A risk prediction model for pregnancy complications and its application

Abstract

The present invention provides a risk prediction model for complications during pregnancy and its application, involving ABHD17A, CFAP157, CTNNBIP1, CTR9, FAM227A, LILRA5, NPTN, NSD1, OBP2B, OR10H4, PAQR9, PLK3, PRSS58, SLC45A1, SP140L, SSR3, STAT1, STK31, TLE1, TMEM238 genes and age, gestational age, ffDNA, T21, T18, T13, BMI, conception method, non-invasive indication, adverse pregnancy and delivery history, whether multiple births, and clinical indications of the number of previous cesarean sections. The model provided by the present invention can efficiently and quickly predict complications during pregnancy and has broad application prospects.

Description

Technical Field

[0001] The present invention belongs to the field of biomedicine, and specifically relates to a pregnancy complication risk prediction model and its application. Background Art

[0002] In a normal pregnancy, the embryo implants in the appropriate part of the uterine cavity and continues to grow until full-term delivery. If the embryo implants outside the uterine cavity, or the embryo or fetus grows and develops in the uterine cavity for too short or too long, or the mother suffers from various pregnancy-specific organ damage, it is a pregnancy complication.

[0003] Pregnancy complications, also known as pregnancy complications, are diseases that occur before or during pregnancy that are not directly caused by pregnancy and do not necessarily disappear even after the pregnancy ends. Pregnancy complications include gestational hypertension, preeclampsia, gestational diabetes, placenta previa, premature birth, etc. Pregnancy complications can have very serious consequences for pregnant women, so it is very necessary to conduct risk prediction and assessment in early pregnancy.

[0004] Studies have shown that the incidence of pregnancy complications is related to clinical indicators such as maternal age and gestational age, as well as a series of biochemical indicators. Currently, a series of physiological and biochemical indicators, clinical indicator data, susceptibility gene expression or specific protein detection are often used to predict pregnancy complications such as preeclampsia. Most of these methods have unsatisfactory results because the indicators or susceptibility genes are affected by many factors.

[0005] Therefore, it is an urgent problem to make up for the current shortcomings in the prediction of pregnancy complications in the early stages of pregnancy and to achieve efficient and rapid prediction of the risks of pregnancy complications. Summary of the invention

[0006] To overcome the deficiencies of the prior art, the present invention provides a risk prediction model for predicting the risk of complications during pregnancy and a method for constructing the model.

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

[0008] A first aspect of the present invention provides a method for constructing a pregnancy complication risk prediction model, the method comprising the following steps:

[0009] (1) Obtaining a biomaker for gene expression;

[0010] (2) Obtain clinical indication information;

[0011] (3) The TSS information of differentially expressed genes was combined with the clinical indication information obtained to construct a prediction model.

[0012] Furthermore, step (1) includes screening differential gene TSS.

[0013] Furthermore, step (1) uses the acquired regional depth information of TSS to screen differential gene TSS.

[0014] Furthermore, the differential gene TSSs were screened by converting the regional depth information of the obtained TSSs into RPKM.

[0015] Furthermore, the formula for converting the regional depth information of TSS into rpkm is rpkm=read counts / (mapped reads (Millions)*TSS length (KB).

[0016] Furthermore, the regional depth information of TSS refers to the depth information within the 1000bp region upstream and downstream of the transcriptome start site.

[0017] Furthermore, the differential gene screening criteria were |log 2 FC|>=1 and FDR<0.1.

[0018] Furthermore, step (1) also includes further screening the screened differentially expressed gene TSSs by a feature selection method.

[0019] Furthermore, the feature selection method is a recursive feature elimination method.

[0020] Furthermore, step (1) further includes calculating the threshold of the differential gene TSS screened by recursive feature elimination method.

[0021] Furthermore, the threshold is the Youden Index.

[0022] Furthermore, the TSS of the differentially expressed genes was binarized according to the obtained threshold.

[0023] Furthermore, in step (3), a prediction model is constructed by means of logistic regression method.

[0024] Furthermore, the pregnancy complication is preeclampsia.

[0025] The second aspect of the present invention provides a pregnancy complication risk prediction model, which is constructed according to the method described in the first aspect of the present invention.

[0026] Furthermore, the differential genes include ABHD17A, CFAP157, CTNNBIP1, CTR9, FAM227A, LILRA5, NPTN, NSD1, OBP2B, OR10H4, PAQR9, PLK3, PRSS58, SLC45A1, SP140L, SSR3, STAT1, STK31, TLE1, and TMEM238.

[0027] Furthermore, the clinical indications include maternal age, gestational age, ffDNA (fetal DNA concentration is the percentage of fetal cfDNA in the mother, i.e., fetal free DNA fragment concentration (Fetal Fraction, FF)), T21 (fetal chromosome 21 detection) results, T18 (fetal chromosome 18 detection) results, T13 (fetal chromosome 13 detection) results, BMI (body mass index), method of conception, non-invasive indications, adverse pregnancy and delivery history, multiparity, and number of previous cesarean sections.

