Method and system for diagnosing or predicting diseases based on intestinal microbial marker combination

Mendel randomized analysis screened out the combination of intestinal microbial markers related to autism, and combined with machine learning models, a system for diagnosing and predicting autism was constructed, solving the problem of poor correlation of eigenvalues ​​in the prior art , achieving accurate diagnosis and risk prediction of autism.

CN118957049AActive Publication Date: 2024-11-15HANGZHOU DEPU MEDICAL LAB CO LTD

Patent Information

Application Number
CN202411200693.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-06-14
Publication Date
2024-11-15
Estimated Expiration
2044-06-14

AI Technical Summary

Technical Problem

The existing model eigenvalues ​​that predict autism based on intestinal microbial markers have poor correlation with the disease, resulting in the inability to effectively explain the causal relationship with autism and lack of effective diagnostic and prediction methods.

Method used

Through Mendel's randomization analysis, the intestinal microbial marker combinations with causal relationships with autism were screened out, including Ruminiclostridium, Sutterella, Eggerthella, Holdemanella, etc., and a prediction system was constructed in combination with machine learning models, and the diagnosis was performed using microbial marker abundance data. and prediction.

Benefits of technology

Accurate diagnosis and risk prediction of autism are achieved, and the accuracy and reliability of predictions are improved by building an effective machine learning model, and medical intervention can be carried out in a timely manner.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118957049A_ABST
    Figure CN118957049A_ABST
Patent Text Reader

Abstract

The invention discloses a method and a system for diagnosing or predicting diseases based on intestinal microbial marker combination, and belongs to the technical field of microbial markers. By utilizing the method and the system provided by the invention, whether the subject suffers from autism or not can be accurately diagnosed or whether the subject has the risk of autism or not can be predicted based on the abundance data of the intestinal microbial marker combination. Furthermore, accurate prediction can be realized on the basis of the obtained level of the autism risk of the predicted subject, so that medical intervention can be performed in time, and the method has a huge clinical application value.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] Related patents This application is a divisional application of the Chinese invention patent application with application number 2024107640214, application date June 14, 2024, and invention name “A combination, system and application of microbial markers for diagnosing or predicting autism”. Technical Field

[0002] The present invention belongs to the technical field of microbial markers, and specifically, relates to a method and system for diagnosing or predicting a disease based on a combination of intestinal microbial markers, particularly autism. Background Art

[0003] Autism spectrum disorder (ASD) is a serious neurobehavioral developmental disorder that begins in infancy. Children with ASD usually develop ASD symptoms between 6 and 24 months of age. Some children develop normally in the early stages, but gradually develop degenerative changes such as loss of language function and social skills between 24 and 36 months of age. In recent years, the incidence of ASD has increased year by year.

[0004] Clinical evidence has shown that intestinal flora imbalance and changes in its metabolites are closely related to the occurrence of ASD. The intestine is the largest digestive, immune and endocrine organ in the human body, and intestinal microorganisms are considered to be the "second genome" that affects human physiological and mental health. Compared with healthy children, the number of Clostridium species in the feces of children with autism has increased significantly, and autism has been significantly improved after treatment with the antibiotic vancomycin. Clostridium not only produces enterotoxins that cause gastrointestinal diseases, but also produces neurotoxins that cause autism. The researchers used pyrosequencing to study the intestinal flora of children with autism and found that the Bacteroidetes and Actinobacteria were significantly increased in children with severe autism. Therefore, metabolic disorders caused by abnormal intestinal bacteria may be one of the pathogenesis of ASD.

[0005] Therefore, screening gut microbial markers and predicting the risk of autism through machine learning models can help humans better predict autism and conduct early intervention. However, there is currently a serious lack of models for predicting autism based on gut microbial markers; the eigenvalues ​​of some prediction models are poorly correlated with autism and have low causal associations, resulting in the eigenvalues ​​often being unable to explain the relationship with autism. Summary of the invention

[0006] In order to solve at least one of the above technical problems, the inventors obtained intestinal microbial markers that are causally related to autism through Mendelian randomization analysis, and further studied the causal relationship with autism. The markers obtained are all intestinal microorganisms that are causally related to autism, which can better perform diagnosis or prediction.

[0007] The first aspect of the present invention provides a combination of microbial markers for diagnosing or predicting the risk of autism, comprising Ruminiclostridium , Sutterella , Eggerthella , Holdemanella , Odoribacter , Oscillibacter , Turicibacter , Terrisporobacter , Blautia and Adlercreutzia .

[0008] Furthermore, the microbial marker combination also includes Ruminococcus , Slackia , Eubacterium , Desulfovibrio , Holdemania , Gordonibacter , Dorea , Collinsella and Anaerotruncus at least one of .

[0009] In some preferred embodiments of the present invention, the microbial marker combination comprises Ruminiclostridium , Sutterella , Eggerthella , Holdemanella , Odoribacter , Oscillibacter , Turicibacter , Terrisporobacter , Blautia , Adlercreutzia .

[0010] In some more preferred embodiments of the present invention, the microbial marker combination comprises Ruminiclostridium , Sutterella , Slackia , Eggerthella , Holdemanella , Odoribacter , Oscillibacter , Turicibacter , Terrisporobacter , Blautia , Adlercreutzia .

[0011] In some more preferred embodiments of the present invention, the microbial marker combination comprises Ruminiclostridium , Sutterella , Slackia , Eggerthella , Holdemanella , Odoribacter , Oscillibacter , Turicibacter , Terrisporobacter , Collinsella , Blautia , Adlercreutzia .

[0012] In some more preferred embodiments of the present invention, the microbial marker combination comprises Ruminococcus , Ruminiclostridium , Sutterella , Slackia , Eggerthella , Holdemanella , Odoribacter , Oscillibacter , Turicibacter , Terrisporobacter , Collinsella , Blautia , Adlercreutzia .

[0013] In some more preferred embodiments of the present invention, the microbial marker combination comprises Ruminococcus , Ruminiclostridium , Sutterella , Slackia , Eggerthella , Holdemanella , Odoribacter , Oscillibacter , Turicibacter , Terrisporobacter , Dorea , Collinsella , Blautia , Adlercreutzia .

