Diabetes intestinal microbial marker, application thereof and method for constructing diabetes detection model

Abstract

The invention provides a diabetes mellitus intestinal microbial marker, application thereof and a method for constructing a diabetes mellitus detection model, and belongs to the technical field of medicine and biomedicine. The method comprises the following steps: extracting biomarkers related to the pathogenesis and progress of diabetes from metagenome data, constructing a random forest model by using a random forest algorithm, and training and testing the constructed random forest model by using a training set and a test set to obtain a diabetes detection model. According to the diabetes detection model, differential bacteria of a diabetic patient and a healthy control can be identified more accurately, so that the accuracy of early auxiliary diagnosis of diabetes is improved, and the treatment effect is improved. The invention provides specific intestinal microbial markers for identifying diabetes mellitus, which reveal the change in the metabolic pathway of the host-microorganism associated with diabetes mellitus, contributing to the discovery of new biomarkers or therapeutic targets for diabetes mellitus.

Description

Technical Field

[0001] The present invention relates to the field of medicine and biomedical technology, and in particular to a diabetic intestinal microbial marker and its application and a method for constructing a diabetic detection model. Background Art

[0002] Diabetes is a chronic disease with high blood sugar as its main indicator, and its incidence rate is on the rise worldwide. The symptoms of diabetes are mainly manifested as "three more and one less", namely polydipsia, polyuria, polyphagia and weight loss. Patients with long-term diabetes are prone to complications such as cardiovascular disease, neuropathy, eye disease, kidney disease, etc., which seriously endanger the health of patients. However, many diabetic patients may not have obvious symptoms in the early stage, or the symptoms are very mild and easy to be ignored, which also makes the early diagnosis of diabetes difficult, leading to worsening of the disease and the occurrence of complications. At present, the diagnostic criteria for diabetes are mainly based on indicators such as fasting blood sugar, postprandial blood sugar and glycosylated hemoglobin. However, these indicators may vary in different populations and different regions, resulting in inconsistent diagnostic results. Therefore, there is an urgent need for a highly accurate diabetes detection method.

[0003] In recent years, more and more studies have shown that there is a close relationship between the intestinal microbiome and diabetes. The imbalance of intestinal microorganisms is considered to be one of the important factors in inducing and exacerbating type 2 diabetes. The increase in the proportion of certain bacterial groups such as Firmicutes and Proteobacteria and the decrease in the proportion of Bacteroidetes may be related to the occurrence of diabetes, but the types of bacteria have not been disclosed.

[0004] Therefore, providing a specific intestinal microbial marker that can be used for early diagnosis and auxiliary treatment of diabetes is of great significance for the diagnosis and treatment of diabetes. Summary of the invention

[0005] The purpose of the present invention is to provide a diabetic intestinal microbial marker and its application and a method for constructing a diabetes detection model. By analyzing the changes in diabetic intestinal microbial markers, early diabetes can be diagnosed, which has a guiding role in the adjustment of intestinal microecology, and can help doctors adjust the intestinal flora of diabetic patients and reduce the incidence of diabetes.

[0006] In order to achieve the above-mentioned object of the invention, the present invention provides the following technical solutions:

[0007] The present invention provides a diabetes intestinal microbial marker, wherein the intestinal microbial marker comprises the following bacterial species: Lactococcus lactis, Eubacterium hallii, Blautia obeum, Fusicatenibacter saccharivorans, Dorea longicatena, Ruthenibacterium lactatiformans, Clostridium bolteae, Clostridium citroniae, Actinomyces graevenitzii, Anaerostipes hadrus, Hungatella hathewayi, Bifidobacterium adolescenti s), Flavonifractor_plautii, Blautia_wexlerae, Actinomyces_naeslundii, Klebsiella_quasipneumoniae, Lactobacillus_sanfranciscensis, Escherichia_coli, Bifidobacterium_pseudocatenulatum, Collinsella_aerofaciens, Romboutsia_ilealis, Bifidobacterium_longum, Eubacterium_sp_CAG_274, Dorea_formicigenerans.

