Application of metabolite in diabetes diagnosis

Abstract

The invention discloses an application of a metabolite in diagnosis of diabetes mellitus. The metabolite is levodopa. According to the invention, the metabolite as the biomarker shows significant difference between diabetic patients and healthy people for the first time, and has a relatively high AUC value, which prompts that the metabolite marker has a relatively high diagnostic value in diabetes mellitus.

Description

TECHNICAL FIELD

[0001] The present application relates to the application of metabolites in the diagnosis of diabetes, belonging to the field of biological medicine. BACKGROUND

[0002] Diabetes is a metabolic disease characterized by high blood sugar. Its incidence in clinical practice is about 9-11%. The incidence of type 2 diabetes accounts for more than 95% of the total incidence of diabetes, which is the main type of diabetes. The onset of diabetes is a slow process, and most diabetic patients may not be diagnosed for years, which can easily cause the occurrence of complications such as macrovascular disease and microvascular disease. Once these complications occur, the existing drug control effect is poor, and the patient's physical health will be seriously affected. Therefore, early diagnosis and intervention of diabetes is very important.

[0003] Untargeted metabolomics is a research method of metabolomics, which aims to comprehensively analyze and identify all small molecule metabolites in the body and their abundance changes. Compared with targeted metabolomics, untargeted metabolomics does not specify certain specific metabolites in advance, but systematically detects and analyzes all metabolites in the sample, so it is more suitable for exploratory research, such as discovering new metabolic pathways and identifying potential biomarkers. Untargeted metabolomics extracts metabolites from biological samples (blood, urine, tissue, etc.); then uses mass spectrometry (MS) or nuclear magnetic resonance (NMR) technology, often combined with liquid chromatography (LC) or gas chromatography (GC), to separate and detect metabolites; the generated raw data is subjected to complex data preprocessing; by comparing with the metabolite database, each metabolite is identified; finally, statistical analysis or network analysis tools are used to explain the relationship between metabolite changes and biological phenomena.

[0004] At present, the main means of detecting diabetes includes several common laboratory tests and rapid detection methods, which aim to assess blood glucose levels and insulin metabolism. These include fasting plasma glucose (FPG), oral glucose tolerance test (OGTT), glycosylated hemoglobin (HbA1c), random blood glucose test, insulin and C-peptide level test, urine glucose test, and urine ketone test. The above detection methods are mostly invasive or minimally invasive; non-invasive detection methods using urine as the detection sample are not sensitive. Therefore, choosing a non-invasive, sensitive sample and using it for untargeted metabolomics research on diabetes is of great significance for finding new biomarkers for early diabetes and making timely diagnosis and treatment. SUMMARY

[0005] In view of the deficiencies of the prior art, the present application aims to provide an application of metabolites in diagnosis of diabetes.

[0006] In order to achieve the above-mentioned application purposes, the present application provides the following technical solutions.

[0007] The first aspect of the present application provides a metabolite marker related to diabetes, and the metabolite marker is levodopa.

[0008] In the present application, metabolites refer to intermediate products and end products of metabolism, and are also sometimes referred to as small molecules or analytes with a molecular weight of less than 1500 daltons. Metabolites are classified as primary metabolites that directly participate in normal growth, development and reproduction. Secondary metabolites do not directly participate in the latter processes, but can have important ecological functions (e.g., antibiotics, pigments). Exemplary biological functions of metabolites include as intermediate or end-point products in biosynthetic pathways or as cell signaling molecules.

[0009] The second aspect of the present application provides an application of a reagent for detecting the level of the metabolite marker of the first aspect of the present application in a sample in the preparation of a product for diagnosing diabetes.

[0010] Further, the reagent detects the level of the metabolite marker in the sample by one or more of targeted or non-targeted nuclear magnetic resonance method, chromatography method, spectroscopy method, mass spectrometry method, chromatography-mass spectrometry method.

