Method for predicting cardiomyopathy typing caused by myocardial cell variation and electronic device

Abstract

The invention provides a method for predicting cardiomyopathy typing caused by myocardial cell variation and an electronic device. The prediction method comprises the following steps: acquiring a variant amino acid type of JPH2 protein of a to-be-predicted variant myocardial cell; if the variation amino acid type is the variation amino acid type of the known cardiomyopathy type, obtaining the cardiomyopathy type caused by myocardial cell variation; if the variant amino acid type does not belong to the variant amino acid type of the known cardiomyopathy type, obtaining the tension index of the variant myocardial cell to be predicted; inputting the tension index into a prediction model of cardiomyopathy typing caused by myocardial cell variation, and outputting a prediction result of cardiomyopathy typing, namely outputting cardiomyopathy typing caused by myocardial cell variation. The tension index of myocardial cells is detected through a quantifiable method, and the disease type of cardiomyopathy caused by myocardial cell variation can be efficiently and accurately predicted.

Description

Technical Field

[0001] The present invention relates to the technical field of cytology, and in particular to a prediction method and an electronic device for the classification of cardiomyopathy caused by cardiomyocyte mutation. Background Art

[0002] Human pluripotent stem cells (hPSCs) have the potential to proliferate indefinitely in vitro and differentiate into cells of all germ layers, including the heart. The system for hPSCs to differentiate into cardiomyocytes in vitro has been very well developed, and can efficiently obtain spontaneously beating human pluripotent stem cell derived cardiomyocytes (hPSCs-CMs) in a short period of time (Publication No.: WO2014078414A1, CN106244526A). The process of hPSCs cardiomyocyte differentiation is consistent with the process of complete embryonic cardiomyocyte development in vivo. During the in vitro differentiation process, it sequentially expresses cardiomyocyte-specific structural proteins and ion channels, and the differentiated hPSCs-CMs have the complex phenotype and functional characteristics of cardiomyocytes in vivo, such as generating similar action potentials and showing spontaneous contractions. The application of hPSCs-CMs can overcome the barrier of obtaining primary cardiomyocytes and break the bottleneck of species differences. In addition, hPSCs-CMs are easy to obtain and can be prepared on a large scale and efficiently, making them an ideal tool for studying human heart disease.

[0003] With the development of next-generation sequencing technology, a large number of large-scale genetic screenings have been performed in healthy and diseased populations. However, the functional interpretation of genetic variants lags behind the identification of variants, resulting in the identification of a large number of variants of unknown significance (VUS) whose pathogenicity cannot be determined. In addition, due to the lack of functional assays, some benign and pathogenic variants are misclassified (PMID: 31752965, PMID: 29868193). This incomplete genetic framework reduces the value of large-scale genetic research and limits the clinical application of genetic information. Therefore, how to provide a method to efficiently and accurately predict the classification of cardiomyopathy caused by cardiomyocyte mutations is of great significance for actual clinical applications. Summary of the invention

[0004] The main purpose of the present invention is to provide a method and an electronic device for predicting the classification of cardiomyopathy caused by cardiomyocyte mutation, so as to solve the problem in the prior art that it is difficult to effectively predict the classification of cardiomyopathy caused by cardiomyocyte mutation.

[0005] In order to achieve the above-mentioned purpose, according to the first aspect of the present invention, a method for predicting cardiomyopathy typing caused by cardiomyocyte mutation is provided, and the prediction method comprises: obtaining the variant amino acid type of the JPH2 protein of the cardiomyocyte mutation to be predicted; if the variant amino acid type is the variant amino acid type of a known cardiomyopathy typing, obtaining the cardiomyopathy typing caused by the cardiomyocyte mutation; if the variant amino acid type does not belong to the variant amino acid type of a known cardiomyopathy typing, obtaining the tension index of the cardiomyocyte mutation to be predicted; inputting the tension index into a prediction model of the cardiomyopathy typing caused by the cardiomyocyte mutation, and outputting the prediction result of the cardiomyopathy typing, that is, outputting the cardiomyopathy typing caused by the cardiomyocyte mutation.

