CN116153414A - Method for constructing early-life age prediction model of host based on intestinal microorganisms - Google Patents
Method for constructing early-life age prediction model of host based on intestinal microorganisms Download PDFInfo
- Publication number
- CN116153414A CN116153414A CN202310130546.8A CN202310130546A CN116153414A CN 116153414 A CN116153414 A CN 116153414A CN 202310130546 A CN202310130546 A CN 202310130546A CN 116153414 A CN116153414 A CN 116153414A
- Authority
- CN
- China
- Prior art keywords
- host
- intestinal
- age
- constructing
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Bioethics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biotechnology (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Theoretical Computer Science (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention provides a method for constructing a host early life age prediction model based on intestinal microorganisms. Based on the relation between the intestinal microbial community change and the host development in the early life of the host, the invention constructs a model for predicting the early life age of the host based on the intestinal microbes by utilizing the important role played by the intestinal microbes in the early life of the host and the continuous development characteristics, and acquires the important intestinal microbial marker information in the early life of the host as one of the evaluation indexes of the health state of the early life of the host; the model is better in prediction effect and higher in precision.
Description
Technical Field
The invention relates to the field of intestinal microorganism research, in particular to a method for constructing a host age prediction model.
Background
There is a close relationship between intestinal microorganisms and host health. On the one hand, intestinal microorganisms are an indispensable part of human body composition, and not only assist human body in absorbing nutrition from food, but also play an important role in functions including substance metabolism, biological barrier, immune regulation, host defense, and the like. For example, intestinal microorganisms can indirectly influence the individual response to immunotherapy, and the flora colonized on the surface of intestinal mucosa plays a key role in the maturation of the host immune system, in terms of the intestinal flora and its metabolites, maintaining the integrity of intestinal epithelial cells and stimulating immune tolerance. In turn, the different health status of the host can affect the lifestyle of the intestinal microorganisms, e.g., the host immune system can suppress the proliferation of pathogenic bacteria in the intestinal tract that cause chronic inflammation; the intestinal microbial compositions of hosts at different age stages are also different, and researches show that the intestinal microbial community structure is obviously changed along with the growth of the ages, for example, the content of beneficial bacteria such as lactobacillus, bifidobacterium and the like is gradually reduced, and the content of potential pathogenic bacteria such as escherichia coli, clostridium perfringens and the like is gradually increased, so that the functions of intestinal epithelial cells are further influenced. The symbiotic and co-evolutionary relationship between intestinal microbial flora and host can promote the development of host immune system and regulate the balance of organism immune system.
With the continuous and intensive research on intestinal microorganisms, the research shows that the intestinal microbial community structure is significantly changed from birth to 2-3 years old, and the microorganisms remain relatively stable. Fredrik
Et al in Cell Host&Microbe published studies indicate that most of the bacterial genera in the adult intestinal microbiota are formed within 3 years of early development,this suggests that the intestinal microbiota may be particularly sensitive early in development and may have a profound effect on later health. Similarly, studies on Cell Reports Medicine by Charisse Petersen et al indicate that the gut microbiota of infants from just birth to 600 days of development is continuously mature, and that a decrease in gut microbiota diversity during development is also found to have a significant correlation with post-host allergic symptoms. Advanced Experimental Medical Biology, a review of the study published in this patent application shows that the first 1000 days of life is a key period for the colonization and formation of microorganisms in the intestinal tract of humans, and is also a key period for the development and maturation of the immune system, and can profoundly influence the metabolic capacity, immune function and microbial composition of the host in the future. These findings are all indicative of the importance of intestinal microorganisms early in the life of the host.