[0011] Further, the chromatography method includes gas chromatography method, capillary electrophoresis method, liquid chromatography method, high liquid chromatography method, ultra-high performance liquid chromatography method.

[0012] Further, the spectroscopy method includes ultraviolet-visible spectroscopy method, infrared spectroscopy method, near-infrared spectroscopy method, nuclear magnetic resonance spectroscopy method.

[0013] Further, the mass spectrometry includes, for example, tandem mass spectrometry, matrix-assisted laser desorption ionization (MALDI) time-of-flight (TOF) mass spectrometry, MALDI-TOF-TOF mass spectrometry, MALDI quadrupole-time-of-flight (Q-TOF) mass spectrometry, electrospray ionization (ESI) TOF mass spectrometry, ESI-Q-TOF, ESI-TOF-TOF, ESI-ion trap mass spectrometry, ESI triple quadrupole mass spectrometry, ESI Fourier transform mass spectrometry (FTMS), MALDI-FTMS, MALDI-ion trap-TOF, and ESI-ion trap TOF. At its most basic level, mass spectrometry involves ionizing molecules and then measuring the masses of the resulting ions. Because molecules ionize in a well-known manner, the molecular weight of a molecule can be determined exactly from the mass of the ion. Chromatography-mass spectrometry, also known as liquid chromatography-mass spectrometry, combines the physical separation capabilities of liquid chromatography (LC) or high-performance liquid chromatography (HPLC) with the mass analysis capabilities of mass spectrometry (MS). HPLC provides advantages over LC with shorter analysis times and better resolution of analytes. This thus increases the selectivity, precision, and accuracy of MS.

[0014] Further, the reagent is for detecting the level of the metabolite marker in the sample by chromatography-mass spectrometry.

[0015] Further, the diagnosis refers to when the level of the metabolite marker in the sample of the subject is down-regulated, the subject has diabetes or is at risk of developing diabetes.

[0016] In the case where reference results are obtained from subjects or populations known not to have diabetes, the disease or susceptibility can be diagnosed based on the difference between the detection results obtained from the sample and the aforementioned reference results, i.e. based on the difference in the qualitative or quantitative composition with respect to at least one metabolite. The difference can be an increase in the absolute or relative amount of the metabolite (also known as up-regulation of the metabolite) or a decrease in the amount of the metabolite or no detectable amount (also known as down-regulation of the metabolite). Preferably, the difference in the relative or absolute amount is significant, i.e. outside the reference value interval of 45 to 55 percentiles, 40 to 60 percentiles, 30 to 70 percentiles, 20 to 80 percentiles, 10 to 9 percentiles, 5 to 95 percentiles.

[0017] Further, the subject refers to any individual of interest, preferably, the subject is a living organism, including humans, other mammals, who has or is suspected to have diabetes.

[0018] Further, the product includes a kit, a chip.

[0019] In the present application, the product can comprise a solid substrate such as a chip, a slide, an array, etc. having reagents capable of detecting and / or quantifying one or more blood metabolites or fecal metabolites immobilized at predetermined locations on the substrate. As an illustrative example, a chip can be provided with reagents immobilized at discrete predetermined locations for detecting and quantifying the concentration of any number or any combination of the metabolite markers in a blood or fecal sample.

[0020] Further, the product also comprises an instruction manual which should clearly instruct how to use the product to assess whether a subject has diabetes or is at risk of developing diabetes.

[0021] Further, the sample is a biological sample. A sample of biological origin (i.e. a biological sample) typically comprises a plurality of metabolites. Preferred experimental samples to be used in the method of the present application are samples from a body fluid, preferably from blood, plasma, serum, feces, lymph, sweat, saliva, tears, semen, vaginal fluid, urine or cerebrospinal fluid, or from a sample from a cell, tissue or organ, e.g. by vivisection. This also includes samples comprising subcellular compartments or organelles (such as mitochondria, Golgi network or peroxisomes). Furthermore, a biological sample also includes a gaseous sample, such as a volatile of an organism. The biological sample is from a subject as specified elsewhere herein. Techniques for obtaining the different types of biological samples as described above are well known in the art. For example, a blood sample is obtained by blood collection, a urine sample is obtained by urine collection, a fecal sample is obtained by fecal collection.

