Application of markers in the preparation of related products for predicting intrahepatic cholestasis of pregnancy

Abstract

The present invention provides an application of a marker in the preparation of related products for predicting intrahepatic cholestasis of pregnancy. Wherein, the marker includes a clinical indicator marker and / or a gene marker, and the clinical indicator marker includes a conception method indicator and any one or more of the following clinical detection indicators: total bile acid, γ-glutamyl transpeptidase, folic acid and aspartate transaminase, and the conception method indicator is whether assisted reproduction; the gene marker includes any one or more of the following: ABCA2, ALDH4A1, ANKRA2, BLVRB, ENTR1, EZR, FCHO2, HIST1H2AE, IQCE, LARS, MMP15, PXK, RNF141, SLC7A2, TGFBR2, TMEM135 and TMEM144. The use of the above markers for detection can achieve high specificity and high sensitivity risk prediction of intrahepatic cholestasis of pregnancy.

Description

Technical Field

[0001] The present invention relates to the field of pregnancy complications, and in particular, to the application of gene markers in the preparation of related products for predicting intrahepatic cholestasis of pregnancy. Background Art

[0002] Intrahepatic cholestasis of pregnancy (ICP) is a complication unique to mid- and late-term pregnancy (clinically, pregnancy is divided into three cycles: early pregnancy before the 13th week, mid-term pregnancy from the 14th to the 27th week, and late pregnancy from the 28th week onwards). It is clinically characterized by skin itching and elevated bile acid levels, which mainly harms the fetus, increasing the rate of premature birth and stillbirth. Early prediction and early intervention can improve pregnancy outcomes. Currently, there is no clinical product for the prediction of intrahepatic cholestasis of pregnancy.

[0003] Currently, the risk of intrahepatic cholestasis of pregnancy is mainly predicted by combining serum alpha-fetoprotein and age as markers, but the accuracy is very low, and the prediction sensitivity and specificity are less than 0.65.

[0004] So far, the main research in this field has focused on assisting the diagnosis of intrahepatic cholestasis of pregnancy, lacking risk prediction, which can support the study of the mechanism of intrahepatic cholestasis of pregnancy and targeted intervention treatment methods. Therefore, there is an urgent need to develop a program that can accurately predict the risk of intrahepatic cholestasis of pregnancy. Summary of the invention

[0005] The main purpose of the present invention is to provide an application of a marker in the preparation of related products for predicting intrahepatic cholestasis of pregnancy, so as to improve the accuracy of risk prediction of intrahepatic cholestasis of pregnancy.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present invention, there is provided an application of a marker in the preparation of related products for predicting intrahepatic cholestasis of pregnancy, wherein the marker includes a clinical indicator marker and / or a gene marker, wherein the clinical indicator marker includes a conception mode indicator and any one or more of the following clinical detection indicators: total bile acid, γ-glutamyl transpeptidase, folic acid and aspartate transaminase, and the conception mode indicator is whether assisted reproduction is used; the gene marker includes any one or more of the following: ABCA2, ALDH4A1, ANKRA2, BLVRB, ENTR1, EZR, FCHO2, HIST1H2AE, IQCE, LARS, MMP15, PXK, RNF141, SLC7A2, TGFBR2, TMEM135 and TMEM144.

[0007] Furthermore, the application includes using detection reagents to detect the expression levels of clinical detection indicators and / or gene markers. Preferably, when the marker is a gene marker, the detection reagent is a detection reagent for detecting the mRNA expression level or protein expression level of the gene marker; more preferably, the detection reagent for detecting the mRNA expression level of the gene marker is a probe and / or primer, and further preferably, it is a related reagent for preparing the mRNA of the gene marker into a high-throughput sequencing library.

[0008] Furthermore, in combination with the conception mode indicator, clinical detection indicators and / or gene markers are detected in biological samples from pregnant women, wherein the biological samples are selected from one or more of the following: plasma, serum, whole blood, urine, and amniotic fluid; preferably, the biological samples are collected from the pregnant woman during the 13th to 25th gestational week; preferably, the related products include a kit or an electronic prediction device.

[0009] In order to achieve the above-mentioned object, according to a second aspect of the present invention, a kit for predicting intrahepatic cholestasis of pregnancy is provided, the kit comprising a detection reagent for a marker of intrahepatic cholestasis of pregnancy, a marker clinical indicator marker and / or a gene marker, wherein the clinical indicator marker comprises a conception mode indicator and any one or more of the following clinical detection indicators: total bile acid, γ-glutamyl transpeptidase, folic acid and aspartate transaminase, and the conception mode indicator is whether assisted reproduction is used; the gene marker comprises any one or more of the following: ABCA2, ALDH4A1, ANKRA2, BLVRB, ENTR1, EZR, FCHO2, HIST1H2AE, IQCE, LARS, MMP15, PXK, RNF141, SLC7A2, TGFBR2, TMEM135 and TMEM144.

[0010] Furthermore, the detection reagent is a detection reagent for detecting clinical detection indicators and / or gene marker expression levels; preferably, when the marker is a gene marker, the detection reagent is a detection reagent for detecting the mRNA or protein expression level of the gene marker; preferably, the detection reagent for detecting the mRNA expression level of the gene marker is a probe and / or primer, and further preferably, it is a related reagent for preparing the mRNA of the gene marker into a high-throughput sequencing library.

[0011] According to a third aspect of the present invention, an electronic device for predicting intrahepatic cholestasis of pregnancy is provided, the electronic device having a built-in risk prediction model for intrahepatic cholestasis of pregnancy in pregnant women, the risk prediction model being generated by training a computer using the expression levels of markers in biological samples from pregnant women who are positive for intrahepatic cholestasis of pregnancy, the markers being clinical indicator markers and / or gene markers, wherein the clinical indicator markers include a conception mode indicator and any one or more of the following clinical detection indicators: total bile acid, γ-glutamyl transpeptidase, folic acid and aspartate transaminase, the conception mode indicator being whether assisted reproduction is used; the gene markers include any one or more of the following: ABCA2, ALDH4A1, ANKRA2, BLVRB, ENTR1, EZR, FCHO2, HIST1H2AE, IQCE, LARS, MMP15, PXK, RNF141, SLC7A2, TGFBR2, TMEM135 and TMEM144.