[0008] The present invention also provides an application of a diabetic intestinal microbial marker, which includes a product for preparing a diagnosis of whether a patient has diabetes or is at risk of diabetes, a target for diabetes condition assessment and treatment, and a construction of a diabetes detection model; the product includes any one of a detection reagent, a detection kit, and a detection chip.

[0009] The present invention also provides an application of a diabetic intestinal microbial marker in treating diabetes.

[0010] The present invention also provides a method for constructing a diabetes detection model, comprising the following steps:

[0011] (1) Total DNA was extracted from the feces of diabetic patients and healthy people, and high-throughput sequencing was performed after pretreatment. The sequencing results were annotated with species and analyzed for composition, gene abundance, function annotation, and difference analysis;

[0012] (2) Using random forest to screen diabetic intestinal microbial markers, constructing a random forest model, optimizing parameters, and training and testing the constructed random forest model with a training set and a test set to obtain a diabetes detection model;

[0013] (3) The metagenome and abundance information of the patient to be tested are input into the diabetes detection model for identification.

[0014] Furthermore, in step (1), the species annotation and composition spectrum analysis includes:

[0015] Alpha diversity analysis, beta diversity analysis, bacterial community sample composition, sample heatmap, and species interaction network analysis.

[0016] Furthermore, in step (1), the gene abundance analysis includes gene Core-Pan curve, gene dilution curve, and correlation analysis between samples of gene numbers.

[0017] Furthermore, in step (1), the functional annotation includes: KEGG data rate functional annotation analysis, HUMAnN3, KO functional abundance and analysis, Module functional abundance and analysis, Pathway functional abundance and analysis.

[0018] Furthermore, in step (1), the difference analysis includes: Lefse analysis, dominant species difference, multivariate analysis of variance, and rank sum test difference.

[0019] Furthermore, in step (2), the parameters for optimizing the parameters are determined according to GridSearchCV.

[0020] The beneficial effects of the present invention compared with the prior art are:

[0021] (1) The present invention provides specific intestinal microbial markers for identifying diabetes. These markers reveal changes in host-microbe metabolic pathways associated with diabetes, which are helpful for discovering new biomarkers or therapeutic targets for diabetes. In addition, the heterologous intestinal microbial markers of the present application can also reflect the status of the intestinal flora of diabetic patients, have a guiding role in the adjustment of intestinal microecology, and can help doctors adjust the intestinal flora of diabetic patients and reduce the incidence of diabetes.

[0022] (2) The present invention extracts biomarkers related to the pathogenesis and progression of diabetes from metagenomic data, uses a random forest algorithm to construct a random forest model, and trains and tests the constructed random forest model with a training set and a test set to obtain a diabetes detection model. The diabetes detection model of the present invention can more accurately identify the differential bacteria between diabetic patients and healthy controls, thereby improving the accuracy of early auxiliary diagnosis of diabetes and improving the treatment effect. In addition, the application of the diabetes detection model of the present invention in clinical practice can reduce expensive medical tests and unnecessary medical interventions, thereby saving medical resources.

[0023] (3) The diabetes detection model of the present invention has a specificity of 98.2964%, a sensitivity of 96%, and an accuracy of 95.4664%, with high model efficiency and conformity. In addition, the ROC curve is close to the upper left corner, with a high true positive rate at each threshold, and the AUC value reaches 0.9977, indicating that the classifier performs well in distinguishing positive and negative samples. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0025] Figure 1 This is a flow chart for constructing a diabetes detection model in Example 1;

[0026] Figure 2 This is a graph showing the results of ten cross-validation runs in Example 1;

[0027] Figure 3 It is the "Mean DecreaseAccuracy" indicator in the random forest model of Example 1;

[0028] Figure 4 is the ROC curve in Example 1;

[0029] Figure 5 This is the judgment standard of the diabetes detection model in Example 1. DETAILED DESCRIPTION

[0030] Various exemplary embodiments of the present invention will now be described in detail. This detailed description should not be considered as limiting the present invention, but should be understood as a more detailed description of certain aspects, features, and embodiments of the present invention.

