Gut microbiota-based autism prediction system for adolescents and model construction method

Abstract

This invention discloses a gut microbiota-based system for predicting autism in adolescents and a method for building a model, belonging to the field of biomedicine and artificial intelligence. It includes a detection module for acquiring quantitative detection results of preset microbial markers in fecal samples from a donor, said microbial markers including active rumenococci and / or thermophilic streptococci; and a comparison module for comparing the quantitative detection results with preset thresholds to determine whether the adolescent has autism. This invention has good feasibility and accuracy, can effectively assess the risk of autism in adolescents, and provides a new tool for clinical diagnosis.

Description

Technical Field

[0001] This invention belongs to the field of biomedicine, specifically relating to a prediction system and model construction method for adolescent autism based on gut microbiota. Background Technology

[0002] Autism Spectrum Disorder (ASD) has become a globally recognized neurodevelopmental disorder. According to the World Health Organization (WHO), approximately 1 in 100 children worldwide has autism, and adolescence is a critical period for symptom onset and intervention. However, current diagnosis of adolescent autism relies primarily on subjective methods such as behavioral observation, scale assessments, and parent interviews, lacking objective, quantifiable biomarkers. Furthermore, the high heterogeneity of adolescent autism symptoms, with some mild or high-functioning patients exhibiting atypical symptoms (often mistaken for introversion or social anxiety), leads to significant misdiagnosis and missed diagnosis, delaying the optimal time for early intervention.

[0003] In response to the above issues, the applicant of this application, in conjunction with the Second Affiliated Hospital of Kunming Medical University, filed an invention patent application on October 31, 2023, entitled "Application of Gut Microbiota Markers in the Diagnosis and Treatment of Autism". The gut microbiota markers include any one or more of the prokaryotic streptococci, streptococci salivarius, albendibrio, and spirochetes.

[0004] While the aforementioned gut microbiota markers can be applied to adolescent autism prediction systems and effectively assess the risk of autism in adolescents, their sample size is small and the collection locations are relatively concentrated. Consequently, the diagnostic accuracy of these gut microbiota markers in diagnosing autism in adolescents needs further improvement. Therefore, it is necessary to develop a prediction system specifically for adolescent autism that can more accurately diagnose autism in adolescents by detecting fecal samples. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a system and model construction method for predicting autism in adolescents based on gut microbiota, which can accurately diagnose whether a adolescent under test has autism.

[0006] The technical solution provided by this invention is as follows: In a first aspect, the present invention provides a prediction system related to autism in adolescents, comprising: a detection module for acquiring quantitative detection results of preset microbial markers in fecal samples of a donor to be tested, wherein the microbial markers include active rumenococcus gnavus and / or Streptococcus thermophilus; and a comparison module for comparing the quantitative detection results with preset thresholds and determining whether the adolescent to be tested has autism based on the comparison results.

[0007] Secondly, the present invention provides a gut microbiota-based autism prediction system for adolescents, comprising: a detection module for acquiring quantitative detection results of preset microbial markers in fecal samples of a donor to be tested, wherein the microbial markers include active rumenococcus gnavus, Streptococcus thermophilus, Streptococcus salivarius, Intestinibacter bartlettii, Anaerostipes hadrus, and Faecalibacterium prausnitzii; a calculation module for calculating the probability that the donor to be tested is an autistic patient based on the quantitative detection results, denoted as an autism patient probability value; and a comparison module for comparing the autism patient probability value with a preset threshold, and determining whether the adolescent to be tested has autism based on the comparison result.

[0008] Thirdly, the present invention provides a method for constructing a predictive model for adolescent autism, characterized in that the method comprises the following steps: collecting fecal samples from adolescent autism patients and healthy adolescents according to preset inclusion and exclusion criteria, and designating the fecal samples from adolescent autism patients as the autism group and the fecal samples from healthy adolescents as the healthy group; performing high-throughput sequencing on the autism group and the healthy group to identify differentially expressed microorganisms between the autism group and the healthy group, wherein the differentially expressed microorganisms include the microbial biomarkers described in any one of claims 1 to 3 in the predictive system; and using the differentially expressed microorganisms as a predictive model for adolescent autism to determine whether the adolescent to be tested has autism.