[0014] In some more preferred embodiments of the present invention, the microbial marker combination comprises Ruminococcus , Ruminiclostridium , Sutterella , Slackia , Eggerthella , Holdemanella , Holdemania , Odoribacter , Oscillibacter , Turicibacter , Terrisporobacter , Dorea , Collinsella , Blautia , Adlercreutzia .

[0015] In some more preferred embodiments of the present invention, the microbial marker combination comprises Ruminococcus , Ruminiclostridium , Sutterella , Slackia , Eubacterium , Eggerthella , Holdemanella , Holdemania , Odoribacter , Oscillibacter , Turicibacter , Terrisporobacter , Dorea , Collinsella , Blautia ,Adlercreutzia .

[0016] In some more preferred embodiments of the present invention, the microbial marker combination comprises Ruminococcus , Ruminiclostridium , Sutterella , Slackia , Eubacterium , Desulfovibrio , Eggerthella , Holdemanella , Holdemania , Odoribacter , Oscillibacter , Turicibacter , Terrisporobacter , Dorea , Collinsella , Blautia , Adlercreutzia .

[0017] In some more preferred embodiments of the present invention, the microbial marker combination comprises Ruminococcus , Ruminiclostridium , Sutterella , Slackia , Eubacterium , Desulfovibrio , Eggerthella , Holdemanella , Holdemania , Odoribacter , Oscillibacter , Turicibacter , Terrisporobacter , Dorea , Collinsella , Blautia , Anaerotruncus , Adlercreutzia .

[0018] In some more preferred embodiments of the present invention, the microbial marker combination comprises Ruminococcus , Ruminiclostridium , Sutterella , Slackia , Eubacterium , Desulfovibrio , Eggerthella , Holdemanella , Holdemania , Odoribacter , Oscillibacter , Gordonibacter , Turicibacter , Terrisporobacter , Dorea , Collinsella , Blautia , Anaerotruncus and Adlercreutzia .

[0019] By detecting the above-mentioned microbial markers, their abundance data are obtained, and further a model is constructed to diagnose whether the subject suffers from autism or predict whether the subject has a risk of autism.

[0020] A second aspect of the present invention provides a system for diagnosing or predicting autism risk, comprising the following modules: A data input module, used to input the abundance data of any combination of microbial markers described in the first aspect of the present invention in the biological sample of the subject; A database storage module, used to store the abundance data of the microbial marker combination in biological samples of a population, wherein the population samples include samples of non-autistic subjects and samples of autistic patients; A disease prediction module is connected to the data input module and the database storage module, respectively, and is used to construct a prediction model using the abundance data of the microbial marker combination in the biological samples of the group, and to diagnose whether the subject suffers from autism or predict whether the subject has a risk of autism based on the abundance data of the microbial marker combination of the subject obtained from the data input module.

[0021] In the present invention, the term "abundance data of a microbial marker combination" includes the abundance data of each microbial marker in the microbial marker combination.

[0022] In some embodiments of the present invention, the abundance data of each microbial marker is obtained based on qPCR, 16S RNA sequencing or metagenomic sequencing.

[0023] In some specific embodiments of the present invention, it refers to the method obtained by 16S RNA sequencing, specifically including: Extracting genomic DNA from the biological sample and performing 16S RNA sequencing to obtain sequencing data; The original reads of the sequencing data are preprocessed, filtered to obtain high-quality reads, compared with the 16S RNA gene reference database, and chimera sequences are removed. Finally, the filtered sequences are clustered in a certain manner (including but not limited to NanoCLUST) to obtain multiple sequence clustering operational taxonomy units (OTUs), and the OTUs are annotated with taxonomy to obtain the abundance data of each microorganism.

[0024] In some embodiments of the invention, the abundance is a relative abundance.

[0025] In the present invention, the biological sample includes but is not limited to feces, intestinal lavage fluid, anal swab samples, preferably, a feces sample.

[0026] In some embodiments of the present invention, in the disease prediction module, the use of the abundance data of the microbial marker combination in the biological sample of the population to construct a prediction model comprises the following steps: S21, randomly dividing the abundance data of the microbial marker combination in the biological samples of the group into two groups, one group is a training set, and the other group is a test set, each group includes the abundance data of the microbial markers of the samples of non-autistic subjects and the samples of autistic patients; S22, using the training set data, build a disease prediction model based on the machine learning algorithm and perform multi-fold cross validation; S23, verifying the obtained prediction model in the test set.

[0027] In some embodiments of the present invention, stratified random sampling is used for grouping, and the grouping ratio may be 7:3, 4:1, etc.

[0028] In some embodiments of the present invention, the machine learning algorithm is selected from any one of the following algorithms: logistic regression algorithm, linear regression algorithm, random forest algorithm, neural network algorithm, support vector machine algorithm, Bayesian classification algorithm, gradient boosting algorithm, K nearest neighbor algorithm and decision tree algorithm.

[0029] In some specific embodiments of the present invention, the machine learning algorithm is a logistic regression algorithm, and the prediction model diagnoses whether the subject has autism or predicts whether the subject has a risk of autism and the level of risk based on the score obtained by the logistic regression algorithm.

[0030] In some preferred embodiments of the present invention, the microbial markers include all 19 microbial markers mentioned above, and in the prediction model, the regression coefficient of each microbial marker is as follows:

[0031] In some preferred embodiments of the present invention, when the score is less than 0.5, the subject does not have autism or has a low risk of autism; when the score is greater than 0.75, the subject has autism or has a high risk of autism; otherwise, the subject has a medium risk of autism.

[0032] The third aspect of the present invention provides the use of an abundance detection reagent of any one of the microbial marker combinations described in the first aspect of the present invention in the preparation of a kit for diagnosing or predicting autism.

[0033] In some preferred embodiments of the present invention, the abundance detection reagent refers to a high-throughput sequencing reagent, including a nucleic acid extraction, amplification reagent and / or purification reagent.

[0034] In some embodiments of the present invention, the abundance detection reagent includes primers and / or probes. Further, the probes are prepared into a chip.