[0031] It should be understood that the terms described in the present invention are only for describing special embodiments and are not intended to limit the present invention. In addition, for the numerical range in the present invention, it should be understood that each intermediate value between the upper and lower limits of the scope is also specifically disclosed. Each smaller range between the intermediate value in any stated value or stated range and any other stated value or intermediate value in the described range is also included in the present invention. The upper and lower limits of these smaller ranges can be independently included or excluded in the scope.

[0032] Unless otherwise indicated, all technical and scientific terms used herein have the same meanings as those generally understood by those skilled in the art. Although the present invention describes only preferred methods and materials, any methods and materials similar or equivalent to those described herein may also be used in the implementation or testing of the present invention. All documents mentioned in this specification are incorporated by reference to disclose and describe the methods and / or materials associated with the documents. In the event of a conflict with any incorporated document, the content of this specification shall prevail.

[0033] It will be apparent to those skilled in the art that various modifications and variations may be made to the specific embodiments of the present invention description without departing from the scope or spirit of the present invention. Other embodiments derived from the present invention description will be apparent to the skilled artisan. The present invention description and examples are exemplary only.

[0034] The words “include,” “including,” “have,” “contain,” etc. used in this document are open-ended terms, meaning including but not limited to.

[0035] The present invention provides a method for constructing a diabetes detection model, which specifically comprises the following steps:

[0036] (1) Total DNA was extracted from the feces of diabetic patients and healthy people, and high-throughput sequencing was performed after pretreatment. The sequencing results were annotated with species and analyzed for composition, gene abundance, function annotation, and difference analysis;

[0037] The species annotation and composition spectrum analysis include:

[0038] Alpha diversity: Shannon, Simpson, Insimpson index analysis;

[0039] beta diversity: Bray-CurtisPCoa / PCA / NMDS / UPGMA analysis;

[0040] Bacteria sample composition, sample heatmap;

[0041] Species interaction network analysis.

[0042] The gene abundance analysis includes gene Core-Pan curve, gene dilution curve, and correlation analysis between samples of gene numbers.

[0043] The functional annotations include: KEGG data rate functional annotation analysis, HUMAnN3: quantitative pathway abundance, KO functional abundance and analysis, Module functional abundance and analysis, Pathway functional abundance and analysis.

[0044] The difference analysis includes: Lefse analysis, dominant species difference, multivariate variance adonis, MaAsLin, and rank sum test difference.

[0045] (2) Using random forest to screen diabetic intestinal microbial markers, constructing a random forest model, optimizing parameters, and training and testing the constructed random forest model with a training set and a test set to obtain a diabetes detection model;

[0046] Among them, the screened microbial markers include the following species: Lactococcus lactis, Eubacterium hallii, Blautia obeum, Fusicatenibacter saccharivorans, Dorea longicatena, Ruthenibacterium lactatiformans, Clostridium bolteae, Clostridium citroniae, Actinomyces graevenitzii, Anaerostipes hadrus, Hungatella hathewayi, Bifidobacterium adolescentis, Fusobacterium prausnitzii, Flavonifractor_plautii), Blautia_wexlerae, Actinomyces_naeslundii, Klebsiella_quasipneumoniae, Lactobacillus_sanfranciscensis, Escherichia_coli, Bifidobacterium_pseudocatenulatum, Collinsella_aerofaciens, Romboutsia_ilealis, Bifidobacterium_longum, Eubacterium_sp_CAG_274, Dorea_formicigenerans.

[0047] (3) The metagenome and abundance information of the patient to be tested are input into the diabetes detection model for identification.