[0022] Further, the sample is selected from the group consisting of blood, serum, plasma, feces.

[0023] Further, the sample is pre-treated prior to its use in the detection according to the present application. The pre-treatment can include treatments necessary to release or isolate the compounds, or to remove excess material or waste. Suitable techniques include centrifugation, extraction, fractionation, purification and / or enrichment of the compounds. Furthermore, other pre-treatments are performed to provide the compounds in a form or concentration suitable for analysis. For example, if gas chromatography coupled to mass spectrometry is used in the method of the present application, it will be necessary to derivatize the compounds prior to the gas chromatography. Suitable and necessary pre-treatments depend on the tools used to perform the method of the present application and are well known to the person skilled in the art. Samples pre-treated as described before are also included in the term "sample" as used in the present application.

[0024] A third aspect of the present application provides a product for the diagnosis of diabetes, the product comprising reagents for detecting the level of the metabolite markers according to the first aspect of the present application in a sample.

[0025] Further, the reagents detect the level of the metabolite markers in the sample by one or several of targeted or non-targeted nuclear magnetic resonance, chromatography, spectroscopy, mass spectrometry, chromatography-mass spectrometry.

[0026] Further, the sample is selected from blood, serum, plasma, and feces.

[0027] Further, the product further comprises reagents for processing the sample.

[0028] Further, the product comprises a kit, a chip.

[0029] The fourth aspect of the present application provides an application of the metabolite marker of the first aspect of the present application in constructing a computational model for diagnosing diabetes.

[0030] The fifth aspect of the present application provides a system for diagnosing diabetes, which comprises:

[0031] 1) a data acquisition unit for acquiring the metabolite marker level data of the first aspect of the present application.

[0032] 2) a data classification unit for comparing the metabolite marker level data with the reference value.

[0033] 3) an output unit for outputting and storing the analysis result, indicating whether the subject has diabetes or has a risk of developing diabetes.

[0034] The sixth aspect of the present application provides an application of the metabolite marker of the first aspect of the present application or a pharmaceutically acceptable salt thereof in preparing a pharmaceutical composition for treating diabetes.

[0035] Further, the pharmaceutically acceptable salt refers to a salt of an active compound and is prepared by reacting the metabolite marker of the first aspect of the present application with a suitable organic or inorganic acid or acid derivative. The pharmaceutically acceptable salt includes but is not limited to hydrochloride, sulfate, phosphate, citrate, hydrobromide, acetate, benzoate, benzenesulfonate, tartrate, carbonate, citrate, gluconate, lactate, malate, methanesulfonate, stearate, valerate, nitrate, sodium salt, calcium salt, potassium salt, zinc salt, and meglumine salt.

[0036] Further, the pharmaceutical composition further comprises a pharmaceutically acceptable carrier.

[0037] Further, the pharmaceutically acceptable carrier refers to any pharmaceutical carrier which does not itself induce the production of antibodies harmful to the individual who receives the composition, and which can be administered without undue toxicity. Suitable carriers can be large, slowly metabolized macromolecules such as proteins, polysaccharides, polylactic acids, polyglycolic acids, polymeric amino acids, and amino acid copolymers. Such carriers are well known in the art. The pharmaceutically acceptable carrier in the pharmaceutical composition can comprise fluids such as water, saline, glycerol, and ethanol. There can also be present auxiliary substances such as wetting or emulsifying agents, pH buffering substances, and the like.

[0038] The advantages and beneficial effects of the present application are: 1. The present application detects and diagnoses diabetes early by detecting metabolites in blood and feces, and the detection of fecal samples has the advantages of non-invasiveness and sensitivity, providing a means for rapid detection of diabetes.