[0006] Furthermore, the prediction model of cardiomyopathy classification caused by cardiomyocyte mutation is obtained by machine learning training using the tension index of cardiomyocytes of samples with different types of cardiomyopathy and healthy samples without cardiomyopathy; wherein, different types of cardiomyopathy include: dilated cardiomyopathy DCM and hypertrophic cardiomyopathy HCM; preferably, the cardiomyocytes of samples with different types of cardiomyopathy and healthy samples without cardiomyopathy are cardiomyocytes with JPH2 gene mutations.

[0007] Furthermore, the output standard of the prediction model is: when the tension index is greater than 0.2, the cardiomyopathy classification is output as hypertrophic cardiomyopathy HCM; when the tension index is less than -0.2, the cardiomyopathy classification is output as dilated cardiomyopathy DCM; when the tension index is ≤0.2 and ≥-0.2, the output is not diseased.

[0008] In order to achieve the above-mentioned purpose, according to a second aspect of the present invention, there is provided a method for constructing a prediction model for the classification of cardiomyopathy caused by cardiomyocyte mutation, the construction method comprising: obtaining the tension index of cardiomyocytes of samples known to suffer from different types of cardiomyopathy and the cardiomyocytes of healthy samples without cardiomyopathy; using the tension index of biological samples known to suffer from different types of cardiomyopathy and those without cardiomyopathy to perform machine learning training to obtain a prediction model for the classification of cardiomyopathy caused by cardiomyocyte mutation; wherein the different types of cardiomyopathy include: dilated cardiomyopathy DCM and hypertrophic cardiomyopathy HCM.

[0009] In order to achieve the above-mentioned purpose, according to the third aspect of the present invention, there is provided an electronic device for predicting the classification of cardiomyopathy caused by cardiomyocyte mutation, the electronic device for predicting has a built-in prediction model for the classification of cardiomyopathy caused by cardiomyocyte mutation, and the electronic device for predicting comprises: a gene information acquisition module, configured to acquire the JPH2 variant amino acid type of the cardiomyocyte mutation to be predicted; a primary screening module, configured to obtain the cardiomyopathy classification caused by cardiomyocyte mutation if the variant amino acid type is a variant amino acid type of a known cardiomyopathy classification; and to acquire the tension index of the cardiomyocyte mutation to be predicted if the variant amino acid type does not belong to a variant amino acid type of a known cardiomyopathy classification; and a prediction module, configured to input the tension index into the prediction model and output the prediction result of the cardiomyopathy classification, that is, output the cardiomyopathy classification caused by cardiomyocyte mutation.

[0010] Furthermore, the prediction model is obtained by machine learning training using the tension index of cardiomyocytes of samples with different types of cardiomyopathy and healthy samples without cardiomyopathy; among them, different types of cardiomyopathy include: dilated cardiomyopathy DCM and hypertrophic cardiomyopathy HCM.

[0011] Furthermore, the cardiomyocytes of samples with different types of cardiomyopathy and the cardiomyocytes of healthy samples without cardiomyopathy are cardiomyocytes with JPH2 gene mutations.

[0012] Furthermore, the output standard of the prediction model is: when the tension index is greater than 0.2, the cardiomyopathy classification is output as hypertrophic cardiomyopathy HCM; when the tension index is less than -0.2, the cardiomyopathy classification is output as dilated cardiomyopathy DCM; when the tension index is ≤0.2 and ≥-0.2, the output is not diseased.

[0013] In order to achieve the above-mentioned purpose, according to the fourth aspect of the present invention, there is provided an electronic device, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the above-mentioned method for predicting the classification of cardiomyopathy caused by myocardial cell mutation or the method for constructing a prediction model for the classification of cardiomyopathy caused by myocardial cell mutation by executing the executable instructions.