To date, some existing technologies have shortcomings in constructing a model for predicting early life age of a host by using intestinal microorganisms, for example, the aging markers of a human microbiome and the aging clock model method of the microbiome constructed by the application of CN113574604a are only suitable for 15-90-year-old host individuals, and are not suitable for predicting early life of the host; for example, CN114093515a application provides an age prediction method based on integrated learning of intestinal flora prediction model, but does not make a distinction judgment on the age of host individuals, and according to the study of significantly different intestinal microorganisms in early life (0-3 years) and later age, the technology may have deviation on early life age prediction, and model prediction performance is less than 60%; while CN111128378A patent application provides a prediction method for assessing infant intestinal flora development age, it does not provide explicit intestinal microbial marker information, nor provides accuracy of prediction model and other assessment indexes, and has no high availability.
Disclosure of Invention
The invention aims to: aiming at the defects of the prior art, the invention provides a method for constructing a model for predicting early life and age of a host based on intestinal microorganisms, which solves the problems of lack of early life prediction research of the host, small data set of the constructed model, insufficient prediction performance of the model and the like in the prior art.
The technical scheme is as follows: in order to solve the technical problems, the invention relates to a method for constructing a host early life age prediction model based on intestinal microorganisms, which comprises the following steps:
step one, collecting intestinal microorganism sequencing original data related to early life and background information of a host;
analyzing and integrating the original data to obtain an intestinal microorganism relative abundance information table for finally constructing an age prediction model;
thirdly, selecting intestinal microbial characteristics, constructing an age prediction model and verifying;
and step four, age prediction is carried out on the sample data to be predicted by using an age prediction model.
Further, step one, relevant documents are searched through keywords including infant gut microbiota and 16S rRNA, the documents obtained through preliminary collection are screened, samples which are not disclosed by the intestinal microbial data sequencing dataset and have no BioProject information and are not clear in the intestinal microbial data sequencing dataset are filtered, the sources of the sequencing samples are non-intestinal and host age information are ambiguous, and the left samples are searched in a database according to the BioProject information in the documents to obtain intestinal microbial sequencing data of the corresponding samples for batch downloading.
Further, step one uses keywords including infant gut microbiota, 16S rRNA to search a database, searches the database for bioprject information, host information and sequencing data of the directly obtained items, filters the sequencing samples from parenteral samples and samples without host age information, and downloads the original sequencing data in batches.
Still further, the database includes an SRA database or an ENA database of NCBI.
Further, the original data are analyzed and integrated in the second step: firstly deleting samples with ages of more than 1000 days, and then converting age information units of different samples into months; secondly, analyzing and processing the original sequencing data, firstly performing primary quality control on the original sequencing data by using Trimmomatic, including removing a joint sequence and a low-quality sequence, and removing samples with the number of sequences less than 20000 after quality control in order to avoid the influence of sequencing depth on the subsequent integration analysis of different projects; and (3) carrying out subsequent analysis on the high-quality sequence after quality control, and finally obtaining a relative abundance information table of intestinal microorganisms.
Still further, the follow-up analysis includes a DADA2 analysis procedure, a QIIME2 analysis procedure, or an OTU analysis procedure of userch, the DADA2 analysis procedure including DADA2 noise reduction treatment, chimera sequence removal, ASV sequence, and sample composition table generation and database species annotation analysis.
Still further, the database of species annotation analysis includes a SILVA database, a Greengenes database, or an RDP database.
Further, step three, constructing an age prediction model by using the intestinal microorganism relative abundance table and the corresponding host age information:
(1) according to the random sampling principle, constructing a training set and a testing set of an age prediction model according to a proportion, constructing a random forest model by using the training set, generating 500 decision trees by default, and evaluating the constructed model by using the testing set;
(2) for the established random forest model, evaluating the importance and side-arrangement of microorganisms in the model by utilizing the function of the importance function in the random forest model: determining the importance of the microorganism according to an IncNodePurity value, wherein the IncNodePurity value is measured by the sum of squares of residual errors and represents the influence of each variable on the heterogeneity of the observed value on each node of the classification tree, so that the importance of the variable is compared, and the larger the value is, the larger the importance of the variable is; screening and obtaining a microbial characteristic data set by using a ten-fold cross validation method;
(3) constructing an age prediction random forest model according to the microbial characteristic data set obtained by screening, constructing a training set and a test set according to the data set, constructing the age prediction random forest model by using the training set, generating 500 decision trees by default, and evaluating the constructed model by using the test set.
