A method and system for assessing the development of infant microecological flora

Abstract

This invention provides a method and system for assessing the development of infant gut microbiota, involving a set of judgment models and standards, including a classification model for the maturity of infant gut microbiota development, a regression model for the developmental age of infant gut microbiota development, and a developmental curve and reference range for microbiota age. This invention extracts and sequences microbial DNA from infant feces, and based on statistical analysis, determines that 27 months of age is a critical node for the maturity of infant gut microbiota development in China. Using this as a dividing line, a machine learning classification model is constructed to determine whether the microbiota development is mature, with an AUC exceeding 97%. Furthermore, based on this, a machine learning regression model is used to predict the developmental age of infant gut microbiota. The regression prediction model is applied to large-scale datasets to predict and set reference ranges for developmental judgment standards, providing a new reference standard for assessing the maturity of infant gut microbiota development.

Description

Technical Field

[0001] This invention relates to the field of gut microbiota analysis, specifically to a method and system for assessing the age-related developmental level of infants' gut microbiota using microbiota information. Background Technology

[0002] Gut microbiota are closely related to human health, especially during the early developmental stages of infancy, playing a crucial role in growth, development, and the maturation of immunity. During the first 1000 days of life, the richness and diversity of an infant's gut microbiota undergoes a dynamic maturation process, representing the optimal time for intervention in its development. Therefore, early assessment of an infant's gut microbiota development is significant for their subsequent healthy growth, guiding subsequent nutritional health and dietary practices.

[0003] Currently, assessments of infant gut microbiota maturity are relatively simplistic, failing to consider the gradual maturation of gut microbiota development before age 3. These methods either rely on one or two microbial biomarkers to predict age or use simple regression models to predict gut microbiota age, thus ignoring the crucial maturation characteristics of the gut microbiota. Therefore, a scientific method and standard for evaluating infant gut microbiota development is urgently needed. Summary of the Invention

[0004] Purpose of the invention: In view of the shortcomings of the prior art, the purpose of this invention is to provide a method and system for assessing the development of infant microecological flora, proposing a classification model for the maturity of infant microecological development, an age regression model for infant microecological development, and a microecological age development curve, so as to scientifically and reasonably assess whether the development of infant microecology is normal.

[0005] Technical solution: To achieve the above-mentioned objectives, the present invention adopts the following technical solution:

[0006] The first aspect of this invention provides a method for assessing the development of infant microecological flora, comprising the following steps:

[0007] Microorganisms in infant feces were extracted and sequenced to obtain microecological community composition data. The microecological maturity judgment model for infants was used for classification to determine whether the microecological community was mature. The microecological maturity judgment model for infants was constructed based on the optimal classification age obtained statistically.

[0008] If it has not matured, a machine learning regression model is used to predict the age of the microbiome to obtain the predicted age of the microbiome.

[0009] Based on the predicted microecological age, and in comparison with the microecological age development curve, a risk assessment is conducted to determine whether the infant's development is advanced or delayed. The microecological age development curve is predicted on a large-scale dataset using a machine learning regression model, and a reference range for development judgment criteria is set.

[0010] Furthermore, the method for constructing the infant microecological maturity judgment model includes the following steps:

[0011] We collected and organized raw sequencing data of infant gut microbiota and its clinical information, analyzed and integrated the sequencing data, and obtained a table of relative abundance of gut microbiota for constructing a classification model of gut microbiota developmental maturity.

[0012] Based on the actual age of the samples, which ranges from 18 to 36 months, all samples were divided into two categories: immature and mature.

[0013] Feature selection was performed on multiple different classification results, and a classification model for the maturity of micro-ecological development was constructed. The accuracy of the classification prediction results was statistically analyzed.

[0014] Compare the accuracy of prediction results for different classification ages to determine the optimal classification age;

[0015] Using the optimal age for classification as the dividing line, a model for judging the maturity of infant microecology is constructed by applying machine learning methods.

[0016] Furthermore, the optimal classification age is 27 months.