[0028] Furthermore, the pregnancy complication is preeclampsia.

[0029] Further, the risk prediction model is expressed as: logit(P)=0.046×ABHD17A-0.037×CFAP157+0.051×CTNNBIP1+0.061×CTR9+0.061×FAM227A-0.049×LILRA5+0.051×NP TN+0.033×NSD1-0.045×OBP2B+0.047×OR10H4-0.048×PAQR9+0.042×PLK3-0.041×PRSS58-0.047×SLC45A1+0.047×SP140L+0.049×SSR3+0.064×STAT1+0.051×ST K31-0.030×TLE1+0.056×TMEM238+0.023×age-0.074×gestational age+0.142×ffDNA-0.003×T21-0.037×T18+0.006×T13+0.121×BMI+0.030×method of conception+0.032×non-invasive indication+0.030×adverse pregnancy and delivery history-0.063×whether multiparous-0.012×number of previous cesarean sections-6.006.

[0030] Furthermore, when logit(P)>0.2, the woman was considered to be at risk of pregnancy complications.

[0031] Furthermore, the pregnancy complication is preeclampsia.

[0032] A third aspect of the present invention provides any one of the following computer-readable storage media:

[0033] 1) It stores a program for executing the method described in the first aspect of the present invention.

[0034] 2) It stores a program for executing the risk prediction model described in the second aspect of the present invention.

[0035] Furthermore, the pregnancy complication is preeclampsia.

[0036] A fourth aspect of the present invention provides any of the following electronic devices:

[0037] 1) An electronic device, comprising a processor, wherein the processor is used to execute an executable program, and the executable program is used to run the method described in the first aspect of the present invention.

[0038] 2) An electronic device comprising a processor, wherein the processor is used to execute an executable program, and the executable program is used to run the risk prediction model described in the second aspect of the present invention.

[0039] Furthermore, the electronic device also includes an input device connected to the processor for receiving input information from the user.

[0040] Furthermore, the electronic device also includes a memory, and the memory is used to store files.

[0041] Furthermore, the electronic device also includes a display device for displaying risk prediction results according to instructions from the input device and the processor.

[0042] Furthermore, the pregnancy complication is preeclampsia.

[0043] The fifth aspect of the present invention provides a device for predicting the risk of complications during pregnancy, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor executes the risk prediction model described in the second aspect of the present invention.

[0044] The sixth aspect of the present invention provides a product for predicting complications during pregnancy, the product comprising a reagent for detecting biomarkers; the biomarkers include one or more of ABHD17A, CFAP157, CTNNBIP1, CTR9, FAM227A, LILRA5, NPTN, NSD1, OBP2B, OR10H4, PAQR9, PLK3, PRSS58, SLC45A1, SP140L, SSR3, STAT1, STK31, TLE1, and TMEM238.

[0045] Furthermore, the reagents include probes for recognizing the biomarker genes; or primers for amplifying the biomarker genes; or binding agents for binding to the biomarker proteins.

[0046] Furthermore, the product includes a nucleic acid membrane strip, a chip or a kit.

[0047] Furthermore, the chip includes a gene chip and a protein chip. The gene chip includes an oligonucleotide probe for the biomarker gene for detecting the transcription level of the biomarker gene, and the protein chip includes a specific binder for the biomarker protein; the kit includes a gene detection kit and a protein detection kit. The gene detection kit includes a reagent or chip for detecting the transcription level of the biomarker gene, and the protein detection kit includes a reagent or chip for detecting the expression level of the biomarker protein.

[0048] Furthermore, the kit includes a qPCR kit, an immunoblotting detection kit, an immunochromatography detection kit, a flow cytometry analysis kit, an immunohistochemistry detection kit, an ELISA kit and an electrochemiluminescence detection kit.

[0049] Furthermore, the pregnancy complication is preeclampsia.

[0050] The seventh aspect of the present invention provides the use of a reagent for detecting biomarkers in a sample in the preparation of a product for predicting pregnancy complications, wherein the biomarkers include one or more of ABHD17A, CFAP157, CTNNBIP1, CTR9, FAM227A, LILRA5, NPTN, NSD1, OBP2B, OR10H4, PAQR9, PLK3, PRSS58, SLC45A1, SP140L, SSR3, STAT1, STK31, TLE1, and TMEM238.

[0051] Furthermore, the reagents include reagents for detecting the expression level of biomarkers in samples through protein immunoassay technology, dye technology, nucleic acid sequencing technology, nucleic acid hybridization technology, chromatography technology, and mass spectrometry technology.

[0052] Furthermore, the sample is selected from a peripheral blood sample.

[0053] Furthermore, the pregnancy complication is preeclampsia.

[0054] The eighth aspect of the present invention provides the use of the biomarkers described in the sixth aspect of the present invention in constructing a risk prediction model for predicting pregnancy complications.

[0055] Advantages and beneficial effects of the present invention:

[0056] The pregnancy complication risk prediction model provided by the present invention can realize rapid and efficient prediction of the risk of pregnancy complication by combining the transcription start site regional depth obtained by free DNA sequencing technology with clinical indications such as the age of the pregnant woman and the gestational age, which is of great significance for the clinical research of pregnancy complications. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a risk prediction model effect evaluation chart. DETAILED DESCRIPTION

[0058] The present invention provides a method for constructing a pregnancy complication risk prediction model, the method comprising the following steps:

[0059] (1) Obtaining a biomaker for gene expression;

[0060] (2) Obtain clinical indication information;

[0061] (3) The TSS information of differentially expressed genes was combined with the clinical indication information obtained to construct a prediction model.

[0062] Furthermore, step (1) includes screening differential gene TSS.

[0063] Furthermore, the regional depth information of the obtained TSS was used to screen the differentially expressed gene TSS.

[0064] Furthermore, the differential gene TSSs were screened by converting the regional depth information of the obtained TSSs into RPKM.

[0065] Furthermore, the formula for converting the regional depth information of TSS into rpkm is rpkm=read counts / (mapped reads (Millions)*TSS length (KB).

[0066] Furthermore, the regional depth information of TSS refers to the depth information within the 1000bp region upstream and downstream of the transcriptome start site.

[0067] Furthermore, the differential gene screening criteria were |log 2 FC|>=1 and FDR<0.1.

[0068] Furthermore, step (1) also includes further screening the screened differentially expressed gene TSSs by a feature selection method.

[0069] In some embodiments of the present invention, the feature selection method includes a filtering method, an embedding method, and a packing method, wherein the packing method includes a recursive feature elimination method.

[0070] In a specific embodiment of the present invention, the feature selection method is selected from the recursive feature elimination method.

[0071] Furthermore, the feature selection method is a recursive feature elimination method.

[0072] Furthermore, step (1) further includes calculating the threshold of the differential gene TSS screened by recursive feature elimination method.

[0073] Furthermore, the threshold is the Youden Index.

[0074] In the present invention, the Youden index, also known as the accuracy index, is a method for evaluating the authenticity of a screening test. Assuming that the harmfulness of false negatives (missed diagnosis rate) and false positives (misdiagnosis rate) is of equal significance, the Youden index can be applied. The Youden index is the sum of sensitivity and specificity minus 1. It represents the total ability of the screening method to find true patients and non-patients. The larger the index, the better the effect of the screening test and the greater the authenticity.

[0075] Furthermore, the TSS of the differentially expressed genes was binarized according to the obtained threshold.

[0076] Furthermore, in step (3), a prediction model is constructed by means of logistic regression method.

[0077] Furthermore, the pregnancy complication is preeclampsia.

[0078] The present invention provides a risk prediction model for pregnancy complications, which is constructed according to the above method. The risk prediction model is expressed as: logit (P) = 0.046 × ABHD17A-0.037 × CF AP157 + 0.051 × CTNNBIP1 + 0.061 × CTR9 + 0.061 × FAM227A-0.049 × LILRA5 + 0.051 × NPTN + 0.033 × NSD1-0.045 × OBP2B + 0.047 × OR10H4-0.048 × PAQR9 + 0.042 × PLK3-0.041 × PRSS58-0.047 × SLC45A1 + 0.047 × SP140L + 0.049 × SSR3 + 0. 064×STAT1+0.051×STK31-0.030×TLE1+0.056×TMEM238+0.023×age-0.074×gestational age+0.142×ffDNA-0.003×T21-0.037×T18+0.006×T13+0.121×BMI+0.030×conception method+0.032×non-invasive indication+0.030×bad pregnancy history-0.063×whether multiple births-0.012×number of previous cesarean sections-6.006;

[0079] When logit(P)>0.2, the woman is considered to be at risk of pregnancy complications.

[0080] The specific values ​​of each indicator in the model are as follows: After the genes in the model are binarized, those above the threshold are 1, and those below the threshold are 0. The thresholds of each gene are as follows:

[0081] ABHD17A=8.58, CFAP157=21.99, CTNNBIP1=17.74, CTR9=10.42, FAM227A=34.81, LILRA5=9.39, NPTN=9.33, NSD1=39.5, OBP2B=39.51, OR10H4=36. 69, PAQR9=11.24, PLK3=8.2, PRSS58=56.2, SLC45A1=21.14, SP140L=34.66, SSR3=17.06, STAT1=12.86, STK31=22.49, TLE1=21.13, TMEM238=20.4;

[0082] The method of conception was divided into natural conception and IVF, where natural conception = 1, IVF = 2;

[0083] Non-invasive indications were divided into advanced age (over 35 years old), abnormal Down syndrome screening, multiple births, abnormal ultrasound, high risk of chromosomal abnormality (previous pregnancy or abnormal parents) or adverse pregnancy and delivery history, among which advanced age = 1, abnormal Down syndrome screening = 2, multiple births = 3, abnormal ultrasound = 4, high risk of chromosomal abnormality (previous pregnancy or abnormal parents) or adverse pregnancy and delivery history = 5; 6 represents social factors;

[0084] With adverse pregnancy and delivery history = 2, without adverse pregnancy and delivery history = 1;

[0085] Prolific = 2, non-prolific = 1.

[0086] The present invention provides any of the following electronic devices:

[0087] 1) An electronic device, comprising a processor, wherein the processor is used to execute an executable program, and the executable program is used to run the above method.

[0088] 2) An electronic device, comprising a processor, wherein the processor is used to execute an executable program, and the executable program is used to run the above-mentioned risk prediction model.

[0089] Furthermore, the pregnancy complication is preeclampsia.

[0090] Each unit in the above-mentioned risk prediction model construction device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned units can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above-mentioned units.

[0091] In some embodiments of the present invention, the electronic device may be a computer device, and the computer device may be a terminal. The computer device includes a processor, a memory, a communication interface, a display device, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for constructing a disease risk prediction model is implemented. The display device of the computer device may be a liquid crystal display or an electronic ink display, and the input device of the computer device may be a touch layer covered on the display screen, or a button, a trackball or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0092] In some embodiments of the present invention, the electronic device is specifically a device for constructing a disease risk prediction model, and the device includes: a processor, the processor is used to execute an executable program, and the executable program is used to run the above method or the above risk prediction model; the electronic device also includes an input device, which is connected to the processor and is used to accept user input information; the electronic device also includes a memory, and the memory is used to store files; the electronic device also includes a display device, which displays the risk prediction results according to the instructions of the input device and the processor.

[0093] The present invention provides a device for predicting the risk of complications during pregnancy. The device comprises an acquisition unit for acquiring data of differentially expressed genes in a sample and related clinical indications.

[0094] The risk prediction device also includes a processor, which executes the above-mentioned risk prediction model.

[0095] The device as applied by the present invention should at least include the above-mentioned unit. The units of the device are operably connected to each other. How to link the units in an operative manner will depend on the type of units included in the device. For example, in the case of applying an instrument for automatic quantitative measurement of differential genes in an acquisition unit, the data obtained by the automatic operation unit can be processed by a processor, for example, by a computer program running on a computer as a data processor, so as to better predict. In one embodiment, the data processor implements the comparison of the amount of differential genes with a reference. Further, in this case, the unit is composed of a single device. However, the acquisition unit and the processor can also be physically separated. In this case, operative linkage can be realized via wired and wireless connections between units that allow data transmission. Wireless connection can use wireless LAN (WLAN) or the Internet. Wired connection can be realized by optical and non-optical cable connection between units. The cable for wired connection is further suitable for high-throughput data transmission.

[0096] The risk prediction device also includes a memory and a computer program stored in the memory and configured to be executed by the processor.

[0097] The present invention also provides a product for predicting complications during pregnancy, the product comprising a reagent for detecting biomarkers; the biomarkers include one or more of ABHD17A, CFAP157, CTNNBIP1, CTR9, FAM227A, LILRA5, NPTN, NSD1, OBP2B, OR10H4, PAQR9, PLK3, PRSS58, SLC45A1, SP140L, SSR3, STAT1, STK31, TLE1, and TMEM238.

[0098] The reagents include probes for recognizing the biomarker genes; or primers for amplifying the biomarker genes; or binding agents for binding to the biomarker proteins.

[0099] The products include but are not limited to nucleic acid membrane strips, chips or kits.

[0100] In some embodiments of the invention, biomarkers include but are not limited to nucleic acids, proteins, and variants and fragments thereof. A biomarker can be a DNA comprising all or part of a nucleic acid sequence encoding the biomarker or a complement of such a sequence. Biomarker nucleic acids useful in the present invention are considered to include DNA and RNA comprising all or part of any target nucleic acid sequence.

[0101] In a specific embodiment of the present invention, the nucleic acid of the biomarker refers to the transcription start site region of the target gene.

[0102] ABHD17A:abhydrolase domain containing 17A,Gene ID:81926。

[0103] CFAP157:cilia and flagella associated protein 157,Gene ID:286207。

[0104] CTNNBIP1:catenin beta interacting protein 1,Gene ID:56998。

[0105] CTR9:CTR9 homolog,Paf1 / RNApolymerase II complex component,Gene ID:9646。

[0106] FAM227A:family with sequence similarity 227member A,Gene ID:646851。

[0107] LILRA5:leukocyte immunoglobulin like receptor A5,Gene ID:353514。

[0108] NPTN:neuroplastin,Gene ID:27020。

[0109] NSD1:nuclear receptor binding SET domain protein 1,Gene ID:64324。

[0110] OBP2B:odorant binding protein 2B,Gene ID:29989。

[0111] OR10H4:olfactory receptor family 10subfamily H member 4,Gene ID:126541。

[0112] PAQR9:progestin and adipoQ receptor family member 9,Gene ID:344838。

[0113] PLK3:polo like kinase 3,Gene ID:1263。

[0114] PRSS58: serine protease 58, Gene ID: 136541.

[0115] SLC45A1: solute carrier family 45member 1, Gene ID: 50651.

[0116] SP140L: SP140 nuclear body protein like, Gene ID: 93349.

[0117] SSR3: signal sequence receptor subunit 3, Gene ID: 6747.

[0118] STAT1: signal transducer and activator of transcription 1, Gene ID: 6772.

[0119] STK31: serine / threonine kinase 31, Gene ID: 56164.

[0120] TLE1: TLE family member 1, transcriptional corepressor, Gene ID: 7088.

[0121] TMEM238: transmembrane protein 238, Gene ID: 388564.

[0122] In some embodiments of the present invention, "probe" refers to a molecule that can bind to a specific sequence or subsequence or other part of another molecule. Unless otherwise indicated, the term "probe" generally refers to a polynucleotide probe that can bind to another polynucleotide (often referred to as a "target polynucleotide") through complementary base pairing. Depending on the stringency of the hybridization conditions, the probe can bind to a target polynucleotide that lacks complete sequence complementarity with the probe. The probe can be labeled directly or indirectly. Hybridization methods include, but are not limited to solution phase, solid phase, mixed phase or in situ hybridization assays. The probe can be labeled or unlabeled. The probe can be produced by molecular cloning of a specific DNA sequence or can be synthesized. A technician in the field to which the present invention belongs can easily determine a variety of primers and probes that can be designed and used in the context of the present invention.

[0123] In some embodiments of the invention, a "primer" refers to an oligonucleotide that hybridizes to a sequence in a target nucleic acid (a "primer binding site") and can serve as a point for initiating synthesis along a complementary strand of nucleic acid under conditions suitable for synthesis.

[0124] In the present invention, the protein binder is, for example, a protein receptor, a lectin that binds to a protein, an antibody against a protein, a peptide body against a protein, a bispecific dual binder, or a bispecific antibody format.

[0125] In the present invention, the nucleic acid membrane strip comprises a substrate and an oligonucleotide probe fixed on the substrate; the substrate can be any substrate suitable for fixing the oligonucleotide probe, such as a nylon membrane, a nitrocellulose membrane, a polypropylene membrane, a glass sheet, a silica gel wafer, or micro-magnetic beads.

[0126] In the present invention, "chip" is also referred to as "array", which refers to a solid support comprising connected nucleic acid or peptide probes. The array generally comprises a plurality of different nucleic acid or peptide probes connected to the surface of a substrate according to different known positions. These arrays, also referred to as "microarrays", can generally be produced using mechanical synthesis methods or light-guided synthesis methods, which incorporate a combination of photolithography and solid phase synthesis methods. The array may comprise a flat surface, or may be a nucleic acid or peptide on a bead, gel, polymer surface, fiber such as an optical fiber, glass or any other suitable substrate. The array may be packaged in a manner to allow for diagnosis of a fully functional device or manipulation of other methods.

[0127] In some embodiments of the invention, a "microarray" is an orderly arrangement of hybridization array elements such as polynucleotide probes (e.g., oligonucleotides) or binding agents (e.g., antibodies) on a substrate. The substrate can be a solid substrate, for example, a glass or silica slide, a bead, a fiber optic binder, or a semi-solid substrate, such as a nitrocellulose membrane. The nucleotide sequence can be DNA, RNA, or any arrangement thereof.

[0128] The kit includes reagents for detecting the gene or protein of the present invention, and one or more substances selected from the following group: a container, instructions for use, a positive control substance, a negative control substance, a buffer, an auxiliary agent or a solvent.

[0129] The kit of the present invention may also be accompanied by an instruction manual for use of the kit, which describes how to use the kit for detection, and how to use the detection results to judge tumor development and select a treatment plan.

[0130] The components of the test kit can be packaged in the form of an aqueous medium or in a lyophilized form. Suitable containers in the test kit usually include at least a vial, test tube, flask, PET bottle, syringe or other container, in which a component can be placed, and preferably, can be appropriately divided. When there is more than one component in the test kit, the test kit will usually also include a second, third or other additional container, in which additional components are placed separately. However, components of different combinations can be contained in a vial. The test kit of the present invention will also usually include a container for accommodating reactants, sealed for commercial sale. Such a container may include a plastic container of injection molding or blow molding, in which the required vial can be retained.

[0131] The present invention provides the use of a reagent for detecting biomarkers in a sample in the preparation of a product for predicting pregnancy complications, wherein the reagent includes a reagent for detecting the expression level of the biomarker in the sample by protein immunoassay technology, dye technology, nucleic acid sequencing technology, nucleic acid hybridization technology, chromatography technology, and mass spectrometry technology.

[0132] In some embodiments of the invention, "sample" may refer to a biological sample, typically a clinical sample, and includes, for example, blood and other body fluids, including but not limited to peripheral blood, serum, plasma, urine, and saliva; and solid tissue samples, such as biopsy specimens, especially those containing cancer cells. In certain embodiments, blood samples such as serum or plasma samples are preferred sample types to be used in the present invention. Generally, obtaining a sample to be analyzed from a subject is not part of the prognostic method of the present invention.

[0133] The term "sample" also includes a sample that has been manipulated or processed in any appropriate manner after purchase, including but not limited to centrifugation, filtration, precipitation, dialysis, chromatography, treatment with reagents, washing, or enrichment for a component of the sample, such as a cell population.

[0134] In a specific embodiment of the present invention, the sample is a peripheral blood sample.

[0135] In some embodiments of the present invention, the term "expression level" generally refers to the amount of a biomarker in a biological sample. "Expression" generally refers to the process by which information (e.g., genetic coding and / or epigenetic information) is converted into a structure that exists and operates in a cell. Therefore, as used herein, "expression" may refer to transcription into polynucleotides, translation into polypeptides, or even polynucleotide and / or polypeptide modifications (e.g., post-translational modifications of polypeptides). Fragments of transcribed polynucleotides, translated polypeptides, or polynucleotide and / or polypeptide modifications (e.g., post-translational modifications of polypeptides) should also be considered expressed, whether they are derived from transcripts generated by alternative splicing or degraded transcripts, or from post-translational processing of polypeptides (e.g., by proteolysis). "Expressed genes" include genes that are transcribed into polynucleotides (e.g., mRNA) and then translated into polypeptides, as well as genes that are transcribed into RNA but not translated into polypeptides (e.g., transport and ribosomal RNA).

[0136] The present invention can use a variety of nucleic acid and protein technologies known to those skilled in the art for detection, including but not limited to: protein immunoassay technology, dye technology, nucleic acid sequencing technology, nucleic acid hybridization technology, chromatography technology, mass spectrometry technology, a few of which are listed here.

[0137] The protein immunoassay of the present invention includes sandwich immunoassays, such as sandwich ELISA, in which two antibodies that recognize different epitopes on the biomarker are used to detect the biomarker; radioimmunoassay (RIA), direct, indirect or comparative enzyme-linked immunosorbent assay (ELISA), enzyme immunoassay (EIA), fluorescent immunoassay (FIA), Western blotting, immunoprecipitation, and any particle-based immunoassay (such as using gold particles, silver particles or latex particles, magnetic particles or quantum dots). For example, the immunoassay can be implemented in the form of a microtiter plate or strip.

[0138] Illustrative non-limiting examples of nucleic acid sequencing methods of the present invention include, but are not limited to, chain terminator (Sanger) sequencing and dye terminator sequencing. One of ordinary skill in the art will recognize that, because RNA is less stable in cells and more susceptible to nuclease attack in experiments, RNA is usually reverse transcribed into DNA before sequencing.

[0139] Another exemplary non-limiting example of the nucleic acid sequencing method of the present invention includes next-generation sequencing (deep sequencing / high-throughput sequencing). High-throughput sequencing technology is a single-molecule cluster-based sequencing-by-synthesis technology based on a proprietary reversible termination chemical reaction principle. During sequencing, random fragments of genomic DNA are attached to an optically transparent glass surface. After extension and bridge amplification, these DNA fragments form hundreds of millions of clusters on the glass surface, each of which is a single-molecule cluster with thousands of copies of the same template. Then, four special deoxyribonucleotides with fluorescent groups are used to sequence the template DNA to be tested through a reversible sequencing-by-synthesis technology.

[0140] Nucleic acid hybridization methods in the present invention include, but are not limited to, in situ hybridization (ISH), microarrays, and Southern or Northern blotting. In situ hybridization (ISH) is a hybridization of specific DNA or RNA sequences in a portion or slice (in situ) of a tissue using a labeled complementary DNA or RNA chain as a probe or in the entire tissue (whole tissue embedding ISH) if the tissue is small enough. DNA ISH can be used to determine the structure of chromosomes. RNA ISH is used to measure and locate mRNA and other transcripts (e.g., ncRNA) in tissue slices or whole tissue embedding. Sample cells and tissues are usually treated to fix the target transcript in situ and increase the entry of the probe. The probe hybridizes with the target sequence at high temperature, and then the excess probe is washed away. Use radioautography, fluorescence microscopy, or immunohistochemistry, respectively, to locate and quantify probes labeled with radioactive, fluorescent, or antigen-labeled bases in tissues. ISH can also use two or more probes labeled with radioactive or other non-radioactive markers to detect two or more transcripts simultaneously.

[0141] Southern and Northern blotting are used to detect specific DNA or RNA sequences, respectively. DNA or RNA extracted from a sample is fragmented, separated by electrophoresis on a matrix gel, and then transferred to a membrane filter. The filter-bound DNA or RNA is hybridized with a labeled probe complementary to the sequence of interest. The hybridized probe bound to the filter is detected. A variation of this procedure is the reverse Northern blotting, in which the substrate nucleic acid fixed to the membrane is a collection of isolated DNA fragments, and the probe is RNA extracted from the tissue and labeled.

[0142] In some embodiments of the present invention, complications during pregnancy include, but are not limited to, early hyperemesis gravidarum, spontaneous abortion, ectopic pregnancy (including uterine rudimentary horn pregnancy and scar pregnancy), late abortion in the middle and late stages, gestational diabetes, hypertensive disorders during pregnancy (including gestational hypertension, preeclampsia, eclampsia, chronic hypertension complicated with pregnancy, chronic hypertension complicated with preeclampsia), intrahepatic cholestasis of pregnancy syndrome, acute fatty liver of pregnancy, premature birth, overdue pregnancy, and premature rupture of membranes.

[0143] In a specific embodiment of the invention, the pregnancy complication is preeclampsia.

[0144] The invention will be further described below in conjunction with specific examples. It should be understood that the specific embodiments described herein are presented by way of example and are not intended to limit the invention. The main features of the invention may be used in a variety of embodiments without departing from the scope of the invention.

[0145] Example Construction of a risk prediction model for pregnancy complications

[0146] (1) Ten samples were randomly selected from the preeclampsia group and the normal control group. The depth information of the 1000 bp region upstream and downstream of the transcriptome start site (TSS) was calculated and converted into rpkm (Reads Per Kilobase Million) using the formula: rpkm = read counts / (mapped reads (Millions)*TSS length (KB). The FC (fold change) of the average rpkm of each gene in the preeclampsia group and the normal control group was calculated, and the log 2 FC, screening differential gene TSS by FDR (False Discovery Rate), the parameter is |log 2 FC|>=1 and FDR<0.1, and a total of 483 differentially expressed gene TSSs were selected.

[0147] (2) The data set containing preeclampsia and normal control samples (a total of 207 cases, including 39 preeclampsia cases and 168 normal controls) was divided into a training set and a test set according to a ratio of 6:4. In the training set, 20 differential gene TSSs were found by recursive feature elimination. The rpkm information of the 20 gene TSSs was binarized, and those above the threshold were classified as 1 and those below the threshold were classified as 0. The threshold was the Youden index. Then, it was combined with clinical indication information (including maternal age, maternal gestational age, ffDNA (the percentage of fetal DNA concentration in the mother's fetal cfDNA, i.e., fetal free DNA fragment concentration (Fetal Fraction, FF)), T21 (fetal chromosome 21 test) results, T18 (fetal chromosome 18 test) results, T13 (fetal chromosome 13 test) results, BMI (body mass index), mode of conception, non-invasive indications, adverse pregnancy and delivery history, multiparity, and number of previous cesarean sections) to form new features. The prediction model was constructed using the logistic regression method in the training set, and a 10-fold cross validation was performed.

[0148] (3) The model is expressed as: logit(P) = 0.046×ABHD17A-0.037×CFAP157+0.051×CTNNBIP1+0.061×CTR9+0.061×FAM227A-0.049×LILRA5+0.051×NPTN+0.033×NSD1-0.045×OBP2B+0.047×OR10H4-0.048×PAQR9+0.042×PLK3-0.041×PRSS58-0.047×SLC45A1+0.047× SP140L+0.049×SSR3+0.064×STAT1+0.051×STK31-0.030×TLE1+0.056×TMEM238+0.023×age-0.074×gestational age+0.142×ffDNA-0.003×T21-0.037×T18+0.006×T13+0.121×BMI+0.030×method of conception+0.032×non-invasive indication+0.030×adverse pregnancy and delivery history-0.063×whether multiple births-0.012×number of previous cesarean sections-6.006.

[0149] (4) The model was evaluated using accuracy, sensitivity, specificity and area under the ROC (Receiver Operating Characteristic) curve (AUC). The results are shown in Table 1.

[0150] Table 1

[0151]

[0152] (5) When logit(P)>0.2, the patient is considered to have a risk of preeclampsia.

[0153] The description of the above embodiments is only used to understand the method and core idea of ​​the present invention. It should be pointed out that, for those skilled in the art, several improvements and modifications can be made to the present invention without departing from the principle of the present invention, and these improvements and modifications will also fall within the scope of protection of the claims of the present invention.

Claims

1. A method for constructing a pregnancy complication risk prediction model, characterized in that: The method comprises the following steps: (1) Obtain biomarkers of gene expression and screen for differentially expressed gene TSSs; (2) Obtain clinical indication information; (3) Combine the TSS information of differentially expressed genes with the clinical indication information to construct a prediction model; The differentially expressed genes include ABHD17A, CFAP157, CTNNBIP1, CTR9, FAM227A, LILRA5, NPTN, NSD1, OBP2B, OR10H4, PAQR9, PLK3, PRSS58, SLC45A1, SP140L, SSR3, STAT1, STK31, TLE1, and TMEM238; The clinical indications include maternal age, gestational age, ffDNA, T21, T18, T13, BMI, mode of conception, non-invasive indications, adverse pregnancy and delivery history, multiparity and number of previous cesarean sections; Wherein, in step (3), a prediction model is constructed by a logistic regression method, and the pregnancy complication is preeclampsia.

2. The method according to claim 1, characterized in that The obtained regional depth information of TSS was used to screen differentially expressed gene TSSs.

3. The method according to claim 2, characterized in that The differential gene TSSs were screened by converting the regional depth information of the obtained TSSs into RPKM.

4. The method according to claim 3, characterized in that The formula for converting the regional depth information of TSS into rpkm is rpkm=read counts / (mapped reads (Millions) * TSS length (KB)).

