Crohn disease intestinal microbial marker, application thereof and method for constructing Crohn disease detection model

Abstract

The invention discloses a Crohn disease enteric microorganism marker and application thereof and a method for constructing a Crohn disease detection model.The Crohn disease enteric microorganism marker is characterized in that enteric microorganisms related to Crohn disease are extracted from metagenome data of samples of Crohn disease patients and healthy people; the method comprises the following steps: establishing a random forest model for diagnosing the Crohn disease through the intestinal microbial marker of the Crohn disease, and evaluating to obtain a Crohn disease detection model; according to the method provided by the invention, the treatment effect can be evaluated, the treatment scheme can be adjusted in time, and a new tool is provided for prognosis evaluation of a patient; the specific intestinal microbial marker aiming at the Crohn's disease is found and applied, so that the accuracy and effectiveness of early auxiliary diagnosis, prognosis and treatment of the Crohn's disease are improved, the understanding of the Crohn's disease is deepened, and the development of microbiomics in clinical application is promoted; new biomarkers can be found easily, and new biomarkers or therapeutic targets can be found.

Description

Technical Field

[0001] The present invention relates to the field of biomedical technology, and more particularly to a Crohn's disease intestinal microbial marker and its application and a method for constructing a Crohn's disease detection model. Background Art

[0002] Crohn's disease (CD) is a chronic inflammatory bowel disease that primarily affects the digestive tract, especially the small intestine and colon. Its incidence varies by region, race, and population; according to the World Health Organization (WHO), the global incidence of Crohn's disease is approximately 10-30 cases per 100,000 people. In some developed countries, such as the United States, Canada, and European countries, the incidence of Crohn's disease is higher, approximately 100-300 cases per 100,000 people; while in developing countries such as Asia and Africa, the incidence of Crohn's disease is relatively low. CD has a serious impact on the patient's quality of life and mental health; therefore, diagnosis and treatment are very important for CD patients.

[0003] At present, the commonly used diagnostic methods for Crohn's disease include clinical manifestations, endoscopy, histopathology, and imaging examinations; however, these methods all have certain shortcomings. The symptoms of Crohn's disease are diverse and similar to those of other intestinal diseases, so it is difficult to make an accurate diagnosis based on clinical manifestations alone. Endoscopy can directly observe changes in the intestinal mucosa, but its results are affected by the operator's technical level and have limited detection capabilities for deep lesions; histopathology can determine the type and extent of lesions, but it requires sufficient tissue samples and has limited detection capabilities for early lesions; imaging examinations can detect structural and functional abnormalities of the intestine, but their results are affected by image quality and the experience of the interpreter, and have limited detection capabilities for early lesions. Therefore, in order to improve the diagnostic accuracy and early detection rate of Crohn's disease, a variety of diagnostic methods need to be used in combination. Dysbiosis of the intestinal microbial community may be related to the occurrence and development of Crohn's disease. Therefore, there is an urgent need for a specific intestinal microbial marker for Crohn's disease (CD) for early auxiliary diagnosis, prognosis, and treatment of Crohn's disease (CD). Summary of the invention

[0004] The purpose of the present invention is to provide a Crohn's disease intestinal microbial marker and its application and a method for constructing a Crohn's disease detection model, so as to detect signs of cancer earlier and monitor the treatment effect by analyzing the composition and functional changes of intestinal microorganisms in Crohn's disease patients.

[0005] To achieve the above object, the present invention provides the following technical solutions: A Crohn's disease intestinal microbial marker, the intestinal microbial marker comprising the following species: Bacteroides stercoris, Alistipes putredinis, Alistipes finegoldii, Ruminococcus torques, Bacteroides finegoldii, Parabacteroides goldsteinii, Firmicutes bacterium CAG 83, Ruminococcus bicirculan, Alistipes shahii, Gemmiger formicilis, Bacteroides eggerthii, Eubacterium ventriosum.

[0006] The present invention provides an application of a Crohn's disease intestinal microbial marker, characterized in that the application includes a product for diagnosing whether a patient has Crohn's disease or Crohn's disease, being used as a target for Crohn's disease condition assessment and treatment, and constructing a Crohn's disease detection model; the product includes any one of a detection reagent, a detection kit, and a detection chip.