And step four, obtaining a microorganism relative abundance table of a host sample to be predicted for the age, and importing an age prediction random forest model for prediction so as to obtain an age prediction result of the host sample to be predicted.
Still further, the means for obtaining the information of the relative abundance of the microorganism in the sample in the fourth step includes 16S rRNA, metagenomic sequencing, and qPCR experimental analysis of the microorganism.
The beneficial effects are that: based on the relation between the intestinal microbial community change and the host development in the early life of the host, the invention constructs a model for predicting the early life age of the host based on the intestinal microbes by utilizing the important functions of the intestinal microbes in the early life of the host and the continuous development characteristics, and acquires the important intestinal microbial marker information in the early life of the host; meanwhile, the feature screening of the prediction model can determine intestinal microbial markers closely related to early age change of the host life and serve as one of the early health state evaluation indexes of the host life; the model is better in prediction effect and higher in precision.
Drawings
FIG. 1 is a flow chart of a predictive model construction method of the present invention;
FIG. 2 is a schematic diagram of prediction accuracy of the predicted age and the actual age by using a training set, wherein the random forest model is constructed based on all microbial characteristics in step three (1);
FIG. 3 is a schematic diagram of prediction accuracy of the predicted age and the actual age using the test set, in step three (1) based on a random forest model constructed by all microbial characteristics;
FIG. 4 is a ten fold cross-validation result graph;
FIG. 5 is a schematic diagram of prediction accuracy of the predicted age and the actual age of the random forest model constructed based on the screened microbial characteristics in step three (3) by using the training set;
fig. 6 is a schematic diagram of prediction accuracy of the predicted age and the actual age using the test set based on the random forest model constructed by the screened microbial characteristics in step three (3).
Detailed Description
A method for constructing a host early life age prediction model based on intestinal microorganisms is shown in figure 1:
step one, collecting raw data of intestinal microorganism sequencing and background information of a host, and in order to make the final model accuracy higher, collecting data as much as possible in the early stage is needed, wherein the data are collected in two ways:
mode one: searching related documents by keywords, wherein the keywords comprise infant gut microbiota and 16S rRNA, searching the documents published in the recent 10 years on an academic platform, filtering the BioProject project numbers in the filtered documents, wherein the BioProject information is not disclosed in an intestinal microbial data sequencing dataset, and the sequencing sample sources are samples with non-intestinal and host age information ambiguities; mode two: the project numbers with bioprject and host information were obtained by direct search in the SRA (Sequence Read Archive) database of NCBI (National Center for Biotechnology Information) using keywords infant gut microbiota and 16S rRNA.
If the numbers of the Bioproject items obtained in the two modes are the same item, only one item is reserved, ftp downloading connection of the corresponding sample microorganism sequencing data can be obtained after the SRA database of the NCBI is searched, the ascp software is used for downloading in batches, background information such as the age of the corresponding host sample is downloaded, and a preliminary data set of a subsequent building model is collected. The downloading of the original data utilizes ftp download connection and ascp download tools, in order to quickly download the original data in batches, other download tools, such as a webget tool or direct clicking of a link on a web interface, can be used.
If the data sets retrieved in the two modes are the same item, only one of the data sets is reserved, and finally the union set of the data sets obtained in the two modes is reserved. In this embodiment, the final 23 data sets collected contain 24104 samples of information.