[0009] The beneficial effects of this invention are as follows: 1. This invention newly discovers six gut microbiota associated with adolescent autism, including: Ruminococcus gnavus, Streptococcus thermophilus, Streptococcus salivarius, Intestinibacter bartlettii, Anaerostipes hadrus, and Faecalibacterium prausnitzii.

[0010] After research and verification, it was found that one or more of the above six gut microbiota can be used to diagnose whether a adolescent with autism has autism.

[0011] 2. The present invention also provides a reagent and / or kit that can use one or more of the above 6 bacterial species as detection markers (i.e., microbial markers) to diagnose whether the adolescent under test has autism. It is completely non-invasive and highly accurate.

[0012] Metagenomic sequencing provides higher resolution, enabling the analysis of microbial communities to reach the species and even strain level, thereby improving the accuracy and reliability of diagnosis. The six species mentioned can also serve as target microorganisms for developing these systems, filling a gap in this field.

[0013] 3. This invention also provides a product and / or prediction system for diagnosing autism in adolescents. This product and / or prediction system can diagnose the risk of autism in a tested adolescent based on the relative abundance values ​​of various bacterial species. The entire diagnostic process is safe, non-invasive, and efficient, demonstrating good feasibility and accuracy. It can effectively assess the risk of autism in a tested adolescent (from a fecal sample), with relatively accurate assessment results. Attached Figure Description

[0014] Figure 1 This is a graph showing the results of the linear discriminant analysis; Figure 2 Box plots showing the relative abundance of autism in individuals with autism and healthy individuals; Figure 3 ROC curve for predicting scores. Detailed Implementation

[0015] The present invention will now be described in further detail with reference to specific embodiments, so that those skilled in the art can understand it.

[0016] The following description of adolescent autism follows the structure you provided, but with a similar approach, incorporating the background issue of "sufficient sample size but insufficient screening": Adolescent autism is a complex neurodevelopmental disorder caused by abnormal neurodevelopment accompanied by synaptic plasticity and an imbalance between excitation and inhibition. It has become one of the most serious public health problems affecting children worldwide. Its harm lies not only in its continuously rising prevalence, but also in the lifelong social communication impairments, stereotyped behaviors, and comorbid intellectual developmental delays it causes, placing a heavy burden on patients, families, and society.

[0017] Autism in adolescents has become a global public health focus: the World Health Organization (WHO) estimates that approximately 1% of children and adolescents worldwide have autism spectrum disorder, with core symptoms often appearing before age 3. However, many mild or atypical cases are not diagnosed until adolescence. Compared to those diagnosed in adulthood, the adolescent brain is still in a critical period of remodeling, with more complex interactions between genetic, epigenetic, and environmental factors, making symptoms more prone to co-occurrence with anxiety, depression, and self-harm. The causes can be attributed to high genetic susceptibility (e.g., hundreds of risk genes such as CHD8 and SHANK3), perinatal immune activation, early sensory deprivation, and gut-immune-central nervous system axis disorders, all contributing to abnormal synaptic pruning and long-range connectivity dysfunction in early cortical development, resulting in a lack of social motivation, narrow interests, and sensory abnormalities. Without behavioral intervention before adolescence, independent living and employability in adulthood are severely impaired, and the risk of comorbid mental disorders increases 3 to 5 times.