[0017] Furthermore, the method for predicting the age of infant gut microbiota using machine learning regression models includes the following steps:

[0018] The gut microbiota composition information of each individual is obtained by sequencing, and the relative abundance of each microbial community is calculated.

[0019] Key biomarkers for assessing the developmental maturity of an individual's gut microbiota were screened using the Boruta method.

[0020] Based on the set of key biomarkers, we iteratively optimized and constructed an individual gut microbiota age prediction model and validated it. We then selected the optimal number of models for subsequent use.

[0021] The gut microbiota age of the test samples was predicted using multiple optimal models, and the average value after removing the highest and lowest values ​​was used as the final individual assessment result.

[0022] Furthermore, the method for generating the microecological age development curve and calculating reasonable reference intervals for microecological development age at different months includes the following steps:

[0023] Collect infant microbiota data, including raw sequencing data and phenotypic information, and construct a reference dataset;

[0024] Analyze the collected raw data to obtain the microbial community composition structure data for each sample;

[0025] The microecological age of each sample is calculated using a machine learning regression model;

[0026] A scatter plot is constructed based on the actual monthly age and microecological age of each sample in the reference dataset. A microecological age development curve is fitted based on the median of the microecological age corresponding to each monthly age. The lower limit of the microecological development age is fitted based on the preset upper limit quantile, and the upper limit of the microecological development age is fitted based on the preset lower limit quantile.

[0027] Furthermore, the infant microecological flora development assessment method also includes a correlation analysis between allergies and abnormalities in age-related microecological development, including the following steps:

[0028] We collected fecal samples from infants and young children to obtain microecological flora data, and collected phenotypic information on whether each individual had an allergy.

[0029] The infant microecological maturity judgment model is used to determine whether the microecological age is mature. For immature samples, machine learning regression model is used to predict the microecological age, and the microecological age development curve is combined to determine whether the microecological age development is abnormal.

[0030] The correlation between the occurrence of allergic diseases and abnormalities in the development of the gut microbiota at an age was analyzed.

[0031] Based on the same inventive concept, a second aspect of the present invention provides an infant microecological flora development assessment system, comprising:

[0032] The microecological development maturity judgment module is used to extract and sequence fecal microorganisms from infants and young children to obtain microecological community composition data. The microecological maturity judgment model is used to classify the microecological community and determine whether the microecological community is mature. The microecological maturity judgment model is constructed based on the optimal classification age obtained statistically.

[0033] The microbial ecosystem age prediction module is used to predict the age of the microbial ecosystem when it is not yet fully developed, using a machine learning regression model.

[0034] The system also includes a risk assessment module, which assesses whether an infant's development is advanced or delayed based on the predicted microecological age and the microecological age development curve. The microecological age development curve is predicted on a large-scale dataset using a machine learning regression model, and a reference range for developmental judgment criteria is set.

[0035] Furthermore, the infant microecological flora development assessment system also includes an allergy association analysis module, which is used to perform association analysis between allergies and whether there are abnormalities in the age-related development of the microecological flora.

[0036] A third aspect of the present invention provides a computer system, including a memory, a processor, and a computer program / instructions stored in the memory and executable on the processor, wherein the computer program / instructions, when executed by the processor, implement the steps of the infant microecological flora development assessment method.

[0037] A fourth aspect of the present invention provides a computer program product, including a computer program / instructions, wherein when the computer program / instructions are executed by a processor, the steps of the infant microecological flora development assessment method are implemented.

[0038] Beneficial Effects: This invention provides a method for assessing the development of infant microbiota, combining machine learning classification and regression models. It can accurately predict and assess the developmental status of the microbiota at different ages of infants based on the composition and structure of fecal microorganisms. First, a classification model determines whether the infant's microbiota is mature. For immature samples, a machine learning regression model accurately predicts the developmental age of the microbiota, and the result is compared with a reference curve to accurately assess whether development is normal. Compared with existing technologies, this invention has the following advantages: 1. This invention provides a model for judging the maturity of the infant's microbiota. Through research on the developmental characteristics of the microbiota in Chinese infants, it has been determined that 27 months of age is a critical node for the maturity of the infant's microbiota. 2. This invention constructs a method for judging the maturity of the infant's microbiota. By combining the microbiota maturity judgment model and the microbiota age prediction model, the accuracy of model construction and prediction can be effectively improved. 3. Based on a large-scale dataset (microbiota samples of infants of different ages worldwide), this invention, for the first time, constructs an infant microbiota age development curve and upper and lower reference intervals, enabling a scientific and reasonable assessment of whether the infant's microbiota development is normal. Attached Figure Description