[0014] In order to achieve the above-mentioned purpose, according to the fifth aspect of the present invention, a computer-readable storage medium is provided, and the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned method for predicting the classification of cardiomyopathy caused by myocardial cell mutation or the above-mentioned method for constructing a prediction model for the classification of cardiomyopathy caused by myocardial cell mutation.

[0015] By applying the technical solution of the present invention, the tension index of cardiomyocytes is detected by a quantifiable method, which can more efficiently and accurately predict the disease classification of cardiomyopathy caused by cardiomyocyte mutations, so as to further realize drug testing and screening for different cardiomyopathy classifications, build an efficient and accurate in vitro drug evaluation system, and realize drug guidance for clinical precision treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings constituting a part of the present application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0017] Figure 1 The peak diagram of DNA sequencing of genomic DNA in Example 1 of the present application after knocking out the JPH2 gene by CRISPR / CAS9 is shown;

[0018] Figure 2 The figure shows the Western Blot detection result of hPSCs with JPH2 gene knockout in Example 1 of the present application;

[0019] Figure 3 The microscopic observation images of cardiomyocytes differentiated from wild-type stem cells and JPH2 knockout stem cells in Example 1 of the present application are shown;

[0020] Figure 4 The schematic diagram of the structure of the lentiviral vector in Example 1 of the present application is shown;

[0021] Figure 5 The microscopic observation diagram of the myocardial cells transfected with lentivirus in Example 1 of the present application is shown;

[0022] Figure 6 A statistical diagram showing the tension index of myocardial cells of different variants known in the cardiomyopathy classification in Example 1 of the present application is shown;

[0023] Figure 7 A statistical graph showing the tension index of cardiomyocytes of different variants with unknown cardiomyopathy type in Example 2 of the present application is shown;

[0024] Figure 8 A statistical graph showing the expression levels of the MYH7 / MYH6 genes in the cardiomyocyte mutation sites L159Q and R97Q in Example 2 of the present application is shown. DETAILED DESCRIPTION

[0025] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present invention will be described in detail below in conjunction with the embodiments.

[0026] Glossary:

[0027] Human myocardial model: refers to any cardiomyocytes differentiated from human pluripotent stem cells with the potential for in vitro myocardial differentiation.

[0028] JPH2 gene: It is a gene for membrane-connected protein and plays a key role in the structure of the myocardial cell membrane junction complex JMC. It is essential for maintaining the excitation-contraction coupling of myocardial cells. Its gene mutation is associated with HCM.

[0029] As mentioned in the background technology, there are many mutations in the prior art that cannot clearly identify the pathogenic type of myocardial cell mutations. In order to be able to more accurately predict the cardiomyopathy typing of myocardial cell mutations, in the first typical embodiment of the present application, a prediction method for cardiomyopathy typing caused by myocardial cell mutations is provided, and the prediction method includes: obtaining the JPH2 variant amino acid type of the myocardial cell to be predicted; if the variant amino acid type is a variant amino acid type of a known cardiomyopathy typing, the cardiomyopathy typing caused by the myocardial cell mutation is obtained; if the variant amino acid type does not belong to the variant amino acid type of a known cardiomyopathy typing, the tension index of the myocardial cell to be predicted is obtained; the tension index is input into the prediction model of the cardiomyopathy typing caused by the myocardial cell mutation, and the prediction result of the cardiomyopathy typing is output, that is, the cardiomyopathy typing caused by the myocardial cell mutation is output. Among them, the variant amino acid type of the known cardiomyopathy typing is shown in Table 1.

[0030] SEQ ID NO: 1: (amino acid sequence of JPH2 protein)

[0031] .

[0032] Table 1:

[0033]

[0034]

[0035] Using the tension index to predict whether samples with myocardial cell mutations have different types of cardiomyopathy can obtain relatively accurate results. Among them, cardiomyopathy has different types due to its different pathogenic mechanisms, which is a further classification of diseases under cardiomyopathy.