[0018] For adolescents with autism, the main treatment options currently include behavioral interventions and symptomatic drug therapy. Behavioral interventions include Applied Behavior Analysis (ABA) and Social Skills Training (SST), which can improve core social deficits and adaptive behaviors. However, the efficacy is limited by the density of therapists, the level of family involvement, and the child's baseline function. Approximately 40% to 50% of adolescents still do not respond well to high-intensity behavioral interventions. In terms of drugs, the US FDA has only approved risperidone and aripiprazole for relieving irritability and stereotyped behaviors. However, they are ineffective for core social communication impairments and may cause significant weight gain, metabolic abnormalities, and extrapyramidal reactions. In addition, there is a lack of precise drugs that target the neurodevelopmental characteristics of adolescence, and clinical drug use is often off-label, making it difficult to control the risks.

[0019] In response to the above-mentioned problems, the applicant of this application filed an invention patent entitled "Application of Gut Microbiota Markers in the Diagnosis and Treatment of Autism" on October 31, 2023, which discovered the microorganisms Bacteroides, Lachnoclostridium, and Parabacteroides. Bifidobacterium, Blautia, and Collinsella Related to autism.

[0020] While the aforementioned gut microbiota biomarkers can be used to assess the risk of autism in adolescents, the healthy human samples used are raw data downloaded from the NCBI database, which has the problem of insufficiently strict sample selection criteria. Therefore, it is necessary to improve these criteria to lay a good foundation for subsequent early warning and mechanism intervention.

[0021] This invention provides a microbial biomarker related to adolescent autism and its application. It not only has a larger sample size and stricter sample screening criteria, but also provides more accurate and representative test results. It can be used as a predictive factor for adolescent autism, thereby diagnosing whether a adolescent being tested has autism. Specifically, the technical concept of this invention is as follows: To address the clinical needs for the diagnosis and detection of autism in adolescents, this invention collects samples from adolescent autism patients and healthy individuals, and through a standardized experimental testing procedure (specific experimental methods are described in Examples 1-3), screens out six microorganisms associated with adolescent autism, including: Ruminococcus gnavus, Streptococcus thermophilus, Streptococcus salivarius, Intestinibacter bartlettii, Anaerostipes hadrus, and Faecalibacterium prausnitzii.

[0022] ROC curve analysis showed that the above six biomarkers have high specificity and sensitivity as detection variables, and these six bacterial species can be used as detection biomarkers for the prediction and diagnosis of adolescent autism.

[0023] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. The following embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. Experimental methods not specifically described in the embodiments are generally performed under conventional conditions.

[0024] Example 1: Sample Collection

[0025] The sample sources and inclusion criteria for adolescent autism are as follows: a. Age 4-10 years; b. Diagnosis of autism spectrum disorder by two or more child psychiatrists based on DSM-5 or ICD-11; c. Assessment results of the Diagnostic Observational Scale for Autism, Version 2 (ADOS-2) or the Diagnostic Interview-Revised Scale for Autism, Version 2 (ADI-R) reaching the diagnostic threshold for autism spectrum disorder; d. Exclusion criteria were given to subjects with Rett syndrome, childhood disintegrative disorder, selective mutism, schizophrenia, bipolar disorder, substance abuse, serious physical illness, or who are pregnant or lactating.

[0026] Exclusion criteria for the autism group: a. Received systemic medication or physical therapy (such as transcranial magnetic stimulation) targeting core autism symptoms within 1 month prior; b. Taken antibiotics, probiotics, or prebiotics within the past 3 months; c. Suffers from any chronic disease that may significantly affect brain function or metabolism (including uncontrolled frequent seizures, liver or kidney dysfunction, severe endocrine disorders, etc.); d. Received medication affecting gastrointestinal motility within 1 week; e. History of functional dyspepsia, aerophagia, or abdominal migraine pain; f. Demonstrates growth retardation (e.g., height or weight below the 3rd percentile for age and sex); g. Suffers from gastrointestinal obstruction or stenosis; h. History of abdominal surgery, peptic ulcer, or inflammatory bowel disease in the family; i. Known presence of a specific genetic syndrome clearly associated with autism (e.g., Fragile X syndrome, tuberous sclerosis, 15q11-q13 repeat syndrome, etc.) that may introduce an independent pathogenic mechanism; j. The researchers deem the patient unsuitable for inclusion in this study.