[0039] Figure 1 This is a flowchart illustrating the overall process of assessing infant microecological flora development according to an embodiment of the present invention.

[0040] Figure 2 This is a comparison chart of the effects of the microecological classification model with different age groups as the dividing line in the embodiments of the present invention.

[0041] Figure 3 This is a diagram illustrating the effect of the microecological maturity judgment model in an embodiment of the present invention.

[0042] Figure 4The diagram shows the prediction effect of microecological development age of Chinese children in the embodiments of the present invention, where (a) shows the prediction effect on the training set and (b) shows the prediction effect on the test set.

[0043] Figure 5 This is a diagram showing the age development curve and reference interval of the infant microecology in an embodiment of the present invention.

[0044] Figure 6 This is a flowchart illustrating the operation of the infant microecological flora development assessment system according to an embodiment of the present invention.

[0045] Figure 7 This is a graph showing the relationship between intestinal age development and the incidence of allergies in an embodiment of the present invention. Detailed Implementation

[0046] The technical solution of the present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0047] Example 1

[0048] like Figure 1 As shown in the figure, this invention discloses a method for assessing the development of infant microecological flora, which mainly includes the following steps:

[0049] Microorganisms were extracted and sequenced from infant feces to obtain microecological community composition data. The microecological maturity judgment model for infants was used for classification to determine whether the microecological community was mature. The infant microecological maturity judgment model was constructed based on the optimal classification age obtained statistically.

[0050] If it has not matured, a machine learning regression model is used to predict the age of the microbiome to obtain the predicted age of the microbiome.

[0051] Based on the predicted microecological age, and in comparison with the microecological age development curve, a risk assessment is conducted to determine whether the infant's development is advanced or delayed. The microecological age development curve is predicted on a large-scale dataset using a machine learning regression model, and a reference range for development judgment criteria is set.

[0052] Based on data from over 800 infant microbiota studies in China, this invention uses statistical methods to calculate the optimal cutoff point for microbiota maturation and constructs a classification model to predict microecological maturity. Furthermore, in children under 3 years old, a regression model is constructed to predict the developmental age of the microbiota. And based on the prediction results from over 20,000 cases globally, a microecological age development curve and reference interval are constructed.

[0053] The following sections provide a detailed introduction to the infant microecological maturity judgment model based on machine learning classification model, the microecological age prediction model based on machine learning regression model, and the generation and reference interval calculation of the microecological age development curve involved in the embodiments of the present invention.

[0054] A machine learning-based classification model for assessing infant gut microbiota maturity can be used to evaluate the developmental maturity of infant gut microbiota. This model primarily involves optimal segmentation points for the microbiota, classification models, and biomarkers. The main steps in constructing the gut microbiota maturity assessment model include:

[0055] Step S101: Collect and merge fecal 16S rRNA sequencing data from 872 Chinese infants and young children across different clinical projects. The sequencing data were processed using the DADA2 (https: / / benjjneb.github.io / dada2 / tutorial.html) 16S amplicon analysis workflow. The steps are as follows:

[0056] (1) First, the 16S rRNA sequence of each sample is obtained by removing the adapter and splitting the sequence. Then, after quality filtering, noise removal, merging and chimera removal, a 100% consistent ASV (Amplicon Sequence Variant) sequence is obtained.

[0057] (2) Align the ASV sequence to the Silva database (v138) to obtain the species name of the sequence.

[0058] (3) Integrate the naming of different reference sequences, merge the abundance of sequences annotated to the same species into the abundance of the same species, and obtain the microbial composition data of the samples used.