[0039] 2. The present application first found that levodopa as a metabolite marker can be used for early diagnosis of diabetes, which has strong difference in patient samples and healthy samples, high detection sensitivity, and provides a strong basis for early diagnosis of diabetes. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 Figure is a graph of 12h fasting blood glucose detection of mice in the modeling process.

[0041] Figure 2 Figure is a graph of glucose tolerance test of mice in each group at the seventh week after intestinal flora transplantation.

[0042] Figure 3 Figure is a graph of glucose tolerance test of mice in each group at the tenth week after intestinal flora transplantation.

[0043] Figure 4 Figure is a graph of the abundance of levodopa in the serum and feces of mice in each group and the ROC curve, wherein A is the abundance of levodopa in the serum of mice in each group, B is the ROC curve of levodopa in the serum for diagnosing diabetes, C is the abundance of levodopa in the feces of mice in each group, and D is the ROC curve of levodopa in the feces for diagnosing diabetes.

[0044] Figure 5 Figure is a graph of the abundance of levodopa in the serum of diabetes patients and healthy people and the ROC curve, wherein A is the abundance of levodopa in the serum of diabetes patients and healthy people, and B is the ROC curve of levodopa in the serum for diagnosing diabetes.

[0045] Figure 6 Figure is a flowchart of a computer-implemented method for diagnosing diabetes.

[0046] Figure 7 Figure is a schematic diagram of the structure of a diabetes diagnosis system.

[0047] Figure 8 Figure is a schematic diagram of the structure of a computer device for diagnosing diabetes. DETAILED DESCRIPTION

[0048] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0049] In some of the processes described in the specification, claims, and accompanying drawings of this invention, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be performed in the order they appear herein, or may be performed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not themselves represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be performed sequentially or in parallel.

[0050] Example 1: Screening and detection of diabetes-related metabolites

[0051] I. Stool collection from diabetic patients

[0052] 1. Cohort Recruitment Population: Clinical samples were obtained from Taihe County People's Hospital. The specimen collection process was approved by the Biomedical Research Ethics Review Committee involving human subjects (ethics number: YZW23002), and was carried out in accordance with the principles of the Declaration of Helsinki, with informed consent from all subjects.

[0053] Clinical samples (3 patients and 12 healthy individuals) collected from February to September 2023 were used for the establishment of a germ-free mouse microbiota transplantation model and subsequent research; clinical samples (30 patients and 37 healthy individuals) collected from January to June 2025 were used as an independent validation set to validate the diagnostic efficacy of levodopa in the blood of diabetic patients and healthy individuals.

[0054] 1.1 Type 2 Diabetes Recruitment Population

[0055] Inclusion criteria: According to the 2006 WHO diabetes diagnostic criteria, T2DM is determined by measured venous blood glucose level, normal glucose tolerance: fasting blood glucose (FBG) <6.1 mmol / L (110 mg / dL) and 2hFBG <7.8 mmol / L (140 mg / dL); T2DM: FBG≥7.0 mmol / L (126 mg / dL), random blood glucose≥11.1 mmol / L (200 mg / dL) or 2h FBG≥11.1 mmol / L (200 mg / dL) after oral glucose tolerance test (OGTT).

[0056] Exclusion criteria: Pregnant women, lactating women; have a history of mental illness; have surgery and other emergency situations; recent use of antibiotics, probiotics and drug abuse; have blood system diseases, endocrine system diseases, have obvious liver and kidney function damage, chronic gastrointestinal function disorders, gastrointestinal diseases, ketosis acidosis disease history; patients undergoing insulin therapy; special type of diabetes, type 1 diabetes patients.

[0057] 1.2 Health control group inclusion criteria: confirmed by physician inquiry, physical examination and blood test as healthy population.