[0035] Beneficial Effects of the Invention Compared with the prior art, the present invention has achieved the following beneficial effects: By using the microbial markers of the present invention and establishing a machine learning model, the AUC in the training set reached 0.9623, in the internal test set it reached 0.8409, and in the external test set it also reached 0.75, indicating that the microbial markers of the present invention can accurately diagnose whether a subject suffers from autism or predict whether a subject has a risk of autism. Furthermore, based on a specific machine learning model, accurate prediction can be achieved based on the predicted degree of autism risk of the subject, so that medical intervention can be carried out in a timely manner, which has great clinical application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 The results of analyzing ebi-a-GCST90016596 using the inverse variance weighted method in Example 1 of the present invention are shown.

[0037] Figure 2 The results of analyzing ebi-a-GCST90016599 using the inverse variance weighted method in Example 1 of the present invention are shown.

[0038] Figure 3 The results of analyzing ebi-a-GCST90016602 using the inverse variance weighted method in Example 1 of the present invention are shown.

[0039] Figure 4 The results of analyzing ebi-a-GCST90016603 using the inverse variance weighted method in Example 1 of the present invention are shown.

[0040] Figure 5 The results of analyzing ebi-a-GCST90016606 using the inverse variance weighted method in Example 1 of the present invention are shown.

[0041] Figure 6 The results of analyzing ebi-a-GCST90016614 using the inverse variance weighted method in Example 1 of the present invention are shown.

[0042] Figure 7 The results of analyzing ebi-a-GCST90016620 using the inverse variance weighted method in Example 1 of the present invention are shown.

[0043] Figure 8 The results of analyzing finn-b-F5_AUTISM using the inverse variance weighted method in Example 1 of the present invention are shown.

[0044] Figure 9 The results of analyzing finn-b-F5_PERVASIVE using the inverse variance weighting method in Example 1 of the present invention are shown.

[0045] Figure 10 The results of analyzing finn-b-KRA_PSY_AUTISM using the inverse variance weighting method in Example 1 of the present invention are shown.

[0046] Figure 11 The results of analyzing finn-b-KRA_PSY_AUTISM_EXMORE using the inverse variance weighting method in Example 1 of the present invention are shown.

[0047] Figure 12 The results of analyzing IEU-A-802 using the inverse variance weighted method in Example 1 of the present invention are shown.

[0048] Figure 13 The results of analyzing IEU-A-806 using the inverse variance weighted method in Example 1 of the present invention are shown.

[0049] Figure 14 The results of analyzing IEU-A-1184 using the inverse variance weighted method in Example 1 of the present invention are shown.

[0050] Figure 15 The results of analyzing IEU-A-1185 using the inverse variance weighted method in Example 1 of the present invention are shown.

[0051] Figure 16 The performance evaluation of the machine learning model in Example 3 of the present invention in the training set and the test set is shown.

[0052] Figure 17 The results of determining the critical value of autism risk using the machine learning model in Example 3 of the present invention are shown.

[0053] Figure 18 The performance evaluation of the machine learning model in Example 3 of the present invention in the external validation set is shown. DETAILED DESCRIPTION

[0054] Unless otherwise indicated, implied from the context, or customary in the prior art, all parts and percentages in this application are based on weight, and the tests and characterization methods used are all synchronized with the filing date of this application. Where applicable, the contents of any patent, patent application or disclosure involved in this application are fully incorporated herein by reference, and their equivalent patent families are also introduced as references, especially the definitions of relevant terms in the art disclosed in these documents. If the definition of a specific term disclosed in the prior art is inconsistent with any definition provided in this application, the definition of the term provided in this application shall prevail.

[0055] In order to make the technical problems, technical solutions and beneficial effects solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments.

[0056] The following examples are used to demonstrate preferred embodiments of the present invention. It will be appreciated by those skilled in the art that the techniques disclosed in the following examples represent techniques discovered by the inventors that can be used to implement the present invention and therefore can be considered as preferred embodiments of the present invention. However, it will be appreciated by those skilled in the art based on this specification that many modifications may be made to the specific embodiments disclosed herein and still achieve the same or similar results without departing from the spirit or scope of the present invention.

[0057] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, and the disclosure and materials cited therein are hereby incorporated by reference.

[0058] Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many technical equivalents to the specific embodiments of the invention described herein. Such equivalents are intended to be encompassed by the claims.

[0059] The experimental methods in the following examples are conventional methods unless otherwise specified. The instruments and equipment used in the following examples are conventional laboratory instruments and equipment unless otherwise specified; the experimental materials used in the following examples are purchased from conventional biochemical reagent stores unless otherwise specified.

[0060] Example 1 Screening of intestinal microbial markers for autism This example screens intestinal microbial markers associated with autism, and the specific screening steps are as follows: 1. Get the dataset The genetic variation data of intestinal microorganisms come from the genome-wide association study (GWAS) published by the Microbial Genome Consortium in 2021, which analyzed the host genotype and 16S rRNA metagenomic data of 18,340 participants, including 122,110 single nucleotide polymorphism (SNP) variation sites, a total of 211 bacterial taxa, including 15 unknown bacterial taxa.

[0061] The genetic variation data of autism comes from the IEU OpenGWAS project, which contains 15 data in total, namely: ebi-a-GCST90016620, ebi-a-GCST90016614, ieu-a-1185, ebi-a-GCST90016606, ebi-a-GCST90016596, ebi-a-GCST90016599, ieu-a-802, ebi-a-GCST90016603, ebi-a-GCST90016602, ieu-a-1184, ieu-a-806, finn-b-F5_AUTISM, finn-b-KRA_PSY_AUTISM, finn-b-KRA_PSY_AUTISM_EXMORE, finn-b-F5_PERVASIVE.

[0062] 2. Select instrumental variables Instrumental variable inclusion criteria: The SNP significance threshold was set at P < 1.0 × 10 -5 , the linkage disequilibrium standard is r 2 <0.001, genetic distance 10000 kb, highly correlated SNPs were removed, and the SNP with the lowest P value was retained.

