Application of biomarker in pancreatic cancer assessment

Abstract

The invention relates to a biological marker related to pancreatic cancer and application of the biological marker, in particular to application of a detection reagent of the biological marker in preparation of a composition or a kit for evaluating, diagnosing or monitoring pancreatic cancer, the biological marker comprises microRNA and CA19-9, and the microRNA comprises any one or a combination of at least two of 19 microRNAs such as hsa-miR-122-5p and the like. The biomarker provided by the invention has high sensitivity and high specificity in distinguishing pancreatic cancer from non-pancreatic cancer, reduces the false positive rate of pancreatic cancer diagnosis, and has wide application prospects.

Description

Technical Field

[0001] The present invention relates to the field of biotechnology, and in particular to the application of biomarkers in the assessment of pancreatic cancer, and specifically to the application of biomarker detection reagents in the preparation of compositions or kits for the assessment, diagnosis or monitoring of pancreatic cancer. Background Art

[0002] Pancreatic cancer is a malignant tumor of the digestive system with high morbidity and mortality, of which more than 90% are pancreatic ductal adenocarcinoma. Due to the special anatomical location of the pancreas, the early onset is hidden and asymptomatic. 80%-85% of patients are already in the locally advanced stage when diagnosed, and only 15%-20% of patients diagnosed in the early stage can be treated with surgical intervention. At the same time, due to factors such as the strong invasiveness of the tumor and resistance to chemotherapy and radiotherapy drugs, the prognosis of pancreatic cancer is poor, and the five-year survival rate of patients is less than 9%. If it can be detected early, the five-year survival rate of pancreatic cancer patients can be increased to 30% to 40%. At the same time, some pancreatic masses are difficult to distinguish from benign lesions or chronic pancreatitis, which increases the difficulty of early diagnosis of pancreatic cancer. Therefore, how to accurately and efficiently differentiate pancreatic cancer from the interference of healthy people, pancreatitis or benign lesions is of great clinical significance.

[0003] Currently, the diagnostic methods for pancreatic ductal adenocarcinoma include chest imaging, pathological examination, and serum tumor marker detection, but the detection effects of these methods are all limited. Chest imaging examination methods include CT, magnetic resonance imaging (MRI), and endoscopic ultrasound (EUS), but imaging detection methods can only see indirect signs, such as pancreatic duct dilatation or pancreatic contour changes, which have poor sensitivity for detecting substantial lesions. Contrast-enhanced endoscopic ultrasonography (CEH EUS) is reported to promote the imaging of parenchymal perfusion and microvessels in pancreaticobiliary diseases, with a sensitivity and specificity of 93% and 80% for the diagnosis of pancreatic cancer, respectively, but the accuracy is often affected by the subjectivity of the endosonographer. Endoscopic ultrasound-guided fine needle aspiration biopsy (EUS-FNA) is an invasive detection method that is prone to infection, bleeding, and tumor spread. At the same time, the high false positive rate will cause the resected histological examination to show benign lesions. CA19-9 is the only serum tumor biomarker approved by the FDA for postoperative monitoring of pancreatic ductal adenocarcinoma, but its sensitivity and specificity for pancreatic cancer diagnosis are limited, and it is easily interfered by factors such as inflammation, jaundice, benign lesions and diabetes and cannot be used as an effective early diagnosis tumor marker. Therefore, there is an urgent need to develop minimally invasive early diagnosis tumor markers to assist in the early diagnosis of pancreatic cancer.

[0004] Small extracellular vesicles (sEVs) are membrane vesicles with a diameter of about 30-150nm, also known as exosomes. Exosomes have attracted extensive attention and in-depth research as an important form of liquid biopsy due to their rich content and dynamic monitoring. Studies have shown that exosomal miRNA is a potential tumor marker that can be used for early diagnosis of pancreatic cancer.

[0005] Lun Wu et al.'s study showed that there were differences in serum exosomal miRNA expression levels in patients with pancreatic ductal adenocarcinoma and chronic pancreatitis. The sensitivity of miR-21 and miR-210 for pancreatic cancer diagnosis was 80% and 83%, respectively. Combining miR-21 and miR-210 with serum CA19-9 could increase the sensitivity of pancreatic cancer diagnosis to 90%. However, there are few studies using healthy people and chronic pancreatitis as control groups, and the diagnostic models for pancreatic cancer and non-pancreatic cancer discovered based on chips or RT-PCR technology are not effective, and unknown miRNAs in exosomes cannot be found, resulting in a lack of efficient exosomal miRNA biomarkers for early diagnosis of pancreatic cancer.