[0058] 2. Sample collection

[0059] Blood sample collection and preservation: For participants, peripheral venous blood was drawn the next morning after admission, and fresh serum samples were collected and immediately frozen at -80℃. All clinical information was collected according to standard procedures.

[0060] Fecal sample collection and preservation: according to the instructions, the fecal microbial genome protection liquid kit was used for collection and storage at -80℃, and the supernatant was centrifuged as the fecal transplant liquid.

[0061] II. Establishment of diabetic mouse model and screening of differential metabolites

[0062] 1. Establishment of diabetic mouse model

[0063] 1.1 Use the optimized flora transplantation method and standard sterile animal model to make conditions, inoculate the feces of patients with human-related diseases into the intestinal tract of mice by gavage, and establish an intestinal flora animal model that can simulate the human diabetes phenotype.

[0064] 1.2 Record the body weight, food intake, water intake of mice every week, and detect the fasting blood glucose of mice every two weeks (detect the blood glucose of mice after fasting for 12 h, and resume feeding after the experiment is completed).

[0065] 1.3 Glucose tolerance test (GTT) is a glucose load test to understand the function of pancreatic beta cells and the body's ability to regulate blood sugar, which is a definitive test for the diagnosis of diabetes.

[0066] Methods: The mice were weighed and labeled at 5 pm the day before the experiment, and then were placed in a clean cage for 12 h of fasting and water deprivation before starting the glucose tolerance test. Fasting blood glucose measurement: The mice were taken out of the cage, and the tail tip was cut off about 1-2 mm with scissors. The tail was gently squeezed along the tail vein to make a drop of blood, and the first drop of blood was discarded. The second drop of blood was used to measure the fasting blood glucose with a blood glucose meter and blood glucose test paper. The measured value was taken as the blood glucose value at 0 min. The glucose concentration for the glucose tolerance test was 2 g / kg body weight, and a 200 mg / ml glucose solution was prepared with normal saline. The mice were gently picked up and injected with the glucose solution using a 1 mL syringe according to the standard abdominal injection procedure. The volume of injection was determined according to the body weight of the mice, and 0.01 mL was injected per g of body weight. The timing started from the completion of injection. The interval between the operation of each mouse was 1 min, so that the blood glucose measurement of each mouse could be accurately completed according to the specified time. At 30 min, 60 min, 90 min, and 120 min, the blood glucose values at each time point of each mouse were measured according to the previous procedure. After the experiment, the mice were allowed to resume eating.

[0067] 1.4 The mice were inoculated with human intestinal flora for 10 weeks, and the mouse feces were collected after the experiment. The feces were stored at -80℃. After the mice were anesthetized with 2.5% isoflurane, the inferior vena cava was opened to collect blood, and EDTA was used for anticoagulation. The collected blood was centrifuged at 3000 rpm and 4℃ for 15 min, and the upper plasma was separated on ice and stored at -80℃.

[0068] 2. Serum and fecal non-targeted metabolomics detection and differential metabolite screening

[0069] 2.1 Sample processing

[0070] 1. Accurately transfer 100 μL of sample to a 1.5 mL centrifuge tube.

[0071] 2. Add 300 μL of extraction solution (methanol:acetonitrile=1:1(v:v)) containing four internal standards (L-2-chlorophenylalanine (0.02 mg / mL), etc.).

[0072] 3. After vortexing for 30 s, perform low-temperature ultrasonic extraction for 30 min (5℃, 40KHz).

[0073] 4. Let the sample stand at -20℃ for 30 min.

[0074] 5. Centrifuge for 15 min (13000 g, 4°C), remove supernatant, and dry under nitrogen.

[0075] 6. Add 100 μL of reconstitution solution (acetonitrile:water = 1:1) for reconstitution.

[0076] 7. Vortex for 30 s, and ultrasonic extraction for 5 min (5°C, 40 KHz).

[0077] 8. Centrifuge for 10 min (13000 g, 4°C), remove supernatant to the sample vial with an internal needle for analysis.