[0027] The sample sources and inclusion criteria for healthy adolescents are as follows: a. Source: The selected candidates are from non-urbanized areas with stable living environments and no record of major infectious disease outbreaks in the past 5 years; the content of heavy metals and organic pollutants in the soil and water must meet the risk control requirements; areas with high-risk environmental factors such as industrial pollution sources and excessive use of agricultural chemicals are excluded.

[0028] b. Information solicitation: 2.1 Age 4-10 years old.

[0029] 2.2 Investigate family medical history. If there is no family medical history, pay special attention to hereditary diseases (including autism, intellectual disability, fragile X syndrome, etc.), digestive system diseases, infectious diseases, and any family history of mental illness or tumors; confirm the average lifespan of the immediate family members of the target family for human gut microbiota screening.

[0030] 2.3 Investigate personal medical history: No history of any neurodevelopmental disorders (including autism spectrum disorder, attention deficit hyperactivity disorder, tic disorders, specific learning disabilities, intellectual developmental disorders, etc.), no gastrointestinal diseases (inflammatory bowel disease, irritable bowel syndrome, chronic constipation or diarrhea, malignant tumors or known polyposis, celiac disease, congenital or chronic liver disease, rectal bleeding, major surgery), no autoimmune diseases, atopic diseases (asthma, atopic dermatitis, eczema, eosinophilic gastrointestinal diseases), cardiovascular or metabolic diseases (such as diabetes, hypertension, heart disease, etc.), neurological diseases (anxiety disorders, multiple sclerosis, Parkinson's disease, etc.), immunosuppression, chronic pain, infectious diseases, community-acquired pneumonia, etc.

[0031] 2.4 The screening subjects should have good on-site language expression ability, mental vitality (no significant abnormalities in social communication or stereotyped behavior), no tattoos, punctures or injuries, and no history of blood transfusions or other high-risk behaviors.

[0032] c. Scale assessment: 3.1 Interviews with child psychiatrists or psychologists indicate that the selected individuals have normal psychological state and social behavior development, and no suspicious signs of autism.

[0033] 3.2 The scores of the Autism Spectrum Quotient (AQ) Adolescent Version, Social Response Scale (SRS), and behavioral assessment systems (such as BASC-3) were all within the normal range; at the same time, the scores of the Self-Rating Mental Health Scale (SCL-90), Self-Rating Depression Scale (SDS), Self-Rating Anxiety Scale (SAS), and Pittsburgh Sleep Quality Index (PSQI) were all normal.

[0034] d. Health check-up: 4.1 A comprehensive physical examination conducted by a professional medical examination institution is passed. Blood routine tests, liver and kidney function tests, hepatitis A / E tests, cytomegalovirus tests, EB virus (IgM + IgG), hepatitis B tests (HBsAg + anti-HBcore), HCV tests, hepatitis C tests, HIV tests (anti-HIV), syphilis tests, C13 breath tests, and endocrine indicator tests all meet relevant requirements. 4.2 Test the exons related to hereditary diseases of the target population, screen for single-gene hereditary diseases (pay special attention to known pathogenic genes related to autism such as CHD8, SHANK3, NLGN3, NRXN1, etc.), and exclude pathogenic and suspected pathogenic mutation sites.

[0035] 4.3 Sensitivity testing for common allergens. Screening subjects had no obvious history of allergic reactions and the test results showed no positive reaction to common allergens.

[0036] e. Stool testing: 5.1 The fecal characteristics of the subjects to be screened should conform to the Bristol fecal classification type III and type IV.

[0037] 5.2 Screening subjects should exclude those carrying pathogenic bacteria, drug-resistant bacteria, and potential pathogenic microorganisms. This includes Clostridium difficile, Salmonella (which easily causes bacterial gastroenteritis), Campylobacter, Yersinia, and Shiga toxin-producing Escherichia coli; antibiotic-resistant bacteria such as vancomycin-resistant enterococci (VRE), extended-spectrum β-lactamase (ESBL), and methicillin-resistant Staphylococcus aureus (MRSA); and viral pathogens such as norovirus (types I and II), enteroviruses, and hepatitis E virus.