[0036] In the study of cardiomyopathy, classification refers to the division of cardiomyopathy into different subtypes based on the etiology, pathological mechanism, clinical manifestations and morphological characteristics of cardiomyopathy. Cardiomyopathy classification is helpful for clinical diagnosis, treatment decision-making and prognosis assessment. The classification of cardiomyopathy is mainly based on abnormal myocardial function and structural changes. Common classifications include the following categories:

[0037] 1. Hypertrophic Cardiomyopathy (HCM): The myocardium, especially the left ventricle, is abnormally thickened. This type of cardiomyopathy may be related to gene mutations, resulting in excessive myocardial contractility.

[0038] 2. Dilated Cardiomyopathy (DCM): The heart chambers expand and the ventricles become thinner, which weakens the heart's pumping function. Its pathogenesis is relatively complex and may include multiple factors such as genetics, infection, and toxins.

[0039] In addition, there are other types of cardiomyopathy:

[0040] 1. Restrictive cardiomyopathy (RCM): The myocardium becomes stiff, limiting the heart's diastolic function and causing the heart to be unable to effectively fill with blood.

[0041] 2. Arrhythmogenic Right Ventricular Cardiomyopathy (ARVC): Mainly affects the right ventricle, causing the myocardium to be replaced by fibrous or fatty tissue, which can easily cause arrhythmias.

[0042] 3. Left Ventricular Noncompaction Cardiomyopathy (LVNC): The left ventricular myocardium is not completely compacted, presenting a spongy structure, which affects heart function.

[0043] Using cardiomyocytes with known cardiomyopathy classification, their tension index and cardiomyopathy classification are analyzed and judged to obtain a prediction model. In a preferred embodiment, the prediction model of cardiomyopathy classification caused by cardiomyocyte mutation is obtained by machine learning training using the tension index of cardiomyocytes of cardiomyocytes of samples with different cardiomyopathy classifications and cardiomyocytes of healthy samples without cardiomyopathy; wherein different types of cardiomyopathy include: dilated cardiomyopathy DCM and hypertrophic cardiomyopathy HCM; preferably, the cardiomyocytes of samples with different cardiomyopathy classifications and the cardiomyocytes of healthy samples without cardiomyopathy are cardiomyocytes with JPH2 gene mutations.

[0044] In order to further obtain more accurate prediction results, in a preferred embodiment, the output standard of the prediction model is: when the tension index is greater than 0.2, the cardiomyopathy classification is output as hypertrophic cardiomyopathy HCM; when the tension index is less than -0.2, the cardiomyopathy classification is output as dilated cardiomyopathy DCM; when the tension index is ≤0.2 and ≥-0.2, the output is not diseased.

[0045] In a second typical embodiment of the present application, a method for constructing a predictive model for the classification of cardiomyopathy caused by cardiomyocyte mutation is provided, the construction method comprising: obtaining tension indexes of cardiomyocytes of samples known to suffer from different types of cardiomyopathy and cardiomyocytes of healthy samples without cardiomyopathy; performing machine learning training using tension indexes of biological samples known to suffer from different types of cardiomyopathy and without cardiomyopathy to obtain a predictive model for the classification of cardiomyopathy caused by cardiomyocyte mutation; wherein different types of cardiomyopathy include: dilated cardiomyopathy DCM and hypertrophic cardiomyopathy HCM.

[0046] In a third typical embodiment of the present application, an electronic device for predicting cardiomyopathy typing caused by cardiomyocyte mutation is provided, the electronic device having a built-in prediction model for cardiomyopathy typing caused by cardiomyocyte mutation, and the electronic device comprises: a gene information acquisition module, configured to acquire the JPH2 variant amino acid type of the cardiomyocyte to be predicted; a primary screening module, configured to obtain the cardiomyopathy typing caused by cardiomyocyte mutation if the variant amino acid type is a variant amino acid type of a known cardiomyopathy typing; and to acquire the tension index of the cardiomyocyte to be predicted if the variant amino acid type does not belong to a variant amino acid type of a known cardiomyopathy typing; and a prediction module, configured to input the tension index into the prediction model and output a prediction result of the cardiomyopathy typing, i.e., output the cardiomyopathy typing caused by cardiomyocyte mutation.

[0047] Using cardiomyocytes with known cardiomyopathy types, their tension index and cardiomyopathy types are analyzed and judged to obtain a prediction model. In a preferred embodiment, the prediction model is obtained by machine learning training using the tension index of cardiomyocytes of cardiomyopathy samples with different types and cardiomyocytes of healthy samples without cardiomyopathy; wherein different types of cardiomyopathy include: dilated cardiomyopathy DCM and hypertrophic cardiomyopathy HCM; preferably, the cardiomyocytes of cardiomyopathy samples with different types and the cardiomyocytes of healthy samples without cardiomyopathy are cardiomyocytes with JPH2 gene mutations.

[0048] In order to further obtain more accurate prediction results, in a preferred embodiment, the output standard of the prediction model is: when the tension index is greater than 0.2, the cardiomyopathy classification is output as hypertrophic cardiomyopathy HCM; when the tension index is less than -0.2, the cardiomyopathy classification is output as dilated cardiomyopathy DCM; when the tension index is ≤0.2 and ≥-0.2, the output is not diseased.

[0049] In a fourth typical embodiment of the present application, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the above-mentioned method for predicting the classification of cardiomyopathy caused by myocardial cell mutation or the method for constructing a prediction model for the classification of cardiomyopathy caused by myocardial cell mutation by executing the executable instructions.

[0050] In a fifth typical embodiment of the present application, a computer-readable storage medium is provided, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned method for predicting the type of cardiomyopathy caused by myocardial cell mutation or the method for constructing a prediction model for the type of cardiomyopathy caused by myocardial cell mutation.

[0051] The present application is further described in detail below in conjunction with specific embodiments. These embodiments should not be construed as limiting the scope of protection claimed in the present application.

[0052] The H9 human embryonic stem cell line in the embodiments of the present application is derived from the Lanfeng Laboratory of the Fuwai Hospital of the Chinese Academy of Medical Sciences; 293T cells are derived from the Lanfeng Laboratory of the Fuwai Hospital of the Chinese Academy of Medical Sciences; lentivirus is derived from Yunzhou Biotechnology (Guangzhou) Co., Ltd.; human pluripotent stem cell culture medium is derived from Beijing Saibei Biotechnology Co., Ltd.; myocardial purification culture medium is derived from Beijing Saibei Biotechnology Co., Ltd.; and myocardial cell maintenance culture medium is derived from Beijing Saibei Biotechnology Co., Ltd.

[0053] Example 1 Testing Standard Training

[0054] 1. Construction of JPH2 knockout H9 human embryonic stem cell line

[0055] CRISPR / CAS9 genome editing technology was used to knock out the target gene JPH2.

[0056] 1.1 Design sgRNA targeting JPH2 gene, the coding sequence of sgRNA is shown in SEQ ID NO: 2, CCGGGTACTTGCCCTCCTCGCGG, and construct CRISPR / CAS9 plasmid;

[0057] 1.2 Transfect 293T cells with CRISPR / CAS9 plasmid, extract genomic DNA of surviving cells after Puromycin screening for PCR, and observe the peak strength of DNA sequencing results (such as Figure 1 As shown) and TA clone sequencing ratio to detect sgRNA activity;

[0058] 1.3 hPSCs were cultured in human pluripotent stem cell culture medium at 37°C in an incubator containing 5% carbon dioxide. After the cells were fully grown, human pluripotent stem cell digestion solution was used for digestion and passage;

[0059] 1.4 After the confluence of hPSCs reaches 70-80%, the highly active CRISPR / CAS9 plasmid is transfected into hPSCs by electroporation;

[0060] 1.5 Use Puromycin to screen out JPH2 gene knockout hPSCs and verify JPH2 gene knockout by Western Blot (e.g. Figure 2 As shown, WT is the wild-type sample, and KO is the JPH2 gene knockout sample).

[0061] 2. Directed differentiation of cardiomyocytes

[0062] 2.1 Using a known cardiomyocyte differentiation protocol (Patent Publication No. CN106244526A), combined with a Wnt pathway promoter (small molecule drug CHIR99021) and inhibitor (small molecule drug IWP2) for cardiomyocyte-directed differentiation;

[0063] 2.2 Use a sugar-free myocardial purification medium containing lactic acid to purify myocardial cells and obtain myocardial cells with a purity of more than 95%;

[0064] 2.3 Use cardiomyocyte maintenance medium to culture cardiomyocytes at 37°C in an incubator containing 5% carbon dioxide. Replace the medium every 2 to 3 days to obtain successfully differentiated cardiomyocytes (such as Figure 3 As shown, WT-CMs are cardiomyocytes differentiated from normal stem cells, and KO-CMs are cardiomyocytes differentiated from JPH2 knockout stem cells).

[0065] 3. Construction of human myocardial models with different JPH2 mutations

[0066] Different JPH2 mutant genes were overexpressed in the JPH2 knockout myocardial model by lentiviral transfection to obtain a large number of human cardiomyocyte models with different JPH2 gene mutations.

[0067] 3.1 A lentiviral vector overexpressing different JPH2 mutant genes was designed and constructed using known methods and packaged. The vector contained a 5'LTR and a 3'LTR of the ψ sequence, a target gene (JPH2) sequence between the 5'LTR and the 3'LTR, and a promoter sequence and a translation initiation sequence operably linked to the target gene sequence (the lentiviral vector structure is as follows: Figure 4 shown);

[0068] 3.2 Virus titer test, according to 1×10 5 The target gene knockout cardiomyocytes were inoculated in each well of a 24-well plate, and the virus was added on the next day. The myocardial maintenance medium was replaced after 12 to 20 hours. The fluorescence was recorded by photographing 72 hours after infection, and the cells were collected to extract genomic DNA and protein. The optimal infection titer was determined by quantitative PCR and Western Blot experiments. The optimal infection titer refers to the viral titer that can make the expression level of mutant genes and mutant proteins close to that of wild-type cardiomyocytes.

[0069] 3.3 Using the optimal infection titer (MOI = 20) to overexpress different JPH2 mutant genes in JPH2 knockout cardiomyocytes (transfection status as shown in Figure 2A). Figure 5 As shown), human cardiomyocytes expressing different JPH2 mutant genes were constructed.

[0070] Among them, the mutation sites of different JPH2 mutant genes are shown in Table 2.

[0071] Table 2:

[0072] serial number Mutation site serial number Mutation site 1 C15G 16 Y141H 2 S101R 17 P55L 3 E169K 18 R572C 4 S235A 19 D252A 5 A405S 20 Y129D 6 C678A 21 Q97 7 E85K 22 R197L 8 L204R 23 G482A 9 G31D 24 P148L 10 G505S 25 E47A 11 E402K 26 S165F 12 M292T 27 T161K 13 R223G 28 L159Q 14 E234A 29 R375C 15 T329N

[0073] 4. Phenotypic identification of human cardiomyocytes expressing different JPH2 mutant genes

[0074] 4.1 Wild-type cardiomyocytes and human cardiomyocytes with JPH2 mutations obtained in step 3 and known cardiomyopathy classification (variation types are shown in Table 3) were cultured in myocardial maintenance medium at 37°C in an incubator containing 5% carbon dioxide for 25 days. Wild-type cardiomyocytes and human cardiomyocytes with different JPH2 mutations were digested and seeded at 50,000 cells / well on a 96-well electrode plate coated with matrix gel in advance. Continue to culture for 3 to 5 days, and subsequent detection can be performed after the cardiomyocytes are stably beating spontaneously on the electrode plate;