[0063] Calculate the F value using the formula: F=[R 2 / (R 2 -1)]×[(NK-1) / K] Among them, N represents the sample size of the gut microbiome GWAS study, K represents the number of instrumental variables, and R 2 represents the extent to which the SNP explains the exposure, R 2 The calculation formula is: 2 =2×β 2 × (1-MAF) × MAF, MAF is the minor allele frequency, and β is the effect size of SNP on exposure.

[0064] F>10 is considered to be able to effectively avoid the bias caused by weak instrumental variables, so SNPs with F<10 were eliminated. A total of 1519 SNPs were obtained as instrumental variables.

[0065] 3. Statistical Analysis Mendelian randomization analysis was performed using the R TwoSampleMR algorithm package. MR analysis methods included inverse-variance weighted (IVW), weighted median, MR-Egger, simple mode, and weighted mode. The IVW method was mainly used for eigenvalue screening, and P < 0.05 was considered statistically significant.

[0066] 4. Sensitivity and pleiotropy analysis In terms of sensitivity, this example calculates Cochran's Q statistic by IVW and MR-Egger regression. If P>0.05, it means there is no obvious heterogeneity. At the same time, the inventors also eliminated the included SNPs one by one by leaving one out method to observe whether it affects the analysis results, and draw a forest map. If P>0.05 is obtained after eliminating a certain SNP, it is considered that the SNP will not have a significant impact on the results.

[0067] In terms of pleiotropy, the inventors simultaneously used the intercept term of MR-Egger regression and the Mendelian randomization pleiotropy residual sum and outlier (MR-PRESSO) to test the horizontal pleiotropy of the included SNPs. In MR-Egger regression, if the intercept tends to 0, it can be considered that there is no horizontal pleiotropy. The horizontal pleiotropy screening retains the characteristic value of P>0.05.

[0068] 5. Summary Analysis IVW is considered the standard method for MR summary data, which uses the Wald ratio method to calculate the causal effect estimate for each included instrumental SNP and then performs a weighted summary analysis.

[0069] The results of the inverse variance weighted analysis of the above 15 data sets in this embodiment (Mendelian randomized forest diagram) are as follows: Figures 1 - 15 shown.

[0070] Depend on Figure 1 It can be seen that in ebi-a-GCST90016596, Lachnospiraceae NK4A136 group (Lachnospira NK4A136 group), Lachnospiraceae NC2004 group (Lachnospirillum NC2004 group) and ButyricicoccusThe causal relationship between Butyric acid bacteria and autism reached a statistically significant level (P<0.05), among which, Lachnospiraceae NK4A136 group and Butyricicoccus It was negatively correlated with the occurrence of autism, suggesting that it was a protective factor for autism, with effect values ​​(odd ratio, OR) of 1.014 (0.95% CI: 1.001-1.027) and 0.984 (0.95% CI: 0.971-0.998), respectively; Lachnospiraceae NC2004 group It is positively correlated with the occurrence of autism, suggesting that it is a risk factor for autism, with an OR value of 0.984 (0.95% CI: 0.970-0.997).

[0071] Depend on Figure 2 It can be seen that in ebi-a-GCST90016599, Christensenellaceae R-7 group (Christensen flora), Dorea ( Dorea Bacteria), Escherichia.Shigella (Shigella spp.), Paraprevotella (Parappella spp.) and Eubacterium coprostanoligenes group The causal relationship between Eubacterium coproducens and autism reached a statistically significant level (P<0.05), among which, Christensenellaceae R-7group , Dorea and Escherichia.Shigella It was positively correlated with the occurrence of autism, suggesting that it is a risk factor for autism, with OR values ​​of 1.025 (0.95% CI: 1.002-1.048), 1.030 (0.95% CI: 1.003-1.057), and 1.032 (0.95% CI: 1.008-1.056), respectively; Paraprevotella and Eubacterium coprostanoligenes group It is negatively correlated with the occurrence of autism, suggesting that it is a protective factor for autism, with OR values ​​of 0.985 (0.95% CI: 0.970-0.999) and 0.975 (0.95% CI: 0.951-0.999), respectively.

[0072] Depend on Figure 3 It can be seen that in ebi-a-GCST90016602, Marvinbryantia (Marvinberry), Ruminococcaceae UCG 005 (Ruminococcaceae UCG 005), Parasutterella (Parasartella spp.), Sutterella (Sutterella spp.), Lachnospiraceae NC2004 group (Lachnospira NC2004 group), Lachnospiraceae UCG 001 (Lachnospiraceae UCG 001), Lachnospira (Lachnospira spp.) and OlsenellaThe causal relationship between (Eurosinophilia australis) and autism reached a statistically significant level (P<0.05), among which, Marvinbryantia , Parasutterella , Lachnospiraceae NC2004 group , Lachnospiraceae UCG 001 and Olsenella It was positively correlated with the occurrence of autism, suggesting that it is a risk factor for autism, with OR values ​​of 1.023 (0.95% CI: 1.002-1.045), 1.027 (0.95% CI: 1.010-1.045), 1.020 (0.95% CI: 1.003-1.038), 1.023 (0.95% CI: 1.003-1.043), and 1.015 (0.95% CI: 1.002-1.028), respectively; Ruminococcaceae UCG 005 , Sutterella and Lachnospira It was negatively correlated with the occurrence of autism, suggesting that it was a protective factor for autism, with OR values ​​of 0.979 (0.95% CI: 0.962-0.996), 0.965 (0.95% CI: 0.932-0.999) and 0.956 (0.95% CI: 0.917-0.997), respectively.

[0073] Depend on Figure 4 It can be seen that in ebi-a-GCST90016603, Marvinbryantia (Marvinberry), Ruminococcus 1 (Ruminococcus 1), Butyrivibrio (Butyrivibrio spp.), Dialister (Diarlisteria spp.), Sutterella (Sutterella spp.), Dorea ( Dorea Bacteria), Ruminococcaceae UCG 005 (Ruminococcaceae UCG 005), Anaerofilum (sulfate-reducing bacteria) and Lachnospiraceae UCG 001 The causal relationship between (Lachnospiraceae UCG001) and autism reached a statistically significant level (P<0.05), among which, Marvinbryantia , Butyrivibrio and Lachnospiraceae UCG 001 It was positively correlated with the occurrence of autism, suggesting that it is a risk factor for autism, with OR values ​​of 1.027 (0.95% CI: 1.006-1.047), 1.014 (0.95% CI: 1.003-1.024), and 1.032 (0.95% CI: 1.009-1.056), respectively; Ruminococcus 1 , Dialister , Sutterella , Dorea , Ruminococcaceae UCG 005 and AnaerofilumIt was negatively correlated with the occurrence of autism, suggesting that it was a protective factor for autism, with OR values ​​of 0.974 (0.95% CI: 0.954-0.994), 0.978 (0.95% CI: 0.957-1.000), 0.956 (0.95% CI: 0.921-0.991), 0.969 (0.95% CI: 0.942-0.996), 0.971 (0.95% CI: 0.950-0.992) and 0.980 (0.95% CI: 0.965-0.995), respectively.