[0059] Step S102: Based on each child's actual age, using 18 to 36 months as the classification age, divide all samples into two categories: immature and mature. Construct a microecological development maturity classification model for each category and statistically analyze the accuracy of the classification prediction results. The operation steps are as follows:

[0060] (1) After standardizing the original species abundance table, age information and species abundance table are merged.

[0061] (2) The samples were divided into immature and mature categories according to age nodes to obtain the initial data for model construction. Gut microbial feature selection was performed, and the top 30 microorganisms with the highest contribution were selected to construct the model. The AUC value, which represents the prediction accuracy of the model, was recorded and repeated 20 times.

[0062] In this embodiment, the selected set of microbial biomarkers for the mature development of infant microecology includes: Enterococcus, UBA1819, Faecalibacterium, Dialister, Bacteroides, Incertae Sedis, Ruminococcus torques group, Staphylococcus, Butyricicoccus, Eubacterium nodatum group, Eubacterium eligens group, Lachnoclostridium, Methyloversatilis, Pseudomonas, Monoglobus, Abiotrophia, Oscillibacter, Blautia, Eubacterium ventriosum group, Sellimonas, Eisenbergiella, Saccharimonadaceae, TM7x, Clostridium innocuum group, Lachnospiraceae NK4A136 group, Ruminococcus gnavus group, Flavonifractor, Eubacterium fissicatena group, Holdemania, and Candidatus Soleaferrea.

[0063] Step S103, for each age category from 18 to 36, repeat steps (2), and finally compare the differences in AUC values ​​of adjacent category prediction results using a t-test. Figure 2 As shown, significant differences emerged in classification performance at 27 and 28 months, indicating that the improvement in classification effectiveness gradually reached saturation after 28 months. Figure 2 Therefore, 27 months is the optimal age for determining developmental maturity.

[0064] Step S104: Based on the results of the previous step, the samples are divided into mature and immature categories using 27 months as the boundary. Biomarkers are screened from the gut microbiota data, and a machine learning binary classification model is constructed. The constructed infant gut microbiota maturity judgment model achieves an AUC of 97.3%. Figure 3 .

[0065] The construction of an infant and toddler gut microbiota age prediction model based on machine learning regression model mainly involves data collection and organization, identification of key biomarkers, and regression model training. Specific steps include:

[0066] Step S201: Data Collection and Processing: Fecal samples from 872 infants were collected for 16S rRNA sequencing to obtain raw sequencing files. The distribution of samples across different age groups is shown in Table 1. The raw sequencing data was then processed using the DADA2 16S amplicon analysis workflow to obtain a species abundance composition table for all samples. The operation steps are as follows:

[0067] (1) First, the original sequence was de-adapted and split to obtain the 16S rRNA sequence of each sample. Then, after quality filtering, noise reduction, merging and chimera removal, a 100% consistent ASV (Amplicon Sequence Variant) sequence was obtained.

[0068] Table 1. Sample distribution by age group

[0069]

[0070]

[0071] (2) Align the ASV sequence to the Silva database (v138) to obtain the species name of the sequence.

[0072] (3) Integrate the names of different reference sequences, merge the abundance of sequences annotated to the same species into the abundance of the same species, and obtain the bacterial community composition data of the sample.

[0073] Step S202, Key Biomarkers: The data from step S201 was split into training and testing sets at a ratio of 4:1. After Boruta feature selection, the data was fitted with the actual developmental age to identify 34 key core bacteria for gut microbiota developmental maturity.

[0074] In this embodiment, the selected set of microbial biomarkers for predicting the developmental age of infants' microecological system includes: Bifidobacteriaceae, Incertae Sedis, Saccharimonadaceae, Abiotrophia, Actinomyces, Bacteroides, Bifidobacterium, Blautia, Butyricicoccus, Clostridium sensu stricto1, Dialister, Enterococcus, Erysipelatoclostridium, Escherichia-Shigella, Faecalibacterium, Flavonifractor, Intestinibacter, Methyloversatilis, Monoglobus, Parabacteroides, Phascolarctobacterium, Pseudomonas, Romboutsia, Rothia, Staphylococcus, Streptococcus, TM7x, UBA1819, [Clostridium]innocuum group, [Eubacterium]hallii group, and [Eubacterium]nodatum. group, [Eubacterium]ventriosum group, [Ruminococcus]gnavus group and [Ruminococcus]torques group.