[0007] The present invention also provides a method for constructing a Crohn's disease detection model using Crohn's disease intestinal microbial markers, comprising the following steps: (1) Total DNA was extracted from the feces of Crohn's disease patients and healthy people, and then sequenced after pretreatment. The sequencing results were annotated with species and analyzed for composition, gene abundance statistics, functional annotation, and differential analysis to screen out Crohn's disease intestinal microbial markers; (2) Establish a random forest model to identify Crohn's disease and healthy people through Crohn's disease intestinal microbial markers, evaluate and obtain a Crohn's disease detection model; (3) The metagenome and abundance information of the patient to be tested are input into the Crohn's disease detection model for identification.

[0008] Furthermore, in step (1), the species annotation and composition spectrum analysis includes: Alpha diversity: Shannon, Simpson, Insimpson index analysis; beta diversity: Bray-CurtisPCoa, PCA, NMDS, UPGMA analysis; Bacteria sample composition, sample heatmap; Species interaction network analysis.

[0009] Furthermore, in step (1), the gene abundance statistics include: gene Core-Pan curve, gene dilution curve, and correlation analysis between gene numbers in samples.

[0010] Furthermore, in the step (1), the functional annotation includes: 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.

[0011] Furthermore, in the step (1), the difference analysis includes: Lefse analysis, dominant species difference, multivariate variance adonis, MaAsLin, rank sum test difference, random forest, pathway functional abundance and analysis.

[0012] Furthermore, high-throughput sequencing is performed in step (1), including: removing adapters using fastp, removing host sequences using bowtie2, performing marker-based species abundance analysis using MetaPhlAn4, and performing analysis using HUMAnN33.

[0013] Furthermore, in step (2), a random forest model for identifying Crohn's disease and healthy people is established by using Crohn's disease intestinal microbial markers, and an evaluation is performed to obtain a Crohn's disease detection model, specifically: Crohn's disease patients and healthy people are divided into training sets and test sets, and the random forest model is trained on the training sets using the sklearn.ensemble.RandomForestClassifier module in python; The evaluation method is: evaluating the fitting degree of the random forest model by drawing a learning curve, and verifying the random forest model by ten-fold cross validation.

[0014] Furthermore, the training parameters of the random forest model in step (2) are: gradient n_estimators={100,500,1000}, max_depth={1, 2, 3, 7, 9}, max_features=["log2", "sqrt"], and the python software GridSearchCV module is used to search for the optimal parameters. The random forest model is rebuilt using the optimal parameters and prediction is performed on the test set.

[0015] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects: (1) The present invention establishes a random forest model for diagnosing Crohn's disease through Crohn's disease intestinal microbial markers, evaluates and verifies it, and obtains a Crohn's disease detection model, which can accurately identify microbial markers related to Crohn's disease (CD), thereby improving the diagnostic accuracy of Crohn's disease (CD); by randomly selecting features to divide Crohn's disease intestinal microbial markers, the generalization ability and anti-overfitting of the random forest model can be increased; by monitoring the level of intestinal microbial markers, combining microbiome and machine learning, the treatment effect can be evaluated and the treatment plan can be adjusted in time, providing a new tool for the prognosis evaluation of patients; and by discovering and applying specific intestinal microbial markers for CD to establish a Crohn's disease detection model, not only the accuracy and effectiveness of early auxiliary diagnosis, prognosis and treatment of CD are improved, but also the understanding of CD is deepened, and the development of microbiome in clinical applications is promoted.

[0016] (2) The method of the present invention reveals changes in host-microbe metabolic pathways associated with CD, which helps to discover new biomarkers and can discover new biomarkers or therapeutic targets.

[0017] (3) The present invention can more accurately identify the differential bacteria between CD patients and healthy controls, thereby improving the accuracy of early auxiliary diagnosis of CD. Through ROC curves and marker bacteria, CD patients can be treated in a personalized manner, thereby improving the treatment effect. The present invention can also be applied in clinical practice to reduce expensive medical tests and unnecessary medical interventions, thereby saving medical resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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 or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0019] The following further describes the Crohn's disease intestinal microbial markers and their applications and the method for constructing a Crohn's disease detection model in the present invention in conjunction with the accompanying drawings; Figure 1 Obtaining a metagenomic flow chart for Example 1; Figure 2 This is a graph of the error results of the cross validation performed ten times in Example 1; Figure 3 It is the "Mean Decrease Accuracy" indicator in the random forest model of Example 1; Figure 4 This is the ROC curve of the random forest model established based on Crohn's disease intestinal microbial markers in Example 1. DETAILED DESCRIPTION

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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.

