, using the information of the DNA mutation obtained by the subject information acquisition unit, using a prediction unit for predicting the onset of the pregnancy hypertension syndrome in the subject to be predicted,
An onset predicting device comprising:   The method according to claim 1, wherein the information on the DNA mutation associated with the pregnancy-induced hypertension syndrome includes information on one or more single nucleotide polymorphisms stored in a candidate list of the single nucleotide polymorphism associated with the pregnancy-induced hypertension syndrome. Onset predictor. The candidate list includes some or all of the single nucleotide polymorphism candidates associated with the pregnancy hypertension syndrome narrowed down by a DNA mutation narrowing device,
The DNA mutation narrowing device,
A feature amount extraction unit that extracts feature amounts from continuous measurement values of quantitative traits related to the pregnancy hypertension syndrome, collected from a plurality of subjects including the subject suffering from the pregnancy hypertension syndrome,
A DNA mutation information acquisition unit for acquiring information on single nucleotide polymorphisms in the plurality of subjects,
An analysis unit that analyzes the association between the feature quantity and the single nucleotide polymorphism included in the information of the single nucleotide polymorphism,
Based on the analysis results of the analysis unit, a DNA mutation extraction unit that extracts single nucleotide polymorphism candidates related to the pregnancy hypertension syndrome,
The onset predicting apparatus according to claim 2, comprising:   The candidate list is, among the candidates for the single nucleotide polymorphism associated with the pregnancy hypertension syndrome narrowed down by the DNA mutation narrowing apparatus, a gene associated with the pregnancy hypertension syndrome, or one existing in the vicinity of the gene. The onset predicting apparatus according to claim 3, comprising the information on the single nucleotide polymorphism.   The onset prediction device according to any one of claims 2 to 4, wherein the candidate list includes information on a single nucleotide polymorphism identified by the rs number shown in FIG. 12, FIG. 13, or FIG.   The creating unit, among the single nucleotide polymorphism candidates included in the candidate list, using information of one or more single nucleotide polymorphisms whose value indicating the degree of harm of the single nucleotide polymorphism is equal to or greater than a threshold value, The onset predicting apparatus according to any one of claims 2 to 5, which creates a predictive model. In the case where the information of the DNA mutation obtained by the subject information obtaining unit does not include a part of the information of the DNA mutation related to the pregnancy hypertension syndrome,
The creating unit creates the prediction model by excluding information on DNA mutations not included in the information on the DNA mutations acquired by the subject information acquiring unit from the information on the DNA mutations related to the pregnancy-induced hypertension syndrome. An onset predicting apparatus according to any one of claims 1 to 6. The creating unit creates a prediction model to predict whether to develop the pregnancy hypertension syndrome,
The onset prediction device according to any one of claims 1 to 7, wherein the prediction unit predicts whether or not the subject develops the pregnancy hypertension syndrome. The creating unit creates a prediction model for predicting the risk of developing the pregnancy hypertension syndrome,
The onset prediction device according to any one of claims 1 to 8, wherein the prediction unit predicts a risk of the subject developing the pregnancy hypertension syndrome. An onset predictive device according to claim 1,
A DNA mutation narrowing-down device that creates a candidate list of DNA mutations related to pregnancy hypertension syndrome used in the onset prediction device,
An onset prediction system including
The DNA mutation narrowing device,
A feature amount extraction unit that extracts feature amounts from continuous measurement values of quantitative traits related to the pregnancy hypertension syndrome, collected from a plurality of subjects including the subject suffering from the pregnancy hypertension syndrome,
A DNA mutation information acquisition unit for acquiring information on single nucleotide polymorphisms in the plurality of subjects,
An analysis unit that analyzes the association between the feature quantity and the single nucleotide polymorphism included in the information of the single nucleotide polymorphism,
Based on the analysis results of the analysis unit, a DNA mutation extraction unit to extract DNA mutation candidates related to the pregnancy hypertension syndrome,
An onset prediction system having

Images