5. The method according to claim 4, characterized in that The regional depth information of TSS refers to the depth information within the 1000bp region upstream and downstream of the transcriptome start site.

6. The method according to claim 3, characterized in that: The screening criteria for differentially expressed genes were |log2FC|>=1 and FDR<0.

1.

7. The method according to claim 1, characterized in that Step (1) also includes further screening the screened differentially expressed gene TSSs by a feature selection method.

8. The method according to claim 7, characterized in that The feature selection method is a recursive feature elimination method.

9. The method according to claim 8, characterized in that Step (1) further includes calculating the threshold of the differentially expressed gene TSSs screened by recursive feature elimination.

10. The method according to claim 9, characterized in that The threshold is the Youden Index.

11. The method according to claim 10, characterized in that The TSS of differentially expressed genes were binarized according to the obtained threshold.

12. A pregnancy complication risk prediction model, characterized in that: The risk prediction model is constructed according to the method described in any one of claims 1-11, and the pregnancy complication is preeclampsia.

13. The risk prediction model according to claim 12, characterized in that: The risk prediction model is expressed as: logit(P)=0.046×ABHD17A-0.037×CFAP157+0.051×CTNNBIP1+0.061×CTR9+0.061×FAM227A-0.049×LILRA5+0.051×NP TN+0.033×NSD1-0.045×OBP2B+0.047×OR10H4-0.048×PAQR9+0.042×PLK3-0.041×PRSS58-0.047×SLC45A1+0.047×SP14 0L+0.049×SSR3+0.064×STAT1+0.051×STK31-0.030×TLE1+0.056×TMEM238+0.023×age-0.074×gestational age+0.142×ffDNA-0.003×T21-0.037×T18+0.006×T13+0.121×BMI+0.030×method of conception+0.032×non-invasive indication+0.030×adverse pregnancy and delivery history-0.063×whether multiple births-0.012×number of previous cesarean sections-6.

006.

14. The risk prediction model according to claim 13, characterized in that: When logit(P)>0.2, the woman is considered to be at risk of pregnancy complications.

15. Any of the following computer-readable storage media: 1) It stores a program for executing the method according to any one of claims 1 to 11; 2) It stores a program for executing the risk prediction model described in any one of claims 12-14.

16. Any of the following electronic devices: 1) An electronic device, characterized in that: The electronic device comprises a processor and a memory, the processor is used to execute an executable program stored in the memory, and the executable program is used to run the method according to any one of claims 1 to 11; 2) An electronic device, characterized in that the electronic device comprises a processor and a memory, the processor is used to execute an executable program stored in the memory, and the executable program is used to run the risk prediction model described in any one of claims 12-14.

17. The electronic device according to claim 16, characterized in that: The electronic device also includes an input device connected to the processor and used for receiving input information from the user.

18. The electronic device according to claim 16, characterized in that: The electronic device also includes a display device for displaying risk prediction results according to instructions from the input device and the processor.

19. A device for predicting the risk of pregnancy complications, characterized in that: The risk prediction device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor executes the risk prediction model described in any one of claims 12-14.

20. Use of a reagent for detecting biomarkers in a sample in the preparation of a product for predicting pregnancy complications, characterized in that: The biomarkers are ABHD17A, CFAP157, CTNNBIP1, CTR9, FAM227A, LILRA5, NPTN, NSD1, OBP2B, OR10H4, PAQR9, PLK3, PRSS58, SLC45A1, SP140L, SSR3, STAT1, STK31, TLE1 and TMEM238; the reagents are probes for recognizing the biomarker genes, primers for amplifying the biomarker genes, or binding agents for binding to the biomarker proteins; and the pregnancy complication is preeclampsia.

21. The use according to claim 20, characterized in that The sample is selected from a peripheral blood sample.

22. The use according to claim 20, characterized in that The product is a nucleic acid membrane strip, a chip or a test kit.

23. The use according to claim 22, characterized in that The chip is a gene chip or a protein chip, the gene chip includes oligonucleotide probes for the biomarker gene for detecting the transcription level of the biomarker gene, and the protein chip includes a specific binder for the biomarker protein; the kit includes a gene detection kit or a protein detection kit, the gene detection kit includes a reagent or a chip for detecting the transcription level of the biomarker gene, and the protein detection kit includes a reagent or a chip for detecting the expression level of the biomarker protein.

24. The use according to claim 22, characterized in that The kit is a qPCR kit, an immunoblotting detection kit, an immunochromatography detection kit, a flow cytometry analysis kit, an immunohistochemistry detection kit, an ELISA kit or an electrochemiluminescence detection kit.

25. The application of biomarkers in constructing a risk prediction model for predicting pregnancy complications, wherein the biomarkers are ABHD17A, CFAP157, CTNNBIP1, CTR9, FAM227A, LILRA5, NPTN, NSD1, OBP2B, OR10H4, PAQR9, PLK3, PRSS58, SLC45A1, SP140L, SSR3, STAT1, STK31, TLE1 and TMEM238; the pregnancy complication is preeclampsia.

Images