[0012] In order to achieve the above-mentioned purpose, according to the fourth aspect of the present invention, a method for constructing a risk prediction model for predicting intrahepatic cholestasis of pregnancy is provided, and the construction method comprises: dividing a group of pregnant women with positive intrahepatic cholestasis of pregnancy and a group of healthy pregnant women into a training set and a validation set; obtaining the index values ​​of markers in biological samples from the group of pregnant women with positive intrahepatic cholestasis of pregnancy and the group of healthy pregnant women in the training set, and using a variety of risk prediction models for machine learning training, so as to select the optimal parameters of each risk prediction model; under the optimal parameters of each risk prediction model, using the index values ​​of the markers in the validation set to verify the prediction effect of the risk prediction model; selecting the risk prediction model with the best prediction effect as the validation set. A risk prediction model for predicting intrahepatic cholestasis of pregnancy; wherein the markers include clinical indicator markers and / or gene markers, the clinical indicator markers include conception method indicators and any one or more of the following clinical detection indicators: total bile acid, γ-glutamyl transpeptidase, folic acid and aspartate aminotransferase, the conception method indicator is whether assisted reproduction is used; the gene markers include any one or more of the following: ABCA2, ALDH4A1, ANKRA2, BLVRB, ENTR1, EZR, FCHO2, HIST1H2AE, IQCE, LARS, MMP15, PXK, RNF141, SLC7A2, TGFBR2, TMEM135 and TMEM144.

[0013] Furthermore, the multiple risk prediction models include one or more of the following: generalized linear model, gradient boosting machine, random forest and support vector machine; preferably, the biological sample is one or more of the following: plasma, serum, whole blood, urine, amniotic fluid; preferably, the biological sample is collected from the pregnant woman during the 13th to 25th gestational week.

[0014] In order to achieve the above-mentioned purpose, according to the fifth aspect of the present invention, a screening method for markers for predicting intrahepatic cholestasis of pregnancy is provided, the screening method comprising: collecting clinical indicator information of each sample from a group of pregnant women with positive intrahepatic cholestasis of pregnancy and a group of healthy pregnant women, the clinical indicator information comprising the following: age, BMI, pregnancy and delivery history, whether the conception method is assisted reproduction, pregnancy complications, liver function indicators and blood routine indicators; taking the clinical indicator information as the first candidate feature, and filling in the missing clinical indicator information; filtering the clinical indicator information whose correlation in the clinical preparation information is higher than the correlation threshold to obtain the second candidate feature; using the Lasso regression model to screen the second candidate feature, and performing cross-validation evaluation, and finally retaining the second candidate feature whose occurrence frequency is higher than the frequency threshold as the clinical indicator marker; and / or detecting the expression of The differences in the spectrum are detected, so as to preliminarily screen out candidate gene markers; at least two machine learning models are used to screen the candidate gene markers, and the gene markers that appear in all machine learning models with a frequency higher than the frequency threshold are retained as the final gene markers; the clinical indicator markers and / or gene markers are markers for predicting intrahepatic cholestasis of pregnancy, wherein the clinical indicator markers include conception mode indicators and any one or more of the following clinical detection indicators: total bile acid, γ-glutamyl transpeptidase, folic acid and aspartate transaminase, and the conception mode indicator is whether assisted reproduction is used; the gene markers include any one or more of the following: ABCA2, ALDH4A1, ANKRA2, BLVRB, ENTR1, EZR, FCHO2, HIST1H2AE, IQCE, LARS, MMP15, PXK, RNF141, SLC7A2, TGFBR2, TMEM135 and TMEM144.

[0015] According to a sixth aspect of the present invention, a computer-readable storage medium is provided, the storage medium comprising a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the above-mentioned method for constructing a risk prediction model for predicting intrahepatic cholestasis of pregnancy or the above-mentioned method for screening markers for predicting intrahepatic cholestasis of pregnancy.

[0016] According to a seventh aspect of the present invention, a processor is provided, and the processor is used to run a program, wherein when the program is run, the method for constructing the risk prediction model for predicting intrahepatic cholestasis of pregnancy or the method for screening markers for predicting intrahepatic cholestasis of pregnancy is executed.

[0017] By applying the technical solution of the present invention, 5 clinical indicator markers and 17 gene markers specifically associated with intrahepatic cholestasis of pregnancy were discovered. By using the markers of the present application as detection objects, a highly specific and sensitive risk prediction of intrahepatic cholestasis of pregnancy was achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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:

[0019] Figure 1A A schematic diagram showing the screening process of clinical markers in Example 1 of the present invention is shown;

[0020] Figure 1B A schematic diagram showing the screening process of gene markers in Example 1 of the present invention is shown;

[0021] Figure 2 A schematic diagram of the process of constructing and verifying a gene marker model in Example 1 of the present invention is shown;

[0022] Figure 3A The ranking result of the screening frequency of each feature in the clinical indicators in Example 1 of the present invention is shown;

[0023] Figure 3B The risk prediction effects of the five clinical index markers on ICP in Example 1 of the present invention are shown;

[0024] Figure 4A The ranking results of the screening frequencies of the characteristics of the candidate gene markers in Example 1 of the present invention are shown;

[0025] Figure 4B The risk prediction effect of 17 gene markers on ICP in Example 1 of the present invention is shown;

[0026] Figure 5 The results show the risk prediction effect of ICP using the combination of 5 clinical index markers and 17 gene markers in Example 1 of the present invention. DETAILED DESCRIPTION

[0027] 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.

[0028] It should be noted that the "diagnosis" described in this application refers to the diagnosis of the disease by certain means at the onset period; while "prediction" refers to the diagnosis of the disease when there is no typical phenotype. In this application, the indicator for clinical diagnosis of intrahepatic cholestasis is total bile acid TBA>10, but in the clinical sample population of this application, all people's TBA is <10, and intrahepatic cholestasis cannot be diagnosed. However, through the prediction scheme of the markers of this application, a part of the patients who are subsequently clinically diagnosed with intrahepatic cholestasis can be distinguished in advance, that is, the "prediction" in this application refers to detection at an earlier period of clinical onset (in this application, it means before the 25th week of pregnancy, preferably between 13-25 weeks of pregnancy, and the average is the 17th week of pregnancy).

[0029] As mentioned in the background technology section, there is currently a demand for clinical early risk prediction of intrahepatic cholestasis of pregnancy in pregnant women. This application uses maternal prenatal examination indicators in early and mid-pregnancy and maternal peripheral blood plasma to generate plasma free RNA expression profiles, compares the difference characteristics of plasma free RNA expression profiles in healthy and late pregnant women diagnosed with intrahepatic cholestasis in early and mid-pregnancy, screens out markers for predicting the risk of intrahepatic cholestasis of pregnancy, and uses machine learning algorithms (generalized linear model, gradient boosting machine, random forest and support vector machine) to construct a risk prediction model for intrahepatic cholestasis of pregnancy, which improves the sensitivity and specificity of intrahepatic cholestasis prediction in mid-pregnancy and achieves early intervention.