[0006] In summary, how to develop a diagnostic biomarker with high sensitivity and specificity for distinguishing pancreatic cancer from non-pancreatic cancer has become one of the urgent problems to be solved in this field. Summary of the invention

[0007] To solve the above technical problems, the present invention provides a biomarker related to pancreatic cancer and its application, as well as the application of the biomarker detection reagent in the preparation of a composition or kit for evaluating, diagnosing or monitoring pancreatic cancer. The combination of microRNA and CA19-9 is used as a biomarker for the diagnosis of pancreatic cancer, which has high sensitivity and high specificity, and a low probability of false positive diagnosis.

[0008] To achieve this object, the present invention adopts the following technical solutions:

[0009] In a first aspect, the present invention provides a use of a biomarker detection reagent in the preparation of a composition or a kit for evaluating, diagnosing or monitoring pancreatic cancer, wherein the biomarker comprises microRNA and CA19-9; the microRNA comprises hsa-miR-122-5p, hsa-miR-134-5p, hsa-miR-140-5p, hsa-miR-142-3p, hsa-miR-145-3p, hsa-miR-148a-3p, hsa-miR-150-5p p, hsa-miR-191-5p, hsa-miR-200b-3p, hsa-miR-204-3p, hsa-miR-206, hsa-miR-224-5p, hsa-miR-24-1-5p, hsa-miR-26b-5p, hsa-miR-483-5p, hsa-miR-485-5p, hsa-miR-664a-5p, hsa-miR-760 or hsa-miR-95-3p, or a combination of at least two thereof.

[0010] The carbohydrate antigen CA19-9 is a mucin-type carbohydrate protein tumor marker, a glycolipid on the cell membrane, a Lewis blood group antigen tumor marker, and exists in the form of salivary mucin in serum. The present invention combines miRNA with CA19-9 as a high-efficiency biomarker for the diagnosis of pancreatic cancer and non-pancreatic cancer, thereby improving the accuracy of pancreatic cancer diagnosis.

[0011] Preferably, the microRNA includes any one of hsa-miR-26b-5p, hsa-miR-95-3p, hsa-miR-224-5p, hsa-miR-150-5p or hsa-miR-122-5p, or a combination of at least two thereof.

[0012] Preferably, the microRNA includes hsa-miR-26b-5p, hsa-miR-95-3p, hsa-miR-224-5p and hsa-miR-150-5p.

[0013] Preferably, the biomarker is used to distinguish between pancreatic cancer patients and non-pancreatic cancer patients.

[0014] Preferably, the non-pancreatic cancer population includes healthy people and pancreatitis patients.

[0015] Preferably, the microRNA is derived from exosomes.

[0016] Preferably, the exosomes are derived from any one or a combination of at least two of blood, serum, serous fluid, plasma, lymph, urine, cerebrospinal fluid, saliva, vaginal secretions, milk, tears or ascites.

[0017] Preferably, the microRNA is derived from plasma exosomes.

[0018] Preferably, the CA19-9 is derived from serum.

[0019] Preferably, the nucleic acid sequence of hsa-miR-26b-5p includes the sequence shown in SEQ ID NO.1.

[0020] Preferably, the nucleic acid sequence of the hsa-miR-95-3p includes the sequence shown in SEQ ID NO.2.

[0021] Preferably, the nucleic acid sequence of the hsa-miR-224-5p includes the sequence shown in SEQ ID NO.3.

[0022] Preferably, the nucleic acid sequence of the hsa-miR-150-5p includes the sequence shown in SEQ ID NO.4.

[0023] SEQ ID NO. 1: UUCAAGUAAUUCAGGAUAGGU.

[0024] SEQ ID NO. 2: UUCAACGGGUAUUUAUUGAGCA.

[0025] SEQ ID NO. 3: CAAGUCACUAGUGGUUCCGUU.

[0026] SEQ ID NO. 4: UCUCCCAACCCUUGUACCAGUG.

[0027] In a second aspect, the present invention provides use of the biomarker described in the first aspect in the diagnosis of pancreatic cancer.

[0028] In a third aspect, the present invention provides a composition or a kit for evaluating, diagnosing or monitoring pancreatic cancer, wherein the composition or the kit comprises a detection reagent for the biomarker described in the first aspect.

[0029] Preferably, the composition or kit comprises a reagent for detecting the content of microRNA and a reagent for detecting the content of CA19-9.

[0030] Preferably, the reagents for detecting the content of microRNA include RNA reverse transcription reagents, DNA amplification primers and amplification reagents.