[0074] Depend on Figure 5 It can be seen that in ebi-a-GCST90016606, Candidatus Soleaferrea (Bacillus sp.), Gordonibacter (Gordonella parafaciens), Roseburia (Rosenbergia spp.), Turicibacter (spore-forming enteric bacteria) and Lachnospiraceae UCG 008 The causal relationship between Lachnospiraceae UCG 008 and autism reached a statistically significant level (P<0.05), among which, Roseburia and Lachnospiraceae UCG 008 It was positively correlated with the occurrence of autism, suggesting that it is a risk factor for autism, with OR values ​​of 1.029 (0.95% CI: 1.009-1.050) and 1.020 (0.95% CI: 1.003-1.037), respectively; Candidatus Soleaferrea , Gordonibacter and Turicibacter It was negatively correlated with the occurrence of autism, suggesting that it was a protective factor for autism, with OR values ​​of 0.970 (0.95% CI: 0.948-0.992), 0.988 (0.95% CI: 0.977-0.999), and 0.981 (0.95% CI: 0.964-0.999), respectively.

[0075] Depend on Figure 6 It can be seen that in ebi-a-GCST90016614, Ruminococcaceae UCG 005 (Ruminococcaceae UCG 005), Ruminococcus 1 (Ruminococcus 1), Parabacteroides (Parabacteroides spp.), Ruminococcaceae UCG 013 (Ruminococcaceae UCG 013), Anaerofilum (sulfate-reducing bacteria), Fusicatenibacter (Fusobacterium spp.) and Sutterella The causal relationship between Sutterella and autism reached a statistically significant level (P<0.05), among which R uminococcaceae UCG 005 , Ruminococcus 1 , Anaerofilum , Fusicatenibacter and SutterellaIt was positively correlated with the occurrence of autism, suggesting that it is a risk factor for autism, with OR values ​​of 1.018 (0.95% CI: 1.005-1.030), 1.014 (0.95% CI: 1.001-1.028), 1.010 (0.95% CI: 1.000-1.021), 1.015 (0.95% CI: 1.001-1.028), and 1.025 (0.95% CI: 1.008-1.044), respectively; Parabacteroides and Ruminococcaceae UCG 013 It was negatively correlated with the occurrence of autism, suggesting that it was a protective factor for autism, with OR values ​​of 0.981 (0.95% CI: 0.967-0.995) and 0.987 (0.95% CI: 0.974-1.000), respectively.

[0076] Depend on Figure 7 It can be seen that in ebi-a-GCST90016620, Adlercreutzia (Adler's Kreutzeria spp.), Anaerofilum (sulfate-reducing bacteria), Desulfovibrio (Desulfovibrio spp.) and Gordonibacter The causal relationship between G. parahaemolyticus and autism reached a statistically significant level (P<0.05), among which Adlercreutzia and Anaerofilum It was positively correlated with the occurrence of autism, suggesting that it is a risk factor for autism, with OR values ​​of 1.026 (0.95% CI: 1.002-1.050) and 1.035 (0.95% CI: 1.015-1.056), respectively; Desulfovibrio and Gordonibacter It was negatively correlated with the occurrence of autism, suggesting that it was a protective factor for autism, with OR values ​​of 0.963 (0.95% CI: 0.937-0.989) and 0.986 (0.95% CI: 0.976-0.996), respectively.

[0077] Depend on Figure 8 It can be seen that in finn-b-F5_AUTISM, Terrisporobacter (Geobasidiomyces spp.) and Collinsella The causal relationship between (Collinsella) and autism reached a statistically significant level (P<0.05), among which, Terrisporobacter It is positively correlated with the occurrence of autism, suggesting that it is a risk factor for autism, with an OR value of 2.987 (0.95% CI: 1.174-7.598), which is very significant; Collinsella It is negatively correlated with the occurrence of autism, suggesting that it is a protective factor for autism, with an OR value of 0.316 (0.95% CI: 0.119-0.838), which is very significant.

[0078] Depend onFigure 9 It can be seen that in finn-b-F5_PERVASIVE, Blautia (Blautella spp.), Eubacterium oxidoreducens group (Redox Eubacterium group), Adlercreutzia (Adler's Kreutzeria spp.), Gordonibacter (Gordonella parafaciens), Sellimonas The causal relationship between Selimonas and autism was statistically significant (P<0.05), among which Gordonibacter and Sellimonas It is positively correlated with the occurrence of autism, suggesting that it is a risk factor for autism, with OR values ​​of 1.890 (0.95% CI: 1.057-3.380) and 1.950 (0.95% CI: 1.101-3.452), respectively, which is very significant; Blautia , Eubacterium oxidoreducens group and Adlercreutzia It is negatively correlated with the occurrence of autism, suggesting that it is a protective factor for autism. The OR values ​​are 0.142 (0.95% CI: 0.039-0.516), 0.335 (0.95% CI: 0.125-0.898) and 0.389 (0.95% CI: 0.161-0.944), respectively, which are very significant.

[0079] Depend on Figure 10 It can be seen that in finn-b-KRA_PSY_AUTISM, Collinsella (Collinsia spp.), Odoribacter (Porphyromonadaceae) and Terrisporobacter The causal relationship between Bacillus sp. and autism reached a statistically significant level (P<0.05), among which, Odoribacter and Terrisporobacter The positive correlation with the occurrence of autism indicates that it is a risk factor for autism, with OR values ​​of 3.006 (95% CI: 1.028-8.793) and 3.108 (95% CI: 1.200-8.049), respectively, which is very significant; Collinsella It is negatively correlated with the occurrence of autism, suggesting that it is a protective factor for autism, with an OR value of 0.336 (95%CI: 0.125-0.905), which is very significant.