[0048] Example 1

[0049] Embodiment 1 of the present invention provides a method for constructing a diabetes detection model, which specifically includes the following steps:

[0050] Fecal samples were collected from 117 diabetic patients and 20 healthy controls in the clinic. The samples were collected to ensure that the patients had not received antibiotic treatment or other related treatments that might affect the intestinal flora. Fecal DNA was extracted using the MagBeads Fecal Genomic Kit. Take 300 mg of fecal sample and 1000 μL Pre-Wash Buffer, vortex until the sample is completely uniform; centrifuge the sample at 14000 rpm for 5 minutes, discard the supernatant, add 980 μL Lysis Buffer F1, 10 μL RNase A Solution and 120 μL Lysis Buffer F2 to the Lysing Matrix E tube, and vortex for 10 minutes; centrifuge at 14000 rpm / min for 5 minutes to separate particle fragments; transfer 900 μL supernatant to a 2.0 mL microcentrifuge tube, add 250 μL PPS, and mix by inverting 20 times; centrifuge at 14000 rpm for 5 minutes, transfer 1000 μL supernatant to a new 2.0 mL microcentrifuge tube, and then add 1000 μL Binding Buffer F and 10 μL Magnetic Beads were vortexed to mix; the test tube was placed on a magnetic rack for 3 minutes to allow the magnetic beads to settle, and then the supernatant was discarded; 1000 μL Wash Buffer F1 was added to the test tube, and the beads were shaken on a shaker for 3 minutes, and the test tube was placed on a magnetic rack for 1 minute to allow the magnetic beads to settle, and then the supernatant was discarded; 1000 μL Wash Buffer F2 was added to the test tube, and the beads were shaken on a shaker for 3 minutes, and the test tube was placed on a magnetic rack for 1 minute, and then the supernatant was discarded; the operation was repeated and washed again with Wash Buffer F2; then the magnetic beads were air-dried at 55°C; 100 μL TE Buffer was added and incubated at 55°C for 5 minutes; the test tube was placed on a magnetic rack until the magnetic beads were precipitated, and the supernatant (eluted DNA) was transferred to a clean 1.5 mL microcentrifuge tube and stored at -20°C for a long time.

[0051] Use an ultrasonic disruptor to randomly break high molecular weight DNA into fragments of about 300 bp, repair the ends of the fragmented DNA to make them blunt ends; connect specific adapter sequences to both ends of the repaired DNA fragments, and remove excess adapters, primers and other impurities through magnetic beads or column purification; use specific primers to PCR amplify the DNA fragments with adapters to enrich a sufficient amount of library fragments; use fastp software to perform quality control on the sequencing data, including removing adapters and low-quality sequences; use Bowtie2 to filter out reads that may come from the host, and then use the Illumina platform for high-throughput sequencing. The sequencing results are sorted according to Figure 1The species annotation and composition spectrum analysis, gene abundance analysis, functional annotation, and differential analysis processes were analyzed, and the results were input into the random forest model. Random forest was used to screen diabetic intestinal microbial markers, and a random forest model was constructed. Biomarkers of 24 bacterial genera that changed significantly between diabetic patients and healthy people were found, including the following genera: Lactococcus lactis, Eubacterium hallii, Blautia obeum, Fusicatenibacter saccharivorans, Dorea longicatena, Ruthenibacterium lactatiformans, Clostridium bolteae, Clostridium citroniae, Actinomyces graevenitzii, Anaerostipes hadrus, Hungatella hathew ayi, Bifidobacterium adolescentis, Flavonifractor plautii, Blautia wexlerae, Actinomyces naeslundii, Klebsiella quasipneumoniae, Lactobacillus sanfranciscensis, Escherichia coli, Bifidobacterium pseudocatenulatum, Collinsella aerofaciens, Romboutsia ilealis, Bifidobacterium longum, Eubacterium sp CAG 274, Dorea formicigenerans.