[0031] Preferably, the reagent for detecting the CA19-9 content includes an antibody that recognizes CA19-9, preferably a monoclonal antibody.

[0032] In a fourth aspect, the present invention provides a diagnostic model for the risk of pancreatic cancer, using the biomarker combination hsa-miR-26b-5p, hsa-miR-95-3p, hsa-miR-224-5p, hsa-miR-150-5p and CA19-9 described in the first aspect, and adopting five machine learning algorithms including K nearest neighbor, random forest, extreme random tree, neural network and gradient boosting machine, presetting different hyperparameters for each algorithm, and training the machine learning algorithm with training set sample data to obtain the diagnostic model.

[0033] The present invention establishes a pancreatic cancer risk prediction model based on the determined biomarkers, namely, a combination of hsa-miR-26b-5p, hsa-miR-95-3p, hsa-miR-224-5p, hsa-miR-150-5p and CA19-9, which has high sensitivity and high specificity.

[0034] Preferably, the risk scoring model of the diagnostic model is as follows:

[0035]

[0036] Where: x i represents the model's prediction result for sample i, P(x i ) is the probability of the corresponding classification of sample i predicted by the diagnostic model, where 0 represents non-cancer, i.e. healthy person or pancreatitis, and 1 represents pancreatic cancer. The classification with the highest probability is taken as the final prediction result of sample i.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] The present invention has developed a biomarker for distinguishing pancreatic cancer from non-pancreatic cancer (including non-disease and pancreatitis), and the detection reagent of the biomarker is applied to the preparation of a composition or kit for evaluating, diagnosing or monitoring pancreatic cancer, wherein the biomarker includes miRNA and CA19-9, preferably miRNA derived from plasma exosomes, with high sensitivity and high specificity. The present invention also establishes a high-efficiency diagnostic model for the risk of pancreatic cancer, reduces the false positive rate of pancreatic cancer diagnosis, reduces the waste of clinical medical resources, and improves the quality of life of pancreatic cancer patients in my country. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is the result of transmission electron microscopy identification of plasma exosomes;

[0040] Figure 2is the distribution diagram of plasma exosome particle size;

[0041] Figure 3 This is the ROC curve diagram for the training cohort;

[0042] Figure 4 ROC curve for the validation cohort. DETAILED DESCRIPTION

[0043] To further illustrate the technical means and effects of the present invention, the present invention is further described below in conjunction with the embodiments and drawings. It should be understood that the specific implementation methods described herein are only used to explain the present invention, rather than to limit the present invention.

[0044] If no specific techniques or conditions are specified in the examples, the techniques or conditions described in the literature in the field or the product instructions are used. If no manufacturer is specified for the reagents or instruments used, they are all conventional products that can be purchased through regular channels.

[0045] Reagents and instruments used in the following examples:

[0046] 0.45 μm centrifugal filter tube: purchased from Corning, USA, product number is CLS8163-100EA;

[0047] 0.22 μm centrifugal filter tube: purchased from Corning, USA, product number is CLS8161-100EA;

[0048] Exosome precipitant: purchased from Shanghai Siludi Biomedical Technology Co., Ltd., product number L3525;

[0049] Transmission electron microscope: purchased from Hitachi High-Technologies, Japan, product number H-7650;

[0050] Nanoparticle tracking analyzer: purchased from Malvern, UK, product model: NanoSight NS300;

[0051] miRNeasy Serum / Plasma Kit: purchased from QIAGEN, China, product number 217184;

[0052] Agilent 2100 analyzer: purchased from Agilent, USA, product number G2939B;

[0053] NEBNext Multiplex Small RNA Library Prep Set for Illumina: purchased from NEB, USA, product number is E7300L;

[0054] NucleoSpin Gel and PCR Clean-up: purchased from MACHEREY-NAGEL, Germany, product number 740609.50;

[0055] GX Touch TM HT nucleic acid analyzer: purchased from PerkinElmer, USA, product number is CLS137031.

[0056] In the following embodiments and test examples, the present invention extracts microRNA from plasma exosomes and applies it to the determination of biomarkers. It is understandable that microRNA from other sources, such as microRNA from blood, serum, serous fluid, plasma, lymph, urine, cerebrospinal fluid, saliva, vaginal secretions, milk, tears or ascites, can be applied to the present invention.

[0057] Example 1

[0058] This embodiment provides a method for discovering biomarkers related to pancreatic cancer and establishing a diagnostic model.

