Kit and application thereof

Abstract

The invention discloses a kit and application thereof, the kit comprises a detection reagent for detecting the expression quantity of one or more RNA molecules, and accurate diagnosis of endometriosis can be realized. In addition, the invention also discloses a method for diagnosing the endometriosis.

Description

Technical Field

[0001] The present invention belongs to the field of molecular biology and medical diagnosis, and specifically relates to the application of one or more RNA molecules in human serum in combination in the preparation of a kit for detecting or diagnosing endometriosis. Background Art

[0002] Endometriosis is a common disease defined as the implantation of endometrial tissue outside the uterine cavity. The incidence rate in women of childbearing age can be as high as 10-15%. Among infertile patients, about 50% suffer from endometriosis, and 70% to 80% of endometriosis patients have varying degrees of pelvic pain symptoms, including dysmenorrhea, chronic pelvic pain, and sexual intercourse pain, which seriously affect the quality of life of patients. At present, the clinical diagnosis of endometriosis mainly relies on physical examination, imaging examination and laparoscopy. However, the results of gynecological examinations are greatly affected by the experience and skills of physicians; the sensitivity of imaging examinations varies depending on the location of endometriosis lesions; and laparoscopy is an invasive operation. Although it is a minimally invasive surgery, it causes great damage to the endometrium. The elevated CA125 level commonly used in clinical gynecology is more common in patients with severe endometriosis, obvious pelvic inflammation, combined with endometriosis cyst rupture or adenomyosis. The specificity of endometriosis detection is poor, and the detection is of little significance for the diagnosis of endometriosis. Therefore, finding molecular markers for the onset of endometriosis and developing early diagnosis kits will undoubtedly have important clinical significance and social application value for patients, as they can accurately diagnose endometriosis through liquid biopsy in the early stages of the disease.

[0003] Up to now, the research on non-coding RNA and early diagnosis of endometriosis is developing continuously, but the current endometriosis diagnostic kits have problems such as low accuracy and poor precision. In addition, the current endometriosis diagnostic kits have poor sensitivity and poor specificity, which also need to be solved urgently. Summary of the invention

[0004] The first aspect of the present invention aims to provide a kit.

[0005] The second aspect of the present invention aims to provide a kit for use in diagnosing endometriosis.

[0006] The third aspect of the present invention aims to provide a method for diagnosing endometriosis, the method comprising the following steps:

[0007] (1) Collecting human serum samples;

[0008] (2) detecting the expression level of one or more RNA molecules as described in claim 1 in a serum sample;

[0009] (3) Inputting the expression level of the RNA molecule in step (2) into the trained machine learning model, outputting the model evaluation result, and determining whether the patient suffers from endometriosis.

[0010] In order to achieve the above object, the technical solution adopted by the present invention is:

[0011] The present invention provides 10 RNA molecules, which are tRF-59:75-Ala-AGC-2-M4, tRF-1:16-Leu-AAG-4-M2, tRF-1:16-Leu-AAG-1-M4, tRF-+1:T33-Gln-CTG-3, tiRNA-1:31-chrM.Met-CAT, tRF-1:16-Gly-CCC-2, tiRNA-1:34-Val-AAC-1-M3, tRF-54:75-His-GTG-1-M2, tRF-58:75-Ala-AGC-1 and tRF-1:28-chrM.Ser-TGA. The nucleotide sequence of the tRF-59:75-Ala-AGC-2-M4 is shown in SEQ ID NO.1; the nucleotide sequence of the tRF-1:16-Leu-AAG-4-M2 is shown in SEQ ID NO.2; the nucleotide sequence of the tRF-1:16-Leu-AAG-1-M4 is shown in SEQ ID NO.3; the nucleotide sequence of the tRF-+1:T33-Gln-CTG-3 is shown in SEQ ID NO.4; the nucleotide sequence of the tiRNA-1:31-chrM.Met-CAT is shown in SEQ ID NO.5; the nucleotide sequence of the tRF-1:16-Gly-CCC-2 is shown in SEQ ID NO.6; the nucleotide sequence of the tiRNA-1:34-Val-AAC-1-M3 is shown in SEQ ID NO.7; the nucleotide sequence of the tRF-54:75-His-GTG-1-M2 is shown in SEQ ID NO.8; the nucleotide sequence of the tRF-58:75-Ala-AGC-1 is shown in SEQ ID NO.9; the nucleotide sequence of the tRF-1:28-chrM.Ser-TGA is shown in SEQ ID NO.10.

[0012] In a first aspect, the present invention provides a kit, which can detect the expression level of one or more RNA molecules.

[0013] In some embodiments of the present invention, the nucleotide sequence of the RNA molecule is SEQ ID NO.1, SEQ ID NO., SEQ ID NO.3, SEQ ID NO.4, SEQ ID NO.5, SEQ ID NO.6, SEQ ID NO.7, SEQ ID NO.8, SEQ ID NO.9 or SEQ ID NO.10.

[0014] In some embodiments of the present invention, the kit is used to diagnose endometriosis, and the kit comprises a detection reagent for detecting the expression amount of RNA molecules in serum.

[0015] In some embodiments of the present invention, the detection reagent includes a reverse transcription reagent and a fluorescent quantitative PCR reaction reagent.

[0016] In some embodiments of the present invention, the reverse transcription reagent includes 5x RT buffer, dNTP mixture, RNase Inhibitor and specific reverse transcription primer.

[0017] In some embodiments of the present invention, the fluorescent quantitative PCR reaction reagents include specific primer pairs, PCR amplification buffer, and a DNA polymerase mixture.

[0018] The second aspect of the present invention aims to provide a kit for use in diagnosing endometriosis.

[0019] In a third aspect of the present invention, the present invention provides a method for diagnosing endometriosis, the method comprising the following steps:

[0020] (1) Collecting human serum samples;

[0021] (2) detecting the expression level of one or more RNA molecules as described in claim 1 in a serum sample;

[0022] (3) Inputting the expression level of the RNA molecule in step (2) into the trained machine learning model, outputting the model evaluation result, and determining whether the patient suffers from endometriosis.

[0023] In some embodiments of the present invention, Trizol reagent can be used to extract RNA molecules in human serum samples.

[0024] In some embodiments of the present invention, cDNA is obtained by RNA reverse transcription reaction, and then the expression amount of RNA molecule is obtained by fluorescent quantitative PCR reaction reagent;

[0025] In some embodiments of the present invention, the reverse transcription reagent includes 5x RT buffer, dNTP mixture, RNase Inhibitor and specific reverse transcription primer.

[0026] In some embodiments of the present invention, the reverse transcription reaction step is incubated at 42° C. for 60 minutes and incubated at 70° C. for 10 minutes.

[0027] In some embodiments of the present invention, a fluorescent quantitative PCR instrument may be used to perform a quantitative PCR reaction.

[0028] In some embodiments of the present invention, the fluorescent quantitative PCR reaction reagents include a specific primer pair, a fluorescent quantitative PCR amplification buffer, and a DNA polymerase mixture.

[0029] In some embodiments of the present invention, one or more RNA molecules as described in claim 1 and an external reference RNA molecule cel-miR-39-3p are detected in a serum sample by real-time fluorescence quantitative PCR, and the cycle number (Cycle Threshold, referred to as cycle number or CT value) when the fluorescence signal in the exponential growth phase of PCR amplification reaches a set threshold is recorded;

[0030] In some embodiments of the present invention, the average cycle number of the RNA molecule and the external reference cel-miR-39-3p is calculated, and the relative expression of the RNA molecule is calculated, that is, the difference between the average cycle number of the RNA molecule and the cel-miR-39-3p, and the calculation formula is: ΔCT = CT RNA molecule - CTcel-miR-39-3p;

[0031] The expression level of the RNA molecule is then input into the trained machine learning model to output the model evaluation results to determine whether the patient has endometriosis.

[0032] In some embodiments of the present invention, each RNA molecule is subjected to diagnostic testing separately, and 14 different machine learning models are used for analysis and modeling to evaluate the diagnostic accuracy of each RNA molecule.

[0033] In some embodiments of the present invention, the diagnostic efficacy of ten RNA molecules, including tRF-59:75-Ala-AGC-2-M4, tRF-1:16-Leu-AAG-4-M2, tRF-1:16-Leu-AAG-1-M4, tRF-+1:T33-Gln-CTG-3, tiRNA-1:31-chrM.Met-CAT, tRF-1:16-Gly-CCC-2, tiRNA-1:34-Val-AAC-1-M3, tRF-54:75-His-GTG-1-M2, tRF-58:75-Ala-AGC-1 and tRF-1:28-chrM.Ser-TGA, are evaluated respectively.

[0034] In some embodiments of the present invention, two RNA molecules are combined for diagnostic testing, and 14 different machine learning models are used for analysis and modeling to evaluate the diagnostic accuracy of different combinations. For example: tRF-1:16-Leu-AAG-1-M4 and tRF-59:75-Ala-AGC-2-M4 are combined for testing; tRF-1:28-chrM.Ser-TGA and tRF-1:16-Leu-AAG-4-M2 are combined for testing; tRF-1:16-Leu-AAG-1-M4 and tRF-1:28-chrM.Ser-TGA are combined for testing; a total of 45 combinations are evaluated for diagnostic efficacy.

[0035] In some embodiments of the present invention, three RNA molecules are subjected to combined diagnostic testing, and 14 different machine learning models are used for analysis and modeling to evaluate the diagnostic accuracy of different combinations. For example, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4 and tRF-1:28-chrM.Ser-TGA are tested together; tRF-54:75-His-GTG-1-M2, tRF-1:16-Leu-AAG-1-M4 and tRF-59:75-Ala-AGC-2-M4 are tested together; tRF-58:75-Ala-AGC-1, tRF-1:16-Leu-AAG-1-M44 and tRF-59:75-Ala-AGC-2-M4 are tested together, and a total of 120 combinations are tested for diagnostic efficacy.

[0036] In some embodiments of the present invention, four RNA molecules are subjected to combined diagnostic testing, and 14 different machine learning models are used for analysis and modeling to evaluate the diagnostic accuracy of different combinations. For example: combined detection of tRF-58:75-Ala-AGC-1, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4 and tRF-1:28-chrM.Ser-TGA; combined detection of tRF-58:75-Ala-AGC-1, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4 and tRF-1:16-Gly-CCC-2; combined detection of tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-1:28-chrM.Ser-TGA and tiRNA-1:31-chrM.Met-CAT; a total of 210 combinations were evaluated for diagnostic efficacy.

[0037] In some embodiments of the present invention, five RNA molecules are subjected to combined diagnostic testing and analyzed and modeled using 14 different machine learning models to evaluate the diagnostic accuracy of different combinations. For example: tRF-58:75-Ala-AGC-1, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-1:28-chrM.Ser-TGA, and tiRNA-1:31-chrM.Met-CAT are jointly tested; tRF-58:75-Ala-AGC-1, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-1:28-chrM.Ser-TGA, and tiRNA-1:31-chrM.Met-CAT are jointly tested; M4, tRF-1:28-chrM.Ser-TGA and tRF-1:16-Gly-CCC-2 were jointly detected; tRF-58:75-Ala-AGC-1, tRF-54:75-His-GTG-1-M2, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4 and tRF-1:28-chrM.Ser-TGA were jointly detected; a total of 252 combinations were evaluated for diagnostic efficacy.

[0038] In some embodiments of the present invention, six RNA molecules were subjected to combined diagnostic testing, and 14 different machine learning models were used for analysis and modeling to evaluate the diagnostic accuracy of different combinations. For example: tRF-58:75-Ala-AGC-1, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Gly-CCC-2, and tRF-1:16-Leu-AAG-4-M2 were jointly tested; tRF-58:75-Ala-AGC-1, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Gly-CCC-2, and tRF-1:16-Leu-AAG-4-M2 were jointly tested; M.Ser-TGA, tRF-1:16-Leu-AAG-4-M2 and tiRNA-1:31-chrM.Met-CAT were jointly detected; tRF-58:75-Ala-AGC-1, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Gly-CCC-2 and tiRNA-1:31-chrM.Met-CAT were jointly detected; a total of 210 combinations were evaluated for diagnostic efficacy.

[0039] In some embodiments of the present invention, seven RNA molecules were subjected to combined diagnostic testing, and 14 different machine learning models were used for analysis and modeling to evaluate the diagnostic accuracy of different combinations. For example: tRF-58:75-Ala-AGC-1, tRF-54:75-His-GTG-1-M2, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Gly-CCC-2, and tRF-1:16-Leu-AAG-4-M2 were jointly tested; RF-1:28-chrM.Ser-TGA, tRF-1:16-Gly-CCC-2 and tiRNA-1:31-chrM.Met-CAT2 were jointly detected; tRF-58:75-Ala-AGC-1, tRF-54:75-His-GTG-1-M2, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Leu-AAG-4-M2 and tiRNA-1:31-chrM.Met-CAT were jointly detected; a total of 120 combinations were evaluated for diagnostic efficacy.

[0040] In some embodiments of the present invention, eight RNA molecules are subjected to combined diagnostic testing, and 14 different machine learning models are used for analysis and modeling to evaluate the diagnostic accuracy of different combinations. For example, tRF-58:75-Ala-AGC-1, tRF-54:75-His-GTG-1-M2, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Gly-CCC-2, tiRNA-1:34-Val-AAC-1-M3, and tiRNA-1:31-chrM.Met-CAT were jointly detected; 3-Gln-CTG-3, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Leu-AAG-4-M2 and tiRNA-1:31-chrM.Met-CAT were jointly detected; tRF-58:75-Ala-AGC-1, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Gly-CCC-2, tRF-1:16-Leu-AAG-4-M2, tiRNA-1:34-Val-AAC-1-M3 and tiRNA-1:31-chrM.Met-CAT were jointly detected; a total of 45 combinations were evaluated for diagnostic efficacy.

[0041] In some embodiments of the present invention, nine RNA molecules were subjected to combined diagnostic testing, and 14 different machine learning models were used for analysis and modeling to evaluate the diagnostic accuracy of different combinations. For example, tRF-58:75-Ala-AGC-1, tRF-54:75-His-GTG-1-M2, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-+1:T33-Gln-CTG-3, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Gly-CCC-2, tRF-1 :16-Leu-AAG-4-M2 and tiRNA-1:31-chrM.Met-CAT were jointly detected; tRF-58:75-Ala-AGC-1, tRF-54:75-His-GTG-1-M2, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Gly-CCC-2, tRF-1:16-Leu-AAG-4-M2, tiRNA-1:34-Val-AAC-1-M3 and tiRNA-1:31-chrM.Met-CAT were jointly detected; tRF-54:75-His-GTG-1-M2, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC -2-M4, tRF-+1:T33-Gln-CTG-3, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Gly-CCC-2, tRF-1:16-Leu-AAG-4-M2, tiRNA-1:34-Val-AAC-1-M3 and tiRNA-1:31-chrM.Met-CAT were used for combined detection; a total of 10 combinations were evaluated for diagnostic efficacy.

[0042] In some embodiments of the present invention, ten RNA molecules are subjected to combined diagnostic testing, and 14 different machine learning models are used for analysis and modeling to evaluate the diagnostic accuracy of different combinations. For example: tRF-58:75-Ala-AGC-1, tRF-54:75-His-GTG-1-M2, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-+1:T33-Gln-CTG-3, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Gly-CCC-2, tRF-1:16-Leu-AAG-4-M2, tiRNA-1:34-Val-AAC-1-M3 and tiRNA-1:31-chrM.Met-CAT are tested together.

[0043] In some embodiments of the present invention, the machine learning model is a support vector machine based on a sigmoid kernel function (SVM with SigmoidKernal), a support vector machine based on a radial basis kernel function (SVM with RadialKernal), a support vector machine based on a polynomial kernel function (SVM with Polynomial Kernal), a support vector machine based on a linear kernel function (SVM with Linear Kernal), a random forest (Random Forest), a quadratic discriminant analysis (Quadratic Discriminant Analysis, QDA), a neural network (Neural Network), a naive Bayes (Naive Bayes), a logistic regression (Logistic Regression), a linear discriminant analysis (Linear Discriminant Analysis, LDA), a K-nearest Neighbors algorithm (KNN), a decision tree (Decision Tree), an adaptive boost (Boost) or a bootstrap aggregating algorithm (Bootstrap aggregating, bagging).

[0044] In some embodiments of the present invention, the machine learning model is a support vector machine (SVM with Radial Kernal), a neural network (Neural Network) or a logistic regression (LogisticRegression) based on a radial basis kernel function; preferably.

[0045] In some embodiments of the present invention, the machine learning model is a support vector machine model based on a radial basis kernel function.

[0046] In some embodiments of the present invention, the machine learning model is a support vector machine model based on a radial basis kernel function, and the RNA molecule for detecting the expression amount of the RNA molecule is tRF-1:16-Leu-AAG-1-M4.

[0047] In some embodiments of the present invention, the machine learning model is a support vector machine model based on a radial basis kernel function, and the RNA molecule combination for detecting the expression amount of RNA molecules is tRF-1:16-Leu-AAG-1-M4 and tRF-59:75-Ala-AGC-2-M4.

[0048] In some embodiments of the present invention, the machine learning model is a support vector machine model based on a radial basis kernel function, and the RNA molecule combination for detecting the expression amount of RNA molecules is tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4 and tRF-+1:T33-Gln-CTG-3.

[0049] In some embodiments of the present invention, the machine learning model is a support vector machine model based on a radial basis kernel function, and the RNA molecule combination for detecting the expression amount of RNA molecules is tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-+1:T33-Gln-CTG-3 and tRF-1:28-chrM.Ser-TGA.

[0050] In some embodiments of the present invention, the machine learning model is a support vector machine model based on a radial basis kernel function, and the RNA molecule combination for detecting the expression amount of RNA molecules is tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-+1:T33-Gln-CTG-3, tRF-1:28-chrM.Ser-TGA and tRF-1:16-Leu-AAG-4-M2.

[0051] In some embodiments of the present invention, the machine learning model is a support vector machine model based on a radial basis kernel function, and the RNA molecule combination for detecting the expression amount of RNA molecules is tRF-58:75-Ala-AGC-1, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-+1:T33-Gln-CTG-3, tRF-1:28-chrM.Ser-TGA and tRF-1:16-Leu-AAG-4-M2.

[0052] In some embodiments of the present invention, the machine learning model is a support vector machine model based on a radial basis kernel function, and the RNA molecule combination for detecting the expression amount of RNA molecules is tRF-58:75-Ala-AGC-1, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-+1:T33-Gln-CTG-3, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Leu-AAG-4-M2 and tiRNA-1:31-chrM.Met-CAT.

[0053] In some embodiments of the present invention, the machine learning model is a support vector machine model based on a radial basis kernel function, and the RNA molecule combination for detecting the expression of RNA molecules is tRF-58:75-Ala-AGC-1, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-+1:T33-Gln-CTG-3, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Leu-AAG-4-M2, tiRNA-1:34-Val-AAC-1-M3 and tiRNA-1:31-chrM.Met-CAT

[0054] In some embodiments of the present invention, the machine learning model is a support vector machine model based on a radial basis kernel function, and the RNA molecule combination for detecting the expression amount of RNA molecules is tRF-58:75-Ala-AGC-1, tRF-54:75-His-GTG-1-M2, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-+1:T33-Gln-CTG-3, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Leu-AAG-4-M2, tiRNA-1:34-Val-AAC-1-M3 and tiRNA-1:31-chrM.Met-CAT.

[0055] In some embodiments of the present invention, the machine learning model is a support vector machine model based on a radial basis kernel function, and the RNA molecule combination for detecting the expression amount of RNA molecules is tRF-58:75-Ala-AGC-1, tRF-54:75-His-GTG-1-M2, tRF-1:16-Leu-AAG-1-M4, tRF-59:75-Ala-AGC-2-M4, tRF-+1:T33-Gln-CTG-3, tRF-1:28-chrM.Ser-TGA, tRF-1:16-Gly-CCC-2, tRF-1:16-Leu-AAG-4-M2, tiRNA-1:34-Val-AAC-1-M3+ and tiRNA-1:31-chrM.Met-CAT.

[0056] The present invention detects RNA molecules in endometriosis patients and normal control endometrial tissues through high-throughput sequencing technology, and screens RNA molecules with significant differential expression. The sample was expanded by collecting qRT-PCR data from 160 endometriosis patients and 163 normal people's serum and constructing and verifying machine learning models. The model results showed that the AUC score and Accuracy score were high for single and combined diagnosis of 1 to 10 RNA molecules, indicating that the accuracy rates in the 14 machine learning models were all high, especially when multiple RNA molecules were used for combined diagnosis, which could significantly improve the model detection accuracy. The inventors selected the highest AUC scores and Accuracy scores from different RNA molecule combinations in 14 different models for verification. The results showed that the AUC scores and Accuracy scores of the support vector machine (SVM with Radial Kernal), neural network, and logistic regression based on the radial basis kernel function were high and stable, and the reliability and accuracy of the models were good, especially the support vector machine (SVM with Radial Kernal) model based on the radial basis kernel function. The present invention finally screened out the RNA molecule composition with the highest AUC score in the support vector machine model based on the radial basis kernel function. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A is the receiver operating characteristic curve (ROC curve) of the test results using a serum RNA molecule to identify endometriosis patients.

[0058] Figure 1 B is the receiver operating characteristic curve (ROC curve) of the test results using two serum RNA molecules to identify endometriosis patients.

[0059] Figure 1C is the receiver operating characteristic curve (ROC curve) of the test results of using three serum RNA molecules to identify endometriosis patients.

[0060] Figure 1 D is the receiver operating characteristic curve (ROC curve) of the test results of using four serum RNA molecules to identify endometriosis patients.

[0061] Figure 1 E is the receiver operating characteristic curve (ROC curve) of the test results of using five serum RNA molecules to identify endometriosis patients.

[0062] Figure 1 F is the receiver operating characteristic curve (ROC curve) of the test results of using six serum RNA molecules to identify endometriosis patients.

[0063] Figure 1 G is the receiver operating characteristic curve (ROC curve) of the test results of using seven serum RNA molecules to identify endometriosis patients.

[0064] Figure 1 H is the receiver operating characteristic curve (ROC curve) of the test results of using eight serum RNA molecules to identify endometriosis patients.

[0065] Figure 1 I is the receiver operating characteristic curve (ROC curve) of the test results of using nine serum RNA molecules to identify endometriosis patients.

[0066] Figure 1 J is the receiver operating characteristic curve (ROC curve) of the test results of using ten serum RNA molecules to identify endometriosis patients.

[0067] Figure 2 A is the AUC score of the support vector machine model based on the Sigmoid kernel function for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0068] Figure 2 B is the Accuracy score of the support vector machine model based on the Sigmoid kernel function for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0069] Figure 2 C is the AUC score of the support vector machine model based on the radial basis kernel function for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0070] Figure 2 D is the Accuracy score of the support vector machine model based on the radial basis kernel function for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0071] Figure 2 E is the AUC score of the support vector machine model based on the polynomial kernel function for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0072] Figure 2 F is the Accuracy score of the support vector machine model based on the polynomial kernel function for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0073] Figure 2 G is the AUC score of the support vector machine model based on the linear kernel function for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0074] Figure 2 H is the Accuracy score of the support vector machine model based on the linear kernel function for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0075] Figure 2 I is the AUC score of the random forest model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0076] Figure 2 J is the accuracy score of the random forest model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0077] Figure 3 A is the AUC score of the secondary discriminant analysis model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0078] Figure 3 B is the accuracy score of the secondary discriminant analysis model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0079] Figure 3 C is the AUC score of the neural network model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0080] Figure 3 D is the accuracy score of the neural network model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0081] Figure 3 E is the AUC score of the naive Bayes model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0082] Figure 3 F is the Accuracy score of the naive Bayes model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0083] Figure 3G is the AUC score of the logistic regression model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0084] Figure 3 H is the Accuracy score of the logistic regression model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0085] Figure 3 I is the AUC score of the linear discriminant analysis model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0086] Figure 3 J is the Accuracy score of the linear discriminant analysis model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0087] Figure 4 A is the AUC score of the K nearest neighbor algorithm model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0088] Figure 4 B is the Accuracy score of the K nearest neighbor algorithm model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0089] Figure 4 C is the AUC score of the decision tree model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0090] Figure 4 D is the Accuracy score of the decision tree model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0091] Figure 4 E is the AUC score of the adaptive boosting model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0092] Figure 4 F is the Accuracy score of the adaptive boosting model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0093] Figure 4 G is the AUC score of the guided clustering algorithm model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0094] Figure 4 H is the Accuracy score of the guided clustering algorithm model for identifying endometriosis patients using a combination of 1 to 10 RNA molecules.

[0095] Figure 5 A is the curve of the highest AUC score of 1 to 10 RNA molecules combined to identify patients with endometriosis in 14 machine models

[0096] Figure 5 B is the curve of the highest Accuracy score of 1 to 10 RNA molecule combinations in identifying endometriosis patients among 14 machine models DETAILED DESCRIPTION

[0097] In order to make the technical personnel in this technical field better understand the scheme of this application, the technical scheme in the embodiment of this application will be clearly and completely described in combination with the drawings in the embodiment of this application. Obviously, the described embodiment is only a part of the embodiment of this application, not all the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0098] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or apparatuses.

[0099] In the present invention, "polynucleotide", "oligonucleotide", "nucleic acid", or "nucleic acid sequence" includes, but is not limited to, mRNA, cDNA, cccDNA, genomic DNA, and synthetic DNA and RNA sequences containing natural nucleoside bases adenine, guanine, cytosine, thymine and uracil, and also includes sequences with one or more modified or unmodified nucleosides. The term "nucleic acid" or "nucleic acid sequence" includes oligonucleotides and polynucleotides. Any of these terms used herein is not limited to length or synthetic origin.

[0100] In the present invention, "sample" can be a tissue or body fluid sample or a separated sample. The term "tissue" used herein refers to any biological material composed of one cell, multiple cells, cell clusters or entire organs. The term tissue used herein includes one or more cells that can be normal or abnormal.

[0101] In the present invention, "PCR reaction" is a molecular biology technique used to amplify specific DNA fragments. It can be regarded as a special DNA replication outside the body. The biggest feature of PCR is that it can significantly increase trace amounts of DNA.

[0102] The present invention is further analyzed below in conjunction with specific examples.

[0103] Example 1

[0104] The clinical samples collected were mainly from female patients who underwent surgical treatment (see Table 1). Five endometrial tissue samples were collected from patients with endometriosis, ectopic tissue, and age-matched non-endometriosis patients (control group). Five pairs of endometriosis ectopic endometrium and eutopic endometrium ESC cells were detected by high-throughput sequencing technology, and 10 RNA molecules with significant differential expression were screened according to the expression level.

[0105] (See Table 2).

[0106] Table 1: Basic information of clinical samples

[0107] Endometriosis (n=5) Control group (n=5) age 34.5±5.5 32.5±8.5 p>0.05 BMI 23.4±1.2 23.1±4.1 p>0.05

[0108] Table 2: Basic information of RNA molecules

[0109]

[0110] Example 2

[0111] Differentially expressed RNA molecules screened by quantitative PCR:

[0112] Step 1: Human serum samples were collected in a study of 163 normal women and 164 endometriosis patients. The specific clinical characteristics of endometriosis patients and normal control groups are shown in Table 3; Step 2: Trizol reagent was used to extract total RNA from human serum; Step 3: cDNA was obtained by RNA reverse transcription reaction, and the reverse transcription reagent was riboSCRIPTTM ReverseTranscriptionKit; Step 4: The fluorescent dye SYBR Green was added to the PCR system using a fluorescent quantitative PCR instrument to perform quantitative PCR reaction using a PCR reaction reagent designed for RNA molecular sequences, and the PCR reaction reagent was a bulger-loop miRNAqRT-PCR StaterKit (Ribobio, China) kit designed for RNA molecular sequences. The reverse transcription reaction system in step 3 included 2u15x RT buffer, 2ul 10mM of each dNTP mixture, 0.5u1Rnase Inhibitor, and 1.5u1 gene-specific reverse primer mixture; the reaction steps were incubation at 42°C for 60 minutes, incubation at 70°C for 10 minutes, and storage at 4°C. In step 4, quantitative PCR was performed using a fluorescent quantitative PCR instrument. The reaction system was: 5 μl of SYBR Green, 2 pmol of each upstream and downstream primer, 1 μl of cDNA, and DEPC water was added to make it equal to 10 μl. The reaction conditions were 95°C for 5 minutes for 1 cycle → 95°C for 10 seconds, and 60°C for 30 seconds for 45 cycles.

[0113] Table 3: Clinical characteristics of patients with endometriosis and normal control group

[0114]

[0115] BMI: body mass index, AFS: American Fertility Society Laparoscopic Endometriosis Scoring System

[0116] Example 3

[0117] The correlation between the expression of 10 differentially expressed RNA molecules in serum and endometriosis was evaluated, and the quantitative PCR test results of 163 normal women and 164 patients with endometriosis were used as data sets. The generalized linear model logistic regression function was used to model and draw the receiver operating characteristic curve (ROC). The ROC curve is a tool for evaluating the performance of a binary classification model. It shows the classification ability of RNA molecules, that is, the diagnostic ability, by drawing the relationship between the true positive rate (TPR) and the false positive rate (FPR) at different thresholds. Generally speaking, the closer the curve is to the upper left corner, the larger the area under the curve, and the better the classification performance of the model, that is, the better the diagnostic ability.

[0118] The results showed that the generalized linear model logistic regression function was used to build a model, and the diagnostic test was evaluated for different combinations of 10 RNA molecules, and the receiver operating characteristic curve (ROC) was drawn. Figure 1 A- Figure 1 It can be seen that classification performance can be achieved when 1 to 10 RNA molecules are used as diagnostic indicators, and the classification ability is improved when multiple RNA molecules are used as joint indicators for diagnosis. Figure 1 This indicates that the expression levels of the 10 differentially expressed RNA molecules in serum are all related to endometriosis.

[0119] Example 4

[0120] The quantitative PCR test results of 163 normal women and 164 endometriosis patients were used as the data set. 20% of the test result data set was divided into a test set, and the remaining 80% was used as a training set. 14 different machine learning models were compiled. For learning algorithms that require multiple iterations, a learning rate adjustment callback was set to optimize the convergence speed and final performance of the model, and early stopping was set to prevent overfitting. The 14 machine learning models are: Support Vector Machine with Sigmoid Kernal, Support Vector Machine with Radial Kernal, Support Vector Machine with Polynomial Kernal, Support Vector Machine with Linear Kernal, Random Forest, Quadratic Discriminant Analysis (QDA), Neural Network, Naive Bayes, Logistic Regression, Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Decision Tree, Adaptive Boosting, and Bootstrap aggregating (bagging). The final output of the model evaluation results is the area under the curve score (the area under the curve between the true positive rate and the false positive rate, AUC) and accuracy score (Accuracy, the proportion of correct predictions) of the detection results of different RNA molecules for single and combined identification of endometriosis patients in the evaluation of 14 machine learning models. The higher the AUC score and Accuracy score, the higher the model detection accuracy.

[0121] The results show:

[0122] 1. Figure 2 , Figure 3 and Figure 4 The AUC scores and Accuracy scores of 1 to 10 RNA molecules alone and in combination for the diagnosis of endometriosis in 14 machine learning models are shown. Figure 2 , Figure 3 and Figure 4 It can be seen that the AUC scores and Accuracy scores of single and combined diagnosis of 1 to 10 RNA molecules are relatively high, indicating that the accuracy rates of the 14 machine learning models are very high, especially when using multiple RNA molecules for combined diagnosis, which can significantly improve the model detection accuracy.

[0123] 2. Select the highest AUC score and Accuracy score in different models and different RNA molecule combinations for plotting ( Figure 5 ), Figure 5 It can be seen that the AUC scores and Accuracy scores of the support vector machine (SVM with Radial Kernal), neural network (NeuralNetwork) and logistic regression (Logistic Regression) based on the radial basis kernel function are high and stable, and the reliability and accuracy of the models are good.

[0124] The inventors selected a support vector machine (SVM with Radial Kernal) model based on radial basis kernel function to diagnose all combinations of RNA molecules. The results are shown in Table 4. Finally, the RNA molecule composition with the highest AUC score in the support vector machine model based on radial basis kernel function was screened out, as shown in Table 5.

[0125] Table 4: AUC scores and Accuracy scores of all combinations of RNA molecules in the support vector model based on the radial basis kernel function

[0126]

[0127]

[0128]

[0129]

[0130]

[0131]

[0132]

[0133]

[0134]

[0135]

[0136]

[0137]

[0138]

[0139]

[0140]

[0141]

[0142]

[0143]

[0144]

[0145]

[0146]

[0147]

[0148]

[0149]

[0150]

[0151]

[0152]

[0153]

[0154]

[0155]

[0156]

[0157]

[0158]

[0159]

[0160]

[0161]

[0162]

[0163]

[0164]

[0165]

[0166]

[0167]

[0168]

[0169]

[0170]

[0171]

[0172]

[0173]

[0174]

[0175]

[0176]

[0177] Table 5: RNA molecular composition of the group with the highest AUC score in the support vector machine model based on the radial basis kernel function

[0178]

[0179]

Claims

1. A kit, characterized in that: The kit comprises a detection reagent for detecting the expression amount of one or more RNA molecules.

2. The kit according to claim 1, characterized in that The nucleotide sequence of the RNA molecule is shown in any one of SEQ ID NO.1 to SEQ ID NO.

10.

3. The kit according to claim 1 or 2, characterized in that The kit is used for diagnosing endometriosis, and the detection reagent is used for detecting the expression amount of one or more RNA molecules in serum.

4. The kit according to claim 3, characterized in that The detection reagent is used to detect the expression levels of 1, 2, 3, 4, 5, 6, 7, 8, 9 or 10 RNA molecules in serum; preferably, the detection reagent is used to detect the expression levels of 3, 4, 5 or 6 RNA molecules in serum; more preferably, the detection reagent is used to detect the expression levels of 4 or 5 RNA molecules in serum.

5. The kit according to claim 4, characterized in that The detection reagents include reverse transcription reagents and PCR reaction reagents.

6. The kit according to claim 5, characterized in that The reverse transcription reagent includes 5x RT buffer, RTMix, RNase Inhibitor and specific reverse transcription primers.

7. Use of the kit according to any one of claims 1 to 6 in diagnosing endometriosis.

8. A method for diagnosing endometriosis, characterized in that: The following steps are involved: (1) Collecting human serum samples; (2) detecting the expression level of one or more RNA molecules as described in claim 1 in a serum sample; (3) Inputting the expression level of the RNA molecule in step (2) into the trained machine learning model, outputting the model evaluation result, and determining whether the patient suffers from endometriosis.

9. The method for diagnosing endometriosis according to claim 8, characterized in that: The machine learning model is a support vector machine based on a sigmoid kernel function (SVM with Sigmoid Kernal), a support vector machine based on a radial basis kernel function (SVM with Radial Kernal), a support vector machine based on a polynomial kernel function (SVM with Polynomial Kernal), a support vector machine based on a linear kernel function (SVM with Linear Kernal), a random forest (Random Forest), a quadratic discriminant analysis (Quadratic Discriminant Analysis, QDA), a neural network (Neural Network), a naive Bayes (Naive Bayes), a logistic regression (Logistic Regression), a linear discriminant analysis (Linear Discriminant Analysis, LDA), a K-nearest Neighbors algorithm (KNN), a decision tree (Decision Tree), an adaptive boost (Boost) or a bootstrap aggregating algorithm (Bootstrap aggregating, bagging).

10. The method for diagnosing endometriosis according to claim 9, characterized in that: The machine learning model is a support vector machine (SVM with Radial Kernal), a neural network (NeuralNetwork) or a logistic regression (Logistic Regression) based on a radial basis kernel function; preferably, the machine learning model is a support vector machine model based on a radial basis kernel function.

Images