[0052] The training set of diabetic patients and healthy people was used to train the random forest model using the python software sklearn.Ensemble.RandomForestClassifier module to obtain the random forest detection model; the model training parameters were set as follows: gradient n_estimators = [100, 500, 1000]; max_depth = [1, 2, 3, 7, 9]; max_features = ["log2", "sqrt"];

[0053] The stability and reliability of the random forest model were verified by ten-fold cross validation. The python software GridSearchCV module was used to search for the best parameters. The random forest model was constructed using the best parameters. The diabetes detection model was obtained by training and testing with the training set and test set. The results are shown in the figure. Figure 2 As shown in Table 1.

[0054] Figure 2In the figure, the vertical axis reflects the value of the cross-validation error, which ranges roughly from 0.02 to 0.08. There are several curves in the line graph, which represent different variable selection methods. The black curve clearly shows the trend of cross-validation error with the increase of the number of variables. This curve initially shows a downward trend, indicating that in the process of increasing variables, the prediction error of the model is gradually decreasing. Both the model training set and the test set have high accuracy, indicating that the model has good results. Among them, Lactococcus lactis, Eubacterium hallii, Blautia obeum, Fusicatenibacter saccharivorans, Dorea longicatena, Ruthenibacterium lactatiformans, Clostridium bolteae, Clostridium citroniae, Actinomyces graevenitzii, Anaerostipes hadrus, Hungatella hathe The retention performance of 24 bacterial genera was the best, including Bifidobacterium wayi, Bifidobacterium adolescentis, Flavonifractor plautii, Blautia wexlerae, Actinomyces naeslundii, Klebsiella quasipneumoniae, Lactobacillus sanfranciscensis, Escherichia coli, Bifidobacterium pseudocatenulatum, Collinsella aerofaciens, Romboutsia ilealis, Bifidobacterium longum, Eubacterium sp CAG 274, and Dorea formicigenerans.

[0055] Table 1 Random forest model indicators

[0056]

[0057]

[0058] In Table 1, "Mean DecreaseAccuracy" and "Mean Decrease Gini" are two important indicators in the random forest model. "Mean Decrease Gini" calculates the impact of each variable on the heterogeneity of the observed values ​​at each node of the classification tree, thereby comparing the importance of the variable. The larger the value, the greater the importance of the variable. "MeanDecreaseAccuracy" indicates the degree of reduction in the prediction accuracy of the random forest. The larger the value, the greater the importance of the variable (see the results). Figure 3 ).

[0059] The horizontal axis (X-axis) of the ROC curve represents 1-Specificity, that is, the false positive rate, which ranges from 0 to 1, reflecting the proportion of negative examples that the model mistakenly predicts as positive examples. The vertical axis (Y-axis) represents Sensitivity, that is, the true positive rate, which measures the ability of the model to correctly identify positive examples. The results are shown in Figure 4 .

[0060] Figure 4 In the figure, the red solid line clearly depicts the ROC curve of the model, and the shaded part represents the confidence interval (CI). The ROC curve in the present invention is close to the upper left corner, and has a higher true positive rate at each threshold. The area under the curve (AUC) is close to 1, indicating that the classification performance of the model is better. The AUC value of the present invention reaches 0.9977, indicating that the classifier performs well in distinguishing positive and negative samples. The CI ranges from 0.9949 to 1, which provides a reliable evaluation of the AUC value, indicating the stability of the model performance.

[0061] The metagenome and abundance information of the patient to be tested are input into the diabetes detection model, and the patient is judged whether he or she is ill based on the predicted score. The judgment criteria are: risk value 0-0.5, low risk; 0.5-0.7 medium risk; 0.7-1 high risk.