Analyzing and integrating the original data collected in the previous step to obtain data for finally constructing an age prediction model:
the age information of the sample is unified and standard, and the invention predicts the age of the host in early life, so that the sample with the age above 1000 days is deleted; secondly, converting age information units of different samples into months, wherein the conversion standard is converted into 2×12=24 (month) according to 1 year=12 months, 1 month=30 days, for example, the age information of a certain sample a is 2 years; sample B age information 45 days, then conversion to 45/30=1.50 (month);
analyzing and processing original sequencing data of samples meeting the age requirement, firstly performing primary quality control on the original sequencing data by using Trimmomatic, including removing a joint sequence and a low-quality sequence, and removing samples with the number of sequences less than 20000 after quality control in order to avoid the influence of sequencing depth on the subsequent integration analysis of different projects; and (3) carrying out subsequent analysis on the quality-controlled high-quality sequence by utilizing a DADA2 flow, sequentially carrying out DADA2 noise reduction treatment, chimera sequence removal, ASV sequence and sample composition table generation and SILVA (version v 138) database species annotation analysis, and finally obtaining a relative abundance information table of intestinal microorganisms. The relative abundance of the microorganism refers to the content ratio of different intestinal microorganisms in the sample, and is a quantitative result. The relative abundance table contains two layers of specific information, namely, description of microorganism composition information, namely, microorganisms; and secondly, the quantitative result of the microorganisms in different samples.
The final number of samples retained in this example was 12085 and the number of annotated microorganism species was 1337, i.e. the final obtained relative abundance information table was a 12085 ×1337 dimensional data matrix.
And thirdly, selecting microbial characteristics, and obtaining an annotated intestinal microbial relative abundance table and corresponding host age information to construct an age prediction model and verify performance. Since not all microorganisms have a considerable contribution to the accuracy of model construction, the characteristics of the relative abundance of these microorganisms over time are not obvious, potentially leading to higher errors in model accuracy and increased computational resource consumption. Therefore, only the microorganism with the highest contribution degree is needed to be selected to construct the model with higher precision, and the utilized computing resource is also greatly reduced.
The microbial characteristic selection is based on the importance of microbial species and cross-validation of ten folds for co-screening, and the specific method is as follows:
(1) according to 12085 (sample) x 1337 (microorganism species) data set obtained in step two, the following is 7:3, constructing an age prediction model training set and a test set, and constructing an age prediction random forest model by using the training set to generate 500 decision trees by default, wherein the interpretation rate of the model reaches 86.04%, which indicates that the change of intestinal microbial communities in early life is closely related to age development. The model prediction performance is evaluated by using the training set and the test set respectively, as shown in fig. 2 and 3, it can be seen that there is an obvious linear relationship between the actual age and the predicted age, and the model fitting effect is evaluated by using a Normalized Mean Square Error (NMSE) for the analysis and prediction results of the training set and the test set, and the NMSE is calculated in the following manner:
NMSE＝mean((pred-obs)^2)/mean((mean(obs)-obs)^2)
where pred denotes the predicted value, obs denotes the actual value, mean denotes the averaging function.
The NMSE values calculated by the training set and the test set are 0.0223 and 0.1313 respectively, the NMSE value range is usually 0-1, the smaller the value is, the better the model is than the strategy of predicting by the mean value, and the higher the model fitting degree is.
(2) The importance of the predicted variables (microbial characteristics) is assessed and the microbial characteristics are screened. The importance of the microorganisms in the random forest model is evaluated by using the importance function in the random forest model, and the importance and the side-by-side of the microorganisms in the random forest model are shown in table 1, the key microorganism species which have important influence on the age prediction model and the corresponding incnodeanity values are shown, and about 20 important microorganism features can be selected through ten-fold cross validation results (fig. 4), so that the model error is low, and the first 20 important microorganism features are selected as data for finally constructing the age prediction random forest model in the embodiment.
TABLE 1 Key microbial markers with important influence on age prediction model
Note that: factor represents specific microbiological feature information; the incnodeanity, increase in node purity, measured by the sum of squares of residuals, represents the effect of each variable on the heterogeneity of the observed values at each node of the classification tree, thereby comparing the importance of the variables. The larger the value, the greater the importance of the variable.
