Classifications

• • G—PHYSICS
  • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
  • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
  • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
  • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
• • C—CHEMISTRY; METALLURGY
  • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
  • C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
  • C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
  • C12Q1/68—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving nucleic acids
  • C12Q1/6876—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes
  • C12Q1/6883—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for diseases caused by alterations of genetic material
• • C—CHEMISTRY; METALLURGY
  • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
  • C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
  • C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
  • C12Q1/68—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving nucleic acids
  • C12Q1/6876—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes
  • C12Q1/6888—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for detection or identification of organisms
  • C12Q1/689—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for detection or identification of organisms for bacteria
• • 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
  • G16B25/00—ICT specially adapted for hybridisation; ICT specially adapted for gene or protein expression
• • G—PHYSICS
  • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
  • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
  • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
  • G16H10/40—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for data related to laboratory analysis, e.g. patient specimen analysis
• • G—PHYSICS
  • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
  • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
  • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
  • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
• • G—PHYSICS
  • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
  • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
  • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
  • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
• • G—PHYSICS
  • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
  • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
  • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
  • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
• • C—CHEMISTRY; METALLURGY
  • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
  • C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
  • C12Q2600/00—Oligonucleotides characterized by their use
  • C12Q2600/112—Disease subtyping, staging or classification
• • C—CHEMISTRY; METALLURGY
  • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
  • C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
  • C12Q2600/00—Oligonucleotides characterized by their use
  • C12Q2600/158—Expression markers
• • 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
  • G16B40/20—Supervised data analysis