[0038] 5.3 The feces of the selected subjects should be free of parasitic infections. Exclude parasites such as Clonorchis sinensis, Clonorchis sinensis, Balantidium coli, Hookworm, Giardia lamblia, Cyclospora cayetta, Trichodina, Strongyloides stercoralis, Intestinal nematodes, Meliostomatella asiatica, Taenia spp., Cryptosporidium spp., Ascaris spp., Entamoeba histolytica, and Entamoeba histolytica.

[0039] Exclusion criteria for healthy adolescents: a. Received any form of mental or psychological treatment (including behavioral intervention, drug treatment, etc.) within the past month; b. Taken antibiotics or probiotics / prebiotics within the past three months; c. Having any chronic illness, including neurobehavioral disorders (especially those with a history or diagnosis of autism, ADHD, Tourette syndrome, etc.); d. Having received medication that affects gastrointestinal motility within the past week; e. Having a history of functional dyspepsia, aerophagia, or abdominal migraine pain; f. Exhibiting growth retardation; g. Having gastrointestinal obstruction or stricture; h. Having a history of abdominal surgery, peptic ulcer, or a family history of inflammatory bowel disease; i. Having a first-degree relative diagnosed with autism spectrum disorder or other pervasive developmental disorder; j. The researchers deem the subject unsuitable for inclusion in this study.

[0040] In summary, both the adolescents with autism and the healthy adolescents obtained written informed consent from themselves and their legal guardians. The fecal samples used in this invention were collected from Hubei Province, totaling 156 adolescents with autism and 155 healthy adolescents. The statistical results are as follows: .

[0041] Example 2: DNA extraction, library construction, and sequencing

[0042] 1. Use the Hi Pure Stool DNA Mini Kit to perform DNA extraction experiments on the collected intestinal samples.

[0043] 2. After extraction, the DNA concentration was detected using Qubit, and the integrity of the extracted genomic DNA was detected by 1.5% agarose gel electrophoresis. The extracted genomic DNA was then subjected to quality control, and qualified genomic DNA samples were selected (DNA concentration ≥20ng / μL, volume ≥20 μL, total amount ≥400 ng).

[0044] 3. For qualified DNA samples, random fragmentation, end repair, A base ligation, adapter and index are added. After adapter ligation, purification and library amplification are performed. After amplification, the DNA concentration is detected (DNA concentration ≥40 ng / μL).

[0045] 4. After the libraries pass the testing, different libraries are pooled according to the effective concentration and target data volume requirements before sequencing. The metagenomic sequencing platform is BGI T7, and the sequencing strategy is PE150.

[0046] Example 3: LEfSe analysis for screening microbial biomarkers

[0047] 1. Split the dataset KneadData software was used for quality control (based on Trimmomatic) and host removal (based on Bowtie2) of the raw data. Kraken2 alignment was used to calculate the sequence number of each species in the sample, and Bracken was used to estimate the actual abundance of species in the sample. 80% of the participants (including those in the disease and healthy groups) were randomly selected as the training set, and the remaining 20% ​​of the samples were used as the validation set. The abundance data of each sample in the training set were then analyzed using LEfSe software, with the default LDA Score filter value set to 2. The sample information is shown in Table 1. The results are as follows Figure 1 As shown, the researchers screened out five biomarkers that were significantly reduced in the autism group, including Streptococcus thermophilus, Anaerostipes hadrus, Ruminococcus gnavus, Faecalibacterium prausnitzii, and Intestinibacter bartlettii; and one biomarker that was significantly increased in the autism group, including Streptococcus salivarius.