(3) The random forest model, i.e. the 12085 (sample) x 20 (microorganism species) dataset, was reconstructed using the 20 microorganism features from the previous screening, again in a random sampling manner according to 7:3, constructing an age prediction model training set and a test set, constructing an age prediction random forest model by using the training set to generate 500 decision trees by default, wherein the interpretation rate of the prediction model reaches 83.43% (figure 5), and respectively evaluating the model predictability by using the training set and the test set, wherein an obvious linear relation exists between the actual age and the predicted age as shown in figures 5 and 6. The model fitting effect was also evaluated on the analytical predictions of the training and test sets using normalized mean variance (NMSE) values 0.0323 and 0.1612, respectively.
The results show that the age prediction random forest model constructed by using the screened 20 important microbial characteristics can effectively reveal the close relationship between the intestinal microbial community of the host and the development of the host in early life, and summarized the following advantages:
a. the interpretation rate of the prediction model is high and reaches 83.43%;
b. the predictive model has high fitting degree and lower error, and NMSE values of the training set and the test set are only 0.0323 and 0.1612 respectively;
c. under the condition that the effect of the prediction model is consistent, the calculation consumption resources for constructing the model by using a small amount of microbial characteristics are less, and meanwhile, the data preparation of the sample to be predicted is more facilitated.
And step four, age prediction is carried out on the host sample to be predicted. For example, there is a 20-month-old infant fecal sample A, and the relative abundance of the microorganism in this sample is obtained by 16S rRNA sequencing and analysis, and it is only necessary to obtain at least one of the microorganisms in Table 1. Specifically, the intestinal microorganisms of the host sample contained 14 microorganisms in total in table 1, and the relative abundance information of the microorganism composition is shown in table 2. The table is directly imported into the random forest age prediction model constructed in the step (3) of the step three of the embodiment, and the predicted age result of the host sample is 15.4 months after operation, which indicates that the intestinal microorganism development of the sample is actual development later than the host age, and suggests that the intestinal microorganism community of the host may need to be adjusted by intervention means.
TABLE 2 microbial characteristic composition information table of sample A to be predicted
Note that: factor represents specific microbiological feature information; abundance (%) represents the relative abundance value of the microorganism.
Claims (10)
1. The method for constructing the early-life age prediction model of the host based on the intestinal microorganisms is characterized by comprising the following steps of:
step one, collecting intestinal microorganism sequencing original data related to early life and background information of a host;
analyzing and integrating the original data to obtain an intestinal microorganism relative abundance information table for finally constructing an age prediction model;
thirdly, selecting intestinal microbial characteristics, constructing an age prediction model and verifying;
and step four, age prediction is carried out on the sample data to be predicted by using an age prediction model.
2. The method for constructing a model of early life and age prediction of a host based on intestinal microorganisms according to claim 1, wherein step one searches related documents by keywords including infant gut microbiota and 16S rRNA, screens the documents obtained by preliminary collection, filters samples without bioprject information, whose intestinal microorganism data sequencing dataset is not disclosed, whose sequencing sample sources are non-intestinal and host age information is not clear, and searches the database for the sequencing data of the intestinal microorganism of the corresponding sample based on the bioprject information in the documents, and downloads the sequencing data of the intestinal microorganism of the corresponding sample in batches.
3. The method for constructing a model of early life and age prediction of a host based on intestinal microorganisms according to claim 1, wherein step one uses keywords including infant gut microbiota and 16S rRNA to search a database, searches the database for bioprject information, host information and sequencing data of directly obtained items, filters samples of parenteral and non-host age information as sequencing sample sources, and downloads raw sequencing data in batch.
4. A method of constructing an early life age prediction model of a host based on enteric microorganisms according to claim 2 or 3, wherein the database comprises an SRA database or an ENA database of NCBI.