[0075] 4.2 Use the CardioExcyte 96 system to test the electrophysiological activity of cardiomyocytes. Use the Recording mode of CardioExcyte Control96 to start the test, and perform a 20-second test every 48 hours, for a total of 3 times;

[0076] 4.3 The test results were exported using the Replay mode of CardioExcyte Control 96. Each online analysis (OA) data point was based on a 20-s scan, where the Tension Index was obtained by calculating the area under the curve of the contraction curve exported by the CardioExcyte 96 system;

[0077] 4.4 Plotting of statistical graphs between Tension Index readings and specific mutation sites of human cardiomyocytes expressing different JPH2 mutant genes shown in Table 3 (e.g. Figure 6 As shown), the obtained tension index and cardiomyopathy classification were used for machine learning training to obtain the judgment standard: when the tension index is greater than 0.2, the cardiomyopathy classification is output as hypertrophic cardiomyopathy HCM; when the tension index is less than -0.2, the cardiomyopathy classification is output as dilated cardiomyopathy DCM; when the tension index is ≤0.2 and ≥-0.2, the output is not sick.

[0078] Among them, the tension index of human cardiomyocytes expressing different JPH2 mutant genes is shown in Table 3.

[0079] Table 3:

[0080]

[0081]

[0082] 5. Based on the tension index of the cardiomyocytes to be tested, the cardiomyopathy classification of the cardiomyocytes to be tested is obtained, so as to achieve targeted large-scale drug testing and screening and provide guidance for clinical precision drug use.

[0083] Example 2 Testing Standard Verification

[0084] The method of step 4 above is used to detect the tension index of the cardiomyocytes of the cardiomyopathy type caused by the unknown gene mutation constructed in this application (such as Figure 7 The tension index is used to determine the type of cardiomyopathy.

[0085] There is no intuitive phenotypic judgment standard for the detection of cardiomyopathy classification. The following uses the ratio of MYH7 and MYH6 expression to objectively judge the type of cardiomyopathy classification. MYH7 and MYH6 are marker genes for HCM / DCM. The ratio of MYH7 to MYH6 (MYH7 / MYH6) is increased in the HCM model and decreased in the DCM model compared with the control overexpressing wild-type JPH2.

[0086] like Figure 8As shown, it can be seen that the expression level of MYH7 / MYH6 increased in the L159Q sample whose cardiomyopathy classification was judged as HCM, and the expression level of MYH7 / MYH6 decreased in the R97Q sample whose cardiomyopathy classification was judged as DCM (wherein the expression level of MYH7 / MYH6 of the wild-type JPH2 used as a control was 1), which further proves the accuracy of the judgment standard of the present application and has certain application significance in the actual judgment of cardiomyopathy classification of myocardial cells.

[0087] Table 4:

[0088]

[0089]

[0090] From the above description, it can be seen that the above-mentioned embodiments of the present invention achieve the following technical effects: by detecting the tension index of myocardial cells by a quantifiable method, it is possible to more efficiently and accurately predict the disease classification of cardiomyopathy caused by myocardial cell mutations, so as to further realize drug testing and screening for different cardiomyopathy classifications, build an efficient and accurate in vitro drug evaluation system, and realize medication guidance for clinical precision treatment.

[0091] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for predicting the classification of cardiomyopathy caused by myocardial cell mutation, characterized in that: The prediction method comprises: Obtaining the variant amino acid type of the JPH2 protein of the cardiomyocytes to be predicted; If the variant amino acid type is a variant amino acid type of a known cardiomyopathy classification, the cardiomyopathy classification caused by the cardiomyocyte mutation is obtained; If the variant amino acid type does not belong to the variant amino acid type of known cardiomyopathy classification, obtaining the tension index of the variant myocardial cell to be predicted; The tension index is input into a prediction model of the cardiomyopathy classification caused by cardiomyocyte mutation, and a prediction result of the cardiomyopathy classification is output, that is, the cardiomyopathy classification caused by the cardiomyocyte mutation is output.