[0078] 9. In addition, 20 μL of supernatant from each sample was mixed as a quality control sample.

[0079] 2.2 LC-MS detection

[0080] Serum metabolomics was analyzed by UHPLC-MS, using a Vanquish Horizon system ultra-high performance liquid chromatography system (Thermo Scientific, Germany) and a Q-Exactive HF-X mass spectrometer (Thermo Scientific, Germany) during the period, which was completed by Shanghai Meiji Biomedicine Technology Co., Ltd. First, a certain mass of sample was accurately measured, and the extraction solution was added for metabolite extraction treatment in a low temperature environment, and then the supernatant metabolite solvent was centrifuged for liquid chromatography-mass spectrometry detection. During the detection process, the QC sample prepared by mixing the experimental samples of the same volume was used for data quality control. Then, the raw data was imported into the metabolomics processing software Progenesis QI v3.0 (Waters Corporation, Milford, USA) for baseline filtering, peak identification, integration, retention time correction, peak alignment, etc., and finally a data matrix containing retention time, mass-to-charge ratio and peak intensity, etc. information was obtained. Then, the software was used for feature peak library identification, and the MS and MS / MS mass spectrum information was matched with the metabolite database, the MS mass error was set to less than 10 ppm, and the metabolites were identified according to the secondary mass spectrum matching score. The main database is mainstream public database such as http: / / www.hmdb.ca / https: / / metlin.scripps.edu / and self-built database.

[0081] III. Experimental results

[0082] 1. Fasting blood glucose (FBG) and IPGTT of mice colonized with intestinal flora of diabetic patients Figure 1 ) and IPGTT ( Figure 2 ) of the seventh week, Figure 3Mice colonized with gut microbiota from healthy volunteers (as shown in the tenth week) exhibited disease characteristics similar to those of diabetic patients, namely elevated fasting blood glucose and impaired glucose tolerance. Specifically, mice with diabetic gut microbiota showed impaired glucose tolerance at seven weeks post-transplantation and severe impairment at ten weeks, suggesting the success of constructing a diabetic mouse model by transplanting gut microbiota from diabetic patients.

[0083] Serum of diabetic microbiota mice ( Figure 4 A in the middle) and intestinal feces ( Figure 4 The L-Dopa content in C) of the diabetic microbiota was significantly lower than that in the control group. The AUC of L-Dopa in serum and feces of the diabetic microbiota was calculated to be 1.000 and 0.912, respectively (e.g., ...). Figure 4 As shown in B and D in the figure, this indicates that the changes in L-Dopa in the serum and fecal intestines of diabetic mice are highly consistent and have a strong correlation with diabetes. This suggests that detecting changes in L-Dopa levels in the serum or gut microbiota of subjects has strong guiding significance for predicting diabetes.

[0084] The serum L-Dopa level in diabetic patients is significantly lower than that in healthy individuals. Figure 5 In the A section, the AUC of L-Dopa in the serum of diabetic patients and healthy individuals was calculated to be 0.953 (e.g., A in A). Figure 5 As shown in B in the figure, this indicates that the changes in L-Dopa in the serum of diabetic patients are highly consistent and have a strong correlation with diabetes. This suggests that detecting changes in serum levels in subjects has strong guiding significance for the early prediction and diagnosis of diabetes.

[0085] Figure 6 This invention displays a schematic flowchart of a computer-implemented method for diagnosing diabetes, specifically comprising the following steps:

[0086] 101: Acquire data, acquire the expression data of metabolite markers of the sample to be tested, wherein the metabolite marker is levodopa.

[0087] In some embodiments, the present invention recruits diabetic patients and healthy controls, collects their blood and fecal samples, and establishes a diabetic mouse model to collect their serum and fecal samples. Non-targeted metabolomics detection is performed to screen differentially expressed metabolite biomarkers. It was found that the metabolite levodopa showed significant differences between diabetic mice and control mice, suggesting that levodopa can be used as a good metabolite biomarker for the diagnosis or auxiliary diagnosis of diabetes.