[0075] Step S203, Model Training: The data from step S201 is randomly split multiple times at a ratio of 4:1 into a training set and a test set. Using the 34 core bacteria in the training set from the previous step as features, a regression model for predicting the age of the gut microbiota is trained multiple times. Random forest is selected for model training. The ten best training models are selected, and the developmental age of the gut microbiota in months is output based on the model.

[0076] Step S204: Based on the prediction results of the ten optimal models, remove the highest and lowest values ​​and take the average value to determine the developmental age in months for each sample.

[0077] Figure 4 The performance of the microbiome age regression prediction model on the training and test sets is presented. In particular, on the test set, there is a correlation of 0.83 between the predicted age and the actual age.

[0078] In this embodiment, a gut microbiota age development curve is fitted and plotted, and the Q10 and Q90 intervals are calculated and defined as the reasonable developmental range. Specific steps include:

[0079] Step S301: Collect global infant fecal microbiota data. Screen infant microbiota data from public databases such as NCBI and SRA, including raw sequencing data and phenotypic information (such as age, sex, country, etc.), and construct a reference dataset.

[0080] Step S302: Process and analyze the raw data collected in step S301 using a unified data analysis workflow to obtain the microbial community composition structure data for each sample.

[0081] Step S303: Calculate the microecological age of each sample in the public dataset using the constructed microecological age prediction model;

[0082] Step S304: Construct a scatter plot based on the actual monthly age and microecological age of each sample in the reference database, and fit a reference curve for microecological development age based on the median (Q50) of the microecological age corresponding to each monthly age. Fit the lower limit of microecological development age based on the 10th percentile (Q10) and the upper limit of microecological development age based on the 90th percentile (Q90).

[0083] In this embodiment, the fitted and plotted infant microecological age development curve and reference interval are as follows: Figure 5 .

[0084] Example 2

[0085] This invention discloses an infant microbiota development assessment system, comprising: a microbiota development maturity judgment module, used to extract and sequence fecal microorganisms from infants to obtain microbiota composition data, classify them using an infant microbiota maturity judgment model, and determine whether the microbiota is mature; a microbiota age prediction module, used to predict the microbiota age using a machine learning regression model when the microbiota is not mature; and a risk assessment module, used to assess the risk of premature or delayed development in infants based on the predicted microbiota age and a microbiota age development curve. This infant microbiota development assessment system originates from the same inventive concept as the aforementioned infant microbiota development assessment method; the specific implementation of each module is described in the above method embodiments.

[0086] Figure 6This paper illustrates the assessment process of an infant microecological flora development assessment system. First, based on sequencing information from infant feces, a microecological maturity assessment model is used to determine whether the microecological development is mature. Combining the infant's actual age with the maturity assessment age (27 months) determined in this invention, the following four scenarios are identified: 1. Actual age ≥ 27 months: Microecological development is mature; considered normal maturity. 2. Actual age ≥ 27 months: Microecological development is immature; considered normal but delayed development. 3. Actual age < 27 months: Microecological development is mature; considered premature development, assessed based on a questionnaire. 4. Actual age < 27 months: Microecological development is immature. This is the scenario that this invention focuses on. A regression model is used to predict the microecological age, and it is determined whether the microecological age falls within the reference range. If so, the microecological age is considered normal; otherwise, it is considered abnormal, requiring interventions such as dietary nutrition intervention.

[0087] Example 3

[0088] This invention discloses a method for assessing the development of infant gut microbiota. Based on Example 1, it further includes: performing a correlation analysis between allergies and abnormalities in gut microbiota development, involving data collection, data processing, gut microbiota age prediction, and the correlation between developmental abnormalities and allergies. Specific steps include:

[0089] Step S401: Data collection: Collect 234 fresh infant feces (most of which were under 3 years old), extract and amplify DNA, and then perform next-generation sequencing. Collect phenotypic information on whether each individual had an allergy.