[0048] Example 4: Verifying the reliability of the above 6 microbial biomarkers

[0049] 1. First, the remaining 20% ​​of the test subjects in Example 1 (including the adolescent autism group and the healthy group) were used as the validation set. The abundance data of each sample in the validation set were first subjected to binary logistic regression, and then the receiver operating function (ROC curve) was analyzed to obtain the cutoff value (optimal cutoff value).

[0050] 2. Use R language statistical software to calculate specificity and sensitivity and plot ROC curves. The software first calculates the threshold of the actual measurement value, and then calculates the number of true positive cases (TP), false positive cases (FP), true negative cases (TN), and false negative cases (FN) corresponding to the threshold. Specificity (true negative rate) = TN / (TN + FP) Sensitivity (true positive rate) = TP / (TP + FN) 3. The ROC curve can be constructed using 1 minus specificity and sensitivity. The integral of the ROC curve is the AUC. To calculate the specificity and sensitivity of a certain indicator, first calculate the Youden coefficient (Youden index = sensitivity + specificity - 1). The specificity and sensitivity corresponding to the maximum value of the Youden coefficient are the specificity and sensitivity of the certain indicator.

[0051] 4. The relative abundance values ​​of microbial biomarkers for single strains were directly analyzed using receiver operating characteristic (ROC) curve testing to determine the cutoff value. The ROC curve for predictive scoring is shown below. Figure 3 As shown in Table 2, the AUC, optimal cutoff value, sensitivity, and specificity of the predicted mimicry markers (markers formed by the combination of 6 single bacterial species) and individual bacteria are shown in Table 2.

[0052] .

[0053] According to Table 2 and Figure 3 As described, for single bacterial species, *Ruminococcus gnavus* had the highest AUC value (approximately 0.908), while *Corynebacterium salivarius* had the lowest (approximately 0.774). The combined AUC value of the four single bacterial species—*Ruminococcus gnavus*, *Streptococcus thermophilus*, *Streptococcus salivarius*, and *Intestinibacter bartlettii*—was 0.973. The AUC value of the mimicry marker (a marker formed by the combination of six single bacterial species) (approximately 0.963) was higher than that of the single bacterial species.

[0054] As can be seen from the above, one or more of the six newly discovered bacterial species in this application can be used as detection variables, and they all have high specificity and sensitivity. Moreover, the AUC of all six microbial markers is greater than 75%. Therefore, one or more of the six microbial markers can be used as detection markers for the diagnosis of adolescent autism.

[0055] Example 5: Establishing a Logistic Regression Model Based on the microbial biomarkers selected above and the relative abundance value of each metabolic biomarker, the binary logistic regression algorithm in RStudio software was used to calculate the first disease probability (also known as the logarithm of dominance y) for each sample. Then, the disease probability optimization formula Z=exp(y) / {1+exp(y)} was used to calculate the disease probability Z of the sample under test. Finally, this disease probability Z was compared with the actual disease status (e.g., severity) of each sample to verify the accuracy of the disease probability calculation equation. Specifically: a. Establishing a model Based on the biomarkers identified above, and considering the proportion of adolescents with autism and patients in the training set, the relative abundance values ​​of the six detected bacterial species were further used as single variables. The linear relationship between the relative abundance values ​​of the six single bacteria and the probability of disease in the samples was then discussed. The logarithm y (also known as the first probability value y) of the subject's dominance was calculated using a binary logistic regression equation. y=A+B1×x1+B2×x2+B3×x3+B4×x4+B5×x5+B6×x6 Where A is the intercept term, B1 to B7 are the regression coefficients of the independent variables; x1 is the relative abundance value of *Streptococcus salivarius*, x2 is the relative abundance value of *Streptococcus thermophilus*, x3 is the relative abundance value of *Anaerostipes hadrus*, x4 is the relative abundance value of *Ruminococcus gnavus*, x5 is the relative abundance value of *Faecalibacterium prausnitzii*, and x6 is the relative abundance value of *Intestinibacter bartlettii*.