[0030] Based on the research results, the applicant proposed the technical solution of the present application. In a typical embodiment, a marker detection reagent is provided for use in the preparation of related products for predicting intrahepatic cholestasis of pregnancy, wherein the marker includes a clinical indicator marker and / or a gene marker, wherein the clinical indicator marker includes a conception mode indicator and any one or more of the following clinical detection indicators: total bile acid, γ-glutamyl transpeptidase, folic acid, and aspartate aminotransferase and conception mode, and the conception mode indicator is whether assisted reproduction is used; the gene marker includes any one or more of the following: ABCA2, ALDH4A1, ANKRA2, BLVRB, ENTR1, EZR, FCHO2, HIST1H2AE, IQCE, LARS, MMP15, PXK, RNF141, SLC7A2, TGFBR2, TMEM135 and TMEM144.

[0031] This application first discovered that the above-mentioned markers in biological samples of pregnant women have a significant correlation with intrahepatic cholestasis of pregnancy, and thus can be used as risk prediction markers for intrahepatic cholestasis of pregnancy. Using the markers of this application as risk prediction markers, risk prediction of intrahepatic cholestasis of pregnancy in the second trimester is achieved, and the prediction sensitivity and specificity are higher than the existing technology.

[0032] In the application of the present application, the detection reagent is a detection reagent for detecting the expression amount of the marker. When the marker is a gene marker, the detection reagent is a detection reagent for the mRNA or protein expression amount of the gene marker; more preferably, the detection reagent for detecting the mRNA expression amount of the gene marker is a probe and / or primer, and further preferably, it is a related reagent for preparing the mRNA of the gene marker into a high-throughput sequencing library.

[0033] Specifically, the detection reagents of clinical index markers can be detected using reagents or kits commonly used in the art. For example, folic acid can be detected using chemiluminescent microparticle immunoassay, the specific applicable kit is the folic acid determination kit (for example, product number: Guoxie Injection 20182402392), and the detection instrument is Abbott I2000; total bile acid can be detected using the enzyme cycling method, the applicable kit is the total bile acid determination kit (product number: Shanghai Xiezhuzhun 20172400590), and the detection instrument is Roche Cobas c702; γ-glutamyl transpeptidase can be detected using the enzyme colorimetric method, the applicable kit is the γ-glutamyl transpeptidase detection kit (product number: Su Xiezhuzhun 20202401213), and the detection instrument is Roche Cobas c702; aspartate aminotransferase can be detected using the enzyme colorimetric method, the applicable kit is the aspartate aminotransferase detection kit (product number: Guoxie Injection 20162404192), and the detection instrument is Roche Cobas c702. It should be noted that the detection steps of all the above clinical index markers are carried out in accordance with the instructions of the kit. In addition, it should be noted that whether the conception method in the above clinical indicators is assisted reproduction can be known through the basic information of the pregnant woman's prenatal examination.

[0034] Since RNA sequencing generally includes a reverse transcription step for producing cDNA molecules for sequencing, when RNA sequencing is used, the detection reagent of the present invention may also include a reagent for converting RNA in a biological sample into a cDNA fragment library.

[0035] The extracellular free RNA in the biological sample can be extracted using a commonly used method or kit in the art or a combination of the two. For example, the TRIzol LS standard RNA extraction procedure can be used to extract extracellular free RNA from a plasma biological sample.

[0036] In a specific embodiment, the extracellular free RNA is quantitatively analyzed, preferably including the use of whole transcriptome sequencing, and the next generation sequencing method is used to sequence the extracellular free RNA in the biological sample (preferably the plasma sample) of the pregnant woman. This method can simultaneously sequence the plasma free mRNA and the free lncRNA. The RT-PCR method can also be used for analysis. Other methods known in the art such as qPCR method can also be used to quantitatively analyze the expression spectrum of the extracellular free RNA.

[0037] Preferably, the quantitative analysis of extracellular free RNA also includes the step of quality control of the original extracellular free RNA sequencing data, preferably including cutting the linker, removing low-quality reads, removing reads <17bp in length, removing rRNA sequences and value RNA and Y RNA sequences, and first aligning the remaining reads to the human transcriptome (in order of miRNA, tRNA and piRNA, mRNA and lncRNA, and finally other RNA). Then the remaining reads are aligned to the human genome. The expression of long RNA (including mRNA and lncRNA) is corrected to TPM, and the formula is as follows:

[0038] TPM=(Ni / Li)*1000000 / (sum(N1 / L1+N2 / L2+N3 / L3+…+Nn / Ln)),

[0039] Among them, Ni is the number of reads mapped to the i-th gene; Li is the length of the i-th gene;

[0040] sum(N1 / L1+N2 / L2+...+Nn / Ln) is the sum of the values ​​of all (n) genes after being standardized by length.

[0041] In the application of the present application, a detection reagent is used to detect markers in a biological sample derived from a pregnant woman, wherein the biological sample derived from the pregnant woman is selected from one or more of the following: plasma, serum, whole blood, urine, and amniotic fluid; preferably, the biological sample is collected from the pregnant woman at the 13th to 25th gestational week. Preferably, plasma, serum or whole blood derived from a pregnant woman is used. The biological sample is most preferably plasma. For example, peripheral blood can be obtained from a pregnant woman and plasma separation can be performed to obtain a plasma biological sample to be used. In addition to plasma, serum or whole blood, other body fluid samples such as urine, amniotic fluid, etc. can also be used. The acquisition of biological samples can be implemented using conventional methods in the art.

[0042] In the present invention, the collection of biological samples can be performed during the 13th to 25th gestational week of the pregnant woman. By using the above-mentioned markers of the present application as risk prediction markers for intrahepatic cholestasis of pregnancy. Using the markers of the present application, the risk prediction of intrahepatic cholestasis of pregnancy can be achieved in the second trimester. The present invention can predict intrahepatic cholestasis of pregnancy before the onset of the disease. Therefore, the method of the present invention is applicable to a wider population and has greater clinical application value.

[0043] By using the clinical indicator markers and / or gene markers of the present invention as markers for predicting intrahepatic cholestasis of pregnancy in pregnant women, a prediction kit for the gene markers of the present invention can be prepared according to the preparation principles of existing kits. Detection probes, chips, etc. for predicting the risk of premature rupture of membranes and premature birth in pregnant women can also be prepared for these gene markers. Therefore, in some preferred application schemes of the present application, the related product can be a kit or an electronic prediction device.

