MiRNA marker related to endometrial receptivity and application of miRNA marker

Abstract

The invention discloses a miRNA (micro Ribonucleic Acid) marker related to endometrial receptivity and an application of the miRNA marker. The miRNA marker comprises the following components: hsa-miR-199b-5p, hsa-miR-33a-3p, hsa-miR-4659a-3p, hsa-miR-7702, hsa-miR-545-5p, hsa-miR-133a-5p, hsa-miR-150-5p, and the like, and is characterized in that the miRNA marker comprises the following components: a miR-199b-5p, a miR-33a-3p, a miR-4659a-3p, a miR-7702, a miR-545- According to the method, the optimal feature combination is obtained by performing correlation analysis and screening on the plasma miRNA of the endometrium of a patient with successful embryo implantation in different receptivity periods, the prediction model is established by utilizing a machine learning method, the probability of the endometrial receptivity of the sample in different periods can be accurately predicted on the basis of maternal serum, and the prediction accuracy is improved. The problems that in the prior art, when whether the embryo can be successfully implanted or not is predicted, the sample extraction process is complex, invasive and invasive are solved.

Description

Technical Field

[0001] The invention belongs to the technical field of biomedicine and relates to a miRNA marker related to endometrial receptivity and an application thereof. Background Art

[0002] In vitro fertilization-embryo transfer (IVF-ET) has become an effective way for infertile women to achieve pregnancy as soon as possible. Although the development and technological innovation of assisted reproductive technology have enabled most infertile patients to obtain high-quality embryos and then become pregnant through in vitro embryo culture technology, some high-quality embryos are still lost in the early or even very early stages of pregnancy. Studies have shown that there is a certain correlation between embryo factors and endometrial receptivity factors and successful embryo implantation.

[0003] Endometrial receptivity refers to the state of molecular and cellular transformation of the endometrium to promote embryo attachment, growth and invasion. The window of implantation (WOI) is a short and specific time window in the endometrial cycle. At this time, the endometrium is receptive and can accept the attachment, growth and invasion of the blastocyst. It usually occurs between the 19th and 24th days of the menstrual cycle, which is the 7th day after the peak of luteinizing hormone (LH) in the natural cycle (LH+7) or the 5th day after progesterone administration in the artificial cycle (P+5). However, not all women have the same WOI. Some women have WOI displacement, including early or delayed, and some women have shortened WOI, which makes the dialogue between the embryo and the endometrium out of sync, leading to implantation failure. Therefore, accurate assessment of the endometrial receptivity and implantation window is of great significance for the successful implantation of the embryo.

[0004] With the development of high-throughput sequencing technology, more and more studies are beginning to shift from traditional histological methods to omics-based methods to evaluate endometrial receptivity. For example, CN114164264A discloses a method for evaluating endometrial receptivity of a patient and a kit for implementing the method, by using RNA sequencing results from endometrial living tissue and the expression levels of genes related to endometrial receptivity to determine the functional state of human endometrial receptivity. CN112469836A discloses a method for determining endometrial state using a sample from a woman, such as an endometrial specimen, the method comprising: (a) performing analysis on an endometrial sample from a woman to determine the microRNA (miRNA) expression profile of the endometrial sample, wherein the miRNA expression profile includes multiple miRNAs, such as the expression levels of 167 miRNAs having sequences of SEQ ID NO: 1 to SEQ ID NO: 167, respectively; and (b) analyzing the miRNA expression profile using, for example, a computer algorithm to obtain a receptivity prediction score. All of the above methods use endometrial curettage to assess the endometrial receptivity, but this method is invasive and can cause changes in the endometrial environment during the biopsy of endometrial tissue, so it has limitations in clinical use.

[0005] In summary, the development of markers related to endometrial receptivity can non-invasively and accurately predict endometrial receptivity, which is of great significance in the field of embryo transplantation. Summary of the invention

[0006] In view of the deficiencies of the prior art and actual needs, the present invention provides a miRNA marker related to endometrial receptivity and its application, screens maternal plasma miRNA markers, and constructs a detection model to achieve the assessment of endometrial receptivity based on maternal serum miRNA, which is of great significance in the field of embryo transplantation.

[0007] To achieve the above object, the present invention adopts the following technical solutions:

[0008] In a first aspect, the present invention provides a miRNA marker associated with endometrial receptivity, wherein the miRNA marker comprises: hsa-miR-199b-5p, hsa-miR-33a-3p, hsa-miR-4659a-3p, hsa-miR-7702, hsa-miR-545-5p, hsa-miR-133a-5p, hsa-miR-150-5p, hsa-miR-152-5p, hsa-miR-6815-3p, hsa-miR-4477b, hsa-miR-26b-5 p, hsa-miR-126-5p, hsa-miR-1270, hsa-miR-544b, hsa-miR-6837-3p, hsa-miR-6799-3p, hsa-miR-6764-5p, hsa-miR-548bb- 3p, hsa-miR-183-3p, hsa-miR-5699-3p, hsa-miR-548ak, hsa-miR-5684, hsa-miR-340-5p, hsa-miR-6850-5p and hsa-let-7a-3p.

[0009] The present invention develops a miRNA marker combination based on maternal plasma, which can effectively characterize endometrial receptivity and effectively solves the problem that the sample extraction process is complicated, invasive and invasive when predicting endometrial receptivity in the prior art.

[0010] In the present invention, the nucleic acid sequence of the miRNA marker is shown in Table 1.

[0011] Table 1

[0012] miRNA marker Nucleic acid sequence Number hsa-miR-199b-5p CCCAGUGUUUAGACUAUCUGUUC SEQ ID NO.1 hsa-miR-33a-3p CAAUGUUUCCACAGUGCAUCAC SEQ ID NO.2 hsa-miR-4659a-3p UUUCUUCUUAGACAUGGCAACG SEQ ID NO.3 hsa-miR-7702 CUUAGACUGCCAGACUCCCUGA SEQ ID NO.4 hsa-miR-545-5p UCAGUAAAUGUUUAUUAGAUGA SEQ ID NO.5 hsa-miR-133a-5p AGCUGGUAAAAUGGAACCAAAU SEQ ID NO.6 hsa-miR-150-5p UCUCCCAACCCUUGUACCAGUG SEQ ID NO.7 hsa-miR-152-5p AGGUUCUGUGAUACACUCCGACU SEQ ID NO.8 hsa-miR-6815-3p UGGCUUCUCUUGCACACCCAG SEQ ID NO.9 hsa-miR-4477b AUUAAGGACAUUUGUGAUUGAU SEQ ID NO.10 hsa-miR-26b-5p UUCAAGUAAUUCAGGAUAGGU SEQ ID NO.11 hsa-miR-126-5p CAUUAUUACUUUUGGUACGCG SEQ ID NO.12 hsa-miR-1270 CUGGAGAUAUGGAAGAGCUGUGU SEQ ID NO.13 hsa-miR-544b ACCUGAGGUUGUGCAUUUCUAA SEQ ID NO.14 hsa-miR-6837-3p CCUUCACUGUGACUCUGCUGCAG SEQ ID NO.15 hsa-miR-6799-3p UGCCCUGCAUGGUGUCCCCACAG SEQ ID NO.16 hsa-miR-6764-5p UCCCAGGGUCUGGUCAGAGUUG SEQ ID NO.17 hsa-miR-548bb-3p CAAAAACCAUAGUUACUUUUGC SEQ ID NO.18 hsa-miR-183-3p GUGAAUUACCGAAGGGCCAUAA SEQ ID NO.19 hsa-miR-5699-3p UCCUGUCUUUCCUUGUUGGAGC SEQ ID NO.20 hsa-miR-548ak AAAAGUAACUGCGGUUUUUGA SEQ ID NO.21 hsa-miR-5684 AACUCUAGCCUGAGCAACAG SEQ ID NO.22 hsa-miR-340-5p UUAUAAAGCAAUGAGACUGAUU SEQ ID NO.23 hsa-miR-6850-5p GUGCGGAACGCUGGCCGGGGCG SEQ ID NO.24 hsa-let-7a-3p CUAUACAAUCUACUGUCUUUC SEQ ID NO.25

[0013] In a second aspect, the present invention provides use of the miRNA markers associated with endometrial receptivity and / or detection reagents thereof described in the first aspect in the preparation of endometrial receptivity detection products.

[0014] In a third aspect, the present invention provides a kit for detecting endometrial receptivity, the kit comprising a reagent for detecting the expression level of the miRNA marker associated with endometrial receptivity described in the first aspect.

[0015] In a fourth aspect, the present invention provides use of the miRNA marker associated with endometrial receptivity described in the first aspect in detecting endometrial receptivity for purposes other than disease diagnosis.

[0016] In a fifth aspect, the present invention provides a method for constructing a model for detecting endometrial receptivity, the method comprising:

[0017] (1) sampling on the 2nd, 5th, 7th and 9th day after the peak of luteinizing hormone (LH) in women, respectively, recorded as D0, D3, D5 and D7, and determining the expression level of the miRNA marker related to endometrial receptivity described in claim 1 in the samples;

[0018] (2) Subtract the expression levels of D3 and D0, D5 and D3, and D7 and D5 of each miRNA to obtain the characteristic expression value x;

[0019] (3) The feature expression is normalized and standardized using equations (1) and (2), wherein x' is the feature expression after normalization and standardization, μ is the mean of the feature expression, σ is the variance, and x max is the maximum value of feature expression, x min The minimum feature expression was obtained, and a model for detecting endometrial receptivity was constructed using machine learning methods.

[0020]

[0021]

[0022] In the present invention, the methods commonly used in the art for detecting miRNA expression are applicable to the present invention. For example, in a specific embodiment of the present invention, the miRNA expression can be detected by sequencing technology, which may include the following steps:

[0023] 1) Filter the raw data of plasma miRNA sequencing: remove 3' end adapters, sequences without adapter insertion, sequences containing polyA and polyT, sequences with only AT or CG, sequences with a single base (A / T / C / G) accounting for more than 80% of a sequence, and sequences with a length of less than 18 nt after removing adapters; and remove duplicates from the filtered sequences;

[0024] 2) Align the filtered sequences to the Rfam database, obtain annotations for the aligned sequences, and extract the sequences aligned to miRNA and those not aligned as the next valid data;

[0025] 3) Quantify the valid data and identify known miRNAs.

[0026] In the present invention, the markers are screened by constructing a training set, comprising the following steps:

[0027] 1) Eliminate the characteristic miRNAs whose expression level in the samples is 0 and the proportion is higher than 80%;

[0028] 2) The difference of miRNA expression levels corresponding to D3 and D0, D5 and D3, and D7 and D5 is taken as a new trend feature, that is, D3-D0 is taken as the miRNA change feature before tolerance, D5-D3 is taken as the miRNA change feature during tolerance, and D7-D5 is taken as the miRNA change feature after tolerance;

[0029] 3) In the constructed new features, the autocorrelation between features is used to eliminate redundant features with correlation greater than 0.8, and then the correlation coefficient of the labels and the F test are used to screen out the preliminary feature combination;

[0030] 4) Construct a pre-training model, and perform secondary screening on the primary screening features according to the feature importance coefficient of the pre-training model to obtain the optimal feature combination.

[0031] Preferably, the code for constructing the training model is:

[0032]

[0033]

[0034] Preferably, the sample comprises any one of serum, plasma, uterine fluid, uterine lavage fluid, vaginal exfoliated cells, vaginal secretions or endometrial biopsy products, or a combination of at least two thereof.

[0035] Preferably, step (1) further comprises the step of standardizing the expression level according to formula (3).

[0036] miRNA i RPM =miRNA i count / total miRNA count×10 6 Formula (3).

[0037] Among them, miRNA i count For each miRNA expression level, miRNA i RPM The expression level of each miRNA is normalized, and the total miRNA count is the sum of the expression levels of all miRNAs.

[0038] Preferably, the machine learning method in step (3) includes linear discriminant.

[0039] Preferably, the code for constructing a model for detecting endometrial receptivity is:

[0040]

[0041] In a sixth aspect, the present invention provides a model for detecting endometrial receptivity, wherein the model for detecting endometrial receptivity is constructed by the method for constructing a model for detecting endometrial receptivity described in the fifth aspect.

[0042] The present invention conducts correlation analysis and screening of plasma miRNAs at different stages of endometrial receptivity in patients with successful embryo implantation, and establishes a prediction model using a machine learning method to accurately predict the probability of different stages of endometrial receptivity in samples.

[0043] In a seventh aspect, the present invention provides a method for detecting endometrial receptivity for non-disease diagnosis purposes, the method comprising:

[0044] Sampling is performed on the 3rd and 5th days after the peak of luteinizing hormone (LH) in women, which are recorded as D3 and D5 respectively, and the expression level of the miRNA marker related to endometrial receptivity described in claim 1 in the samples is determined. The expression levels corresponding to D5 and D3 of each miRNA are subtracted to obtain the characteristic expression level, and the characteristic expression level is input into the model for detecting endometrial receptivity described in the sixth aspect to detect endometrial receptivity.

[0045] The present invention obtains the optimal feature combination by performing correlation analysis and screening on the plasma miRNA of different endometrial receptivity periods of patients with successful embryo implantation, and establishes a prediction model using machine learning methods. It can accurately predict the probability of different periods of endometrial receptivity of samples based on maternal serum, effectively solving the problem that the sample extraction process of traditional detection methods is complex, invasive and invasive.

[0046] In the present invention, the sample may include any one of serum, plasma, uterine fluid, uterine lavage fluid, vaginal exfoliated cells, vaginal secretions or endometrial biopsy products, or a combination of at least two of them.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] The present invention provides a group of maternal plasma miRNA markers related to endometrial receptivity, which mainly solves the problem that the sample extraction process is complex, invasive and invasive when predicting endometrial receptivity in the prior art; at the same time, a method for predicting endometrial receptivity is constructed based on machine learning methods, which can accurately predict the probability of sample endometrial receptivity at different stages based on maternal serum, and provide patients with recommendations on embryo transplantation time. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 Analyze the flow chart of the present invention. DETAILED DESCRIPTION

[0050] To further illustrate the technical means and effects of the present invention, the present invention is further described below in conjunction with the embodiments and drawings. It should be understood that the specific implementation methods described herein are only used to explain the present invention, rather than to limit the present invention.

[0051] If no specific techniques or conditions are specified in the examples, the techniques or conditions described in the literature in the field or the product instructions are used. If no manufacturer is specified for the reagents or instruments used, they are all conventional products that can be purchased through regular channels.

[0052] In a specific embodiment of the present invention, the plasma miRNAs of different endometrial receptivity periods of patients with successful embryo implantation are analyzed and screened to obtain the optimal feature combination, and a prediction model is established using a machine learning method, which can accurately predict the probability of different periods of endometrial receptivity of samples based on maternal serum. The complete analysis flow chart is shown in FIG. Figure 1 shown.

[0053] Example 1

[0054] This embodiment constructs a model for detecting endometrial receptivity.

[0055] 1. Preparation and loading of plasma samples

[0056] (1) In this example, peripheral blood samples were collected from 50 infertile women who had only fallopian tube factors and underwent natural cycle frozen-thaw blastocyst transfer. Peripheral blood was collected from each patient at four time points (D0, D3, D5, and D7, where D0 was 2 days after the peak of female luteinizing hormone (LH), recorded as the ovulation day). 5 mL of peripheral blood sample was centrifuged at 4°C for 10 minutes with a centrifugal force of 2000×g. The plasma was then packaged and stored in a -80°C environment for subsequent experimental use.

[0057] (2) The absorbance was measured at 414 nm using a Thermo Scientific Nanodrop One spectrophotometer, and plasma samples with a ΔCq (quantification cycle) of ≤0.2 were selected as non-hemolyzed samples. For samples with a ΔCq (quantification cycle) of miR-23a and miR-451 of >0.2, samples with a ΔCq (quantification cycle) of <7 were selected as non-hemolyzed samples.

[0058] 2. Extraction and library construction of miRNA

[0059] (1) Plasma miRNA was extracted using miRNeasy Serum / Plasma Advanced Kit (Qiagen).

[0060] (2) Use the TruSeq small RNA library preparation kit and HiSeq2500 (Illumina, San Diego, USA) system to construct and sequence miRNA libraries.

[0061] 3. Analysis of miRNA offline data

[0062] (1) The raw data of plasma miRNA sequencing were filtered using cutadapt software (v3.4): 3' end adapters, sequences without adapter insertions, sequences containing polyA or polyT, sequences with only AT or CG, sequences with a single base (A / T / C / G) accounting for more than 80% of a sequence, and sequences with a length of less than 18 nt after adapter removal; and the filtered sequences were deduplicated.

[0063] (2) Use bowtie software (v1.34.0) to align the quality-controlled sequences to the Rfam database, obtain annotations for the aligned sequences, and extract the sequences aligned to miRNA and those not aligned as the subsequent valid data.

[0064] (3) Use miRDeep2 (v0.1.3) to quantify valid data and identify known miRNAs.

[0065] (4) The known miRNA quantitative results were standardized according to the following formula:

[0066] miRNA i RPM =miRNA i count / total miRNA count×10 6 ;

[0067] The total miRNA count represents the sum of all known miRNA counts; miRNA i RPM The results were normalized for each miRNA quantification result.

[0068] 4. Screening of features to predict embryo transfer outcomes

[0069] (1) For the plasma miRNA expression data obtained above, based on the expression of each miRNA in the sample, the miRNA with an expression level of 0 in 80% of the samples was screened out.

[0070] (2) The expression data of the same miRNA at different time points in the same sample were subtracted to reflect the change trend of miRNA, that is, D3-D0 was considered as before tolerance, D5-D3 was considered as during tolerance, and D7-D5 was considered as after tolerance.

[0071] (3) The difference features obtained in step (2) are calculated for their pairwise correlations. The correlation between any two difference features is required to be less than 0.8. Otherwise, one of the features is randomly eliminated.

[0072] (4) Using the correlation between label calculation and difference features and combining it with the F-test method, we screen out the first 50 features of each method and take their union to screen out the preliminary feature combination.

[0073] (5) A pre-training model was constructed using a logistic regression method to obtain the importance coefficient of the model. In this embodiment, a feature set with a feature importance coefficient greater than 0.9 and less than -0.7 was selected when distinguishing the pre-tolerance, mid-tolerance, and post-tolerance models. A feature set with a feature importance coefficient greater than 0.4 and less than -0.3 was selected when distinguishing the mid-tolerance and post-tolerance models. The union of the two finally obtained 25 miRNA candidate features (including hsa-miR-199b-5p, hsa-miR-33a-3p, hsa-miR-4659a-3p, hsa-miR-7702, hsa-miR-545-5p, hsa-miR-133a-5p, hsa-miR-150-5p, hsa-miR-152-5p, hsa-miR-6815-3p, hsa-miR-4477b, hsa-miR-26b-5p, hsa-miR-126-5p, hsa-miR-1270, hsa-miR-544b, hsa-miR-6837-3p, hsa-miR-6799-3p, hsa-miR-6764-5p, hsa-miR-548bb-3p, hsa-miR-183-3p, hsa-miR-5699-3p, hsa-miR-548ak, hsa-miR-5684, hsa-miR-340-5p, hsa-miR-6850-5p and hsa-let-7a-3p) were included in the construction of the prediction model.

[0074] 5. Construction of a model to predict embryo transfer outcomes

[0075] (1) Normalize and standardize the selected optimal feature set. The specific formula is as follows:

[0076]

[0077] (2) Plasma miRNA samples from 50 patients with successful embryo transfer were taken from D0, D3, D5, and D7, and the data were processed by difference as training sets. A stratified sampling cross-validation method was used during training to obtain a stable and reliable model. In this embodiment, a 10-fold stratified cross-validation method was used.

[0078] (3) A machine learning method using a linear discriminant algorithm is used to construct a prediction model based on the above-mentioned confirmed features in the training set.

[0079] (4) The area under the receiver operating characteristic curve (ROC) (AUC) and prediction accuracy (ACC) of the model in the training set were calculated. The results are shown in Table 2. In the training set, the ACC of the model constructed using the linear discriminant method can reach 76.6%, and the AUC reaches 90%.

[0080] Table 2

[0081] Accuracy ACC AUC Specificity Sensitivity Training set 0.77 0.90 0.92 0.78

[0082] The code to build the training model is:

[0083]

[0084]

[0085] The code for constructing the model for detecting endometrial receptivity is:

[0086]

[0087]

[0088] Example 2

[0089] In this example, the effect of the model constructed in Example 1 was verified using plasma miRNA samples from 13 patients with successful embryo transplantation.

[0090] 1. The steps of obtaining plasma samples and analyzing the expression of plasma miRNA are the same as those in Example 1.

[0091] 2. Extract the 25 miRNA features obtained in Example 1 for each sample and perform difference processing to obtain new features. Normalize the features of the test set samples with reference to Example 1, and then use the model constructed in Example 1 as input to predict the probability of different stages of endometrial receptivity of the samples.

[0092] 3. The computational model predicts the effectiveness of embryo transfer outcomes in the test set.

[0093] The AUC and ACC of the model on the test set are calculated. The results are shown in Table 3. It can be seen that on the test set, the ACC of the model built using the linear discriminant algorithm can reach 74.36% and the AUC can reach 81%.

[0094] Table 3

[0095] Accuracy ACC AUC Specificity Sensitivity Validation set 0.74 0.81 0.85 0.85

[0096] Example 3

[0097] This example is based on plasma miRNA samples at D3 and D5 of 21 patients with embryo transplantation failure to observe the changes in the implantation window of patients with embryo transplantation failure.

[0098] 1. The steps of obtaining plasma samples and analyzing the expression of plasma miRNA are the same as those in Example 1.

[0099] 2. Extract the 25 miRNA features of D3 and D5 obtained in Example 1 for each sample, perform difference processing (i.e., D5-D3) to obtain new features, normalize the features of the test set samples with reference to Example 1, and then use the model constructed in Example 1 as input to predict the probability of the sample in different endometrial receptive periods.

[0100] 3. The computational model was effective in predicting embryo transfer results in the test set. As shown in Table 4, among the 21 failed patients, 11 were predicted to have an earlier receptive period, 4 were predicted to have no change in receptive period, and 6 were predicted to have a delayed receptive period.

[0101] Table 4

[0102] Acceptance in Advance The tolerance period remains unchanged Tolerance for delay Implantation failure group 11 4 6

[0103] In summary, the present invention provides a group of endometrial receptivity biomarkers and a method for judging endometrial receptivity, which mainly solves the problem that the sample extraction process is complex, invasive and invasive when predicting whether the embryo can successfully implant. By performing correlation analysis and screening on the plasma miRNA of the endometrium of patients with successful embryo implantation at different receptive stages, the optimal feature combination is obtained, and a prediction model is established using a machine learning method. The final model predicts the endometrial receptivity effect in the validation set samples. The area under the receiver operating characteristic curve (ROC) (AUC) reaches 0.81, and the prediction accuracy (ACC) reaches 0.74.

[0104] The applicant declares that the present invention illustrates the detailed method of the present invention through the above-mentioned embodiments, but the present invention is not limited to the above-mentioned detailed method, that is, it does not mean that the present invention must rely on the above-mentioned detailed method to be implemented. Those skilled in the art should understand that any improvement of the present invention, equivalent replacement of various raw materials of the product of the present invention, addition of auxiliary components, selection of specific methods, etc., all fall within the protection scope and disclosure scope of the present invention.

Claims

1. A miRNA marker associated with endometrial receptivity, characterized in that: The miRNA markers include: hsa-miR-199b-5p, hsa-miR-33a-3p, hsa-miR-4659a-3p, hsa-miR-7702, hsa-miR-545-5p, hsa-miR-133a-5p, hsa-miR-150-5p, hsa-miR-152-5p, hsa-miR-6815-3p, hsa-miR-4477b, hsa-miR-26b-5p, hsa-miR-126-5p , hsa-miR-1270, hsa-miR-544b, hsa-miR-6837-3p, hsa-miR-6799-3p, hsa-miR-6764-5p, hsa-miR-548bb-3p, hsa-m iR-183-3p, hsa-miR-5699-3p, hsa-miR-548ak, hsa-miR-5684, hsa-miR-340-5p, hsa-miR-6850-5p and hsa-let-7a-3p.

2. Use of the miRNA markers associated with endometrial receptivity and / or their detection reagents as described in claim 1 in the preparation of endometrial receptivity detection products.

3. A kit for detecting endometrial receptivity, characterized in that: The kit comprises a reagent for detecting the expression level of the miRNA marker associated with endometrial receptivity according to claim 1.

4. Use of the miRNA marker associated with endometrial receptivity according to claim 1 in detecting endometrial receptivity for purposes other than disease diagnosis.

5. A method for constructing a model for detecting endometrial receptivity, characterized in that: The method comprises: (1) sampling on the 2nd, 5th, 7th and 9th day after the peak of luteinizing hormone (LH) in women, respectively, recorded as D0, D3, D5 and D7, wherein D0 is recorded as the ovulation day, and determining the expression level of the miRNA marker related to endometrial receptivity described in claim 1 in the sample; (2) Subtract the expression levels of D3 and D0, D5 and D3, and D7 and D5 of each miRNA to obtain the characteristic expression value x; (3) The feature expression is normalized and standardized using equations (1) and (2), wherein x' is the feature expression after normalization and standardization, μ is the mean of the feature expression, σ is the variance, and x max is the maximum value of feature expression, x min The minimum value of feature expression was used to construct a model for detecting endometrial receptivity using machine learning methods; 6. The method for constructing a model for detecting endometrial receptivity according to claim 5, characterized in that: The sample includes any one of serum, plasma, uterine fluid, uterine lavage fluid, vaginal exfoliated cells, vaginal secretions or endometrial biopsy products, or a combination of at least two of them.

7. The method for constructing a model for detecting endometrial receptivity according to claim 5 or 6, characterized in that: Step (1) also includes the step of normalizing the expression amount according to formula (3); miRNA iRPM = miRNA icount / total miRNA count×10 6 Equation (3); Among them, miRNA icount For each miRNA expression level, miRNA iRPM The result after normalization of each miRNA expression level, and the total miRNA count is the sum of all miRNA expression levels; Preferably, the machine learning method in step (3) includes linear discriminant.

8. A model for detecting endometrial receptivity, characterized in that: The model for detecting endometrial receptivity is constructed by the method for constructing a model for detecting endometrial receptivity described in any one of claims 5 to 7.

9. A method for detecting endometrial receptivity for non-disease diagnosis purposes, characterized in that: The method comprises: Samples are taken on the 5th and 7th days after the peak of luteinizing hormone (LH) in women, recorded as D3 and D5 respectively, and the expression levels of the miRNA markers related to endometrial receptivity described in claim 1 in the samples are determined. The expression levels corresponding to D5 and D3 of each miRNA are subtracted to obtain the characteristic expression level, and the characteristic expression level is input into the model for detecting endometrial receptivity described in claim 8 to detect endometrial receptivity.

10. The method for detecting endometrial receptivity for non-disease diagnosis purposes according to claim 9, characterized in that: The sample includes any one of serum, plasma, uterine fluid, uterine lavage fluid, vaginal exfoliated cells, vaginal secretions or endometrial biopsy products, or a combination of at least two of them.

Images