Definitions

• the present invention relates to a method and device for determining the risk of neurodegenerative diseases.
• Neurodegenerative diseases are a group of diseases of the central nervous system that are caused by damage or loss of a specific group of nerve cells, and clinically, they are diseases of unknown cause that develop latently and cause psychiatric and neurological symptoms to progress slowly. Point.
• proteins have been classified based on the concept of proteinopathy, in which the same pathogenic protein causes a common pathological condition, based on the main abnormal proteins that accumulate in nerve cells or glial cells and their accumulation patterns.
• Tauopathy such as Alzheimer's disease (AD), TDP43 proteinopathy such as amyotrophic lateral sclerosis (ALS), Parkinson's disease (PD), dementia with Lewy bodies (DLB), multiple system atrophy (MSA) ) is classified as a synucleinopathy.
• Non-Patent Document 1 Non-Patent Document 1
• Non-Patent Document 2 uses a logistic regression analysis method based on microbiome genus and species data from salivary RNA sequencing to distinguish between early Parkinson's disease (PD) patients and healthy individuals from data on 11 bacterial groups.
• an object of the present invention is to provide a risk determination method that can stratify and evaluate the risk of neurodegenerative diseases into a plurality of diseases using easily collected saliva samples.
• the present inventor used the expression levels of multiple types of bacteria obtained from analysis of the salivary microbiota of healthy subjects and patients with multiple diseases belonging to neurodegenerative diseases as explanatory variables. Using a predictive model generated by machine learning using an algorithm obtained as the objective variable to obtain the disease status of patients stratified by disease as training data, multiple types obtained from analysis of the salivary flora of the subjects were used. The inventors have discovered that by applying the expression level of bacteria in the above prediction model, it is possible to stratify and evaluate the risk of neurodegenerative diseases of the subject into a plurality of diseases, and have completed the present invention.
• the present invention provides the following inventions [1] to [8].
• [1] A method executed by a processor of a computer, the method comprising: obtaining the expression levels of multiple types of bacteria from analysis of the salivary flora of the subject; Inputting the obtained expression levels of the plurality of types of bacteria into a prediction model to stratify and evaluate the risk of neurodegenerative diseases of the subject into a plurality of diseases,
• the above prediction model uses the expression levels of multiple types of bacteria obtained from analysis of the salivary flora of healthy subjects and patients with multiple diseases belonging to neurodegenerative diseases as explanatory variables, and uses the expression levels of multiple types of bacteria as explanatory variables, and It is generated by machine learning using an algorithm as training data to obtain the disease status of patients stratified by the objective variables.
• the plurality of types of bacteria are bacterial species with high expression levels in the analysis of the salivary flora of the stratified patients, and/or patients with different diseases in the analysis of the stratified patients' salivary flora.
• a risk determination method for stratifying and evaluating the risk of neurodegenerative diseases into multiple diseases characterized by including bacterial species with significant differences in expression levels among them.
• the above-mentioned stratification of multiple diseases includes stratification of healthy elderly people, mild cognitive impairment (MCI) and dementia (DE), and stratification of healthy elderly people, mild cognitive impairment (MCI) and dementia (DE). and stratification of dementia with Lewy bodies (DLB), or stratification of Parkinson's disease (PD) and dementia with Lewy bodies (DLB), the risk determination method according to [1].
• the plurality of types of bacteria are [Eubacterium] brachy, Porphyromonas endodontalis, Alloprevotella tannerae, Capnocytophaga leadbetteri, Streptococcus gordonii, Campylobacter concisus, Tannerella forsythia, Filifactor alocis, [Eubacterium] nodatum, Streptococcus cristatus, Neisseria elongata, Treponema denticola, Actinomyces oris, [Eubacterium] saphenum, Streptococcus constellatus, Parvimonas micra, Prevotella denticola, Leptotrichia hofstadii, Fusobacterium nucleatum, Catonella morbi, Lac
• a processor a storage device that stores a computer program executed by the processor; Equipped with a communication circuit that accepts the expression levels of multiple types of bacteria from analysis of salivary flora obtained from subjects, The processor executes the computer program to obtain the expression levels of the plurality of types of bacteria received by the communication circuit, inputting the obtained expression levels of the plurality of types of bacteria into a prediction model, stratifying and evaluating the risk of neurodegenerative diseases of the subject into a plurality of diseases;
• the above prediction model uses the expression levels of multiple types of bacteria obtained from analysis of the salivary flora of healthy subjects and patients with multiple diseases belonging to neurodegenerative diseases as explanatory variables, and uses the expression levels of multiple types of bacteria as explanatory variables, and It is generated by machine learning using an algorithm as training data to obtain the disease status of patients stratified by the objective variables.