[0024] The words “include,” “including,” “have,” “contain,” etc. used in this document are open-ended terms, meaning including but not limited to.

[0025] The present invention provides a method for constructing a Crohn's disease detection model using Crohn's disease intestinal microbial markers, comprising the following steps: (1) Total DNA was extracted from the feces of Crohn's disease patients and healthy people, and then sequenced after pretreatment. The sequencing results were annotated with species and analyzed for composition, gene abundance statistics, functional annotation, and differential analysis to screen out Crohn's disease intestinal microbial markers; (2) Establish a random forest model to identify Crohn's disease and healthy people through Crohn's disease intestinal microbial markers, evaluate and obtain a Crohn's disease detection model; (3) The metagenome and abundance information of the patient to be tested are input into the Crohn's disease detection model for identification.

[0026] In the step (1), the species annotation and composition spectrum analysis includes: Alpha diversity: Shannon, Simpson, Insimpson index analysis; beta diversity: Bray-CurtisPCoa, PCA, NMDS, UPGMA analysis; Bacteria sample composition, sample heatmap; Species interaction network analysis.

[0027] In the step (1), the gene abundance statistics include: gene Core-Pan curve, gene dilution curve, and correlation analysis between samples of gene numbers.

[0028] In the step (1), the functional annotation includes: 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.

[0029] In the step (1), the difference analysis includes: Lefse analysis, dominant species difference, multivariate variance adonis, MaAsLin, rank sum test difference, random forest, pathway functional abundance and analysis.

[0030] The high-throughput sequencing is performed in step (1), including: removing the adapter using fastp, removing the host sequence using bowtie2, performing marker-based species abundance analysis using MetaPhlAn4, and performing analysis using HUMAnN33.

[0031] In step (2), a random forest model for identifying Crohn's disease and healthy people is established by using Crohn's disease intestinal microbial markers, and an evaluation is performed to obtain a Crohn's disease detection model, specifically: Crohn's disease patients and healthy people are divided into a training set and a test set, and a random forest model is trained on the training set using the sklearn.ensemble.RandomForestClassifier module in python; The evaluation method is: evaluating the fitting degree of the random forest model by drawing a learning curve, and verifying the random forest model by ten-fold cross validation.

[0032] The training parameters of the random forest model in step (2) are: gradient n_estimators={100, 500, 1000}, max_depth={1, 2, 3, 7, 9}, max_features=["log2", "sqrt"]. The python software GridSearchCV module is used to search for the optimal parameters, and the random forest model is rebuilt using the optimal parameters and predicted on the test set.

[0033] The present invention provides an intestinal microbial marker for Crohn's disease, which comprises the following bacterial species: Bacteroides stercoris, Alistipes putredinis, Alistipes finegoldii, Ruminococcus torques, Bacteroides finegoldii, Parabacteroides goldsteinii, Firmicutes bacterium CAG 83, Ruminococcus bicirculan, Alistipes shahii, Gemmiger formicilis, Bacteroides eggerthii, and Eubacterium ventriosum.

[0034] The present invention also provides an application of a Crohn's disease intestinal microbial marker, which includes a product for diagnosing whether a patient has Crohn's disease or Crohn's disease, a target for Crohn's disease condition assessment and treatment, and a Crohn's disease detection model; the product includes any one of a detection reagent, a detection kit, and a detection chip.

[0035] Example 1 Screening of intestinal microbial markers for Crohn's disease: like Figure 1As shown, stool samples from 48 patients with Crohn's disease and 46 healthy controls were collected from the clinic. Before sampling, it was ensured that the patients had not received antibiotic treatment or other related treatments that might affect the intestinal flora, and relevant clinical information was recorded; 5 g of stool samples were collected using a sterile spoon to avoid cross contamination, and total DNA was extracted from the stool samples using a DNA extraction kit to remove proteins and other impurities to obtain pure DNA. Qualified DNA samples were tested for library construction and library testing. Qualified libraries will be sequenced using DNBSEQ PE150bp, and the data obtained from sequencing (Raw Data) will be analyzed, including the removal of adapters using fastp, the removal of host sequences using bowtie2, the marker-based species abundance analysis using MetaPhlAn4, and the functional analysis using tools such as HUMAnN33. Finally, the differences between samples were deeply explored through the difference analysis step, using methods such as Lefse analysis, comparison of metabolic species differences, multivariate analysis of variance (such as adonis and MAdLIN), and random forests (such as Figure 1 ), found biomarkers that changed significantly between Crohn's disease patients and healthy people, including the following genera: Bacteroides stercoris, Alistipes putredinis, Alistipes finegoldii, Ruminococcus torques, Bacteroides finegoldii, Parabacteroides goldsteinii, Firmicutes bacterium CAG 83, Ruminococcus bicirculan, Alistipes shahii, Gemmiger formicilis, Bacteroides eggerthii, Eubacterium ventriosum.