[0090] Step S402, Data Processing: The sequencing data is processed using the 16S amplicon analysis workflow based on DADA2 (https: / / benjjneb.github.io / dada2 / tutorial.html). The operation steps are as follows:

[0091] (a) First, the 16S rRNA sequence of the sample is obtained by de-adaptor and splitting the sequence. Then, after quality filtering, noise reduction, merging and chimera removal, a 100% identical ASV (Amplicon Sequence Variant) sequence is obtained.

[0092] (b) Align the ASV sequences to the Silva database (v138) to obtain species names for the sequences.

[0093] (c) Integrate the nomenclature of different reference sequences, merge the abundance of sequences annotated to the same species into the abundance of the same species, and obtain the microbial composition data of the sample.

[0094] Step S403, Determining the maturity of the microecological age: Apply the microecological maturity judgment model to predict whether the sample is mature.

[0095] Step S404, Microbial Ecosystem Age Prediction: Since the sample ages are still relatively young, most of them are judged as immature by the maturity judgment model. For the samples judged as immature in the previous step, the microbial ecosystem age is predicted using a machine learning regression model to obtain the specific microbial ecosystem development age.

[0096] Step S405: Association between allergies and abnormal microecological development: In this study of 234 samples, the association between the occurrence of allergic diseases and abnormal microecological development (normal range between Q10 and Q90, abnormal range outside this range) was analyzed. The results are shown in Table 2. In normal children, the rate of abnormal microecological development was 14.29%, while in children with allergies, the rate was as high as 42.14%. Figure 7 As shown.

[0097] Table 2. Association between microecological age assessment results and allergic phenotype

[0098]

[0099] This embodiment demonstrates that, based on microecological age assessment, the microecological age of allergic children is more likely to deviate from the reference range compared to normal children, providing new insights for the early prevention and treatment of common allergic diseases in infants and young children.

[0100] Example 4

[0101] This invention discloses an infant microecological flora development assessment system. Based on Example 2, it further includes an allergy correlation analysis module, used to perform correlation analysis between allergies and abnormalities in microecological age development. Detailed implementation steps of this module can be found in Example 3.

[0102] Example 5

[0103] This invention discloses a computer system including a memory, a processor, and a computer program / instructions stored in the memory and executable on the processor. When the computer program / instructions are executed by the processor, they implement the steps of the method in the aforementioned method embodiments.

[0104] Example 6

[0105] This invention discloses a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the method described in the foregoing method embodiments.

Claims

1. A method for assessing the development of infant microecological flora, characterized in that, Includes the following steps: Microorganisms in infant feces were extracted and sequenced to obtain microecological flora composition data. The microecological maturity judgment model of infants was used to classify and determine whether the microecological flora was mature. The microecological maturity judgment model of infants was constructed based on the optimal classification age obtained from the statistical analysis of infant samples with actual ages of 18 to 36 months, and the optimal classification age was 27 months. If it has not matured, a machine learning regression model is used to predict the age of the microbiome to obtain the predicted age of the microbiome. Based on the predicted microecological age, and by comparing it with the microecological age development curve, a risk assessment is conducted to determine whether the infants and young children are developing ahead of or behind. The microecological age development curve is predicted on a large-scale dataset using a machine learning regression model, and a reference range for development judgment criteria is set. Specifically, a scatter plot is constructed based on the actual monthly age and microecological age of the sample. The microecological age development curve is fitted based on the median of the microecological age corresponding to each monthly age. The lower limit of the microecological development age is fitted based on the preset upper limit quantile, and the upper limit of the microecological development age is fitted based on the preset lower limit quantile.