• the plurality of types of bacteria are bacterial species with high expression levels in the analysis of the salivary flora of the stratified patients, and/or patients with different diseases in the analysis of the stratified patients' salivary flora.
• a risk determination device that stratifies and evaluates the risk of neurodegenerative diseases into multiple diseases, characterized by including bacterial species with significant differences in expression levels between the two.
• the above-mentioned stratification of multiple diseases includes stratification between healthy elderly, mild cognitive impairment (MCI) and dementia (DE), and stratification between healthy elderly and mild cognitive impairment (MCI) and dementia (DE). and stratification of dementia with Lewy bodies (DLB), or stratification of Parkinson's disease (PD) and dementia with Lewy bodies (DLB), the risk assessment device according to [5].
• the risk determination device wherein the plurality of diseases include dementia with Lewy bodies (DLB) and Parkinson's disease (PD).
• the plurality of types of bacteria are [Eubacterium] brachy, Porphyromonas endodontalis, Alloprevotella tannerae, Capnocytophaga leadbetteri, Streptococcus gordonii, Campylobacter concisus, Tannerella forsythia, Filifactor alocis, [Eubacterium] nodatum, Streptococcus cristatus, Neisseria elongata, Treponema denticola, Actinomyces oris, [Eubacterium] saphenum, Streptococcus constellatus, Parvimonas micra, Prevotella denticola, Leptotrichia hofstadii, Fusobacterium nucleatum, Catonella morbi, Lac
• multiple diseases such as healthy subjects, MCI, dementia, AD and DLB, and DLB and PD can be classified using a small amount of easily collected saliva sample. stratification to accurately determine neurodegenerative disease risk. Therefore, it is useful as a means for determining the risk of neurodegenerative diseases in regular medical examinations, and contributes to stratified early diagnosis of neurodegenerative diseases.
• FIG. 1 is a diagram showing the configuration of a determination method of the present invention.
• FIG. 2 is a diagram illustrating an example of the configuration of a risk assessment device.
• 2 is a flowchart illustrating the operation of the determination process in the determination method and risk determination device of the present invention.
• 2 is a flowchart illustrating the operation of training processing in the determination method and risk determination device of the present invention.
• FIG. 3 is a diagram showing the AUC-RF obtained by constructing a prediction model by performing machine learning based on the expression levels of 94 types of bacteria (Table 1) with high expression levels at the species level.
• FIG. 3 is a diagram showing the AUC-RF obtained by constructing a prediction model by performing machine learning based on the expression levels of 95 types of bacteria (Table 2) with high expression levels at the species level.
• FIG. 4 is a diagram showing the AUC-RF obtained by constructing a prediction model by performing machine learning based on the expression levels of 74 types of bacteria (Table 4) with high expression levels at the species level.
• the present invention provides a risk determination method and a determination device for stratifying and evaluating the risk of neurodegenerative diseases into a plurality of diseases.
• neurodegenerative diseases refers to a group of diseases in which each region of the nervous system is affected and exhibits various degenerative changes mainly in nerve cells.
• tauopathies such as Alzheimer's disease (AD); TDP43 proteinopathies such as amyotrophic lateral sclerosis (ALS); Parkinson's disease (PD), dementia with Lewy bodies (DLB), multiple system atrophy ( Examples include synucleinopathy such as MSA).
• the neurodegenerative diseases of the present invention include mild cognitive impairment (MCI).
• tauopathies that indicate cognitive decline, including AD.
• AD Alzheimer's disease
• tauopathies include primary age-related tauopathies, chronic traumatic encephalopathy, progressive supranuclear palsy, corticobasal degeneration, FTDP-17, and Lytiko-Podig disease.
• stratification means grouping. Therefore, in the present invention, any plurality of these neurodegenerative diseases can be stratified and evaluated. Examples include stratification between healthy elderly, MCI, and dementia (DE), stratification between healthy elderly, MCI, dementia (DE), and DLB, and stratification between PD and DLB.
• stratification into healthy subjects, MCI, dementia, and DLB, and stratification into PD and DLB are more preferable.
• both PD and DLB are synucleinopathies, being able to stratify these diseases would be extremely useful.
• dementia (DE) can be stratified into tauopathy and synucleinopathy.
• saliva usually refers to the secreted fluid secreted into the oral cavity from the salivary glands.
• the saliva to be measured in the present invention is saliva collected from healthy individuals and patients with neurodegenerative diseases.
• salivary microbiota refers to a collection of living bacteria in saliva, and their genetic information is sometimes called the microbiome.
• the salivary microbiota is preferably determined by measuring the genetic information of bacteria, specifically 16S rRNA, and therefore is preferably the microbiome.
• One aspect of the risk assessment method of the present invention is A method performed by a processor of a computer, the method comprising: obtaining the expression levels of multiple types of bacteria from analysis of the salivary flora of the subject; Inputting the obtained expression levels of the plurality of types of bacteria into a prediction model to stratify and evaluate the risk of neurodegenerative diseases of the subject into a plurality of diseases,
• the above prediction model uses the expression levels of multiple types of bacteria obtained from analysis of the salivary flora of healthy subjects and patients with multiple diseases belonging to neurodegenerative diseases as explanatory variables, and uses the expression levels of multiple types of bacteria as explanatory variables, and It is generated by machine learning using an algorithm as training data to obtain the disease status of patients stratified by the objective variables.
• the plurality of types of bacteria are bacterial species with high expression levels in the analysis of the salivary flora of the stratified patients, and/or patients with different diseases in the analysis of the stratified patients' salivary flora. This is a risk determination method that stratifies and evaluates the risk of neurodegenerative diseases into multiple diseases, which is characterized by including bacterial species that have significant differences in expression levels among them.
• the method of the present invention includes a step 1 in which the bacterial expression level acquisition device 10 acquires the expression levels of multiple types of bacteria from analysis of the salivary flora of the subject, and a determination device in the processor of the computer.
• step 2 of inputting the obtained expression levels of the plurality of types of bacteria into a prediction model according to No. 20, and stratifying and evaluating the risk of neurodegenerative diseases of the subject into a plurality of diseases.
• step 1 can be carried out, for example, as follows.
• the V1-V2 region of 16S rRNA is amplified by PCR, and the fragments amplified by PCR are sequenced using a next-generation sequencer.
• the determined sequences (reads) that pass a quality check are clustered at a similarity of 97% to form operational taxonomic units (OTUs).
• the OTU sequences are identified by referring to the 16S rRNA sequences registered in the genome database.
• the expression level of each species can be identified from the number of reads for each OTU.
• the process of obtaining the expression levels of multiple types of bacteria from the analysis of the salivary bacterial flora in order to construct a prediction model is also carried out in a similar manner.
• Step 2 is to stratify the risk of neurodegenerative diseases of the subject into a plurality of diseases by inputting the obtained expression levels of the plurality of types of bacteria into a prediction model by the determination device 20 in the processor of the computer. This is done by evaluating. Since the prediction model is input in advance to the processor of the computer that performs step 2, as shown in FIG. It is possible to stratify and evaluate the risks of multiple diseases, and output prediction results.
• the prediction model uses the expression levels of multiple types of bacteria obtained from analysis of the salivary flora of healthy subjects and patients with multiple neurodegenerative diseases as explanatory variables. It is generated by machine learning using an algorithm obtained as the objective variable to obtain stratified patient disease states as training data. For example, as shown in Figure 4, the expression levels of multiple types of bacteria obtained from analysis of the salivary flora of healthy subjects and patients with multiple diseases belonging to neurodegenerative diseases, which are explanatory variables, are obtained and used. Then, a predictive model is generated by machine learning using an algorithm as training data, which uses an algorithm obtained as a target variable to obtain the disease status of patients stratified into healthy subjects and multiple diseases belonging to neurodegenerative diseases. Can be done.
• the above-mentioned bacterial species and their expression levels are analyzed for a cohort consisting of healthy elderly (HC), patients with mild cognitive impairment (MCI), and patients with dementia (DE). From the analysis of bacterial species and their expression levels, we identify bacterial species with high expression levels and characteristic bacterial species (bacterial species that serve as markers with significant differences). Then, using the expression levels of multiple types of bacteria obtained from analysis of the salivary flora of healthy subjects and patients with multiple diseases belonging to neurodegenerative diseases as explanatory variables, we stratified them into healthy subjects and patients with multiple diseases belonging to neurodegenerative diseases.
• a predictive model can be constructed by machine learning using an algorithm obtained as training data to obtain the patient's disease state as a target variable.
• the machine learning for example, random forest can be adopted.
• the plurality of types of bacteria are bacterial species that have a high expression level in the analysis of the salivary flora of the stratified patients, and/or the analysis of the stratified salivary flora of the patients.
• stratifying bacteria to include bacterial species that have significant differences in expression levels between patients with different diseases, it is possible to stratify and evaluate the risk of neurodegenerative diseases into multiple diseases.
• stratification into healthy subjects, MCI, dementia, DLB, PD and DLB, etc. can be performed.
• stratification into healthy subjects, MCI, dementia, and DLB, and stratification into PD and DLB are more preferable.
• both PD and DLB are synucleinopathies, being able to stratify these diseases would be extremely useful.
• PD can be classified according to severity.
• PD is classified into mild (Horn & Yahr severity level 1 or 2) and severe disease (Horn & Yahr severity 3 or higher) based on Horn & Yahr severity.
• mild PD mild PD
• severe PD severe PD
• early stage 5 years or less from onset
• late stage 6 years or more
• examples of bacteria that can be used to stratify the risk of neurodegenerative diseases into multiple diseases include one or more of the bacteria shown in Table 1 below.
• the bacterial species in Table 1 are those used for stratification between healthy subjects, MCI, DE, and DLB.
• the bacterial species used for healthy subjects, DLB, and PD were one or more selected from the bacterial species shown in Table 2.
• the bacterial species used for healthy subjects, DLB, and PD were one or more selected from the bacterial species shown in Table 3.
• the bacterial species used for healthy subjects, DLB, and PD were one or more selected from Table 4.
• One aspect of the determination device of the present invention is a processor; a storage device that stores a computer program executed by the processor; Equipped with a communication circuit that accepts the expression levels of multiple types of bacteria from analysis of salivary flora obtained from subjects, The processor executes the computer program to obtain the expression levels of the plurality of types of bacteria received by the communication circuit, inputting the obtained expression levels of the plurality of types of bacteria into a prediction model, stratifying and evaluating the risk of neurodegenerative diseases of the subject into a plurality of diseases;
• the above prediction model uses the expression levels of multiple types of bacteria obtained from analysis of the salivary flora of healthy subjects and patients with multiple diseases belonging to neurodegenerative diseases as explanatory variables, and uses the expression levels of multiple types of bacteria as explanatory variables, and It is generated by machine learning using an algorithm as training data to obtain the disease status of patients stratified by the objective variables.
• the plurality of types of bacteria are bacterial species with high expression levels in the analysis of the salivary flora of the stratified patients, and/or patients with different diseases in the analysis of the stratified patients' salivary flora.
• This is a risk determination device that stratifies and evaluates the risk of neurodegenerative diseases into multiple diseases, which is characterized by including bacterial species that have significant differences in expression levels among them.
• FIG. 2 shows an outline of the determination device of the present invention.
• the determination device 20 is configured with an information processing device such as a computer, for example.
• the determination device 20 includes a CPU 21 that performs calculation processing, a storage device 22 that stores various data and computer programs, and an input/output interface (I/F) 26 that communicates with other devices.
• I/F input/output interface
• the prediction model 21 is generated by machine learning using as training data an algorithm obtained as an explanatory variable the expression levels of multiple types of bacteria obtained from the analysis of the salivary bacterial flora of healthy individuals and patients with multiple neurodegenerative diseases, and as a target variable obtaining the disease state of patients stratified into healthy individuals and multiple neurodegenerative diseases.
• the explanatory variables are the expression levels of multiple types of bacteria obtained from the analysis of the salivary microbiota of healthy individuals and patients with multiple neurodegenerative diseases
• a prediction model can be generated by performing machine learning on the training data of an algorithm that uses the explanatory variables to obtain the disease state of patients stratified into healthy individuals and multiple neurodegenerative diseases.
• the above-mentioned bacterial species and their expression levels are analyzed for a cohort consisting of healthy elderly people (HC), patients with mild cognitive impairment (MCI), and patients with dementia (DE). From the analysis of the bacterial species and their expression levels, bacterial species with high expression levels and characteristic bacterial species (bacterial species that serve as markers with significant differences) are identified. Then, a prediction model can be constructed by machine learning using an algorithm obtained as training data, with the expression levels of multiple types of bacteria obtained from the analysis of the salivary microbiota of healthy people and patients with multiple diseases belonging to neurodegenerative diseases as explanatory variables, and the objective variable being to obtain the disease state of patients stratified into healthy people and multiple diseases belonging to neurodegenerative diseases.
• random forests can be adopted as the machine learning.
• the plurality of types of bacteria are bacterial species that have a high expression level in the analysis of the salivary flora of the stratified patients, and/or the analysis of the stratified salivary flora of the patients.
• stratifying bacteria to include bacterial species that have significant differences in expression levels between patients with different diseases, it is possible to stratify and evaluate the risk of neurodegenerative diseases into multiple diseases.
• stratification into healthy subjects, MCI, dementia, DLB, PD and DLB, etc. can be performed.
• stratification into healthy subjects, MCI, dementia, and DLB, and stratification into PD and DLB are more preferable.
• both PD and DLB are synucleinopathies, being able to stratify these diseases would be extremely useful.
• the processor executes the computer program to obtain the expression levels of the plurality of types of bacteria received by the communication circuit.
• Step 1 This is performed by inputting the obtained expression levels of the plurality of types of bacteria into the prediction model 21 and stratifying and evaluating the risk of neurodegenerative diseases of the subject into a plurality of diseases (step 2).
• step 1 can be performed, for example, as follows.
• the V1-V2 region of 16S rRNA is amplified by PCR, and the base sequence of the PCR-amplified fragment is determined using a next-generation sequencer.
• the base sequence of the PCR-amplified fragment is determined using a next-generation sequencer.
• reads that have passed the quality check are clustered with a degree of similarity of 97% to form operational classification units (OTUs).
• the bacterial species of each OTU is identified by referring to the base sequence of the OTU and the base sequence of 16S rRNA registered in a genome database.
• the expression level of each bacterial species can be identified from the number of reads for each OTU. Note that the step of obtaining the expression levels of a plurality of types of bacteria from the analysis of salivary bacterial flora for constructing a predictive model is also performed in the same manner.
• Step 2 is performed by inputting the acquired expression levels of the multiple types of bacteria into a prediction model by a determination device 20 in a computer processor, and stratifying and evaluating the subject's risk of neurodegenerative disease into multiple diseases.
• a prediction model has been input in advance into the processor of the computer performing step 2. Therefore, by inputting the expression levels of the multiple types of bacteria obtained in step 1, as shown in Figure 3, the subject's risk of neurodegenerative disease can be stratified into multiple diseases and evaluated, and the prediction results are output.
• Example 1 (Stratification of HC, MCI, DE, and DLB) In multiple cohorts, saliva (0.5-1 .0 mL) was collected. Since it has been suggested that the microbiome may differ depending on the living environment and diet, healthy subjects were chosen to have a spouse or cohabitant with similar lifestyle habits whenever possible. Additionally, patients receiving antibiotics were excluded to minimize drug effects.
• Bacterial deoxyribonucleic acid (DNA) is extracted from the collected saliva using lysozyme and achromopeptidase. The extracted DNA is purified using a phenol-chloroform solution or the like. Using this DNA solution as a template, amplification was performed by PCR using primers designed for the V1-V2 region of the 16S rRNA gene. The nucleotide sequence was obtained from the obtained amplification product using a next generation sequencer such as MiSeq.
• a next generation sequencer such as MiSeq.
• a quality check was performed on the obtained sequence data, primer sequences were removed, and OTU analysis was performed by clustering with a degree of similarity of 97%.
• the OTU base sequence was referenced to the 16S rRNA base sequence registered in the genome database to identify the bacterial species and analyze the bacterial species composition.
• MCI and Machine learning is used to identify these diseases with high accuracy using multiple types of highly expressed bacterial species and characteristic bacterial species (bacterial species that serve as markers with significant differences) between two groups: DE, MCI and DLB, and DE and DLB. We determined combinations of multiple bacteria that could be stratified.
• the constructed prediction model was verified using a different cohort of patients from the patient cohort used for model construction. Alternatively, the prediction accuracy was verified by cross-validation of the constructed prediction model in the cohort used for model construction.
• a prediction model was constructed by performing machine learning based on the expression levels of 94 types of bacteria (Table 1) with high expression levels at the species level.
• the obtained AUC-RF is shown in FIG.
• HC and MCI, HC and DE tauopathy
• MCI and DE semucleinopathy
• MCI and DE tauopathy
• MCI and DLB semucleinopathy
• DE tauopathy
• Example 2 (Stratification of HC, DLB, and PD) In the same manner as in Example 1, stratification of HC, DLB, and PD was attempted. A prediction model was constructed by performing machine learning based on the expression levels of 95 types of bacteria (Table 2) with high expression levels at the species level. The obtained AUC-RF is shown in FIG. 2. As is clear from Figure 6, it was found that the risks of neurodegenerative diseases of HC, DLB, and PD can be stratified and predicted with high accuracy.
• Example 3 (Stratification of HC, DLB, mild PD, and severe PD) In the same manner as in Example 1, an attempt was made to stratify HC, DLB, mild PD, and severe PD. A prediction model was constructed by performing machine learning based on the expression levels of 34 types of bacteria (Table 3) with high expression levels at the species level. The obtained AUC-RF is shown in FIG. As is clear from Figure 7, it was found that the risks of neurodegenerative diseases of HC, DLB, mild PD, and severe PD can be stratified and predicted with high accuracy.
• Example 4 (Stratification of HC, DLB, early PD, and late PD) In the same manner as in Example 1, an attempt was made to stratify HC, DLB, early PD, and late PD. A prediction model was constructed by performing machine learning based on the expression levels of 74 types of bacteria (Table 4) with high expression levels at the species level. The obtained AUC-RF is shown in FIG. As is clear from Figure 8, it was found that the risk of neurodegenerative diseases of HC, DLB, early PD, and late PD can be stratified and predicted with high accuracy.
• multiple diseases such as healthy subjects, MCI, dementia, AD and DLB, and DLB and PD can be classified using a small amount of easily collected saliva sample. stratification to accurately determine neurodegenerative disease risk. Therefore, it is useful as a means for determining the risk of neurodegenerative diseases in regular medical examinations, and contributes to stratified early diagnosis of neurodegenerative diseases.

Landscapes

• Health & Medical Sciences (AREA)
• Engineering & Computer Science (AREA)
• Chemical & Material Sciences (AREA)
• Life Sciences & Earth Sciences (AREA)
• Medical Informatics (AREA)
• Public Health (AREA)
• General Health & Medical Sciences (AREA)
• Proteomics, Peptides & Aminoacids (AREA)
• Organic Chemistry (AREA)
• Analytical Chemistry (AREA)
• Data Mining & Analysis (AREA)
• Pathology (AREA)
• Primary Health Care (AREA)
• Epidemiology (AREA)
• Biomedical Technology (AREA)
• Databases & Information Systems (AREA)
• Zoology (AREA)
• Wood Science & Technology (AREA)
• Genetics & Genomics (AREA)
• Physics & Mathematics (AREA)
• Biophysics (AREA)
• Molecular Biology (AREA)
• Biotechnology (AREA)
• Bioinformatics & Cheminformatics (AREA)
• Biochemistry (AREA)
• Immunology (AREA)
• General Engineering & Computer Science (AREA)
• Microbiology (AREA)
• Bioinformatics & Computational Biology (AREA)
• Evolutionary Biology (AREA)
• Spectroscopy & Molecular Physics (AREA)
• Theoretical Computer Science (AREA)
• Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
• Investigating Or Analysing Biological Materials (AREA)

Priority Applications (4)

Applications Claiming Priority (2)

Publications (1)

Family

ID=90454260

Family Applications (1)

Country Status (5)

Cited By (2)

Citations (3)

• 2023
  • 2023-09-07 KR KR1020257011515A patent/KR20250073634A/ko active Pending
  • 2023-09-07 WO PCT/JP2023/032629 patent/WO2024062931A1/ja not_active Ceased
  • 2023-09-07 JP JP2023556884A patent/JP7610810B2/ja active Active
  • 2023-09-07 US US19/111,824 patent/US20260018300A1/en active Pending
  • 2023-09-07 EP EP23868054.0A patent/EP4593037A1/en active Pending

Patent Citations (3)

Non-Patent Citations (2)

Also Published As

Similar Documents

Legal Events