[0044] In a second typical embodiment of the present application, a kit for predicting intrahepatic cholestasis of pregnancy is provided, the kit comprising a detection reagent for a marker of intrahepatic cholestasis of pregnancy, a marker clinical indicator marker and / or a gene marker, wherein the clinical indicator marker comprises a conception mode indicator and any one or more of the following clinical detection indicators: total bile acid, γ-glutamyl transpeptidase, folic acid, and aspartate aminotransferase and conception mode, the conception mode indicator is whether assisted reproduction is used; the gene marker comprises any one or more of the following: ABCA2, ALDH4A1, ANKRA2, BLVRB, ENTR1, EZR, FCHO2, HIST1H2AE, IQCE, LARS, MMP15, PXK, RNF141, SLC7A2, TGFBR2, TMEM135 and TMEM144.

[0045] The above-mentioned markers have a significant correlation with intrahepatic cholestasis of pregnancy, and thus can be used as risk prediction markers for intrahepatic cholestasis of pregnancy. Therefore, the kit including the markers of the present application can improve the specificity and sensitivity of risk prediction for intrahepatic cholestasis of pregnancy by using these markers as marker factors for risk prediction.

[0046] In some preferred embodiments, the detection reagent is a detection reagent for detecting the expression amount of a marker. When the marker is a gene marker, the detection reagent is a detection reagent for detecting the mRNA or protein expression amount of the above-mentioned gene marker; preferably, the detection reagent for detecting the mRNA expression amount of the gene marker is a probe and / or primer, and further preferably, it is a related reagent for preparing the mRNA of the gene marker into a high-throughput sequencing library.

[0047] Specifically, the detection reagents of clinical index markers can be detected using reagents commonly used in the field. For example, folic acid can be detected using chemiluminescent microparticle immunoassay, the specific applicable kit is the folic acid determination kit (for example, product number: Guoxie Injection 20182402392), and the detection instrument is Abbott I2000; total bile acid can be detected using the enzyme cycling method, the applicable kit is the total bile acid determination kit (product number: Shanghai Xiezhuzhun 20172400590), and the detection instrument is Roche Cobas c702; γ-glutamyl transpeptidase can be detected using the enzyme colorimetric method, the applicable kit is the γ-glutamyl transpeptidase detection kit (product number: Su Xiezhuzhun 20202401213), and the detection instrument is Roche Cobas c702; aspartate aminotransferase can be detected using the enzyme colorimetric method, the applicable kit is the aspartate aminotransferase detection kit (product number: Guoxie Injection 20162404192), and the detection instrument is Roche Cobas c702. It should be noted that the detection steps of all the above clinical index markers are carried out in accordance with the instructions of the kit. Among them, whether the conception method is assisted reproduction can be learned from the basic information of the pregnant woman's prenatal examination.

[0048] Since RNA sequencing generally includes a reverse transcription step for producing cDNA molecules for sequencing, when RNA sequencing is used, the detection reagent of the present invention may also include a reagent for converting RNA in a biological sample into a cDNA fragment library.

[0049] In a third typical embodiment of the present application, an electronic device for predicting intrahepatic cholestasis of pregnancy is also provided, the electronic device having a built-in risk prediction model for intrahepatic cholestasis of pregnancy in pregnant women, the risk prediction model being generated by training a computer using the expression levels of markers in biological samples from pregnant women who are positive for intrahepatic cholestasis of pregnancy, the markers being clinical indicator markers and / or gene markers, wherein the clinical indicator markers include a conception mode indicator and any one or more of the following clinical detection indicators: total bile acid, γ-glutamyl transpeptidase, folic acid, and aspartate transaminase and conception mode, the conception mode indicator being whether assisted reproduction is used; the gene markers include any one or more of the following: ABCA2, ALDH4A1, ANKRA2, BLVRB, ENTR1, EZR, FCHO2, HIST1H2AE, IQCE, LARS, MMP15, PXK, RNF141, SLC7A2, TGFBR2, TMEM135 and TMEM144.

[0050] In a fourth typical embodiment of the present application, a method for constructing a risk prediction model for predicting intrahepatic cholestasis of pregnancy is provided, the method comprising:

[0051] The pregnant women with positive intrahepatic cholestasis of pregnancy and the healthy pregnant women were divided into training set and validation set;

[0052] Obtain the index values ​​of the markers in the biological samples from pregnant women with positive intrahepatic cholestasis of pregnancy and healthy pregnant women in the training set, use multiple risk prediction models for machine learning training, and select the optimal parameters of each risk prediction model;

[0053] Under the optimal parameters of each risk prediction model, the indicator values ​​of the markers in the validation set were used to verify the prediction effect of the risk prediction model;

[0054] The risk prediction model with the best prediction effect was selected as the risk prediction model for intrahepatic cholestasis of pregnancy;

[0055] Among them, the markers include clinical indicator markers and / or gene markers. The clinical indicator markers include conception method indicators and any one or more of the following clinical detection indicators: total bile acid, γ-glutamyl transpeptidase, folic acid, and aspartate aminotransferase and conception method. The conception method indicator is whether assisted reproduction is used; the gene markers include any one or more of the following: ABCA2, ALDH4A1, ANKRA2, BLVRB, ENTR1, EZR, FCHO2, HIST1H2AE, IQCE, LARS, MMP15, PXK, RNF141, SLC7A2, TGFBR2, TMEM135 and TMEM144.

[0056] In a preferred embodiment, the multiple risk prediction models include one or more of the following: generalized linear model, gradient boosting machine, random forest and support vector machine.

[0057] Training the computer can be implemented by machine learning methods. Machine learning methods are selected from regression methods, classification methods, or combinations thereof. "Machine learning" generally refers to an algorithm that gives a computer learning ability without explicit programming, including an algorithm that learns from data and makes predictions about the data. The machine learning methods used in the present invention may include random forests, least absolute shrinkage and selection operator logistic regression, regularized logistic regression, XGBoost, decision tree learning, artificial neural networks, deep neural networks, support vector machines, rule-based machine learning, generalized linear models, gradient boosting machines, etc. Preferably, the machine learning method includes one or more of the following: generalized linear models, gradient boosting machines, random forests, support vector machines.

[0058] In the model construction method of the present invention, the training set and the validation set can be split according to a certain ratio as needed. Preferably, all pregnant women with positive intrahepatic cholestasis of pregnancy are randomly split into a training set and a validation set at a ratio of 7:3, and all healthy pregnant women are randomly split into a training set and a validation set at a ratio of 7:3. The screening of the best marker is completed in the training set, and the validation set is used to test the best marker and the prediction effect of the model.

[0059] In a preferred embodiment, candidate gene markers are preliminarily screened by comparing the differences in gene expression profiles between a pregnant woman group with positive intrahepatic cholestasis of pregnancy and a healthy pregnant woman group. Gene markers may include mRNA genes and lncRNA genes. This step can be implemented, for example, using the DESeq2 package (R software package). Finally, the top 1000 genes are selected as candidate molecular markers according to the order from small to large according to the p value, and further screened in the subsequent prediction model. The candidate molecular markers are first screened using the lasso model and random forest, and the high-frequency features that appear in both are used as the final gene markers.

[0060] In a preferred embodiment, in the training set, based on the best gene markers and / or best clinical index markers finally screened out, four machine learning methods are used: generalized linear model (GLM), gradient boosting machine (GBM), random forest (RF) and support vector machine (SVM)) to predict the risk of intrahepatic cholestasis of pregnancy. Preferably, each algorithm uses a 7-fold cross-validation method to select the optimal parameters for predictive model construction. The formed model can be verified in the validation set.

[0061] Preferably, the effect of the validation set can be verified, the model with the best effect can be selected and the feature importance can be calculated.

[0062] Preferably, gene markers and clinical indicator markers can be used alone as markers to evaluate the risk prediction effect, or can be used together as markers to verify the risk prediction effect, thereby constructing a risk prediction model.

[0063] In a preferred embodiment, the prediction model constructed by the method of the present invention can realize the risk prediction of intrahepatic cholestasis of pregnancy before the onset of the disease, so it is only necessary to combine clinical prenatal examination indicators and / or take peripheral blood of pregnant women to predict the risk of intrahepatic cholestasis of pregnancy by non-invasive methods. The AUC (area under the receiver operating characteristic curve) of the prediction of ICP using clinical indicator markers alone is 0.81 and 0.751 in the training set and validation set, respectively, with a sensitivity of 64% and a specificity of 79% in the validation set. The AUC of the prediction of ICP using gene markers alone is 0.94 and 0.74 in the training set and validation set, respectively, with a sensitivity of 55% and a specificity of 81%. When the two types of markers are used in combination, the AUC of the prediction of ICP is 0.97 and 0.84 in the training set and validation set, respectively, with a sensitivity of 73% and a specificity of 84% in the validation set, which are significantly higher than the existing technology level.

[0064] It should be noted that in the risk prediction model, the risk score automatically calculated by the model can be used to evaluate and predict the risk of intrahepatic cholestasis of pregnancy. The optimal threshold is determined based on the ROC curve and Youden coefficient.

[0065] In a preferred embodiment, the biological sample is one or more of the following: plasma, serum, whole blood, urine, amniotic fluid; preferably, the biological sample is collected from the pregnant woman at the 13th to 25th gestational week. The biological sample is most preferably plasma. For example, peripheral blood can be obtained from a pregnant woman and plasma can be separated to obtain a plasma biological sample to be used. In addition to plasma, serum or whole blood, other body fluid samples such as urine, amniotic fluid, etc. can also be used. The acquisition of biological samples can be implemented by conventional methods in the art.

[0066] In the present invention, the collection of biological samples can be performed during the 13th to 25th gestational week of the pregnant woman. By using the above-mentioned markers of the present application as risk prediction markers for intrahepatic cholestasis of pregnancy. Using the markers of the present application, the risk prediction of intrahepatic cholestasis of pregnancy can be achieved in the second trimester. The present invention can predict intrahepatic cholestasis of pregnancy before the onset of the disease. Therefore, the method of the present invention is applicable to a wider population and has greater clinical application value.

[0067] In a fifth typical embodiment of the present application, a method for screening markers for predicting intrahepatic cholestasis of pregnancy is provided, the screening method comprising:

[0068] Clinical index information of each sample from pregnant women with positive intrahepatic cholestasis of pregnancy and healthy pregnant women was collected. The clinical index information included the following: age, BMI, pregnancy and delivery history, pregnancy complications, liver function indexes and blood routine indexes;

[0069] Clinical indicator information is used as the first candidate feature to fill in the missing clinical indicator information;

[0070] Filtering the clinical indicator information whose correlation in the clinical preparation information is higher than the correlation threshold to obtain the second candidate feature;

[0071] The second candidate features are screened using the Lasso regression model, and cross-validated and evaluated, and the second candidate features with a frequency higher than the frequency threshold are finally retained as clinical indicator markers; and / or

[0072] Detect differences in expression profiles in biological samples from pregnant women with positive intrahepatic cholestasis of pregnancy and healthy pregnant women, thereby preliminarily screening candidate gene markers;

[0073] At least two machine learning models are used to screen candidate gene markers, and gene markers that appear in all machine learning models at a frequency higher than a frequency threshold are retained as final gene markers;

[0074] Clinical indicator markers and / or gene markers are markers for predicting intrahepatic cholestasis of pregnancy, wherein the clinical indicator markers include a conception method indicator and any one or more of the following clinical detection indicators: total bile acid, γ-glutamyl transpeptidase, folic acid, aspartate aminotransferase and conception method, and the conception method indicator is whether assisted reproduction is used; the gene markers include any one or more of the following: ABCA2, ALDH4A1, ANKRA2, BLVRB, ENTR1, EZR, FCHO2, HIST1H2AE, IQCE, LARS, MMP15, PXK, RNF141, SLC7A2, TGFBR2, TMEM135 and TMEM144.

[0075] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the present invention.

[0076] It can be known from the description of the above implementation mode that a person skilled in the art can clearly understand that the present application can be implemented by means of software plus necessary hardware devices such as detection instruments. Based on such an understanding, the data processing part of the technical solution of the present application can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment of the present application or some parts of the embodiments.

[0077] The present application can be used in many general or special computing system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0078] Obviously, those skilled in the art should understand that some modules or steps of the present application described above can be implemented in a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented with program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0079] In a preferred embodiment, a computer-readable storage medium is provided, the storage medium including a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the above-mentioned method for constructing a risk prediction model for predicting intrahepatic cholestasis of pregnancy or the above-mentioned method for screening markers for predicting intrahepatic cholestasis of pregnancy.

[0080] In a preferred embodiment, a processor is provided, which is used to run a program, wherein when the program is run, the method for constructing the risk prediction model for predicting intrahepatic cholestasis of pregnancy or the method for screening markers for predicting intrahepatic cholestasis of pregnancy is executed.

[0081] The beneficial effects of the present application will be further illustrated below with reference to specific embodiments.

[0082] Example 1

[0083] (1) Sample enrollment

[0084] Singleton pregnant women were collected from hospitals. After removing pregnant women with insufficient clinical information, a total of 203 pregnant women were enrolled, of which 149 were enrolled in 2017 and 2018. They were used as training sets, including 43 pregnant women who subsequently developed intrahepatic cholestasis of pregnancy (ICP) and 106 healthy pregnant women. The validation set included 54 pregnant women enrolled in 2016, of whom 11 subsequently developed ICP and 43 were healthy.

[0085] (2) Clinical information collection and processing

[0086] Clinical information of the samples was collected from all pregnant women, including basic information (age, BMI, etc.), pregnancy history and pregnancy complications, liver function indicators and blood routine. Detailed clinical information is shown in Table 1.

[0087] Table 1:

[0088]

[0089]

[0090] (3) Obtaining maternal plasma

[0091] Peripheral blood samples from 203 singleton pregnant women were obtained from the hospital, with an average gestational age of 17 weeks. All blood samples were immediately stored at 4°C and plasma separated within 8 hours. Plasma separation was performed using a two-step centrifugation method, at 1,600 g for 10 minutes at 4°C and then at 12,000 g for 10 minutes. After plasma separation, it was immediately stored at -80°C awaiting further processing.

[0092] (4) cfRNA extraction and sequencing

[0093] Trizol LS was added to the plasma and immediately vortexed to mix. The subsequent cfRNA extraction step can be performed using methods familiar in the art. cfRNA sequencing was performed using whole transcriptome sequencing and next-generation sequencing of plasma samples from ICP and healthy pregnant women.

[0094] (5) Quantification of cfRNA expression profile

[0095] The original cfRNA sequencing data was quality controlled, including cutting the adapter, removing low-quality reads, removing reads <17bp in length, removing rRNA sequences, value RNA, and Y RNA sequences. The remaining reads were first aligned to the human transcriptome (in order of miRNA, tRNA, and piRNA, mRNA, and lncRNA, and finally other RNAs), and then the remaining reads were aligned to the human genome. The expression of long RNA (including mRNA and lncRNA) was corrected to TPM, and the formula is as follows.

[0096] TPM=(Ni / Li)*1000000 / (sum(N1 / L1+N2 / L2+N3 / L3+…+Nn / Ln))

[0097] Ni is the number of reads aligned to the i-th gene; Li is the length of the i-th gene; sum(N1 / L1+N2 / L2+...+Nn / Ln) is the sum of the values ​​of all (n) genes after being standardized by length.

[0098] (6) Molecular marker screening

[0099] All molecular marker screening was completed in the training set, and the validation set was used to test the predictive effect of the molecular markers and models.

[0100] (6.1) Clinical information as features

[0101] The clinical information used as candidate features is shown in Table 1 (“Yes” in the last column). Figure 1A As shown in the figure, because some samples lack some clinical information, the bagImpute function (caret package of R) is used to fill in, and then the highly correlated variables are excluded (here, the correlation between features is high, and the high correlation variables are removed in order to provide more information with fewer features. The threshold of high correlation here is the Pearson correlation coefficient>0.6), and then the lasso algorithm is used to screen the features. Cross-validation is used for evaluation, and all candidate features that appear frequently are used as the final clinical information features.

[0102] (6.2) Plasma free RNA as a feature

[0103] First, candidate molecular markers were preliminarily screened by comparing the expression profiles of the ICP group and the healthy group. Figure 1BAs shown in Figure 2, differential analysis was performed for each mRNA gene in the two groups, and this step was implemented using the DESeq2 package (R software package). Finally, the top 1000 genes were selected as candidate molecular markers according to the order of p-value from small to large, and further screened in the subsequent prediction model. The candidate molecular markers were first screened using the lasso model and random forest, and the high-frequency features (here the frequency threshold is 7 times or more) that appeared in both were used as the final gene markers, and the information is shown in Table 2.

[0104] Table 2:

[0105]

[0106]

[0107] (7) Construction and validation of marker-based models

[0108] like Figure 2 As shown in the figure, in the training set, based on the final screened features (mRNA molecules, clinical information), four machine learning algorithms (generalized linear model --- GLM, generalized linear model; gradient boosting machine --- GBM, Gradient Boosting Machine; random forest --- RF, Random Forest and support vector machine --- SVM, support vector machine) are used to assess the risk of premature birth. Each algorithm uses a 7-fold cross-validation method to select the optimal parameters for predictive model construction. The final model will be verified in the validation set, and the best model will be selected as the final model and the feature importance will be calculated. At the same time, mRNA molecular markers will be tested and verified together with clinical indicators to build a model together.

[0109] (8) Evaluation of the predictive effect of molecular markers on ICP risk

[0110] (8.1) Predictive effect of clinical information on ICP risk

[0111] After feature selection of clinical indicators, 5 clinical indicator markers were generated, such as Figure 3A The prediction AUC of ICP in the training set and validation set were 0.81 and 0.751, respectively, with a sensitivity of 64% and a specificity of 79% in the validation set, as shown in Table 4 and Figure 3B shown.

[0112] (8.2) Predictive effect of molecular markers on ICP risk

[0113] After feature selection of mRNA, 17 clinical indicators were generated, such as Figure 4A As shown. Using a single mRNA as a feature for training and prediction, it was found that PXK, RNF141 and FCHO2 had the highest AUC in the seven-fold cross-validation of the training set, as shown in Table 3. At the same time, ABCA2 and SLC7A2 are functionally related to the liver. Therefore, these five genes were gradually accumulated for training and prediction. The results are shown in Tables 4 and Figure 4B The combined prediction effect of PXK, RNF141, FCHO2, ABCA2 and SLC7A2 on ICP was better than that of the combined 17 genes. The AUC of the five-gene combination in the training set and validation set was 0.86 and 0.80, respectively, with a sensitivity of 64% and a specificity of 84% in the validation set, as shown in Table 4 and Figure 4B shown.

[0114] (8.3) Predictive effect of combined markers on ICP risk

[0115] After combining clinical indicators and mRNA characteristics, the prediction effect of ICP is as follows Figure 5 As shown in Table 4, the prediction effect of 5 genes combined with clinical information is similar to that of 17 genes combined with clinical information. The prediction AUC of 5 genes combined with clinical information is 0.89 and 0.87 in the training set and validation set, respectively, with a sensitivity of 73% and a specificity of 86% in the validation set. The prediction AUC of 17 genes combined with clinical information is 0.97 and 0.84 in the training set and validation set, respectively, with a sensitivity of 73% and a specificity of 84% in the validation set. Figure 5 And as shown in Table 4.

[0116] Table 3:

[0117] feature 7-fold cross validation AUC PX 0.745479025 RNF141 0.727919501 FCHO2 0.716914683 IQCE 0.700325964 SLC7A2 0.696605726 BLVRB 0.695521542 ENTR1 0.692410714 MMP15 0.689965986 TMEM135 0.682794785 TGFBR2 0.67154195 TMEM144 0.663378685 ANKRA2 0.649964569 EZR 0.635962302 HIST1H2AE 0.632312925 LARS 0.630626417 ALDH4A1 0.626388889 ABCA2 0.623511905 .

[0118] Table 4:

[0119]

[0120] In the above table, RNA groupX refers to RNA group X. For example, RNAgroup17 refers to RNA group 17, which refers to the combination of 17 mRNAs, and so on. RNAclin17 is a combination of 17 mRNAs and all clinical indicator markers.

[0121] From the above results, it can be seen that the above embodiments of the present invention achieve the following technical effects: Since plasma free RNA comes from various tissues throughout the body, it provides a means to monitor the health status of tissues, including reproductive tissues, such as the placenta. Based on plasma free RNA and clinical prenatal examination indicators during pregnancy, combined with machine learning algorithms, molecular markers for predicting the risk of intrahepatic cholestasis during pregnancy can be screened, and the prediction of intrahepatic cholestasis during pregnancy in the second trimester can be achieved by constructing a model.

[0122] The present invention only needs to take the peripheral blood of pregnant women to use a non-invasive method to predict the risk of intrahepatic cholestasis with high accuracy and early stage, and the prediction sensitivity in the second trimester is above 0.7 and the specificity is above 0.8, both of which are higher than the existing technical level. The method of the present invention can be applied to prediction in the second trimester, which is helpful to achieve early intervention.

[0123] 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. Use of a marker in the preparation of a product for predicting intrahepatic cholestasis of pregnancy, characterized in that: The marker is selected from any one of the following groups 1) to 11): 1) Gene marker: ABCA2; 2) Gene markers: ABCA2+SLC7A2; 3) Gene markers: ABCA2+SLC7A2+PXK; 4) Gene markers: ABCA2+SLC7A2+PXK+RNF141; 5) Gene markers: ABCA2+SLC7A2+PXK+RNF141+FCHO2; 6) Genetic markers: ABCA2+ALDH4A1+ANKRA2+BLVRB+ENTR1+EZR+FCHO2+HIST1H2AE+IQCE+LARS+MMP15+PXK+RNF141+SLC7A2+TGFBR2+TMEM135+TMEM144; 7) Genetic markers: ABCA2+SLC7A2; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 8) Genetic markers: ABCA2+SLC7A2+PXK; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 9) Genetic markers: ABCA2+SLC7A2+PXK+RNF141; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 10) Genetic markers: ABCA2+SLC7A2+PXK+RNF141+FCHO2; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 11) Genetic markers: ABCA2+ALDH4A1+ANKRA2+BLVRB+ENTR1+EZR+FCHO2+HIST1H2AE+IQCE+LARS+MMP15+PXK+RNF141+SLC7A2+TGFBR2+TMEM135+TMEM144; and Clinical indicator markers: folic acid + whether assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate aminotransferase.

2. The use according to claim 1, characterized in that: The application includes using a detection reagent to detect the clinical detection index and the expression amount of the gene marker.

3. The use according to claim 2, characterized in that: When the marker is the gene marker, the detection reagent is a detection reagent for detecting the mRNA expression level or protein expression level of the gene marker.

4. The use according to claim 3, characterized in that: The detection reagent for detecting the mRNA expression amount of the gene marker is a probe and / or a primer.

5. The use according to claim 3, characterized in that: The detection reagent is a reagent related to preparing the mRNA of the gene marker into a high-throughput sequencing library.

6. The use according to any one of claims 1 to 5, characterized in that In combination with whether assisted reproduction is used, the clinical detection indicators and / or the gene markers in the biological samples from the pregnant woman are detected, wherein the biological samples are selected from one or more of the following: plasma, serum, whole blood, urine, and amniotic fluid.

7. The use according to claim 6, characterized in that: The biological sample is collected from the pregnant woman during the 13th to 25th gestational week.

8. The use according to claim 6, characterized in that: The related products include kits or electronic prediction devices.

9. A kit for predicting intrahepatic cholestasis of pregnancy, characterized in that: The kit comprises a detection reagent for a marker of intrahepatic cholestasis of pregnancy, The marker is selected from any one of the following groups 1) to 11): 1) Gene marker: ABCA2; 2) Gene markers: ABCA2+SLC7A2; 3) Gene markers: ABCA2+SLC7A2+PXK; 4) Gene markers: ABCA2+SLC7A2+PXK+RNF141; 5) Gene markers: ABCA2+SLC7A2+PXK+RNF141+FCHO2; 6) Genetic markers: ABCA2+ALDH4A1+ANKRA2+BLVRB+ENTR1+EZR+FCHO2+HIST1H2AE+IQCE+LARS+MMP15+PXK+RNF141+SLC7A2+TGFBR2+TMEM135+TMEM144; 7) Genetic markers: ABCA2+SLC7A2; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 8) Genetic markers: ABCA2+SLC7A2+PXK; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 9) Genetic markers: ABCA2+SLC7A2+PXK+RNF141; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 10) Genetic markers: ABCA2+SLC7A2+PXK+RNF141+FCHO2; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 11) Genetic markers: ABCA2+ALDH4A1+ANKRA2+BLVRB+ENTR1+EZR+FCHO2+HIST1H2AE+IQCE+LARS+MMP15+PXK+RNF141+SLC7A2+TGFBR2+TMEM135+TMEM144; and Clinical indicator markers: folic acid + whether assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate aminotransferase.

10. The kit according to claim 9, characterized in that The detection reagent is a detection reagent for detecting the clinical detection index and the expression amount of the gene marker.

11. The kit according to claim 10, characterized in that When the marker is the gene marker, the detection reagent is a detection reagent for detecting the mRNA expression level or protein expression level of the gene marker.

12. The kit according to claim 11, characterized in that The detection reagent for detecting the mRNA expression amount of the gene marker is a probe and / or a primer.

13. The kit according to claim 12, characterized in that The detection reagent is a reagent related to preparing the mRNA of the gene marker into a high-throughput sequencing library.

14. An electronic device for predicting intrahepatic cholestasis of pregnancy, characterized in that: The electronic device has a built-in risk prediction model for intrahepatic cholestasis of pregnancy, and the risk prediction model is generated by training a computer using the expression levels of markers in biological samples from pregnant women who are positive for intrahepatic cholestasis of pregnancy. The marker is selected from any one of the following groups 1) to 11): 1) Gene marker: ABCA2; 2) Gene markers: ABCA2+SLC7A2; 3) Gene markers: ABCA2+SLC7A2+PXK; 4) Gene markers: ABCA2+SLC7A2+PXK+RNF141; 5) Gene markers: ABCA2+SLC7A2+PXK+RNF141+FCHO2; 6) Genetic markers: ABCA2+ALDH4A1+ANKRA2+BLVRB+ENTR1+EZR+FCHO2+HIST1H2AE+IQCE+LARS+MMP15+PXK+RNF141+SLC7A2+TGFBR2+TMEM135+TMEM144; 7) Genetic markers: ABCA2+SLC7A2; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 8) Genetic markers: ABCA2+SLC7A2+PXK; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 9) Genetic markers: ABCA2+SLC7A2+PXK+RNF141; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 10) Genetic markers: ABCA2+SLC7A2+PXK+RNF141+FCHO2; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 11) Genetic markers: ABCA2+ALDH4A1+ANKRA2+BLVRB+ENTR1+EZR+FCHO2+HIST1H2AE+IQCE+LARS+MMP15+PXK+RNF141+SLC7A2+TGFBR2+TMEM135+TMEM144; and Clinical indicator markers: folic acid + whether assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate aminotransferase.

15. A method for constructing a risk prediction model for predicting intrahepatic cholestasis of pregnancy, characterized in that: The construction method comprises: The pregnant women with positive intrahepatic cholestasis of pregnancy and the healthy pregnant women were divided into training set and validation set; Obtaining the index values ​​of the markers in the biological samples from the group of pregnant women with positive intrahepatic cholestasis of pregnancy and the group of healthy pregnant women in the training set, and performing machine learning training using a variety of risk prediction models, thereby selecting the optimal parameters of each of the risk prediction models; Under the optimal parameters of each of the risk prediction models, using the index values ​​of the markers in the validation set to verify the prediction effect of the risk prediction model; selecting the risk prediction model with the best prediction effect as the risk prediction model for predicting intrahepatic cholestasis of pregnancy; Wherein, the marker is selected from any one of the following groups 1) to 11): 1) Gene marker: ABCA2; 2) Gene markers: ABCA2+SLC7A2; 3) Gene markers: ABCA2+SLC7A2+PXK; 4) Gene markers: ABCA2+SLC7A2+PXK+RNF141; 5) Gene markers: ABCA2+SLC7A2+PXK+RNF141+FCHO2; 6) Genetic markers: ABCA2+ALDH4A1+ANKRA2+BLVRB+ENTR1+EZR+FCHO2+HIST1H2AE+IQCE+LARS+MMP15+PXK+RNF141+SLC7A2+TGFBR2+TMEM135+TMEM144; 7) Genetic markers: ABCA2+SLC7A2; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 8) Genetic markers: ABCA2+SLC7A2+PXK; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 9) Genetic markers: ABCA2+SLC7A2+PXK+RNF141; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 10) Genetic markers: ABCA2+SLC7A2+PXK+RNF141+FCHO2; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 11) Genetic markers: ABCA2+ALDH4A1+ANKRA2+BLVRB+ENTR1+EZR+FCHO2+HIST1H2AE+IQCE+LARS+MMP15+PXK+RNF141+SLC7A2+TGFBR2+TMEM135+TMEM144; and Clinical indicator markers: folic acid + whether assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate aminotransferase.

16. The construction method according to claim 15, characterized in that: The various risk prediction models include one or more of the following: generalized linear model, gradient boosting machine, random forest and support vector machine.

17. The construction method according to claim 15, characterized in that: The biological sample is one or more of the following: plasma, serum, whole blood, urine, and amniotic fluid.

18. The construction method according to claim 15, characterized in that: The biological samples are collected from pregnant women during the 13th to 25th gestational week.

19. A method for screening markers for predicting intrahepatic cholestasis of pregnancy, characterized in that: The screening method comprises: The clinical index information of each sample in the pregnant women group with positive intrahepatic cholestasis of pregnancy and the healthy pregnant women group was collected, and the clinical index information included the following: age, BMI, pregnancy and delivery history, whether the conception method was assisted reproduction, pregnancy complications, liver function indexes and blood routine indexes; Using the clinical indicator information as the first candidate feature to fill in the missing clinical indicator information; Filtering the clinical indicator information whose correlation is higher than the correlation threshold in the clinical preparation information to obtain a second candidate feature; Using the Lasso regression model to screen the second candidate features, and performing cross-validation evaluation, and finally retaining the second candidate features with an occurrence frequency higher than a frequency threshold as clinical indicator markers; and / or Detecting differences in expression profiles in biological samples from the group of pregnant women with positive intrahepatic cholestasis of pregnancy and the group of healthy pregnant women, thereby preliminarily screening candidate gene markers; Using at least two machine learning models to screen the candidate gene markers, and retaining the gene markers that appear in all the machine learning models at a frequency higher than a frequency threshold as the final gene markers; 1) the clinical index marker and the gene marker, or 2) the gene marker is the marker for predicting intrahepatic cholestasis of pregnancy, The marker is selected from any one of the following groups 1) to 11): 1) Gene marker: ABCA2; 2) Gene markers: ABCA2+SLC7A2; 3) Gene markers: ABCA2+SLC7A2+PXK; 4) Gene markers: ABCA2+SLC7A2+PXK+RNF141; 5) Gene markers: ABCA2+SLC7A2+PXK+RNF141+FCHO2; 6) Genetic markers: ABCA2+ALDH4A1+ANKRA2+BLVRB+ENTR1+EZR+FCHO2+HIST1H2AE+IQCE+LARS+MMP15+PXK+RNF141+SLC7A2+TGFBR2+TMEM135+TMEM144; 7) Genetic markers: ABCA2+SLC7A2; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 8) Genetic markers: ABCA2+SLC7A2+PXK; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 9) Genetic markers: ABCA2+SLC7A2+PXK+RNF141; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 10) Genetic markers: ABCA2+SLC7A2+PXK+RNF141+FCHO2; and Clinical indicator markers: folic acid + assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate transaminase; 11) Genetic markers: ABCA2+ALDH4A1+ANKRA2+BLVRB+ENTR1+EZR+FCHO2+HIST1H2AE+IQCE+LARS+MMP15+PXK+RNF141+SLC7A2+TGFBR2+TMEM135+TMEM144; and Clinical indicator markers: folic acid + whether assisted reproduction + γ-glutamyl transpeptidase + total bile acid + aspartate aminotransferase.

20. A computer-readable storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the method for constructing a risk prediction model for predicting intrahepatic cholestasis of pregnancy described in any one of claims 15 to 18 or the method for screening markers for predicting intrahepatic cholestasis of pregnancy described in claim 19.

21. A processor, characterized in that: The processor is used to run a program, wherein when the program is run, the method for constructing a risk prediction model for predicting intrahepatic cholestasis of pregnancy described in any one of claims 15 to 18 or the method for screening markers for predicting intrahepatic cholestasis of pregnancy described in claim 19 is executed.

Images