[0088] 102: classification prediction, based on the prediction model, a classification prediction is made to obtain a classification result of whether the sample to be tested has diabetes. If the expression level of the metabolite marker is lower than the reference value, a classification result that the sample to be tested has diabetes or has a risk of developing diabetes is obtained; if the expression level of the metabolite marker is higher than the reference value, a classification result that the sample to be tested does not have diabetes is obtained.

[0089] In some embodiments, the method for constructing the prediction model belongs to the known art of those skilled in the art, and the steps of associating the expression level of the metabolite marker with a certain possibility or risk can be implemented and realized in different ways. Preferably, the expression level of the metabolite marker is mathematically associated with the fundamental question of whether or not to have diabetes. The determination of the metabolite marker can be combined with other clinical characteristics by any suitable prior art mathematical method, and a prediction model is constructed by a machine learning algorithm. The clinical characteristics include fasting blood glucose, 2-hour post-load blood glucose, urine glucose, urine ketone body, glycosylated hemoglobin, etc.

[0090] In some embodiments, the method of constructing the prediction model comprises: obtaining the expression levels of the metabolite markers of the training set samples and the clinical characteristics corresponding to the samples, the clinical characteristics including diabetic patients and healthy controls; constructing a model based on the expression levels of the metabolite markers and the clinical characteristics, obtaining the constructed prediction model by machine learning, and verifying the effectiveness of the constructed prediction model. The machine learning includes an algorithm model developed by various development tools; the development tools include one or more of TensorFlow, Scikit Learn, PyTorch, OpenNN, RapidMiner, Azure Machine Learning, Apache Mahout, Shogun, KNIME, Vertex AI, H2Oai, Anaconda, Keras, Tableau, Fast.ai, Catalyst, Amazon ML, MLJAR, and Spell. The algorithm model includes one or more of convolutional neural network, auto-encoding, deep belief network, linear regression, logistic regression, Lasso regression, Ridge regression, linear discriminant analysis, K-nearest neighbor algorithm, decision tree, perception, support vector machine, ensemble learning, correlation analysis, naive Bayes, AdaBoost, GBDT, XGBoost, LightGBM, CatBoost, or random forest. The verification of the effectiveness of the prediction model can be performed by the ROC curve, which is a plot of the true positive rate (sensitivity) of a test against the false positive rate (100%-specificity) of the test. It is useful to depict the performance of a particular feature (e.g., any entry of the metabolite markers described in the present disclosure and / or additional biomedical information) when distinguishing between two populations (e.g., individuals with metabolite markers higher than the reference value and lower than the reference value). The ROC curve can be generated with respect to individual features, and can be generated with respect to other individual outputs, for example, a combination of two or more features can be combined mathematically (e.g., added, subtracted, multiplied, etc.) to provide an individual sum value, and the individual sum value can be plotted in the ROC curve. In addition, any combination of multiple features in which the combination is derived from individual output values can be plotted in the ROC curve.

[0091] In the present disclosure, the term "reference value" refers to a value that is statistically related to a particular result when compared to the result of an analysis. In some embodiments, the reference value is determined from statistical conclusions of metabolomics analysis of a population of diabetic patients and a population of healthy controls. Some such studies are shown in the Examples section herein, but studies from the literature and experience of users of the methods described herein can also be used to generate or adjust the reference value.

[0092] 103: output result: output the classification result.

[0093] Figure 7 A structural schematic diagram of a diabetes diagnosis system provided by the present application is shown.

[0094] The system is programmed or otherwise configured to include a data acquisition unit 201, a data classification unit 202, and an output unit 203.

[0095] The data acquisition unit 201 is configured to acquire metabolite marker expression data in a sample.