[0080] Depend on Figure 11 It can be seen that in finn-b-KRA_PSY_AUTISM_EXMORE, Oscillibacter (Oscibacillus spp.) and Blautia The causal relationship between Blautia and autism reached a statistically significant level (P<0.05), among which, OscillibacterIt is positively correlated with the occurrence of autism, suggesting that it is a risk factor for autism, with an OR value of 1.996 (95%CI: 1.030-3.865), which is very significant; Blautia It is negatively correlated with the occurrence of autism, suggesting that it is a protective factor for autism, with an OR value of 0.281 (95%CI: 0.095-0.830), which is very significant.

[0081] Depend on Figure 12 It can be seen that in IEU-A-802, Lachnospiraceae NC2004 group (Lachnospira NC2004 group), Howardella (Hospital), Slackia (Slackia spp.), Eubacterium hallii group (Eubacterium hallii group), Turicibacter (Spore-forming enteric bacteria), Desulfovibrio (Desulfovibrio spp.), Eggerthella (Eggella spp.), Adlercreutzia (Adler's Kreutzeria spp.), Anaerotruncus (Anaerobic Coccidia) and Ruminiclostridium 6 The causal relationship between (Ruminal Clostridium 6) and autism reached a statistically significant level (P<0.05), among which, Lachnospiraceae NC2004 group , Slackia , Turicibacter and Eggerthella It is positively correlated with the occurrence of autism, suggesting that it is a risk factor for autism, with OR values ​​of 1.367 (95%CI: 1.017-1.838), 1.386 (95%CI: 1.031-1.864), 1.372 (95%CI: 1.031-1.825) and 1.436 (95%CI: 1.054-1.955), respectively, which are very significant; Howardella , Eubacterium hallii group , Desulfovibrio , Adlercreutzia , Anaerotruncus and Ruminiclostridium 6 It is negatively correlated with the occurrence of autism, suggesting that it is a protective factor for autism. The OR values ​​are 0.789 (95%CI: 0.630-0.990), 0.575 (95%CI: 0.390-0.848), 0.683 (95%CI: 0.486-0.960), 0.695 (95%CI: 0.516-0.936, P= 0.017), 0.603 (95%CI: 0.397-0.916) and 0.733 (95%CI: 0.545-0.987), which are very significant.

[0082] Depend on Figure 13 It can be seen that in IEU-A-806, Dorea ( Dorea Bacteria), Lachnospiraceae NC2004group (Lachnospira NC2004 group), Anaerotruncus (Anaerobic Coccidia), Ruminiclostridium 9 (Clostridium rumenii 9), Holdemania (Haldemannia cerevisiae) and Eisenbergiella The causal relationship between Eisenbergia and autism reached a statistically significant level (P<0.05), among which, Lachnospiraceae NC2004 group , Ruminiclostridium 9 and Holdemania It is positively correlated with the occurrence of autism, suggesting that it is a risk factor for autism, with OR values ​​of 1.255 (95%CI: 1.002-1.573), 1.556 (95%CI: 1.168-2.071) and 1.196 (95%CI: 1.002-1.429), respectively, which are very significant; Dorea , Anaerotruncus and Eisenbergiella It is negatively correlated with the occurrence of autism, suggesting that it is a protective factor for autism. The OR values ​​are 0.721 (95%CI: 0.532-0.979), 0.699 (95%CI: 0.525-0.931) and 0.783 (95%CI: 0.652-0.939), respectively, which are very significant.

[0083] Depend on Figure 14 It can be seen that in IEU-A-1184, Turicibacter (Spore-forming enteric bacteria), Lachnospiraceae NC2004 group (Lachnospira NC2004 group), Dorea ( Dorea Bacteria), Holdemanella (Holdemania dimorphus), Ruminiclostridium 9 (Clostridium rumenii 9), Anaerotruncus (Anaerobic Coccidia) and Eisenbergiella The causal relationship between Eisenbergia and autism reached a statistically significant level (P<0.05), among which, Turicibacter , Lachnospiraceae NC2004 group , Holdemanella and Ruminiclostridium 9 It is positively correlated with the occurrence of autism, suggesting that it is a risk factor for autism, with OR values ​​of 1.372 (95%CI: 1.056-1.782), 1.308 (95%CI: 1.029-1.662), 1.322 (95%CI: 1.030-1.696) and 1.486 (95%CI: 1.036-2.131), respectively, which are very significant; Dorea , Anaerotruncus and EisenbergiellaIt is negatively correlated with the occurrence of autism, suggesting that it is a protective factor for autism. The OR values ​​are 0.705 (95%CI: 0.508-0.978), 0.696 (95%CI: 0.519-0.935) and 0.785 (95%CI: 0.649-0.949), respectively, which are very significant.

[0084] Depend on Figure 15 It can be seen that in IEU-A-1185, Ruminococcus 1 (Ruminococcus 1), Turicibacter (Spore-forming enteric bacteria), Ruminiclostridium 5 (Clostridium rumenicola 5), Sutterella (Sutterella spp.), Dorea ( Dorea Bacteria), Ruminococcaceae UCG 005 The causal relationship between Ruminococcaceae UCG 005 and autism reached a statistically significant level (P<0.05), among which, Turicibacter It is positively correlated with the occurrence of autism, suggesting that it is a risk factor for autism, with an OR value of 1.372 (95% CI: 1.056-1.782), which is very significant; Ruminococcus 1 , Ruminiclostridium 5 , Sutterella , Dorea and Ruminococcaceae UCG 005 It is negatively correlated with the occurrence of autism, suggesting that it is a protective factor for autism. The OR values ​​are 0.831 (95%CI: 0.705-0.981), 0.812 (95%CI: 0.687-0.961), 0.821 (95%CI: 0.684-0.987, P= 0.036), 0.811 (95%CI: 0.686-0.959) and 0.776 (95%CI: 0.670-0.898), respectively, which are very significant.

[0085] After filtering out the eigenvalues ​​with smaller effect sizes (OR values), the final eigenvalues ​​(markers) included 19 intestinal microbial genera, as shown in Table 1: Table 1 19 microbial markers

[0086] Example 2 Autism Prediction Machine Learning Model This embodiment uses the LogisticRegression function in the Python sklearn.linear_model module to perform logistic regression modeling on the data. Logistic regression maps the results of multivariate linear regression analysis to the logit function z=1 / (1+exp(y)), binarizes the data according to the threshold, and predicts the binary variable.

[0087] This example constructs a prediction model for calculating the host's autism risk based on the abundance values ​​of intestinal microbial markers screened in Example 1. The specific steps are as follows: S1, Dataset acquisition: The datasets of the control group and the case group were both from the microphenodb database.

[0088] S2, divide the data set into a training set and an internal validation set. In this embodiment, 25% of the samples are used as the internal validation set.

[0089] S3, a logistic regression model was established using cross-validation. When the parameter regularization strength coefficient Cs was 50, the model had the best effect. The best regularization strength coefficient was used to train a new logistic regression model using the training set. At this time, the regression coefficients of each microbial marker were shown in Table 2, and the constant = 13.6968.

[0090] Table 2 Regression coefficients of microbial markers

[0091] The above model was used to analyze the training set, and the AUC was 0.9623.

[0092] S4, use the trained model to make predictions on the internal validation set.

[0093] The ROC curve of the internal validation set is as follows Figure 16 As shown, AUC = 0.8409, accuracy = 78%.

[0094] S5, according to the predicted probability value of the data set, the samples are divided into low-risk, medium-risk and high-risk groups. The low-risk prediction score is <0.5, and the high-risk prediction score is >0.75.

[0095] The total sample size was 324 cases, of which 54.3% (176 people) were at low risk, 20.1% (65 people) were at medium risk, and 25.6% (83 people) were at high risk. Figure 17 As shown. It can be seen that the risk critical point selected in this embodiment can successfully stratify the population according to the different risks of autism.

[0096] Example 3 Model Performance Evaluation The inventors applied the autism prediction model constructed using Example 2 to an external validation set.

[0097] The external validation set mainly comes from real physical examination sample data. The sample type is feces, with a total of 19 samples, including 8 cases with autism and 11 healthy controls. Nanopore 16S RNA sequencing analysis was used. The specific analysis steps are as follows: (1) Sequencing DNA extraction: DNA was extracted using a fecal sample bacterial genome extraction kit, and the extracted DNA concentration and purity were tested using Nanodrop; 16S rRNA amplification: Targeted amplification of the V4 region of the bacterial 16S rRNA gene region was performed using a 16S sequencing library construction kit for 30 cycles. The reaction conditions were: 95°C, 1 min, 94°C, 30 s, 62°C, 30 s, 62°C, 2 min, 62°C, 5 min; then maintained at 4°C. Recover PCR products: Purify the target fragments using AMPure XP beads and quantify using Qubit; Adapter ligation: Mix the above barcoded libraries according to the concentration ratio into a 10 μL system, so that the total amount of DNA after mixing is 200 ng. Add 1 μL RAP to the mixed sample, blow gently with a pipette tip to mix, and react at room temperature for 5 minutes.

[0098] Finally, the constructed library was sequenced using the GridION nanopore sequencer.

[0099] (2) Bioinformatics analysis First, NanoStat software was used to quality control, filter, and remove sequencing adapters of the raw data to obtain high-quality reads. Minimap2 was used for global alignment to find chimeras, and then yacrd was used to remove chimera sequences. Filtlong software was then used to filter data of specific length and Q value. Finally, the filtered sequences were clustered in a certain way (NanoCLUST in this embodiment) to obtain multiple sequence clustering operational taxonomy units (OTUs), and the OTUs were annotated with taxonomy to obtain species abundance information.

[0100] (3) Model prediction The abundance information of intestinal microbial markers in the case group and the control group was collated, and then model prediction and risk level classification were performed.

[0101] The model constructed in Example 2 was used to perform the prediction analysis of the external validation data. The results are as follows: Figure 18 As shown, AUC=0.75, accuracy rate 62%. The above results show that the model constructed by using Example 2 can distinguish autistic patients from healthy people, and can be used clinically to assist in diagnosing whether a subject has autism.

[0102] Example 4 Further evaluation of model performance In order to further verify that the model constructed in Example 2 can be used to predict the risk of autism, the inventors collected 110 samples. Using the prediction model, 16 samples were high risk, 65 samples were low risk, and the rest were medium risk (29 samples).

[0103] Further follow-up revealed that among the high-risk groups, there were 7 cases with autistic tendencies or autism diagnosis, and among the low-risk groups, there were 64 cases without autism. This shows that the prediction model is very accurate.

[0104] The high-risk group will continue to be followed up year by year, and the medium-risk group will receive early intervention through family education and other means.

[0105] Example 5 Further screening of markers The inventors further screened the microbial markers obtained in Example 2 using a stepwise regression approach, and the results are shown in Table 3: Table 3 Results of further screening of microbial markers

[0106] Note: In Table 3, R 2 represents the coefficient of determination, AIC represents the Akaike information criterion, which is a standard for evaluating the complexity of statistical models and measuring the goodness of fit of statistical models. AIC=2k-2ln(L), where k is the number of model parameters and L is the likelihood function. BIC represents the Bayesian information criterion, which is used to evaluate the quality of the model. The smaller the BIC, the better the model. BIC=kln(n)-ln(L), where k is the number of model parameters, n is the number of samples, and L is the likelihood function. MSE represents the mean squared error, which is a measure of the degree of difference between the model prediction value and the actual value.

[0107] As shown in Table 3, the markers screened by stepwise regression are removed step by step according to the number based on the combination of microbial markers in Table 1. Gordonibacter , Anaerotruncus , Desulfovibrio , Eubacterium , Holdemania , Dorea , Ruminococcus , Collinsella and Slackia .

[0108] The model prediction was performed using the combination of markers screened by the above stepwise regression, and the results are shown in Table 4.

[0109] Table 4 Model prediction results of each marker combination obtained by stepwise regression

[0110] As shown in Table 4, when the microbial markers are only Ruminiclostridium , Sutterella , Eggerthella , Holdemanella , Odoribacter , Oscillibacter , Turicibacter , Terrisporobacter , Blautia and Adlercreutzia When the AUC in the training set and the internal validation set is high, it also reaches 0.6932 in the external validation set. Slackia , Collinsella , Ruminococcus and Dorea After that, the AUC did not improve significantly, but it gradually increased Holdemania , Eubacterium , Desulfovibrio , Anaerotruncus and Gordonibacter After that, the AUC in the external validation set increased significantly, reaching around 0.75.

[0111] All documents mentioned in the present invention are cited as references in this application, just as each document is cited as reference individually. In addition, it should be understood that after reading the above teachings of the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms also fall within the scope defined by the claims attached to this application.

Claims

1. A method for constructing a disease prediction model based on a combination of intestinal microbial markers, characterized in that: The disease prediction model is used to diagnose or predict autism, and the intestinal microbial marker combination includes: Ruminiclostridium , Sutterella , Eggerthella , Holdemanella , Odoribacter , Oscillibacter , Turicibacter , Terrisporobacter , Blautia and Adlercreutzia , the method comprises the following steps: S21, randomly dividing the abundance data of the intestinal microbial marker combination in the biological samples of the group into two groups, one group is a training set, and the other group is a test set, each group includes the abundance data of the intestinal microbial marker of the samples of non-autistic subjects and the samples of autistic patients; S22, using the training set data, build a disease prediction model based on the machine learning algorithm and perform multi-fold cross validation; S23, verify the obtained disease prediction model in the test set.

2. The method according to claim 1, characterized in that The intestinal microbial marker combination also includes Ruminococcus , Slackia , Eubacterium , Desulfovibrio , Holdemania , Gordonibacter , Dorea , Collinsella and Anaerotruncus at least one of .

3. The method according to claim 1 or 2, characterized in that The abundance data of the intestinal microbial marker combination is obtained based on qPCR, 16S RNA sequencing or metagenomic sequencing.

4. The method according to claim 1 or 2, characterized in that: The machine learning algorithm is selected from any one of the following algorithms: Logistic regression algorithm, linear regression algorithm, random forest algorithm, neural network algorithm, support vector machine algorithm, Bayesian classification algorithm, gradient boosting algorithm, K nearest neighbor algorithm and decision tree algorithm.

5. The method according to claim 4, characterized in that The machine learning algorithm is a logistic regression algorithm, and the prediction model diagnoses whether the subject suffers from autism or predicts whether the subject has a risk of autism based on the score obtained by the logistic regression algorithm.

6. The method according to claim 5, characterized in that The intestinal microbial marker combination includes Ruminococcus , Ruminiclostridium , Sutterella , Slackia , Eubacterium , Desulfovibrio , Eggerthella , Holdemanella , Holdemania , Odoribacter , Oscillibacter , Gordonibacter , Turicibacter , Terrisporobacter , Dorea , Collinsella , Blautia , Anaerotruncus and Adlercreutzia, The regression coefficients of each intestinal microbial marker are as follows: Constant = 13.6968, When the score is less than 0.5, the subject does not have autism or has a low risk of autism; when the score is greater than 0.75, the subject has autism or has a high risk of autism; otherwise, the subject has a medium risk of autism.

7. A system for diagnosing or predicting autism, characterized in that: Includes the following modules: A data input module is used to input the abundance data of the intestinal microbial marker combination obtained in the subject's biological sample, wherein the intestinal microbial marker combination includes Ruminococcus , Ruminiclostridium , Sutterella , Slackia , Eubacterium , Desulfovibrio , Eggerthella , Holdemanella , Holdemania , Odoribacter , Oscillibacter , Gordonibacter , Turicibacter , Terrisporobacter , Dorea , Collinsella , Blautia , Anaerotruncus and Adlercreutzia ; A database storage module, used to store the abundance data of the intestinal microbial marker combination in biological samples of a group, wherein the group samples include samples of non-autistic subjects and samples of autistic patients; a disease prediction module, connected to the data input module and the database storage module respectively, for constructing a prediction model using the abundance data of the intestinal microbial marker combination in the biological samples of the population, and diagnosing whether the subject suffers from autism or predicting whether the subject has a risk of autism based on the abundance data of the intestinal microbial marker combination of the subject obtained from the data input module, Wherein, in the disease prediction module, the construction of a prediction model using the abundance data of the intestinal microbial marker combination in the biological sample of the group includes the following steps: S21, randomly dividing the abundance data of the intestinal microbial marker combination in the biological samples of the group into two groups, one group is a training set, and the other group is a test set, each group includes the abundance data of the microbial markers of the samples of non-autistic subjects and the samples of autistic patients; S22, using the training set data, build a disease prediction model based on the machine learning algorithm and perform multi-fold cross validation; S23, in the test set, verify the obtained prediction model, The machine learning algorithm is a logistic regression algorithm, and the prediction model diagnoses whether the subject suffers from autism or predicts whether the subject has a risk of autism based on the score obtained by the logistic regression algorithm. The regression coefficients of each intestinal microbial marker are as follows: Constant = 13.6968, When the score is less than 0.5, the subject does not have autism or has a low risk of autism; when the score is greater than 0.75, the subject has autism or has a high risk of autism; otherwise, the subject has a medium risk of autism.

8. The system according to claim 7, characterized in that The abundance data of the intestinal microbial marker combination obtained in the data input module is obtained based on qPCR, 16S RNA sequencing or metagenomic sequencing.

Citation Information

Patent Citations

  • Oral flora microorganisms for children autism assessment

    CN111455076A

  • In-vitro evaluation method for autism intestinal bacteria transplantation effectiveness

    CN115011674A

  • Method for excavating intestinal flora biomarkers of autism

    CN117577195A

  • Colorectal adenoma intestinal microbial marker and application thereof

    CN117965715A

Cited By

  • Method for establishing a screening model for autism spectrum disorder and screening method and system thereof

    TWI931228B