5. The method for constructing an early life age prediction model of a host based on intestinal microorganisms according to claim 1, wherein the step two is to analyze and integrate raw data: firstly deleting samples with ages of more than 1000 days, and then converting age information units of different samples into months; secondly, analyzing and processing the original sequencing data, and firstly, performing primary quality control on the original sequencing data by using Trimmomatic, wherein the primary quality control comprises the removal of a joint sequence and a low-quality sequence; and (3) carrying out subsequent analysis on the high-quality sequence after quality control, and finally obtaining a relative abundance information table of intestinal microorganisms.
6. The method of claim 5, wherein the follow-up analysis comprises DADA2 analysis procedure, QIIME2 analysis procedure, or USEARCH OTU analysis procedure, and wherein the DADA2 analysis procedure comprises DADA2 noise reduction treatment, chimera sequence removal, ASV sequence, and sample composition table generation and database species annotation analysis.
7. The method of claim 6, wherein the database of species annotation analysis comprises a SILVA database, a Greengenes database or an RDP database.
8. The method for constructing an early life age prediction model of a host based on intestinal microorganisms according to claim 1, wherein the third step constructs an age prediction model using the intestinal microorganism relative abundance table and the corresponding host age information:
(1) according to the random sampling principle, constructing a training set and a testing set of an age prediction model according to a proportion, constructing a random forest model by using the training set, generating 500 decision trees by default, and evaluating the constructed model by using the testing set;
(2) for the established random forest model, evaluating the importance and side-arrangement of microorganisms in the model by utilizing the function of the importance function in the random forest model: determining the importance of the microorganism according to the IncNodePurty value, wherein the larger the value is, the larger the importance of the variable is; screening and obtaining a microbial characteristic data set by using a ten-fold cross validation method;
(3) constructing an age prediction random forest model according to the microbial characteristic data set obtained by screening, constructing a training set and a test set according to the data set, constructing the age prediction random forest model by using the training set, generating 500 decision trees by default, and evaluating the constructed model by using the test set.
9. The method for constructing an early life age prediction model of a host based on intestinal microorganisms according to claim 1, wherein the fourth step is to obtain a relative abundance table of microorganisms of a host sample to be predicted for the age, and introduce an age prediction random forest model for prediction, thereby obtaining an age prediction result of the host sample to be predicted.
10. The method for constructing an early life age prediction model of a host based on intestinal microorganisms according to claim 9, wherein the means for acquiring the information of the relative abundance of the microorganisms in the sample in the fourth step comprises 16S rRNA, metagenomic sequencing and qPCR experimental analysis of the microorganisms.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310130546.8A CN116153414A (en) | 2023-02-17 | 2023-02-17 | Method for constructing early-life age prediction model of host based on intestinal microorganisms |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310130546.8A CN116153414A (en) | 2023-02-17 | 2023-02-17 | Method for constructing early-life age prediction model of host based on intestinal microorganisms |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116153414A true CN116153414A (en) | 2023-05-23 |
Family
ID=86350378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310130546.8A Pending CN116153414A (en) | 2023-02-17 | 2023-02-17 | Method for constructing early-life age prediction model of host based on intestinal microorganisms |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116153414A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110308255A (en) * | 2019-05-08 | 2019-10-08 | 宁波大学 | One kind is based on Pollution indicating bacteria group to coastal waters degree of water pollution quantitative forecasting technique |