[0059] (1) Establishment of training cohort and validation cohort

[0060] Blood samples were collected, and samples with pathological diagnosis of non-pancreatic ductal adenocarcinoma, no surgical operation, and severe hemolysis (hemolysis grade ≥ 5) were removed, and patients with chronic pancreatitis and pancreatic ductal adenocarcinoma were retained. In addition, blood samples from healthy people were collected, and 30% of the samples were randomly selected as the validation cohort, and the rest were used as the training cohort.

[0061] (2) Extraction and characterization of plasma exosomes

[0062] (a) Blood collection and exosome extraction

[0063] Collect 10 mL of blood sample into an anticoagulant vacuum blood collection tube, place the tube in a precooled centrifuge and centrifuge at 1600 g, 4 °C for 10 min, transfer the supernatant to a new 1.5 mL centrifuge tube, centrifuge again at 16000 g, 4 °C for 15 min, and finally divide the supernatant into 1 mL per tube and store in a -80 °C refrigerator.

[0064] Take out the plasma sample, incubate it in a 37℃ water bath until it is completely thawed, centrifuge at 12000g, 4℃ for 10min, transfer 500μL of supernatant to a 0.45μm centrifugal filter tube, centrifuge at 12000g, 4℃ for 5min, filter, transfer the filtrate to a 0.22μm centrifugal filter tube, centrifuge at 12000g, 4℃ for 5min and filter again. Pipette the filtrate into a 1.5mL centrifuge tube, add 1 / 4 volume of exosome precipitant, mix well, incubate at 4℃ for 30min, then centrifuge at 4700g, 4℃ for 30min, discard the supernatant after centrifugation, and finally add 200μL PBS to suspend the exosomes.

[0065] (b) Characteristics of plasma exosomes

[0066] In order to detect the characteristics of plasma exosomes in pancreatic cancer and non-pancreatic cancer patients, the present invention uses transmission electron microscopy to detect the morphology of exosomes and nanoparticle tracking analysis (NTA) to detect the particle size distribution of exosomes.

[0067] Identification of exosome morphological characteristics: First, the isolated exosomes were resuspended in PBS, and 4% paraformaldehyde was added to fix the exosomes, and then the exosomes were transferred to a carbon-coated 200-mesh electron microscope copper grid. The copper grid was first washed twice with PBS, and then washed with fresh PBS containing glycine (50mM) for 3 minutes, and then washed again with fresh PBS containing 0.5% BSA for 10 minutes, and finally stained with 2% uranyl acetate. After staining, the exosome morphology was observed using a transmission electron microscope.

[0068] Exosome particle size distribution detection: First, take the separated exosomes and dilute them with PBS to 1×10 7 -1×10 9 / mL. Subsequently, NTA was turned on and 1mL of the diluted sample was injected into the sample chamber. The 488nm excitation module was used, and the lens parameters of the camera were set. The shutter value was selected as 890, the gain value was selected as 146, and the detection threshold was set to 7. At least 200 complete tracks were analyzed and obtained for each video. Finally, the nanoparticle tracking data of exosomes was analyzed using the NTA analysis software.

[0069] (3) Extraction and expression of plasma exosome miRNA

[0070] (a) Plasma exosome miRNA was extracted using the miRNeasy Serum / Plasma Kit. The specific experimental steps were in accordance with the product instructions, and then miRNA quantification and fragment distribution were detected using the Agilent 2100 Bioanalyzer.

[0071] (b) Expression detection of plasma exosomes

[0072] The library was constructed using the NEBNext Multiplex Small RNA Library Prep Set for Illumina kit. The specific experimental steps were in accordance with the product manual. The amount of miRNA loaded in each plasma sample was 100 ng, and the total volume did not exceed 6 μL. The library was constructed by connecting the 3' adapter, hybridizing the reverse transcription primer, connecting the 5' adapter, reverse transcription, and PCR amplification. The PCR product was then purified using the NucleoSpin Gel and PCR Clean-up kit, and the DNA was finally eluted with 30 μl NE buffer. DNA library quality control was performed using GX Touch TM HT nucleic acid analyzer and its supporting chips and reagents were used for sequencing on the Illumina Nova6000 platform with a sequencing strategy of PE150 to obtain small RNA sequencing data.

[0073] (4) Sequencing data analysis process

[0074] (a) Sequencing data alignment: After removing the sequencing adapters of the small RNA sequencing data, the sequencing data were aligned to the human reference genome hg19 using BWA software, and the number of reads aligned to the miRNA was counted.

[0075] (b) miRNA annotation: miRNAs were annotated using the Gencode v25 and miRBase v21 databases, and those annotated as known mature miRNAs were retained for subsequent analysis.

[0076] (c) miRNA filtering: For the training cohort, mature miRNAs with a length of less than or equal to 30 nt and covered by at least g samples in the training cohort data with no less than 10 reads were retained for subsequent analysis, where g is the minimum number of samples in the group after the cohort was grouped; for the validation cohort, miRNAs screened by the training cohort were retained for subsequent analysis.

[0077] (d) Normalization of miRNA expression: The trimmed mean of M-values ​​(TMM) method in the limma analysis package in R language was used to normalize the miRNA expression levels of the training cohort samples and the validation cohort samples, respectively.

[0078] (5) Discovery of biomarkers

[0079] Based on the expression of miRNAs in the training cohort, the samples were grouped according to the pathological test results, and statistical and machine learning methods were used to discover miRNAs that can be used to distinguish non-cancerous (healthy people and pancreatitis) and pancreatic ductal adenocarcinoma patients as biomarkers. The process is as follows:

[0080] (a) Training cohort grouping: Based on the results of sample pathology tests, the patient samples in the training cohort were divided into two groups: a non-cancer group (healthy people and chronic pancreatitis) and a pancreatic ductal adenocarcinoma group.

[0081] (b) Statistical methods for biomarker screening: First, the Kruskal-Wallis U test was used to analyze the expression differences of all miRNAs between the two groups, and the mutual information (MI) between all miRNA expressions and sample groups was calculated. The miRNAs with a statistical difference p value ≤ 0.1 between the groups and a mutual information score in the top 10% of all markers were screened. Then, the correlation coefficients between these miRNAs were calculated, and only the miRNAs with the largest variance were retained as candidate biomarkers among the miRNAs with a correlation coefficient > 0.8 for subsequent analysis.

[0082] (c) Screening of biomarkers using machine learning methods: The miRNA screened in step (c) was used as the initial marker and first screened using three machine learning feature screening methods.

[0083] Method 1: Evaluate the classification performance of each marker on the sample separately, and mark the markers with a performance score <0.8 as candidate discarded markers; Method 2: First, take all the initial markers as a whole to evaluate the classification performance of the sample, then randomly shuffle the expression of the markers in the sample in turn, calculate the degree of reduction in the classification performance score after the expression of each marker is shuffled, and mark the markers with a performance score reduction of <0.01 as candidate discarded markers; Method 3: First, take all the initial markers as a whole to evaluate the classification performance of the sample, and sort the markers according to their importance, then add one marker at a time starting from the most important marker and evaluate the improvement in the model score, and mark the markers with a score improvement of <0.01 as candidate discarded markers.

[0084] The intersection of candidate discarded markers obtained by the above three methods was discarded to obtain the remaining 19 markers. Subsequently, five machine learning algorithms, including K-nearest neighbor (KNN), random forest, extremely randomized trees, neural network, and gradient boosting machine (GBM), were used to train and evaluate the classification effect and feature weights of the remaining markers as a whole on the training set data. Markers with feature weights <5% were marked as candidate discarded markers. If a marker was marked as discarded by all algorithms, it was not retained. Combining the above methods, 5 candidate markers were obtained for subsequent analysis.

[0085] (d) Evaluation of candidate marker combinations: The candidate markers were combined with CA19-9 for permutation and combination, and five machine learning algorithms, including K-nearest neighbor, random forest, extreme random tree, neural network, and gradient boosting machine, were used to train and evaluate the classification effect and feature weight of all marker combinations on the training set data using a 5-fold cross-validation method. Based on the training results, markers with low feature weights and no improvement in model classification performance were removed, and finally four miRNA markers were confirmed to be combined with CA19-9 for the construction of pancreatic cancer and non-pancreatic cancer risk score models.

[0086] (6) Construction of risk scoring model for pancreatic cancer and non-pancreatic cancer

[0087] Pancreatic cancer and non-pancreatic cancer were used as the classification prediction targets. The marker combination discovered in step (5) was used. Five machine learning algorithms, namely, K nearest neighbor, random forest, extreme random tree, neural network and gradient boosting machine, were used. Different hyperparameters were preset for each algorithm. The machine learning algorithm was trained using the training set sample data to obtain a diagnostic model. A risk scoring model of the diagnostic model was constructed. The model formula is as follows:

[0088]

[0089] Where: x i represents the model's prediction result for sample i, P(x i ) is the probability of the corresponding classification of sample i predicted by the diagnostic model, where 0 represents non-cancer, i.e. healthy person or pancreatitis, and 1 represents pancreatic cancer. The classification with the highest probability is taken as the final prediction result of sample i. The trained model is saved in the hard disk as a file. When calling the model, the sample marker expression value is input to obtain the model prediction result.

[0090] (7) Evaluation and verification of risk scoring model performance

[0091] In the training set, the 4-fold cross-validation method was used to evaluate the classification effect and feature weight of the model. In the validation set, the self-sampling method (bootstrap, 100 times) was used to evaluate the classification effect and feature weight of the model. Model evaluation and validation indicators include the area under the receiver operating characteristic curve (AUC, ranging from 0 to 1), balanced accuracy (ranging from 0 to 1), specificity (ranging from 0 to 1), and sensitivity (ranging from 0 to 1). The higher the value, the better the model classification performance.

[0092] (8) Application of risk scoring models for pancreatic cancer and non-pancreatic cancer

[0093] (a) Peripheral blood was collected from patients with suspected pancreatic cancer in clinical diagnosis, plasma exosomes were obtained, and the expression of biomarkers was obtained using small RNA sequencing;

[0094] (b) using the risk scoring model, the expression values ​​of plasma exosomal hsa-miR-26b-5p, hsa-miR-95-3p, hsa-miR-224-5p, and hsa-miR-150-5p, and the expression level of serum CA19-9 were obtained, and the values ​​were put into the trained model formula and program to calculate the probability of each patient being predicted to have non-pancreatic cancer and pancreatic cancer;

[0095] (c) Select the output result with the highest probability and give the predicted results of pancreatic cancer risk for each patient.

[0096] Test Example 1

[0097] This test case obtained biomarkers associated with pancreatic cancer and characterized their specificity and sensitivity.

[0098] (1) Establishment of training cohort and validation cohort

[0099] Blood samples from 107 patients were collected, and samples with pathological diagnosis of non-pancreatic ductal adenocarcinoma, no surgical operation and severe hemolysis (hemolysis grade ≥ 5) were removed. 32 patients with chronic pancreatitis and 56 patients with pancreatic ductal adenocarcinoma were retained for inclusion in the group, and blood samples were collected from patients before surgery. In addition, blood samples from 27 healthy people were collected. Finally, a total of 115 samples were included in the group, 30% of which were randomly selected as the validation cohort, and the rest were used as the training cohort.

[0100] The training cohort consisted of 80 cases, including 41 non-cancerous samples (healthy people and patients with chronic pancreatitis) and 39 pancreatic ductal adenocarcinoma samples. The validation cohort consisted of 35 cases, including 18 non-cancerous samples and 17 pancreatic ductal adenocarcinoma samples. Table 1 shows the clinical information of the patients, including the gender and age information of chronic pancreatitis and pancreatic ductal adenocarcinoma samples and the serum CA19-9 expression results of all samples. The analysis results showed that there was no significant difference in gender, age, serum CA19-9 expression and the proportion of samples of different classifications between the two groups of patients.

[0101] Table 1

[0102]

[0103]

[0104] (2) Extraction and characteristics of plasma exosomes

[0105] The exosomes were extracted from the plasma of pancreatic cancer and non-pancreatic cancer patients, and the morphology of the exosomes was detected by transmission electron microscopy, such as Figure 1 As shown, exosomes present a typical "horseshoe-shaped" morphology, and the NTA test results are as follows Figure 2 As shown, the average particle size of exosomes in representative samples was 123.3 nm, which was consistent with the particle size distribution of exosomes.

[0106] (3) Discovery of biomarkers

[0107] The present invention uses small RNA sequencing to detect the expression level of plasma exosomal miRNA in pancreatic cancer patients and non-pancreatic cancer people. The statistical method Kruskal-Wallis U test is used to analyze the expression difference of all miRNAs between pancreatic cancer patients and non-pancreatic cancer people and the correlation coefficient between miRNAs. At the same time, three machine learning feature screening methods are used to screen miRNAs that can be used to distinguish pancreatic cancer patients from non-pancreatic cancer people as biomarkers. Candidate molecular markers include hsa-miR-122-5p, hsa-miR-134-5p, hsa-miR-140-5p, hsa-miR-142-3p, hsa-miR-145-3p, hsa-miR-148a-3p, hsa -miR-150-5p, hsa-miR-191-5p, hsa-miR-200b-3p, hsa-miR-204-3p, hsa-miR-206, hsa-miR-224-5p, hsa-miR-24-1-5p, hsa-miR-26b-5p, hsa-miR-483-5p, hsa-miR-485-5p, hsa-miR-664a-5p, hsa-miR-760, and hsa-miR-95-3p, a total of 19, were used for subsequent analysis. Subsequently, five machine learning algorithms, including K nearest neighbor, random forest, extreme random tree, neural network, and gradient boosting machine, were used to mark markers with feature weights < 5% as candidate discarded markers. If a marker was marked as discarded by all algorithms, it was not retained. A total of five markers were obtained as candidate markers, including hsa-miR-26b-5p, hsa-miR-95-3p, hsa-miR-224-5p, hsa-miR-150-5p, and hsa-miR-122 -5p, and the last five candidate markers were combined with CA19-9 for permutations and combinations (a total of 63 combinations). The marker hsa-miR-122-5p, which had a low feature weight and did not improve the model classification performance, was removed. The final marker combination was CA19-9 and four miRNAs (hsa-miR-26b-5p, hsa-miR-95-3p, hsa-miR-224-5p, and hsa-miR-150-5p), which was used to subsequently construct a pancreatic cancer and non-pancreatic cancer risk scoring model.

[0108] (4) Pancreatic cancer and non-pancreatic cancer risk scoring model

[0109] In order to construct a pancreatic cancer and non-pancreatic cancer risk scoring model, the miRNA expression data of the training cohort was used. In the training set, the classification effect and feature weight of the model were evaluated using the 4-fold cross-validation method. Combined with the pathological test results, a pancreatic cancer and non-pancreatic cancer risk scoring model was constructed. The predicted results of the risk of pancreatic cancer for each patient were given according to the model formula and program.

[0110] The model evaluation indicators include the area under the receiver operating characteristic curve (ROC curve) (AUC, value range 0-1), balanced accuracy (value range 0-1), specificity (value range 0-1) and sensitivity (value range 0-1). The results are shown in Table 2, which are 0.96, 0.95, 0.93 and 0.97 respectively. The ROC curve is shown in Figure 3 The results showed that in the training cohort, this risk prediction model had a high AUC, balanced accuracy, specificity and sensitivity, and had better model prediction performance.

[0111] Table 2

[0112]

[0113] (5) Application and efficacy validation of pancreatic cancer and non-pancreatic cancer risk scoring models

[0114] The expression values ​​of plasma exosomes hsa-miR-26b-5p, hsa-miR-95-3p, hsa-miR-224-5p, and hsa-miR-150-5p and serum CA19-9 of the validation cohort were brought into the trained model formula and program to calculate the probability of each patient being predicted to have non-pancreatic cancer and pancreatic cancer. The output result with the highest probability was selected to give the predicted result of each patient's risk of pancreatic cancer.

[0115] In order to verify the effectiveness of the risk score model in predicting pancreatic cancer, the self-sampling method (bootstrap, 100 times) was used to evaluate the classification effect and feature weight of the model for the validation set. Taking the pathological test results as the true value, the model evaluation indicators include the area under the receiver operating characteristic curve (ROC curve) (AUC, ranging from 0 to 1), balanced accuracy (ranging from 0 to 1), specificity (ranging from 0 to 1) and sensitivity (ranging from 0 to 1). The results are shown in Table 3, which are 0.93, 0.91, 1 and 0.82 respectively. The ROC curve is shown in Figure 4 The results showed that in the validation cohort, this risk prediction model had a high AUC, balanced accuracy, specificity, and sensitivity, and had a better predictive performance.

[0116] Table 3

[0117] Algorithm Model AUC Balanced Accuracy Specificity Sensitivity Neural Network (NeuralNetTorch) 0.9314 0.9118 1.0000 0.8235 Neural Network (NeuralNetFastAI) 0.9673 0.8824 1.0000 0.7647 Random Forest (RandomForestGini) 0.9510 0.8824 1.0000 0.7647 Gradient Boosting Machine (LightGBMXT) 0.9673 0.8824 1.0000 0.7647 Gradient Boosting Machine (LightGBM) 0.9771 0.8824 1.0000 0.7647 Random Forest (RandomForestEntr) 0.9608 0.8824 1.0000 0.7647 ExtraTreesGini 0.9641 0.9118 1.0000 0.8235 ExtraTreesEntr 0.9608 0.8824 1.0000 0.7647 Gradient Boosting Machine (CatBoost) 0.9673 0.8824 1.0000 0.7647 K NeighborsUnif 0.9363 0.8562 0.8889 0.8235

[0118] In summary, the present invention has developed a biomarker for distinguishing pancreatic cancer from non-pancreatic cancer (including non-disease and pancreatitis), and applied the detection reagent of the biomarker to prepare a composition or kit for evaluating, diagnosing or monitoring pancreatic cancer, wherein the biomarker includes plasma exosome miRNA and CA19-9, which have high sensitivity and high specificity. The present invention also establishes a high-efficiency diagnostic model for the risk of pancreatic cancer, reduces the false positive rate of pancreatic cancer diagnosis, reduces the waste of clinical medical resources, and improves the quality of life of pancreatic cancer patients in my country.