2. The method for assessing the development of infant microecological flora according to claim 1, characterized in that, The method for constructing the infant microecological maturity assessment model includes the following steps: We collected and organized raw sequencing data of infant gut microbiota and its clinical information, analyzed and integrated the sequencing data, and obtained a table of relative abundance of gut microbiota for constructing a classification model of gut microbiota developmental maturity. Based on the actual age of the samples, which ranges from 18 to 36 months, all samples were divided into two categories: immature and mature. Feature selection was performed on multiple different classification results, and a classification model for the maturity of micro-ecological development was constructed. The accuracy of the classification prediction results was statistically analyzed. Compare the accuracy of prediction results for different classification ages to determine the optimal classification age; Using the optimal age for classification as the dividing line, a model for judging the maturity of infant microecology is constructed by applying machine learning methods.

3. The method for assessing the development of infant microecological flora according to claim 1, characterized in that, The method for predicting the age of infant gut microbiota using machine learning regression models includes the following steps: The gut microbiota composition information of each individual is obtained by sequencing, and the relative abundance of each microbial community is calculated. Key biomarkers for assessing the developmental maturity of an individual's gut microbiota were screened using the Boruta method. Based on the set of key biomarkers, we iteratively optimized and constructed an individual gut microbiota age prediction model and validated it. We then selected the optimal number of models for subsequent use. The gut microbiota age of the test samples was predicted using multiple optimal models, and the average value after removing the highest and lowest values ​​was used as the final individual assessment result.

4. The method for assessing the development of infant microecological flora according to claim 1, characterized in that, The method for generating the microecological age development curve and calculating the reasonable reference range of microecological development age at different months includes the following steps: Collect infant microbiota data, including raw sequencing data and phenotypic information, and construct a reference dataset; Analyze the collected raw data to obtain the microbial community composition structure data for each sample; The microecological age of each sample is calculated using a machine learning regression model; A scatter plot is constructed based on the actual monthly age and microecological age of each sample in the reference dataset. A microecological age development curve is fitted based on the median of the microecological age corresponding to each monthly age. The lower limit of the microecological development age is fitted based on the preset upper limit quantile, and the upper limit of the microecological development age is fitted based on the preset lower limit quantile.

5. The method for assessing the development of infant microecological flora according to claim 1, characterized in that, It also includes an association analysis between allergies and abnormalities in the development of the gut microbiota at an age, including the following steps: We collected fecal samples from infants and young children to obtain microecological flora data, and collected phenotypic information on whether each individual had an allergy. The infant microecological maturity judgment model is used to determine whether the microecological age is mature. For immature samples, machine learning regression model is used to predict the microecological age, and the microecological age development curve is combined to determine whether the microecological age development is abnormal. The correlation between the occurrence of allergic diseases and abnormalities in the development of the gut microbiota at an age was analyzed.

6. A microecological flora development assessment system for infants and young children, characterized in that, include: The microecological development maturity judgment module is used to extract and sequence fecal microorganisms from infants and young children to obtain microecological community composition data. The microecological maturity judgment model is used to classify the microecological community and determine whether the microecological community is mature. The microecological maturity judgment model is constructed based on the optimal classification age obtained from the statistical analysis of infant samples with actual ages of 18 to 36 months, and the optimal classification age is 27 months. The microbial ecosystem age prediction module is used to predict the age of the microbial ecosystem when it is not yet fully developed, using a machine learning regression model. And a risk assessment module, which is used to assess whether infants and young children are ahead or behind in development based on the predicted microecological age and the microecological age development curve. The microecological age development curve is predicted on a large-scale dataset using a machine learning regression model, and a reference range for development judgment criteria is set. Specifically, a scatter plot is constructed based on the actual monthly age and microecological age of the sample. The microecological age development curve is fitted based on the median of the microecological age corresponding to each monthly age. The lower limit of the microecological development age is fitted based on the preset upper limit quantile, and the upper limit of the microecological development age is fitted based on the preset lower limit quantile.

7. The infant microecological flora development assessment system according to claim 6, characterized in that, It also includes an allergy association analysis module, which is used to analyze the correlation between allergies and abnormalities in the development of the gut microbiota at an age.

8. A computer system comprising a memory, a processor, and computer programs / instructions stored in the memory and executable on the processor, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1-5.

9. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1-5.

Images