2. The prediction method according to claim 1, characterized in that: The prediction model of cardiomyopathy classification caused by cardiomyocyte variation is obtained by machine learning training using the tension index of cardiomyocytes of samples with cardiomyopathy of different classifications and cardiomyocytes of healthy samples without cardiomyopathy; Among them, different types of cardiomyopathy include: dilated cardiomyopathy DCM and hypertrophic cardiomyopathy HCM; Preferably, the cardiomyocytes of samples suffering from cardiomyopathy of different types and the cardiomyocytes of healthy samples without cardiomyopathy are cardiomyocytes with JPH2 gene mutation.

3. The prediction method according to claim 1, characterized in that: The output criteria of the prediction model are: When the tension index is greater than 0.2, the cardiomyopathy classification is output as hypertrophic cardiomyopathy HCM; When the tension index is less than -0.2, the cardiomyopathy classification is output as dilated cardiomyopathy DCM; When the tension index is ≤ 0.2 and ≥ -0.2, the output is not diseased.

4. A method for constructing a prediction model for the classification of cardiomyopathy caused by myocardial cell mutation, characterized in that: The construction method comprises: Obtaining the tension index of cardiomyocytes from samples with known different types of cardiomyopathy and from healthy samples without cardiomyopathy; Using the tension index of biological samples of patients with different types of cardiomyopathy and patients without cardiomyopathy to perform machine learning training, a prediction model for the cardiomyopathy classification caused by the cardiomyocyte mutation is obtained; Among them, different types of cardiomyopathy include: dilated cardiomyopathy DCM and hypertrophic cardiomyopathy HCM.

5. An electronic device for predicting the classification of cardiomyopathy caused by myocardial cell mutation, characterized in that: The prediction electronic device has a built-in prediction model for the classification of cardiomyopathy caused by myocardial cell mutation, and the prediction electronic device includes: A gene information acquisition module is configured to acquire the JPH2 variant amino acid type of the variant cardiomyocyte to be predicted; The primary screening module is configured to obtain the cardiomyopathy type caused by the myocardial cell mutation if the variant amino acid type is a variant amino acid type of a known cardiomyopathy type; and obtain the tension index of the myocardial cell mutation to be predicted if the variant amino acid type does not belong to the variant amino acid type of a known cardiomyopathy type. The prediction module is configured to input the tension index into the prediction model and output a prediction result of the cardiomyopathy classification, that is, output the cardiomyopathy classification caused by the cardiomyocyte mutation.

6. The prediction electronic device according to claim 5, characterized in that: The prediction model is obtained by machine learning training using the tension index of cardiomyocytes of samples with different types of cardiomyopathy and healthy samples without cardiomyopathy; Among them, different types of cardiomyopathy include: dilated cardiomyopathy DCM and hypertrophic cardiomyopathy HCM.

7. The prediction electronic device according to claim 6, characterized in that: The cardiomyocytes of the samples with different types of cardiomyopathy and the cardiomyocytes of the healthy samples without cardiomyopathy are cardiomyocytes with JPH2 gene mutations.

8. The prediction electronic device according to claim 5, characterized in that: The output criteria of the prediction model are: When the tension index is greater than 0.2, the cardiomyopathy classification is output as hypertrophic cardiomyopathy HCM; When the tension index is less than -0.2, the cardiomyopathy classification is output as dilated cardiomyopathy DCM; When the tension index is ≤ 0.2 and ≥ -0.2, the output is not diseased.

9. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to execute the method for predicting the classification of cardiomyopathy caused by cardiomyocyte mutation described in any one of claims 1 to 3 or the method for constructing a prediction model for the classification of cardiomyopathy caused by cardiomyocyte mutation described in claim 4 by executing the executable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method for predicting the classification of cardiomyopathy caused by cardiomyocyte mutation described in any one of claims 1 to 3 or the method for constructing a prediction model for the classification of cardiomyopathy caused by cardiomyocyte mutation described in claim 4.

Images