[0119] The applicant declares that the above is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Those skilled in the art should understand that any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention shall fall within the protection scope and disclosure scope of the present invention.

Claims

1. Use of a biomarker detection reagent in the preparation of a composition or kit for evaluating, diagnosing or monitoring pancreatic cancer, characterized in that: The biomarkers include microRNA and CA19-9; the microRNAs include hsa-miR-122-5p, hsa-miR-134-5p, hsa-miR-140-5p, hsa-miR-142-3p, hsa-miR-145-3p, hsa-miR-148a-3p, hsa-miR-150-5p, hsa-miR-191-5p, hsa-miR- any one of hsa-miR-200b-3p, hsa-miR-204-3p, hsa-miR-206, hsa-miR-224-5p, hsa-miR-24-1-5p, hsa-miR-26b-5p, hsa-miR-483-5p, hsa-miR-485-5p, hsa-miR-664a-5p, hsa-miR-760 or hsa-miR-95-3p, or a combination of at least two thereof.

2. The use according to claim 1, characterized in that: The microRNA includes any one of hsa-miR-26b-5p, hsa-miR-95-3p, hsa-miR-224-5p, hsa-miR-150-5p or hsa-miR-122-5p, or a combination of at least two thereof.

3. The use according to claim 1, characterized in that: The microRNAs include hsa-miR-26b-5p, hsa-miR-95-3p, hsa-miR-224-5p and hsa-miR-150-5p; Preferably, the biomarker is used to distinguish between pancreatic cancer patients and non-pancreatic cancer patients; Preferably, the non-pancreatic cancer population includes healthy people and pancreatitis patients.

4. The use according to claim 1, characterized in that: The microRNA is derived from exosomes; Preferably, the exosomes are derived from any one or a combination of at least two of blood, serum, serous fluid, plasma, lymph, urine, cerebrospinal fluid, saliva, vaginal secretions, milk, tears or ascites; Preferably, the microRNA is derived from plasma exosomes; Preferably, the CA19-9 is derived from serum.

5. The use according to claim 1, characterized in that: The nucleic acid sequence of hsa-miR-26b-5p includes the sequence shown in SEQ ID NO.1; Preferably, the nucleic acid sequence of hsa-miR-95-3p includes the sequence shown in SEQ ID NO.2; Preferably, the nucleic acid sequence of hsa-miR-224-5p includes the sequence shown in SEQ ID NO.3; Preferably, the nucleic acid sequence of the hsa-miR-150-5p includes the sequence shown in SEQ ID NO.

4.

6. Use of the biomarker as claimed in any one of claims 1 to 5 in the diagnosis of pancreatic cancer.

7. A composition or kit for evaluating, diagnosing or monitoring pancreatic cancer, characterized in that: The composition or kit comprises a detection reagent for the biomarker described in any one of claims 1-5.

8. The composition or kit according to claim 7, characterized in that The composition or kit includes a reagent for detecting the content of microRNA and a reagent for detecting the content of CA19-9; Preferably, the reagents for detecting the microRNA content include RNA reverse transcription reagents, DNA amplification primers and amplification reagents; Preferably, the reagent for detecting the CA19-9 content includes an antibody that recognizes CA19-9, preferably a monoclonal antibody.

9. A diagnostic model for the risk of pancreatic cancer, characterized in that: Using the biomarker combination hsa-miR-26b-5p, hsa-miR-95-3p, hsa-miR-224-5p, hsa-miR-150-5p and CA19-9 described in any one of claims 1 to 5, a total of five machine learning algorithms including K nearest neighbor, random forest, extreme random tree, neural network and gradient boosting machine are adopted, different hyperparameters are preset for each algorithm, and the machine learning algorithm is trained using the training set sample data to obtain the diagnostic model.

10. The diagnostic model according to claim 9, characterized in that The risk scoring model of the diagnostic model is as follows: Where: x i represents the model's prediction result for sample i, P(x i ) is the probability of the corresponding classification of sample i predicted by the diagnostic model, where 0 represents non-cancer, i.e. healthy person or pancreatitis, and 1 represents pancreatic cancer. The classification with the highest probability is taken as the final prediction result of sample i.

Images