[0062] Example 2

[0063] Example 2 of the present invention tested the specificity, sensitivity, and accuracy of the diabetes detection model of Example 1, and the specific method is as follows:

[0064] The results of the diabetes detection model were compared with the results of the metagenomic detection using a formula to obtain the TPR (sensitivity), TNR (specificity), and ACC (accuracy) of the evaluation model.

[0065] TPR, also known as recall rate, measures the model's ability to correctly identify positive samples, TNR measures the model's ability to correctly identify negative samples, and ACC measures the proportion of the model's overall correct predictions.

[0066] The formula is as follows:

[0067] TPR = TP / (TP+FN);

[0068] TNR = TN / (TN + FP);

[0069] ACC=(TP+TN) / (TP+TN+FP+FN);

[0070] Among them, TP (True Positive), TN (True Negative), FP (False Positive) and FN (False Negative).

[0071] The calculation results show that the TPR is 98.2964% specificity, TNR is 96% sensitivity, and ACC is 95.4664% accuracy. The results show that the evaluation model has a high model efficiency and conformity.

[0072] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A diabetic intestinal microbial marker, characterized in that: The diabetic intestinal microbial markers include the following species: Lactococcus lactis, Eubacterium hallii, Blautia obeum, Fusicatenibacter saccharivorans, Dorea longicatena, Ruthenibacterium lactatiformans, Clostridium bolteae, Clostridium citroniae, Actinomyces graevenitzii, Anaerostipes hadrus, Hungatella hathewayi, Bifidobacterium adolescentis, Flavonifra ctor_plautii), Blautia_wexlerae, Actinomyces_naeslundii, Klebsiella_quasipneumoniae, Lactobacillus_sanfranciscensis, Escherichia_coli, Bifidobacterium_pseudocatenulatum, Collinsella_aerofaciens, Romboutsia_ilealis, Bifidobacterium_longum, Eubacterium_sp_CAG_274, Dorea_formicigenerans.

2. An application of the diabetic intestinal microbial marker according to claim 1, characterized in that: The application includes the preparation of products for diagnosing whether a patient has diabetes or is at risk of diabetes, using them as targets for diabetes disease assessment and treatment, and constructing diabetes detection models; the product includes any one of a detection reagent, a detection kit, and a detection chip.

3. Use of the diabetic intestinal microbial marker according to claim 1 in the treatment of diabetes.

4. A method for constructing a diabetes detection model, characterized in that: The steps include: (1) Total DNA was extracted from the feces of diabetic patients and healthy people, and high-throughput sequencing was performed after pretreatment. The sequencing results were annotated with species and analyzed for composition, gene abundance, function annotation, and difference analysis; (2) Use random forest to screen diabetic intestinal microbial markers, construct a random forest model, optimize parameters, and train and test the constructed random forest model using training sets and test sets to obtain a diabetes detection model; (3) The metagenome and abundance information of the patient to be tested are input into the diabetes detection model for identification.

5. The method for constructing a diabetes detection model according to claim 3, characterized in that: In step (1), the species annotation and composition spectrum analysis includes: Alpha diversity analysis, beta diversity analysis, bacterial community sample composition, sample heatmap, and species interaction network analysis.

6. The method for constructing a diabetes detection model according to claim 3, characterized in that: In step (1), the gene abundance analysis includes gene Core-Pan curve, gene dilution curve, and correlation analysis between gene numbers in samples.

7. The method for constructing a diabetes detection model according to claim 3, characterized in that: In step (1), the functional annotation includes: KEGG data rate functional annotation analysis, HUMAnN3, KO functional abundance and analysis, Module functional abundance and analysis, Pathway functional abundance and analysis.

8. The method for constructing a diabetes detection model according to claim 3, characterized in that: In step (1), the difference analysis includes: Lefse analysis, dominant species difference, multivariate analysis of variance, and rank sum test difference.

9. The method for constructing a diabetes detection model according to claim 3, characterized in that: In step (2), the parameters for optimizing the parameters are determined according to GridSearchCV.

Images