[0036] Example 2 The ability of establishing a Crohn's disease detection model using biomarkers to distinguish Crohn's disease patients from healthy controls Based on the metagenomic data of clinical Crohn's disease patients and healthy people's samples, features related to Crohn's disease were extracted from the metagenomic data, including differential microbial species abundance, and a random forest algorithm was used to build a model. In the process of building a decision tree, Crohn's disease patients and healthy people's samples were divided into training sets and test sets, and the training set was trained with a random forest model using the python software sklearn.Ensemble.RandomForestClassifier module. The fitting of the model was evaluated by drawing a learning curve, and the stability and reliability of the model were further verified by 10-fold cross validation. The model training parameter settings were as follows: gradient n_estimators = [100, 500, 1000]; max_depth = [1, 2, 3, 7, 9]; max_features = ["log2", "sqrt"]; the method for training the random forest model by ten-fold cross validation was to use the python software GridSearchCV module to search for the best parameters, use the best parameters to reconstruct the random forest model, obtain the Crohn's disease detection model, and make predictions on the test set.

[0037] Through ten cross-validations, the stability and reliability of the model are fully demonstrated. Figure 2 As shown in the figure, the vertical axis reflects the value of the cross-validation error, which ranges roughly from 0.10 to 0.30. There are several curves in the line chart, corresponding to different variable selection methods. Figure 2 The black curve in the middle clearly shows the change trend of cross-validation error as the number of variables increases. The curve initially shows a downward trend, which shows that the prediction error of the random forest model gradually decreases as the number of variables increases. The random forest model has a high accuracy in both the training set and the test set, which is enough to show that the model has excellent results. The retention performance of 12 bacterial genera is the best.

[0038] As shown in Table 1, "Mean Decrease Accuracy" and "Mean Decrease Gini" are two key indicators in the random forest model. "Mean Decrease Accuracy" represents the degree of reduction in the prediction accuracy of the random forest. The larger this value is, the more important the variable is ( Figure 3 ). "Mean Decrease Gini" is used to calculate the impact of each variable on the heterogeneity of the observed values ​​at each node of the classification tree, and then compare the importance of the variables. The larger the value, the greater the importance of the variable.

[0039] The ROC curve can comprehensively evaluate the performance of the random forest model, thereby obtaining a Crohn's disease detection model. The horizontal axis (X-axis) of the ROC curve represents 1 - Specificity, that is, the false positive rate, which ranges from 0 to 1 and reflects the proportion of the model mistakenly predicting negative examples as positive examples. The vertical axis (Y-axis) is Sensitivity, that is, the true positive rate, which is used to measure the ability of the random forest model to correctly identify positive examples. Figure 4 In the figure, the solid red line clearly outlines 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 0.911, which shows that the classifier performs well in distinguishing positive and negative samples. The CI ranges from 0.8887 to 0.9333, which reliably evaluates the AUC value and highlights the stability of the performance of the random forest model.

[0040]

[0041] Example 3 Calculate the specificity, sensitivity, and accuracy of the Crohn's disease detection model.

[0042] The results of the Crohn's disease detection model were compared with the results of the macrogene detection using the formula to obtain the TPR (sensitivity), TNR (specificity), and ACC (accuracy) of the Crohn's disease detection model. TPR, also known as the recall rate, measures the ability of the Crohn's disease detection model to correctly identify positive samples, TNR measures the ability of the Crohn's disease detection model to correctly identify negative samples, and ACC measures the overall correct prediction ratio of the Crohn's disease detection model.

[0043] The formula is shown below.

[0044] TPR <- TP / (TP + FN) TNR <- TN / (TN + FP) ACC <- (TP + TN) / (TP + TN + FP + FN) Among them, TP (True Positive), TN (True Negative), FP (False Positive) and FN (False Negative).

[0045] Calculations yielded: TPR: 92.3464% specificity, TNR: 94% sensitivity, ACC: 96.44649% accuracy. The results show that the evaluation model exhibits high model efficiency and compliance. The above description of the disclosed embodiments enables professionals and technicians in the field to implement or use the present invention. Various modifications to these embodiments will be apparent to professionals and technicians in the field, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features disclosed herein.

Claims

1. A Crohn's disease intestinal microbial marker, characterized in that: The intestinal microbial markers include the following species: Bacteroides stercoris, Alistipes putredinis, Alistipes finegoldii, Ruminococcus torques, Bacteroides finegoldii, Parabacteroides goldsteinii, Firmicutes bacterium CAG 83, Ruminococcus bicirculan, Alistipes shahii, Gemmiger formicilis, Bacteroides eggerthii, Eubacterium ventriosum.

2. A use of the Crohn's disease intestinal microbial marker according to claim 1, characterized in that: The applications include products for diagnosing whether a patient has Crohn's disease or Crohn's disease, as targets for Crohn's disease condition assessment and treatment, and for building a Crohn's disease detection model; the products include any one of a detection reagent, a detection kit, and a detection chip.

3. A method for constructing a Crohn's disease detection model using the Crohn's disease intestinal microbial markers according to claim 1, characterized in that: The following steps are involved: (1) Total DNA was extracted from the feces of Crohn's disease patients and healthy people, and then sequenced after pretreatment. The sequencing results were annotated with species and analyzed for composition, gene abundance statistics, functional annotation, and differential analysis to screen out Crohn's disease intestinal microbial markers; (2) Establish a random forest model to identify Crohn's disease and healthy people through Crohn's disease intestinal microbial markers, evaluate and obtain a Crohn's disease detection model; (3) The metagenome and abundance information of the patient to be tested are input into the Crohn's disease detection model for identification.

4. The method for constructing a Crohn's disease detection model according to claim 3, characterized in that: In the step (1), the species annotation and composition spectrum analysis includes: Alpha diversity: Shannon, Simpson, Insimpson index analysis; beta diversity: Bray-CurtisPCoa, PCA, NMDS, UPGMA analysis; Bacteria sample composition, sample heatmap; Species interaction network analysis.

5. The method for constructing a Crohn's disease detection model according to claim 3, characterized in that: In the step (1), the gene abundance statistics include: gene Core-Pan curve, gene dilution curve, and correlation analysis between samples of gene numbers.

6. The method for constructing a Crohn's disease detection model according to claim 3, characterized in that: In the step (1), the functional annotation includes: 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.

7. The method for constructing a Crohn's disease detection model according to claim 3, characterized in that: In the step (1), the difference analysis includes: Lefse analysis, dominant species difference, multivariate variance adonis, MaAsLin, rank sum test difference, random forest, pathway functional abundance and analysis.

8. The method for constructing a Crohn's disease detection model according to claim 3, characterized in that: The high-throughput sequencing is performed in step (1), including: removing the adapter using fastp, removing the host sequence using bowtie2, performing marker-based species abundance analysis using MetaPhlAn4, and performing analysis using HUMAnN33.

9. The method for constructing a Crohn's disease detection model according to claim 3, characterized in that: In step (2), a random forest model for identifying Crohn's disease and healthy people is established by using Crohn's disease intestinal microbial markers, and an evaluation is performed to obtain a Crohn's disease detection model, specifically: Crohn's disease patients and healthy people are divided into training sets and test sets, and the random forest model is trained on the training sets using the sklearn.ensemble.RandomForestClassifier module in python; The evaluation method is: evaluating the fitting degree of the random forest model by drawing a learning curve, and verifying the random forest model by ten-fold cross validation.

10. The method for constructing a Crohn's disease detection model according to claim 9, characterized in that: The training parameters of the random forest model in step (2) are: gradient n_estimators={100, 500, 1000}, max_depth={1, 2,3, 7, 9}, max_features=["log2", "sqrt"]. The python software GridSearchCV module is used to search for the optimal parameters, and the random forest model is rebuilt using the optimal parameters and predicted on the test set.

Images