| CN114093515A (en) * | 2021-11-17 | 2022-02-25 | 江南大学 | Age prediction method based on intestinal flora prediction model ensemble learning |
| CN114891904A (en) * | 2022-04-29 | 2022-08-12 | 上海金域医学检验所有限公司 | Maternal intestinal flora marker for children ASD diagnosis and application thereof |
| CN115527608A (en) * | 2022-11-08 | 2022-12-27 | 广西爱生生命科技有限公司 | Intestinal age prediction method and system |
| CN115662505A (en) * | 2022-09-13 | 2023-01-31 | 山西医科大学 | Intestinal type scoring model for undifferentiated spondyloarthropathy as well as construction method and application of intestinal type scoring model |
-
2023
- 2023-02-17 CN CN202310130546.8A patent/CN116153414A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110308255A (en) * | 2019-05-08 | 2019-10-08 | 宁波大学 | One kind is based on Pollution indicating bacteria group to coastal waters degree of water pollution quantitative forecasting technique |
| CN114093515A (en) * | 2021-11-17 | 2022-02-25 | 江南大学 | Age prediction method based on intestinal flora prediction model ensemble learning |
| CN114891904A (en) * | 2022-04-29 | 2022-08-12 | 上海金域医学检验所有限公司 | Maternal intestinal flora marker for children ASD diagnosis and application thereof |
| CN115662505A (en) * | 2022-09-13 | 2023-01-31 | 山西医科大学 | Intestinal type scoring model for undifferentiated spondyloarthropathy as well as construction method and application of intestinal type scoring model |
| CN115527608A (en) * | 2022-11-08 | 2022-12-27 | 广西爱生生命科技有限公司 | Intestinal age prediction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Blanco-Míguez et al. | Extending and improving metagenomic taxonomic profiling with uncharacterized species using MetaPhlAn 4 | |
| Wu et al. | Guild-based analysis for understanding gut microbiome in human health and diseases | |
| Arrieta et al. | Early infancy microbial and metabolic alterations affect risk of childhood asthma | |
| CN105368944B (en) | Biomarker of detectable disease and application thereof | |
| CN104540962B (en) | Diabetes biomarker and its application | |
| CN108804875A (en) | A method of analyzing micropopulation body function using macro genomic data | |
| CN104603283B (en) | Determine the method and system of abnormality associated biomarkers | |
| McKenney et al. | Feeding strategy shapes gut metagenomic enrichment and functional specialization in captive lemurs | |
| CN110176305A (en) | A method of utilizing high-throughput gene sequencing assessment intestinal flora health | |
| CN108345768B (en) | Method for determining maturity of intestinal flora of infants and marker combination | |
| Malukiewicz et al. | The gut microbiome of exudivorous marmosets in the wild and captivity | |
| CN112852916A (en) | Marker combination for intestinal microecology, auxiliary diagnosis model and application of marker combination | |
| Jacobson et al. | Analysis of global human gut metagenomes shows that metabolic resilience potential for short-chain fatty acid production is strongly influenced by lifestyle | |
| de Gonzalo-Calvo et al. | Plasma microRNA profiling reveals novel biomarkers of epicardial adipose tissue: a multidetector computed tomography study | |
| Levi Mortera et al. | Functional and taxonomic traits of the gut microbiota in type 1 diabetes children at the onset: A metaproteomic study | |
| CN116153414A (en) | Method for constructing early-life age prediction model of host based on intestinal microorganisms | |
| Fernández-Baca et al. | Rice plant–soil microbiome interactions driven by root and shoot biomass | |
| Brown et al. | Fecal 1H-NMR metabolomics: A comparison of sample preparation methods for NMR and novel in silico baseline correction | |
| Wilmanski et al. | Gut Microbiome Pattern Reflects Healthy Aging and Predicts Extended Survival in Humans | |
| Wei et al. | A machine vision system for automated non-invasive assessment of cell viability via dark field microscopy, wavelet feature selection and classification | |
| RU2721234C1 (en) | Method and system for tracking a ration and forming an opinion on the quality of nutrition and / or individual nutrition recommendations | |
| CN110211629A (en) | A kind of concept and method of the assessment macro gene of microbiologic population (or the macro heredity of common biocoene) diversity and similitude | |
| CN111128378B (en) | Prediction method for evaluating infant intestinal flora development age | |
| Dong et al. | A new alignment-free whole metagenome comparison tool and its application on gut microbiomes of wild giant pandas | |
| Zhang et al. | Sex-and Age-Dependent Associations between Parabacteroides and Obesity: Evidence from Two Population Cohort |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |