A METHOD FOR PREDICTING THE RISK OF PREMATURE BIRTH AND THE DELIVERY TIME, AS WELL AS ITS APPLICATION

Abstract

Provided are a protein marker related to premature delivery, a method for constructing a premature delivery risk assessment and prediction model, a prediction model, a prediction system, a method for predicting a premature delivery risk and a delivery time, and related applications thereof. Several protein markers related to premature delivery are found, and the protein markers are applied to the field of premature delivery prediction. Moreover, the application of LUM and / or TIMP1 in premature delivery prediction is also found. LUM and / or TIMP1 in a sample of a pregnant woman is tested, then a test result is compared with a predetermined threshold value, and on the basis of a comparison result, whether the pregnant woman has a premature delivery risk or whether the pregnant woman is about to deliver within a predetermined timeframe is determined. Therefore, a premature delivery risk and a delivery time can be accurately predicted 1-2 weeks in advance by means of only collecting cervical and vaginal secretions of the pregnant woman and by using a non-invasive method.

Description

A method for predicting premature birth risk and delivery time and its application Technical Field

[0001] The present invention relates to the field of biomedicine, and in particular to protein markers associated with premature birth, methods for constructing premature birth risk assessment prediction models, prediction models, prediction systems, methods for predicting premature birth risk and delivery time, and related applications thereof. Background Art

[0002] Premature delivery (PTB) generally refers to childbirth between 28 and 37 weeks of gestation. Newborns born at this time are called premature babies. Existing data show that the number of premature babies worldwide has reached and exceeded 1 / 10 of the total number of newborns. At the same time, the younger the gestational age, the lower the survival rate of premature babies. Premature babies have an increased risk of illness due to immature organ systems and low resistance. Premature birth is also the leading cause of death in children under 5 years old. Therefore, researchers have been committed to actively studying premature birth prediction methods during pregnancy and developing effective premature birth prediction products to intervene in premature birth outcomes.

[0003] In 1995, the U.S. Food and Drug Administration (FDA) approved the Rapid fFN Test, a test kit developed by Hologic, Inc., for predicting the risk of preterm birth. This patent (EP1936376B1) describes the use of fetal fibronectin (fFN) protein levels in maternal body fluids (urine, whole blood, plasma, saliva, or cervical or vaginal secretions) between 20 and 36 weeks of gestation to predict the risk of preterm birth. Research results show that this method, which measures fFN, has a sensitivity of 83.3% and a specificity of 84.2% for predicting delivery within 14 days in patients at high risk of preterm birth, with negative and positive predictive values ​​of 99.4% and 14.6%, respectively. While this method has an excellent negative predictive value, meaning it accurately predicts women who will not deliver preterm, only 14.6% of women predicted to deliver preterm, resulting in a high false-positive rate and limited clinical utility.

[0004] In 1999, OY MEDIX BIOCHEMICA AB launched the Actim PROM Test, a test kit used to predict the risk of preterm birth or determine imminent delivery. A negative test result clearly indicates that the patient will not deliver within 7-14 days. This patent (WO1999058974A1) assesses cervical ripening and, therefore, the risk of preterm delivery by detecting phosphorylated insulin-like growth factor binding protein 1 (phIGFBP-1) in cervicovaginal secretions. Research results show that this method, which measures phIGFBP1, has a sensitivity of 71.8% and a specificity of 75.3% for predicting delivery within 14 days in patients at high risk of preterm birth, with negative and positive predictive values ​​of 95.9% and 24.8%, respectively. This method also performs well in terms of negative predictive value, with an accuracy of 95.9% for predicting term delivery. However, only 24.8% of women predicted to deliver preterm actually deliver, resulting in a high false-positive rate and limited clinical utility.

[0005] In 2021, Sera Prognostics, Inc. launched the PreTRM Test, which is used to detect two proteins in the blood of pregnant women: insulin-like growth factor-binding protein 4 (IBP4) and sex hormone-binding globulin (SHBG) to predict the gestational age of delivery and the risk of premature birth. This patent (CN108450003B) predicts the gestational age of delivery and the risk of premature birth in pregnant women by the ratio of the two proteins, IBP4 / SHBG. Specifically, the technology uses two protein markers in pregnant women's blood samples to construct a prediction model through the ratio of the two (IBP4 / SHBG), but the performance of the constructed model is AUC of 0.75 in the validation set, and the prediction performance is poor. In addition, the prediction model needs to limit the prediction objects of pregnant women with a BMI between 22-37 and a gestational age of 19-21 weeks. Therefore, this technical method needs to further improve its predictive performance before it can be used in clinical practice.

[0006] Therefore, whether it is setting protein marker thresholds to predict the risk of premature birth, or using protein markers as input to build a risk prediction model, although multi-field research and exploration have been carried out on premature birth in existing technologies, the actual application effect of current research results is still insufficient, and the clinical prediction performance still needs to be improved. Summary of the Invention

[0007] Through in-depth and systematic research on the proteomic data of cervicovaginal secretion samples from pregnant women with spontaneous preterm birth and full-term birth, the present invention discovered several protein markers with predictive value for premature birth and applied them to the prediction of premature birth risk. It also developed a new method for constructing a premature birth risk assessment prediction model, a method for predicting premature birth risk and delivery time, and related applications.

[0008] The present invention has discovered several protein markers associated with preterm birth for the first time and applied them to the field of preterm birth prediction for the first time. These protein markers include: Lumican (LUM), β-2-microglobulin (B2M), and α1-microglobulin (AMBP). The present invention also discovered several combinations of LUM, B2M, AMBP, metalloproteinase inhibitor 1 (TIMP1), and fibronectin 1 (FN1), such as combinations comprising one or at least two of these protein markers, for use in the prediction of preterm birth.

[0009] As one application, in a first aspect, the present invention provides the application of the above-mentioned protein markers and different combinations thereof in constructing a premature birth risk assessment prediction model.

[0010] In the second aspect, the present invention provides a method for constructing a premature birth risk prediction model based on the protein markers in the first aspect, that is, using data of at least one protein marker among basement membrane polysaccharide, β2 microglobulin, α1 microglobulin, metalloproteinase inhibitor 1 and fibronectin 1 of pregnant women as modeling factors to construct a prediction model, and the pregnant women participating in the model construction include pregnant women who have premature births and pregnant women who have full-term births.

[0011] In a third aspect, based on the prediction model obtained in the second aspect, the present invention provides a method for assessing and predicting the risk of premature birth, the method comprising:

[0012] 1) obtaining data on at least one protein marker selected from the group consisting of basement membrane glycan, β2 microglobulin, α1 microglobulin, metalloproteinase inhibitor 1, and fibronectin 1 of the pregnant woman to be tested;

[0013] 2) Inputting the obtained data of at least one protein marker of basement membrane polysaccharide, β2 microglobulin, α1 microglobulin, metalloproteinase inhibitor 1 and fibronectin 1 of the above-mentioned pregnant woman into the prediction model for processing to obtain the risk value of premature birth of the above-mentioned pregnant woman. When the risk value is higher than the set threshold, the pregnant woman is determined to be at high risk of premature birth.

[0014] In a specific embodiment of the present invention, data on basement membrane glycan, β2 microglobulin, α1 microglobulin, metalloproteinase inhibitor 1, and fibronectin 1 are obtained from a pregnant woman to be tested. The obtained data on basement membrane glycan, β2 microglobulin, α1 microglobulin, metalloproteinase inhibitor 1, and fibronectin 1 are input into a prediction model for processing to obtain a risk value for premature birth for the pregnant woman to be tested. The prediction model parameters are related to factors such as the model construction method and the protein quantitative detection method (platform).

[0015] In a fourth aspect, based on the prediction method of the third aspect, the present invention provides a prediction system for premature birth risk assessment, the system comprising:

[0016] 1) a device for acquiring data on at least one protein marker selected from the group consisting of basement membrane glycan, β2 microglobulin, α1 microglobulin, inhibitor of metalloproteinase 1, and fibronectin 1 of a pregnant woman to be tested;

[0017] 2) a device for performing prediction model processing on the data of at least one protein marker of basement membrane glycan, β2 microglobulin, α1 microglobulin, metalloproteinase inhibitor 1, and fibronectin 1 of the pregnant woman obtained in 1);

[0018] 3) A device for outputting prediction results.

[0019] In a fifth aspect, the present invention provides a product for predicting and assessing the risk of premature birth, comprising: a memory and a processor. The memory is configured to store a program; the processor is configured to execute the program stored in the memory to implement the method for predicting and assessing the risk of premature birth as described in the third aspect.

[0020] At the same time, the present invention also provides a computer-readable storage medium, on which a program is stored, and the program can be executed by a processor to implement the premature birth risk assessment and prediction method mentioned in the third aspect above.

[0021] In addition, the present invention also provides a computer-readable storage medium, which stores the prediction model obtained by the construction method of the second aspect.

[0022] In addition to the above-mentioned construction of a premature birth risk assessment and prediction model through protein markers, in the sixth aspect, the present invention also provides another application of the above-mentioned protein markers: predicting the risk of premature birth by detecting protein markers in pregnant women's samples and judging by threshold values, for example, after detecting LUM and / or TIMP1, comparing them with predetermined thresholds, and judging whether the pregnant woman has a risk of premature birth based on the comparison results.

[0023] Specifically, in a specific embodiment of the present invention, the above-mentioned predetermined threshold value is a LUM protein concentration of 5.19 ng / ml and / or a TIMP1 protein concentration of 14.81 ng / ml. In some embodiments, when the protein concentration of LUM protein in the pregnant sample is detected alone, when the LUM protein concentration obtained by the pregnant sample detection exceeds 5.19 ng / ml, it is predicted that the pregnant woman has a risk of premature birth or a high risk of premature birth. In some embodiments, when the protein concentration of TIMP1 protein in the pregnant sample is detected alone, when the TIMP1 protein concentration obtained by the pregnant sample detection exceeds 14.81 ng / ml, it is predicted that the pregnant woman has a risk of premature birth or a high risk of premature birth. In some embodiments, when the protein concentration of LUM and TIMP1 in the pregnant sample is detected simultaneously, when the LUM protein concentration obtained by the pregnant sample detection exceeds 5.19 ng / ml or the TIMP1 protein concentration exceeds 14.81 ng / ml (i.e., at least one of the two proteins exceeds its predetermined threshold value), it is predicted that the pregnant woman has a risk of premature birth or a high risk of premature birth. In some embodiments, when the protein concentrations of LUM and TIMP1 in a pregnant woman's sample are simultaneously tested, when the LUM protein concentration detected in the pregnant woman's sample exceeds 5.19 ng / ml and the TIMP1 protein concentration exceeds 14.81 ng / ml, it is predicted that the pregnant woman has a risk of premature birth or a high risk of premature birth.

[0024] At the same time, the above-mentioned application also includes determining whether a pregnant woman will experience premature delivery within a predetermined time frame, that is, after detecting LUM and / or TIMP1 in a pregnant woman's sample, comparing them with a predetermined threshold value, and judging whether the pregnant woman's delivery time is within the predetermined time frame based on the comparison result. Therefore, the present invention also provides the application of LUM and / or TIMP1 as protein markers in predicting the time of delivery. Specifically, the above-mentioned application is achieved by detecting LUM and / or TIMP1 in a pregnant woman's sample, comparing them with a predetermined threshold value, and judging whether the pregnant woman will give birth within the predetermined time frame based on the comparison result. In a specific embodiment of the present invention, the above-mentioned predetermined threshold value is a LUM protein concentration of 5.19 ng / ml and / or a TIMP1 protein concentration of 14.81 ng / ml. In some embodiments, when the protein concentration of LUM protein in the pregnant woman's sample is detected separately, when the LUM protein concentration obtained by the pregnant woman's sample detection exceeds 5.19 ng / ml, it is predicted that the pregnant woman will give birth within the predetermined time frame. In some embodiments, when the protein concentration of TIMP1 protein in the pregnant woman's sample is detected alone, when the TIMP1 protein concentration obtained by the pregnant woman's sample detection exceeds 14.81 ng / ml, it is predicted that the pregnant woman will give birth within a predetermined time frame. In some embodiments, when the protein concentration of LUM and TIMP1 in the pregnant woman's sample is detected simultaneously, when the LUM protein concentration obtained by the pregnant woman's sample detection exceeds 5.19 ng / ml or the TIMP1 protein concentration exceeds 14.81 ng / ml (i.e., at least one of the two proteins exceeds its predetermined threshold value), it is predicted that the pregnant woman will give birth within a predetermined time frame. In some embodiments, when the protein concentration of LUM and TIMP1 in the pregnant woman's sample is detected simultaneously, when the LUM protein concentration obtained by the pregnant woman's sample detection exceeds 5.19 ng / ml and the TIMP1 protein concentration exceeds 14.81 ng / ml, it is predicted that the pregnant woman will give birth within a predetermined time frame. In some specific embodiments, the above-mentioned predetermined time frame is 1 week (7 days) and / or 2 weeks (14 days).

[0025] In the seventh aspect, based on the detection results of protein markers, the present invention provides a method for predicting the risk of premature birth, which includes: detecting LUM and / or TIMP1 in pregnant women's samples, comparing the concentration value obtained after the detection with a predetermined threshold, and determining that the pregnant woman has a risk of premature birth or a high risk of premature birth if the concentration value is higher than the predetermined threshold.

[0026] In the eighth aspect, similar to the seventh aspect above, the present invention provides a method for predicting the time of delivery, which includes: detecting LUM and / or TIMP1 in a pregnant woman's sample, comparing the concentration value obtained after the detection with a predetermined threshold, and determining that the pregnant woman will give birth within a predetermined time frame if the concentration value is higher than the predetermined threshold.

[0027] In a ninth aspect, the present invention provides a detection kit for protein markers related to premature birth, wherein the protein markers detected by the kit are at least one of basement membrane polysaccharide, β2 microglobulin, α1 microglobulin, metalloproteinase inhibitor 1 and fibronectin 1.

[0028] In some specific embodiments, the present invention provides a premature birth prediction kit based on the prediction method of the seventh aspect, wherein the kit comprises an antibody for detecting LUM and / or an antibody for detecting TIMP1.

[0029] In a tenth aspect, the present invention provides a delivery time prediction kit based on the prediction method of the eighth aspect, wherein the kit comprises an antibody for detecting LUM and / or an antibody for detecting TIMP1.

[0030] The present invention has the beneficial effect of identifying multiple protein markers associated with preterm birth for the first time, providing new test targets for more accurate prediction of preterm birth risk. The protein markers provided by the present invention and their detection enable non-invasive prediction of preterm birth risk and delivery time, one to two weeks in advance, requiring only the collection of cervicovaginal secretions from pregnant women. Furthermore, the present invention determined that when the LUM protein concentration in the supernatant of vaginal secretions exceeds a set threshold of 5.19 ng / ml, the risk of preterm birth is predicted, with a positive predictive value of 43.01% for delivery within one week and 46.24% for delivery within two weeks. Furthermore, the threshold for predicting delivery within one or two weeks for TIMP1 is set at 14.81 ng / ml. When the concentration of at least one of the LUM and TIMP1 proteins exceeds the set threshold, i.e., a positive LUM+TIMP1 test, the positive predictive value for predicting delivery within one or two weeks is 40.59% and 43.56% respectively. These results demonstrate that LUM protein and LUM+TIMP1 alone are more accurate in predicting premature delivery within one and two weeks than other existing protein markers, such as FN1 protein. This will significantly improve the accuracy of predicting premature birth and delivery time, helping clinicians to take timely intervention measures to reduce the incidence of premature birth and its associated adverse outcomes.

[0031] At the same time, based on the protein markers and their combinations obtained by screening, the premature birth risk prediction model constructed by the present invention in 426 samples has an accuracy significantly higher than the existing technology. Its internal validation set AUC = 0.95, and the two external validation sets are 0.90 and 0.92 respectively. The predicted specificity is 96.4±0.0%, the sensitivity is 76.2±7.8%, the negative predictive value is 94.7±2.3% and the positive predictive value is 80.0%±12.7%.

[0032] In addition, the prediction model provided by the present invention can predict the risk of premature birth as early as 25 weeks of pregnancy and up to 9 weeks in advance, and the risk of premature birth can be predicted in advance using a non-invasive method by simply collecting cervical and vaginal secretions from pregnant women. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] FIG1 is a trend data graph for determining the number of proteins required for the model in Example 1 of the present invention, wherein FIGA represents the median value of the performance (AUC) of all models at a specific number of proteins, and FIGB represents the maximum value of the performance (AUC) of all models at a specific number of proteins;

[0034] FIG2 shows the performance data of the prediction model constructed in Example 1 of the present invention on the internal validation set and the external validation set;

[0035] FIG3 is a schematic diagram showing the results of the enzyme-linked immunosorbent assay and fluorescent immunochromatographic method for verifying the trend control of five markers in Example 1 of the present invention, wherein PTB represents premature birth and Ctr represents a normal control;

[0036] Figure 4 is a graph showing the differential expression distribution of LUM, TIMP1, and FN1 proteins in different data sets in Example 4 of the present invention, wherein Figure 4A shows the differential expression distribution of LUM, TIMP1, and FN1 proteins between the TTD < 1 week and TTD > 1 week groups in the training set; Figure 4B shows the differential expression distribution of LUM, TIMP1, and FN1 proteins between the TTD < 2 weeks and TTD > 2 weeks groups in the training set; Figure 4C shows the differential expression distribution of LUM, TIMP1, and FN1 proteins between the TTD < 1 week and TTD > 1 week groups in the validation set; and Figure 4D shows the differential expression distribution of LUM, TIMP1, and FN1 proteins between the TTD < 2 weeks and TTD > 2 weeks groups in the validation set;

[0037] Figure 5 shows the prediction effects of LUM, TIMP1, and FN1 proteins in screening for premature birth risk and delivery time in Example 4 of the present invention; Figure 5A shows the AUC comparison of LUM, TIMP1, and FN1 proteins in the training set for predicting premature birth within TTD <1 week, Figure 5B shows the AUC comparison of LUM, TIMP1, and FN1 proteins in the training set for predicting premature birth within TTD <2 weeks, Figure 5C shows the AUC comparison of LUM, TIMP1, and FN1 proteins in the validation set for predicting premature birth within TTD <1 week, and Figure 5D shows the AUC comparison of LUM, TIMP1, and FN1 proteins in the validation set for predicting premature birth within TTD <2 weeks. DETAILED DESCRIPTION

[0038] Proteins, as core executors of life, have the potential to profoundly reflect the physiological changes in maternal-fetal interactions during pregnancy and serve as biomarkers for predicting preterm birth. Numerous studies based on serum and vaginal secretions have identified several protein markers for predicting preterm birth, including fetal fibrinectin (fFN), phosphorylated isoform of insulin-like growth factor binding protein-1 (phIGFBP-1), and placental alpha-microglobulin-1 (PAMG-1). fFN, a gap junction glycoprotein found in cervical or vaginal secretions, functions as an "adhesive" that maintains the connection between the chorion and decidua. Detection of fFN in vaginal secretions indicates disruption of the connection between the chorion and decidua, thus serving as a biomarker for impending labor. PhIGFBP-1 is primarily synthesized in decidual cells. When threatened preterm labor or premature labor is accompanied by uterine contractions, the decidua separates from the chorion, resulting in the release of phIGFBP-1 into the cervical mucus, which can be used to predict the risk of preterm birth. Similarly, PAMG-1 is a fetal glycoprotein secreted by decidual cells into the amniotic fluid. Its concentration in the blood is low, and when the fetal membranes are intact, PAMG-1 concentrations in cervicovaginal secretions are extremely low. Therefore, PAMG-1 can be used as a marker for detecting premature rupture of membranes. Existing studies have shown that the negative predictive values ​​of fFN, phIGFBP-1, and PAMG-1 for predicting preterm birth within seven days of threatened preterm labor are quite reliable, at 87%-98%, 98%-99%, and 96%-98%, respectively. However, their positive predictive values ​​are relatively low, at 8%-34%, 19%-35%, and 35%-76%, respectively. This has limited the widespread clinical application of these protein biomarkers. Therefore, developing more accurate methods for predicting premature birth and delivery time to achieve early and accurate prediction of premature birth and early intervention remains an unresolved clinical pain point.

[0039] Based on the limitations of the existing technology, the present invention uses the differences in protein expression levels in cervical and vaginal secretions to find protein markers for risk prediction before the occurrence of premature birth diseases. On the one hand, it is suitable for screening when there are early signs of premature birth, especially for pregnant women at high risk of premature birth in the middle and late stages of pregnancy (with a history of premature birth, multiple miscarriages, cervical dilation ≤3cm or premature symptoms such as uterine contractions, intermittent lower abdominal pain and pelvic pressure, and meeting one of the above conditions). Premature birth disease risk is predicted in advance using a non-invasive method, and a premature birth risk prediction model is constructed to achieve high-accuracy premature birth risk prediction. On the other hand, when predicting the risk of premature birth for all pregnant women in the middle and late stages of pregnancy (suitable for universal screening or screening when there are early signs of premature birth), accurate prediction of premature birth risk and delivery time can be achieved by directly detecting one or more of these protein markers and then performing threshold judgment.

[0040] First, the present invention systematically analyzed the protein expression profiles in maternal cervicovaginal secretions during pregnancy, comparing the differential protein expression profiles of cervicovaginal secretions between women experiencing spontaneous preterm birth and those who delivered at term. This method, from a diverse range of proteins, identified protein markers associated with the prediction of preterm birth. This expanded the range of protein markers associated with preterm birth, laying the foundation for the subsequent development of more accurate preterm birth risk prediction models and applications such as direct threshold determination based on protein marker detection. Furthermore, the analysis of proteins in cervicovaginal secretions revealed the value of different protein types in cervicovaginal secretions in predicting preterm birth. Among them, LUM, B2M, and AMBP were discovered for the first time by the present invention to be associated with preterm birth and could serve as protein markers for preterm birth, a finding not previously reported. Furthermore, the present invention proposes the application of one or more combinations of LUM, B2M, AMBP, TIMP1, and FN1 in the field of preterm birth prediction. Table 1 lists the aforementioned protein markers and their clinical significance.

[0041] Table 1 Protein markers and their clinical significance

[0042] The above-mentioned protein markers LUM, B2M, AMBP, TIMP1, and FN1 can be detected by various methods, such as protein arrays, proteomics, expression proteomics, mass spectrometry (e.g., liquid chromatography-mass spectrometry (LC-MS), multiple reaction monitoring (MRM), selected reaction monitoring (SRM), scheduled MRM, scheduled SRM, 2D PAGE, 3D PAGE, electrophoresis, proteome chips, proteome microarrays, Edman degradation, direct or indirect ELISA, immunosorbent assay, immuno-PCR, proximity extension assay, Luminex assay or homogenization assay, time-resolved fluorescence (TRF), fluorescent oxygen channeling immunoassay (FOCI) or luminescent oxygen channeling immunoassay), targeted protein detection techniques such as liquid chromatography-mass spectrometry, chemiluminescence immunoassay, and fluorescent immunoassay, all of which can produce similar detection results.

[0043] In addition, in addition to the above-mentioned protein markers themselves being used as detection objects in the prediction of premature birth, the expression levels or transcriptome information of the genes corresponding to these proteins can also be detected and applied to the prediction of premature birth. Therefore, the application of the above-mentioned protein markers in the prediction of premature birth involves multiple aspects and different forms. For example, such an application can be a kit for accurately detecting the above-mentioned protein markers, or a related reagent for analyzing the transcriptome of the above-mentioned protein markers, etc. At the same time, it can also be to combine these detection or analysis results and use machine learning to construct a premature birth risk prediction model and perform risk prediction. The gene information of the above-mentioned protein markers is shown in Table 2.

[0044] Table 2 Biological information of protein markers

[0045] Regarding the detection of the aforementioned protein markers, in one embodiment of the present invention, protein extraction is performed on cervicovaginal secretions obtained from pregnant women. It should be understood that in addition to cervicovaginal secretions, extraction, detection, and analysis of relevant protein markers or their transcriptomes can also be performed on other sample types, such as whole blood, plasma, amniotic fluid, serum, and urine.

[0046] Secondly, the present invention utilizes the above-mentioned protein markers and their different combinations to construct a model for predicting the risk of premature birth. The construction method includes: obtaining relevant data of at least one protein marker among basement membrane polysaccharide, β2 microglobulin, α1 microglobulin, metalloproteinase inhibitor 1 and fibronectin 1 of pregnant women as relevant modeling factors, and constructing a training sample set with these modeling factors and their corresponding pregnant women, and the above-mentioned pregnant women include pregnant women with premature birth and pregnant women with full-term birth. Based on the above-mentioned training sample set, several types of model training are performed, and the several types of models after training are verified and evaluated, and the best prediction model is confirmed according to the model evaluation indicators. It should be understood that the above-mentioned prediction model can usually be evaluated by multiple indicators such as accuracy, precision, ROC curve, AUC, etc., and the best prediction model is confirmed according to the aforementioned indicators.

[0047] In a specific embodiment of the present invention, the above-mentioned construction method includes:

[0048] 1) Determine the model training set samples and internal validation set samples, both of which include pregnant women with preterm births and pregnant women with full-term births;

[0049] 2) using at least one protein marker of basement membrane glycan, β2-microglobulin, α1-microglobulin, metalloproteinase inhibitor 1, and fibronectin 1 from pregnant women in the above model training set as features, a prediction model was constructed using the logistic regression method. The model construction used a 5-fold cross-validation grid search method to automatically adjust the model parameters to obtain the optimized prediction model;

[0050] 3) Use the above internal validation set samples to evaluate the performance of the prediction model in 2).

[0051] After obtaining the above prediction model, we can further use independent verification samples to independently evaluate the performance of the above optimal prediction model.

[0052] Those skilled in the art will appreciate that, in addition to constructing a predictive model using the aforementioned logistic regression method, one can also utilize data from at least one of the aforementioned pregnant women's LUM, B2M, AMBP, TIMP1, and FN1 as input, with the outcome of whether the pregnant woman experienced premature birth, to construct a model using machine learning, deep learning, or artificial intelligence models to obtain a model for assessing and predicting the risk of premature birth. The algorithm or model type used to construct the predictive model does not constitute a limitation of the present invention. In fact, the aforementioned protein markers and their combinations in the present invention have demonstrated excellent predictive effectiveness in models constructed using a variety of different algorithms.

[0053] In a specific embodiment of the present invention, the above-mentioned construction method includes:

[0054] 1) Determine the model training set samples and internal validation set samples, both of which include pregnant women with preterm births and pregnant women with full-term births;

[0055] 2) using at least one protein marker of basement membrane glycan, β2 microglobulin, α1 microglobulin, metalloproteinase inhibitor 1, and fibronectin 1 from the pregnant women in the above model training set samples as features, and constructing a prediction model using a random forest algorithm;

[0056] 3) Use the above internal validation set samples to evaluate the performance of the prediction model in 2).

[0057] After obtaining the above prediction model, we can further use independent verification samples to independently evaluate the performance of the above prediction model.

[0058] In a specific embodiment of the present invention, the above-mentioned construction method includes:

[0059] 1) Determine the model training set samples and internal validation set samples, both of which include pregnant women with preterm births and pregnant women with full-term births;

[0060] 2) using at least one protein marker of basement membrane glycan, β2 microglobulin, α1 microglobulin, metalloproteinase inhibitor 1, and fibronectin 1 from pregnant women in the above model training set samples as features, and constructing a prediction model using a neural network algorithm;

[0061] 3) Use the above internal validation set samples to evaluate the performance of the prediction model in 2).

[0062] After obtaining the above prediction model, we can further use independent verification samples to independently evaluate the performance of the above prediction model.

[0063] It should be noted that the above description mentioned that LUM, B2M, AMBP, TIMP1 and FN1 and their corresponding various combinations can be fully utilized in model construction to carry out specific model construction, so that multiple groups of different prediction models can be obtained, and multiple groups of different ROC curves (Receiver operating characteristic curve, ROC) can also be obtained. According to different ROC curves, the sensitivity, specificity, positive predictive value and negative predictive value of each model for predicting preterm birth can be calculated respectively, and the optimal model can be selected.

[0064] In one embodiment of the present invention, the threshold is the threshold at which the Youden Index (Youden Index = sensitivity + specificity) is maximized. It should be understood that other methods—model evaluation indicators of the prediction model—can also be used to determine the threshold, such as setting the threshold based on a specific model specificity.

[0065] It should be understood that after the model is constructed by the above method, when performing premature birth risk assessment and prediction, the combination of protein markers used by the corresponding model inputs the data of LUM, B2M, AMBP, TIMP1 and FN1 of the pregnant woman to be tested into the prediction model, and the model can automatically calculate the risk value, and evaluate the premature birth risk as high risk, medium risk and low risk according to the risk value.

[0066] Furthermore, in addition to the above-mentioned method of constructing a model for prediction, the present invention also provides a method for directly performing threshold determination using the test results of protein markers. In the present invention, after in-depth research, it was found that when one or both of LUM and TIMP1 are combined, the risk of premature birth and delivery time can be directly predicted by detecting their concentrations, and the positive predictive value of this prediction is surprisingly much higher than the positive predictive value of other protein marker threshold determinations in the prior art, demonstrating the important value of this protein marker and its combination in the field of premature birth prediction. The above two proteins can also further predict delivery time. Herein, "delivery time (TTD)" is the total length of time from a predetermined starting time point (e.g., the time when a patient shows potential signs of premature birth, which refers to the sampling time in the present invention) until the patient delivers their fetus. TTD can be defined as "within a predetermined time frame," for example, within about 7 or 14 days from the time the prediction is made. As used herein, "predicted delivery time (predicted TTD)" means determining the possibility of delivery within a predetermined time frame (e.g., within 7 or 14 days). In some aspects, predicting TTD includes determining that spontaneous premature birth before the due date is highly likely within a predetermined time point. In some aspects, predicting TTD includes excluding spontaneous premature birth before the due date within a predetermined time point (i.e., determining that spontaneous premature birth before the due date is highly unlikely within a predetermined time frame). "Preterm birth" is defined herein as delivery before 37 weeks of gestational age. Therefore, the gestational age of pregnant women to whom the above-mentioned premature birth prediction method using LUM and / or TIMP1 and the delivery time prediction method are applicable is 20-36 weeks. +6 In addition, the gestational age of pregnant women suitable for the above method can also be 20-33 weeks. +6 Week, 20-34 +6 Week, 20-35 +6 week.

[0067] As noted above, LUM and TIMP1 proteins can be obtained from maternal samples, preferably cervicovaginal secretions. It should be understood that other samples, such as whole blood, plasma, amniotic fluid, serum, and urine, can also be used as samples to obtain the relevant proteins. Furthermore, quantitative detection of LUM and TIMP1 proteins can be performed using the various methods mentioned above. Considering the convenience, cost, and time of the test, ELISA enzyme-linked immunosorbent assay (ELISA) is preferred in the present invention for detecting protein concentrations in samples.

[0068] Based on the above-mentioned LUM and TIMP1 proteins, the method for predicting the risk of premature birth provided by the present invention comprises: obtaining LUM and / or TIMP1 in a pregnant woman's sample, performing a concentration test on the LUM and / or TIMP1, comparing the protein concentration value obtained after the test with a predetermined threshold value, and if the protein concentration value is higher than the predetermined threshold value, the pregnant woman is judged to have a risk of premature birth or a high risk of premature birth. Otherwise, the pregnant woman is judged to have no risk of premature birth or a low risk of premature birth. The above-mentioned predetermined threshold value is a LUM protein concentration of 5.19 ng / ml and / or a TIMP1 protein concentration of 14.81 ng / ml. Specifically, in some embodiments, the LUM protein in the pregnant woman's sample is obtained separately and a concentration test is performed. When the LUM protein concentration obtained by the pregnant woman's sample test exceeds 5.19 ng / ml, it is predicted that the pregnant woman has a risk of premature birth or a high risk of premature birth. On the contrary, when the LUM protein concentration does not exceed 5.19 ng / ml, the pregnant woman has no risk of premature birth or a low risk of premature birth. Alternatively, in some embodiments, TIMP1 protein is obtained from a pregnant sample alone and a concentration test is performed. When the TIMP1 protein concentration obtained from the pregnant sample exceeds 14.81 ng / ml, the pregnant woman is predicted to have a risk of premature birth or a high risk of premature birth. Conversely, when the TIMP1 protein concentration obtained from the pregnant sample does not exceed 14.81 ng / ml, the pregnant woman is not at risk of premature birth or has a low risk of premature birth. In some embodiments, LUM and TIMP1 proteins are obtained from a pregnant sample simultaneously and a concentration test is performed. When the LUM protein concentration obtained from the pregnant sample exceeds 5.19 ng / ml or the TIMP1 protein concentration exceeds 14.81 ng / ml (i.e., at least one of the two proteins exceeds its predetermined threshold), the pregnant woman is predicted to have a risk of premature birth or a high risk of premature birth. Alternatively, LUM and TIMP1 proteins are obtained from a pregnant sample simultaneously and a concentration test is performed. When the LUM protein concentration obtained from the pregnant sample exceeds 5.19 ng / ml and the TIMP1 protein concentration exceeds 14.81 ng / ml, the pregnant woman is predicted to have a risk of premature birth or a high risk of premature birth.

[0069] Based on the aforementioned LUM and TIMP1 proteins, the present invention also provides a TTD prediction method, comprising: obtaining LUM and / or TIMP1 from a pregnant woman's sample, testing their concentrations, and comparing the protein concentrations obtained with a predetermined threshold. If the concentrations exceed the predetermined thresholds, it is determined that the pregnant woman will give birth within a predetermined timeframe; otherwise, it is determined that the pregnant woman will not give birth. The predetermined thresholds are a LUM protein concentration of 5.19 ng / ml and / or a TIMP1 protein concentration of 14.81 ng / ml. Specifically, in some embodiments, LUM protein is obtained from a pregnant woman's sample and tested for concentration. If the LUM protein concentration obtained from the sample exceeds 5.19 ng / ml, it is predicted that the pregnant woman will give birth within the predetermined timeframe. Otherwise, it is determined that the pregnant woman will not give birth within the predetermined timeframe. Alternatively, in some embodiments, TIMP1 protein is obtained from a pregnant woman's sample and tested for concentration. If the TIMP1 protein concentration obtained from the sample exceeds 14.81 ng / ml, it is predicted that the pregnant woman will give birth within the predetermined timeframe. On the contrary, when the TIMP1 protein concentration obtained from the pregnant woman's sample does not exceed 14.81 ng / ml, the pregnant woman will not give birth within the predetermined time frame. In some embodiments, the LUM and TIMP1 proteins in the pregnant woman's sample are obtained simultaneously and the concentration is detected. When the LUM protein concentration obtained from the pregnant woman's sample exceeds 5.19 ng / ml or the TIMP1 protein concentration exceeds 14.81 ng / ml (i.e., at least one of the two proteins exceeds its predetermined threshold value), it is predicted that the pregnant woman will give birth within the predetermined time frame. Further, in some embodiments, the LUM and TIMP1 proteins in the pregnant woman's sample are obtained simultaneously and the concentration is detected. When the LUM protein concentration obtained from the pregnant woman's sample exceeds 5.19 ng / ml and the TIMP1 protein concentration exceeds 14.81 ng / ml, it is predicted that the pregnant woman will give birth within the predetermined time frame. The above-mentioned predetermined time frame is 1 week (7 days) and / or 2 weeks (14 days).

[0070] The present invention will be further described in detail below through specific embodiments with reference to the accompanying drawings.

[0071] Example 1: Screening of protein markers and construction of a premature birth risk prediction model

[0072] 1. Sample acquisition

[0073] (1) Obtaining maternal cervicovaginal secretion samples

[0074] Cervicovaginal secretions were obtained from pregnant women at the hospital, including those who had both premature and full-term deliveries. Sampling method: Obstetricians used endoscopy to obtain samples. During the speculum examination, a sterile swab was placed in the posterior fornix of the vagina and allowed to soak for 30 seconds. When removing the swab, avoid touching other parts of the vagina. The swab was stored in a dry, sterile cryovial with the cap securely screwed on. It was temporarily stored at 4°C and transferred to -80°C for long-term storage within 8 hours. It was then transported on dry ice.

[0075] The above samples include a training set and an internal validation set (a total of 165 cases, 54 premature births and 111 full-term births). Specific information such as sample demographics and clinical characteristics is shown in Table 3.

[0076] Table 3 Demographic and clinical characteristics of the training set and internal validation set samples

[0077] (2) Extraction of protein from maternal cervicovaginal secretion samples

[0078] a. Break off the swab head and place it into a 2ml EP tube;

[0079] b. Add 500 μl of 1× phosphate buffer (PBS: 10 mmol / L Phosphate buffer; 137 mmol / L NaCl; 2.7 mmol / L KCl; pH 7.4) to the EP tube to wet the swab tip.

[0080] c. The vaginal secretion sample was resuspended in 1 ml of lysis buffer (1% SDS, 100 mM ABC pH 8.5) and lysed, and then sonicated on ice for 20 minutes;

[0081] d. The lysate was centrifuged and the supernatant was reduced and alkylated;

[0082] e. Take 200 μl of protein solution and add it to a 96-well plate containing 20 μl of Magnetic Sera-Mag Speed ​​Beads (containing 10 μl each of magnetic beads A and magnetic beads B). Add 200 μl of 100% acetonitrile (ACN) to each well and incubate for 20 minutes.

[0083] f. Place on a magnetic stand for 5 minutes, remove the supernatant, and wash the beads twice with 200 μl 80% ethanol (EtOH) and once with 200 μl 100% ACN.

[0084] g. Resuspend the beads in 50 μl of 100 mM ABC and sonicate in a water bath for 5 minutes. Add sequencing-grade trypsin (5 μl of 0.1 μg / μl trypsin dissolved in ddH2O) at a 1:20 enzyme:protein ratio and disperse the beads to ensure efficient digestion.

[0085] h. The samples were incubated overnight in a thermomixer at 37°C and 1000 rpm. The peptides bound to the beads were eluted with 2% ACN containing 0.1% FA, and the supernatant was collected in a new tube for LC-MS analysis.

[0086] 2. Acquisition of proteomic data

[0087] a. Using a capture column (Acclaim PepMap C18, 5 μm, The digested peptides were separated by Ultimate 3000 RSLC (Thermo Fisher Scientific, USA) with a diameter of 100 μm × 2 cm, and then the peptides were analyzed using a homemade C18 analytical column (1.8 μm, The outlet of the analytical column was directly connected to an Orbitrap Fusion Lumos Tribrid mass spectrometer (Thermo Fisher Scientific, USA).

[0088] b. For MS setup, the capillary temperature was set to 325°C. Data-independent acquisition (DIA) mode was used for protein quantification. Full-scan MS spectra were acquired in the Orbitrap over the mass range m / z 400–1,200 at a resolution of 60,000 FWHM.

[0089] c. The raw files were processed using DIA-NN (version 1.8.1). DIA-NN uses a protein sequence database (UniProt, UP000005640, 20431 proteins) to predict a spectral library, which was then used to search and quantify the DIA data. The precursor and protein FDRs were set to 1%.

[0090] 3. Screening of protein markers for the prediction of premature birth risk and construction of prediction models

[0091] 1) Preliminary filtering of mass spectrometry data: proteins with missing values ​​greater than 20% were eliminated.

[0092] 2) Preliminary screening of protein markers for the prediction of preterm birth risk: In a sample of 165 cases (54 preterm and 111 term), 3855 proteins identified by mass spectrometry were preliminarily screened using the Jackknifing and Elastic net (EN) algorithms. A total of 293 proteins were identified by the two methods as potentially predictive of preterm birth. The first method, using the Jackknifing method, identified a total of 264 biomarkers. The Jackknifing method employed 1000 repeated random samplings, each extracting 90% of the preterm and term samples. A statistical analysis of differences was performed, and the results of the 1000 differential analyses were pooled. The upper limit of the confidence interval of the 1000 corrected P values ​​was less than 0.05, and the up- and down-regulation trends of the 1000 identified proteins were the same. Based on these identification criteria, a total of 179 upregulated proteins and 85 downregulated proteins (a total of 264 proteins) were obtained. The second approach employed LOOCV (leave-on-out CV) cross-validation, combined with the EN (Elastic Net) algorithm, to evaluate the performance of the prediction model by screening different numbers of proteins. A total of 2, 3, 4, … 50 protein combinations were screened for predictive performance, and a total of 96 proteins were selected during model construction. Using these two methods, a total of 293 protein markers were initially identified (67 of which were found in both methods). To further narrow the selection, a corrected P value of less than 0.01 and an area under the AUROC curve of greater than 0.7 for each marker were used as thresholds. This resulted in a preliminary selection of 112 proteins as candidate protein markers.

[0093] 3) Protein Marker Combination Screening: To achieve optimal predictive performance using the fewest protein markers, this example further traverses all protein combinations (2, 3, 4…10 proteins) for the 112 candidate protein markers obtained in the previous step. Considering the potential for subsequent clinical translational applications, protein markers with commercially available antibodies (63) were prioritized in the combination process. The training set was divided into two parts: a model construction set and an internal validation set (model construction set: 27 preterm births and 56 term births, internal validation set: 27 preterm births and 55 term births). A predictive model was constructed using logistic regression. A 5-fold cross-validation grid search (GridSearchCV) method was used to automatically adjust the model parameters to obtain the optimal predictive model. Finally, model performance was evaluated in the internal validation set (using the area under the AUROC curve as the model prediction performance metric).

[0094] Analysis revealed that as the number of proteins in the prediction model increased, the model's prediction accuracy gradually increased. As shown in Figure 1, prediction performance gradually increased from one to five proteins, but continued addition of proteins plateaued, with no significant improvement in model performance beyond five proteins. This result suggests that the optimal number of proteins in the model is 4-5, providing a reference for determining the final number of protein combinations.

[0095] 4) Independent Validation of Model Predictive Performance: All samples were used in the above protein marker screening process, so using the internal validation set samples for model evaluation may have data information leakage issues. Therefore, this study used two completely independent external validation set samples (external validation set 1: 11 premature births and 116 full-term births; external validation set 2: 24 premature births and 110 full-term births) to independently evaluate the performance of the above model (a model constructed using any combination of the 63 protein markers with commercially available antibodies selected in 3) above). Ultimately, 42 protein combinations were screened out with AUROC greater than 0.9 in the training set, internal validation set, and external validation set. Specific information such as sample demographics and clinical characteristics of the external validation set samples is shown in Table 4. The relevant sample acquisition and protein extraction and testing were the same as those of the training set and internal validation set.

[0096] Table 4 Demographic and clinical characteristics of the external validation set samples

[0097] 5) Protein marker combination determination: The 42 protein combinations in 4) above were subjected to frequency statistics, and several frequently selected proteins were found. Among them, the top five proteins included LUM, TIMP1, FN1, B2M, and AMBP. These five protein markers were all shown to be upregulated in the differential expression analysis.

[0098] The above five proteins LUM, TIMP1, FN1, B2M and AMBP were used to construct the model using the same prediction model construction method as in the above 3) protein marker combination screening. The prediction performance of the models of different combinations in different data sets is shown in Table 5, where the area under the AUROC curve was used as the model prediction performance indicator.

[0099] Table 5 Prediction performance of various combinations of 5 protein markers

[0100] The prediction model constructed by the logistic regression method using five protein markers at the same time is as follows:

[0101] Risk of premature birth = 1 / (1+ea*AMBP+b*TIMP1+c*B2M+d*FN1+f*LUM-0.85);

[0102] Among them, LUM, B2M, AMBP, TIMP1 and FN1 are the charge-to-mass ratios of LUM, B2M, AMBP, TIMP1 and FN1 obtained by mass spectrometry detection of cervical and vaginal secretion samples of pregnant women, and the coefficients a, b, c, d and f are: a is 5.74e -4 , b is 5.48e -3 , c is 4.15e -3 , d is 1.76e -4 , f is 2.04e -4 .

[0103] The performance data of the above prediction model on the internal validation set and the external validation set are shown in Table 6 and Figure 2.

[0104] Table 6 AUC and specificity of the internal and external validation sets of the optimal model

[0105] 4. Validation of Marker Performance by Enzyme-Linked Immunosorbent Assay: Validation of the five protein markers using ELISA / fluorescent immunochromatography assays was conducted. The results were highly consistent with the mass spectrometry proteomics trend control data (as shown in Figure 3), showing that all markers were upregulated. Therefore, ELISA / fluorescent immunochromatography assays can be used for protein marker detection and application in predictive models.

[0106] The above experimental data show that the present invention uses the above five proteins as a feature combination, combined with a machine learning model, to predict the risk of premature birth as early as 25 weeks of gestation and up to 9 weeks in advance. For example, in the external validation of this embodiment, the risk of premature birth can be predicted based on the gestational age of 25 weeks. +6 A sample of a pregnant woman enrolled in the group at week 1 was tested for the relative concentrations of the above five proteins. Based on the risk prediction model, the risk value of premature birth for this pregnant woman was output (the model output value was 0.33, which was converted to a relative risk of 85%), indicating a high risk of premature birth. The follow-up outcome was that this pregnant woman was 34 +6 The model accurately predicted the risk of preterm birth in the 426-case external validation set, with an AUC of 0.93 for the training set, 0.95 for the internal validation set, and 0.90 and 0.92 for the external validation set, respectively. The specificity was 96.4±0.0% and the sensitivity was 76.2±7.8%.

[0107] Specifically, the preterm birth prediction model in this example achieved an AUC of 0.95, a specificity of 96.4%, a sensitivity of 85.2%, a negative predictive value (NPV) of 93.1%, and a positive predictive value (PPV) of 92.0% in the first internal validation set of 82 cases (27 preterm births and 55 healthy controls), which are higher than the state of the art. In a second, completely independent external validation set of 127 cases (11 preterm births and 116 healthy controls), the AUC was 0.90, with a specificity of 96.4%, a sensitivity of 72.7%, a negative predictive value (NPV) of 97.3%, and a positive predictive value (PPV) of 66.7%, which are also higher than the state of the art. In a third, completely independent external validation set of 134 cases (24 preterm births and 110 healthy controls), the AUC was 0.92, with a specificity of 96.4%, a sensitivity of 70.8%, a negative predictive value (NPV) of 93.8%, and a positive predictive value (PPV) of 81.0%, which are also higher than the state of the art.

[0108] In addition, those skilled in the art should understand that in addition to the above-mentioned construction of the prediction model using the logistic regression method, at least one of the data of LUM, B2M, AMBP, TIMP1 and FN1 of the pregnant women can be used as input, and whether the pregnant woman has premature birth is used as output. The model can be constructed through machine learning, deep learning or artificial intelligence model substitution to obtain a premature birth risk assessment prediction model, such as the following Examples 2 and 3.

[0109] Example 2

[0110] In this example, the same sample set as in Example 1 (including training set, internal validation set, external validation sets 1 and 2) was used, and the above-mentioned five proteins LUM, TIMP1, FN1, B2M and AMBP were used to construct a prediction model using the random forest algorithm. The prediction performance of the prediction models with different combinations in different data sets is shown in Table 7, where the area under the AUROC curve was used as the prediction performance indicator of the prediction model.

[0111] Table 7 Prediction performance of random forest model for multiple combinations of 5 protein markers

[0112] It can be seen from Table 7 that, similar to the results in Table 5, the AUCs of different combinations of the above five proteins LUM, TIMP1, FN1, B2M and AMBP in the internal validation set and external validation set of the prediction model constructed using the random forest algorithm are generally above 0.9, indicating that the random forest model constructed using different combinations of the five proteins LUM, TIMP1, FN1, B2M and AMBP in the present invention can effectively predict the risk of premature birth.

[0113] Example 3

[0114] In this example, the same sample set as in Example 1 (including training set, internal validation set, external validation sets 1 and 2) was used, and the above-mentioned five proteins LUM, TIMP1, FN1, B2M and AMBP were used to construct a prediction model using a neural network algorithm. The prediction performance of the prediction models with different combinations in different data sets is shown in Table 8, where the area under the AUROC curve was used as the prediction performance indicator of the prediction model.

[0115] Table 8 Prediction performance of neural network models for multiple combinations of 5 protein markers

[0116] It can be seen from Table 8 that, similar to the results in Tables 5 and 7, the different combinations of the above five proteins LUM, TIMP1, FN1, B2M and AMBP have AUCs in the internal validation set and the external validation set of the prediction model constructed using the neural network algorithm that are mostly above 0.9, indicating that the neural network model constructed using different combinations of the five proteins LUM, TIMP1, FN1, B2M and AMBP in the present invention can effectively predict the risk of premature birth.

[0117] Example 4

[0118] 1. Sample enrollment: This case was divided into two batches: mid- to late-pregnancy (20-36 +6 The first cohort included 80 women with symptoms of preterm birth or high-risk factors for preterm birth and 297 women at low risk for preterm birth. The second cohort included 133 women with symptoms of preterm birth or high-risk factors for preterm birth and 259 women at low risk for preterm birth. The first cohort served as the training set, while the second cohort served as the validation set. After enrollment, vaginal secretion samples were collected from the women, and clinical follow-up was conducted for three to six months to determine their final delivery time and clinical outcomes.

[0119] 2. Acquiring a cervicovaginal secretion sample is the same as step 1 in Example 1 ("(1) Acquiring a maternal cervicovaginal secretion sample" in "1. Acquiring a sample"). In this step, a sterile swab is placed in the posterior fornix of the vagina and allowed to remain there for 30 seconds until the swab is soaked. Alternatively, a sterile swab is placed in the posterior fornix of the vagina and applied to both side walls of the vaginal canal 3-5 times per side wall.

[0120] 3. Processing of vaginal secretion supernatant samples: Take out the swab from the -80℃ freezer and thaw it at room temperature; Use tweezers to move the swab into the EP tube, and add 500ul 1X PBS to the EP tube containing the swab; Invert and mix 10 times; Place the EP tube on a tube rack and put it into the ultrasonic instrument, place an empty sample box on the EP tube to press it down, and ultrasonicate at 40Hz for 10 minutes; Set the centrifuge to 4℃, place the EP tube containing the swab and PBS solution in the centrifuge, and centrifuge at 10,000rpm for 10 minutes; Transfer the supernatant to the EP tube, replacing a new gun tip each time; Put the EP tube containing the supernatant into a box and place it in the -80℃ freezer.

[0121] 4. Protein quantification: ELISA assays for LUM, TIMP1, and FN1 proteins were performed according to the instructions of the R&D company's LUM, TIMP1, and FN1 ELISA kits (catalog numbers DY2846-05, DTM100, and DFBN10, respectively).

[0122] Specifically, a microplate is coated with a purified human target protein capture antibody to form a solid-phase antibody. 100 μL of reference and test samples are added to the coated microwells in sequence and incubated at room temperature for 2 hours. 100 μL of detection antibody is added and incubated at room temperature for 2 hours. 100 μL of horseradish peroxidase-labeled streptavidin is added to form an antibody-antigen-enzyme-labeled antibody complex and incubated at room temperature for 20 minutes. After thorough washing, a substrate solution is added for color development and incubated at room temperature for 20 minutes. The reaction is terminated by adding a stop solution. The absorbance (OD value) is measured at a wavelength of 450 nm using a microplate reader, and the human target protein content in the sample is calculated using a standard curve.

[0123] 5. Sample Grouping: All enrolled women underwent final clinical follow-up. This study investigated the prediction of preterm birth risk and delivery time in the general population of pregnant women. The TTD < 1 and 2 weeks group refers to preterm women who delivered within 1 and 2 weeks of sampling; the TTD > 1 and 2 weeks group includes both preterm births (delivery greater than 1 and 2 weeks after sampling) and term births (gestational age interval between sampling and delivery greater than 1 and 2 weeks). Clinical information and sample sizes for each group are shown in Tables 9 and 10. The first batch of enrolled samples served as the training set to determine the optimal thresholds for LUM and FN1 protein prediction of delivery time. The second batch of samples served as the validation set to verify the accuracy of the two proteins in predicting preterm birth risk and delivery time.

[0124] It should be understood that in the present invention, the prediction of premature birth can be achieved through the prediction of TTD, so the prediction of the delivery time can also be understood as a more accurate time confirmation in the prediction of premature birth.

[0125] Table 9 Demographic and clinical characteristics of training and validation set samples

[0126] Table 10. Number of samples in the training and validation sets corresponding to different delivery time groups

[0127] 6. Expression Difference Analysis: Comparison of the expression distribution of FN1, TIMP1, and LUM proteins in different groups in the training and validation sets showed that the expression levels of LUM, TIMP1, and FN1 proteins in the TTD < 2 weeks group and TTD < 1 week group were significantly higher than those in the TTD > 2 weeks group and TTD > 1 week group, respectively (all P values ​​less than 0.01, Wilcoxon rank sum test, see Figure 4).

[0128] 7. Determination of the optimal threshold for predicting delivery time: In the training set, the AUCs for LUM protein in predicting preterm birth within one and two weeks of sampling were 0.88 and 0.89, respectively. In the validation set, the AUCs for LUM in predicting preterm birth within one and two weeks of sampling were 0.81 and 0.8, respectively. The screening AUCs were significantly higher than those for FN1 (P < 0.05, Delong test) (see Figure 5). The optimal thresholds for LUM and TIMP1 in predicting preterm birth within one and two weeks of sampling were determined based on the maximum Youden index. The threshold corresponding to the maximum Youden index is the protein concentration threshold at which the sum of sensitivity and specificity is maximized, and were 5.19 ng / ml and 14.81 ng / ml, respectively. The optimal thresholds for FN1 in predicting preterm birth within one and two weeks of sampling were 194.43 ng / ml and 222.51 ng / ml, respectively (see Tables 11-12).

[0129] Table 11. Comparison of the effectiveness of LUM and TIMP1 proteins in predicting premature birth within 1 week of sampling

[0130] Table 12. Comparison of the effectiveness of LUM and TIMP1 proteins in predicting premature birth within 2 weeks of sampling

[0131] 8. Comparison of the effectiveness of predicting premature birth risk and delivery time (see Table 11-12)

[0132] The accuracy of different proteins in the validation set in predicting delivery time within 1 week and 2 weeks of sampling was compared.

[0133] 1) The sensitivity, specificity, positive predictive value, and negative predictive value of LUM protein in the validation set for screening preterm birth within 1 week were all superior to those of FN1. When the cutoff value was set at 5.19 ng / ml, it indicated that pregnant women were at high risk of preterm birth and high risk of delivery within 1 week, with corresponding sensitivity, specificity, positive predictive value, and negative predictive value of 68.97%, 84.13%, 43.01%, and 93.98%, respectively.

[0134] At the same time, the TIMP1 protein concentration in the vaginal supernatant of pregnant women exceeded the set threshold of 14.81 ng / ml, indicating that the pregnant women were at high risk of premature birth and high risk of delivery within 1 week. The prediction accuracy is shown in Table 11.

[0135] 2) In the validation set, LUM protein screening demonstrated superior sensitivity, specificity, positive predictive value, and negative predictive value for preterm birth within 2 weeks compared to FN1. A cutoff of 5.19 ng / ml, indicating a high risk of preterm birth and delivery within 2 weeks, had corresponding sensitivity, specificity, positive predictive value, and negative predictive value of 66.15%, 84.71%, 46.24%, and 92.64%, respectively.

[0136] Similarly, when the TIMP1 protein concentration in the vaginal supernatant of pregnant women exceeds the set threshold of 14.81 ng / ml, it indicates that the pregnant women are at high risk of premature birth and high risk of delivery within 2 weeks. The prediction accuracy is shown in Table 12.

[0137] 3) When both LUM and TIMP1 protein concentrations exceeded the set thresholds, i.e., LUM+TIMP1 double positivity, the positive predictive values ​​for predicting delivery within 1 or 2 weeks were 90% and 95%, respectively; when either LUM or TIMP1 protein concentration exceeded the set thresholds (including TIMP1 positive and LUM negative, TIMP1 positive and LUM positive, TIMP1 negative and LUM positive), i.e., LUM+TIMP1 single positivity, the sensitivity for predicting delivery within 1 or 2 weeks was 70.69% and 67.69%, the specificity was 82.04% and 82.57%, and the positive predictive value was 40.59% and 43.56%, respectively; these results showed that LUM protein and LUM+TIMP1 single positivity were more accurate than FN1 protein in predicting premature delivery within 1 and 2 weeks, as shown in Tables 11-12.

[0138] The above examples are used to illustrate the present invention, which are only used to help understand the present invention and are not intended to limit the present invention. Those skilled in the art can make several simple deductions, modifications or substitutions based on the concept of the present invention.

Claims

1. Use of LUM and / or TIMP1 as protein biomarkers to predict preterm birth.

2. The use according to paragraph 1, including: detection of LUM and / or TIMP1 in a sample taken from a pregnant woman; comparing the detected LUM and / or TIMP1 value with a predetermined threshold value; and determining whether a pregnant woman is at risk of preterm birth based on the results of the comparison.

3. The use according to paragraph 1, including: detection of LUM and / or TIMP1 in a sample taken from a pregnant woman; comparing the detected LUM and / or TIMP1 value with a predetermined threshold value; and determining whether a pregnant woman's due date is within a predetermined time frame based on comparison results.

4. The use according to claim 2, wherein the predetermined threshold value is a LUM protein concentration of 5.19 ng / ml and / or a TIMP1 protein concentration of 14.81 ng / ml.

5. Use of LUM and / or TIMP1 as a protein biomarker for predicting the timing of delivery, including: detection of LUM and / or TIMP1 in a sample taken from a pregnant woman; comparing the detected LUM and / or TIMP1 value with a predetermined threshold value; and determining whether a pregnant woman's due date is within a predetermined time frame based on comparison results.

6. The use according to claim 5, wherein the predetermined threshold value is a LUM protein concentration of 5.19 ng / ml and / or a TIMP1 protein concentration of 14.81 ng / ml.

7. Use according to paragraph 3 or 5, wherein the specified period of time is 1 week and / or 2 weeks.

8. A method for predicting the risk of preterm birth, including: detection of LUM and / or TIMP1 in a sample taken from a pregnant woman; comparing the detected concentration value with a predetermined threshold value; and determining that a pregnant woman is at risk of preterm birth if the detected concentration value exceeds a predetermined threshold level.

9. The prediction method according to claim 8, wherein the predetermined threshold value is a LUM protein concentration of 5.19 ng / ml and / or a TIMP1 protein concentration of 14.81 ng / ml.

10. The method according to paragraph 9, wherein: LUM protein is detected in a sample taken from a pregnant woman and the pregnant woman is presumed to be at risk of preterm delivery if the concentration of LUM protein detected in the sample taken from the pregnant woman exceeds 5.19 ng / mL; or TIMP1 protein is detected in a sample taken from a pregnant woman and the pregnant woman is presumed to be at risk of preterm delivery if the concentration of TIMP1 protein detected in the sample taken from the pregnant woman exceeds 14.81 ng / mL; or LUM and TIMP1 proteins are detected in a sample collected from a pregnant woman and the pregnant woman is presumed to be at risk of preterm delivery if the concentration of the detected LUM protein in the sample collected from the pregnant woman exceeds 5.19 ng / mL or the concentration of the detected TIMP1 protein exceeds 14.81 ng / mL; or LUM and TIMP1 proteins are detected in a sample taken from a pregnant woman, and the pregnant woman is presumed to be at risk of preterm delivery if the concentration of the detected LUM protein in the sample taken from the pregnant woman exceeds 5.19 ng / mL and the concentration of the detected TIMP1 protein exceeds 14.81 ng / mL.

11. A method for predicting the timing of delivery, comprising: detecting LUM and / or TIMP1 in a sample taken from a pregnant woman; comparing the detected concentration value with a predetermined cutoff value; and determining that a pregnant woman's due date is within a predetermined time period if the detected concentration value exceeds a predetermined threshold level.

12. The prediction method according to claim 11, wherein the given threshold value is a LUM protein concentration of 5.19 ng / ml and / or a TIMP1 protein concentration of 14.81 ng / ml.

13. The forecasting method according to paragraph 12, in which: the LUM protein is detected in a sample taken from a pregnant woman and she is expected to give birth within a specified period of time if the concentration of the detected LUM protein in the sample taken from the pregnant woman is greater than 5.19 ng / mL; or TIMP1 protein is detected in a sample taken from a pregnant woman and the pregnant woman is predicted to give birth within a specified time period if the concentration of TIMP1 protein detected in the sample taken from the pregnant woman is greater than 14.81 ng / mL; or the pregnant woman's sample is found to contain both LUM and TIMP1 proteins and the pregnant woman is predicted to deliver within a specified time period if the concentration of the detected LUM protein in the pregnant woman's sample is greater than 5.19 ng / mL or the concentration of the detected TIMP1 protein is greater than 14.81 ng / mL; or The LUM and TIMP1 proteins are detected in a sample taken from a pregnant woman, and the pregnant woman is predicted to give birth within a specified time period if the concentration of the detected LUM protein in the sample taken from the pregnant woman is greater than 5.19 ng / mL and the concentration of the detected TIMP1 protein is greater than 14.81 ng / mL.

14. The forecasting method according to paragraph 11, wherein the specified period of time is 1 week and / or 2 weeks.

15. The use according to any of paragraphs 1-7 or the method of prediction according to any of paragraphs 8-14, wherein the gestational age is from 20 weeks to 36 weeks and 6 days, It is preferable that the pregnancy period be between 20 weeks and 35 weeks and 6 days, It is preferable that the pregnancy period be between 20 weeks and 34 weeks and 6 days, It is preferable that the pregnancy period be between 20 weeks and 33 weeks and 6 days.

16. The use according to any of paragraphs 1-7 or the method of prediction according to any of paragraphs 8-14, wherein the sample taken from the pregnant woman is cervicovaginal discharge.

17. The use according to any one of claims 1 to 7 or the method for predicting according to any one of claims 8 to 14, wherein LUM and / or TIMP1 are determined by means of an enzyme-linked immunosorbent assay (ELISA).

18. A kit for predicting the risk of preterm birth using the method described in any of claims 8-10, wherein the kit comprises an antibody for detecting LUM and / or an antibody for detecting TIMP1.

19. A kit for predicting the date of delivery using the method described in any of claims 11-14, wherein the kit comprises an antibody for detecting LUM and / or an antibody for detecting TIMP1.