[0096] The data classification unit 202 is configured to compare the metabolite marker expression data with reference values obtained from a prediction model constructed based on the method described in item 102, and obtain a classification result that the sample has diabetes or is at risk of developing diabetes if the expression level of the metabolite marker is lower than the reference value, or obtain a classification result that the sample does not have diabetes if the expression level of the metabolite marker is higher than the reference value.

[0097] The output unit 203 is configured to output the classification result.

[0098] The system can be an electronic device of a user or a computer system remotely located relative to the electronic device.

[0099] Figure 8 A structural schematic diagram of a computer device for diagnosing diabetes provided by the present application is shown.

[0100] The computer device 300 includes a processor 301 and a memory 302 coupled to the processor 301, and the memory 302 stores program instructions which, when executed by the processor 301, cause the processor 301 to perform the computer-implemented method for diagnosing diabetes described above. The computer device 300 can be a mobile electronic device.

[0101] The processor 301 can also be referred to as a central processing unit (CPU). The processor 301 can be an integrated circuit chip that has processing capability. The processor 301 can also be a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The general purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0102] The storage medium of the embodiment of the present application stores program instructions capable of implementing the computer-implemented method for diagnosing diabetes described above, wherein the program instructions can be stored in the storage medium in the form of a software product, including a plurality of instructions to cause a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes, or a computer, a server, a mobile phone, a tablet computer, etc.

[0103] It should be understood that the system, device and method described in the present application can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms. The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e. they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment of the present application.

[0104] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0105] The above description of the embodiments is only for understanding the method of the present application and its core idea. It should be noted that for those skilled in the art, without departing from the principles of the present application, the present application can be improved and modified in several ways, and these improvements and modifications will also fall within the protection scope of the claims of the present application.

Claims

1. A metabolite biomarker associated with diabetes, characterized in that, The metabolite marker is levodopa.

2. The use of the reagent for detecting the level of the metabolite markers of claim 1 in a sample in the preparation of products for diagnosing diabetes.

3. The application according to claim 2, characterized in that, The reagent detects the level of metabolite markers in a sample using one or more of the following methods: targeted or non-targeted nuclear magnetic resonance, chromatography, spectroscopy, mass spectrometry, and chromatography-mass spectrometry; preferably, the reagent detects the level of metabolite markers in a sample using chromatography-mass spectrometry.

4. The application according to claim 2, characterized in that, The diagnosis refers to the fact that a subject has diabetes or is at risk of developing diabetes when the levels of metabolite markers in the subject's sample are downregulated; preferably, the product includes a reagent kit and a chip.

5. The application according to claim 2, characterized in that, The samples were selected from blood, serum, plasma, and feces.

6. A product for diagnosing diabetes, characterized in that, The product includes a reagent for detecting the level of the metabolite markers of claim 1 in a sample.

7. The product according to claim 6, characterized in that, The reagent detects the level of metabolite markers in a sample using one or more of the following methods: targeted or non-targeted nuclear magnetic resonance, chromatography, spectroscopy, mass spectrometry, and chromatography-mass spectrometry; preferably, the sample is selected from blood, serum, plasma, or feces; preferably, the product also includes reagents for sample processing; preferably, the product includes a kit and a chip.

8. The application of the metabolite biomarkers of claim 1 in constructing a computational model for diagnosing diabetes.

9. A diabetes diagnostic system, characterized in that, The system includes: 1) a data acquisition unit: acquiring the level data of the metabolite markers as described in claim 1 in the sample; 2) a data classification unit: comparing the level data of the metabolite markers with reference values; 3) an output unit: outputting and storing the analysis results, indicating whether the subject has diabetes or is at risk of developing diabetes.

10. The use of the metabolite marker of claim 1 or a pharmaceutically acceptable salt thereof in the preparation of a pharmaceutical composition for the treatment of diabetes; preferably, the pharmaceutical composition further comprises a pharmaceutically acceptable carrier.

Images