[0056] b. Determine the values ​​of A and B1 to B7 above. After statistical analysis of the sample data, the values ​​were: A = -0.5175, B1 = 45.2045, B2 = -10.6914, B3 = -45.7213, B4 = -23.2247, B5 = -0.2721, and B6 = -27.796. At this point, after rearrangement, the formula for calculating the logarithm y of the dominance is: y=-0.5175+45.2045×X1-10.6914×X2-45.7213×X3-23.2247×X4-0.2721×X5-27.796×X6; c. Calculate the disease probability Z of the subjects to be tested. Substitute the first probability value y into the following formula to calculate the probability Z that the subject is a patient: Z = exp(y) / {1 + exp(y)}; where Z is the probability value that the subject is a patient, and exp(y) is the natural exponential function of the first probability value y.

[0057] After processing, the formula for calculating the probability Z of disease is:

[0058] d. Validation set data calculation and statistical analysis Based on the validation set data, the relative abundance of each single bacterial species in the disease group and the healthy group for each sample was obtained. Then, the first probability value y was obtained using the aforementioned binary logistic regression method. The probability Z of the test sample being a patient was then calculated using the formula. The results are shown in Tables 3 and 4, where "patient" refers to a patient with irritable bowel syndrome.

[0059] Table 4 shows the relative abundance mean and standard deviation for each bacterial species. The relative abundance mean determines the central location of the data distribution, while the standard deviation reflects the dispersion of the data relative to the mean. The p-value is a statistic calculated using the rank-sum test formula. The lower the p-value, the greater the difference between the disease group and the healthy group.

[0060]

[0061]

[0062]

[0063]

[0064]

[0065] Note: In Table 3, E represents powers of 10. For example, 6.78E-05 means 6.78 * 10^6. -5 .

[0066]

[0067] Note: In Table 4, the mean refers to the relative abundance mean, and the standard deviation is similarly defined. E represents a power of 10. For example, 5.25E-10 means 5.25 * 10^10. -10.

[0068] Example 6: Predictive system associated with adolescent autism Based on the above embodiments, this embodiment provides a predictive system related to adolescent autism, a predictive system for assessing the risk that a subject is autistic, the predictive system including a detection module and a comparison module, specifically: The detection module is used to obtain quantitative detection results of a single bacterial species in the fecal sample of the subject to be tested; wherein, the single bacterial species may include one or more of the following: Ruminococcus gnavus, Streptococcus thermophilus, Streptococcus salivarius, Intestinibacter bartlettii, Anaerostipes hadrus, and Faecalibacterium prausnitzii; The comparison module is used to compare the quantitative detection results with a preset threshold, and to determine the risk of the subject being autistic based on the comparison results.

[0069] Preferably, the quantitative detection results include one or more of relative abundance, absolute abundance, and total microbial load information, and the preset threshold is a range of values ​​determined by the mean and standard deviation of the quantitative detection results.

[0070] In practical application, to illustrate how the prediction system assesses the risk of a adolescent being diagnosed with autism, this invention uses relative abundance values ​​as an example. Specifically: The detection module obtains the relative abundance value of active rumenococci in the fecal sample of the test subject, which is recorded as the first abundance value. This first abundance value is also the quantitative detection result obtained by the detection module. The comparison module compares the first abundance value with the mean and standard deviation of active rumenococci in Table 4 to assess the risk that the subject is autistic. For example, if the first abundance value is within the range defined by the mean and standard deviation of autistic patients, the risk that the subject is autistic is high; otherwise, the risk that the subject is autistic is low.

[0071] Similarly, referring to the above-mentioned detection and assessment methods for active rumen cocci, the prediction system can also perform similar detection and assessment of microorganisms such as Streptococcus thermophilus, Streptococcus salivarius, Intestinibacter bartlettii, Anaerostipes hadrus, and Faecalibacterium prausnitzii, thereby assessing the risk of the adolescent being tested having autism.

[0072] Due to factors such as genetics and environment, it is normal that not all seven newly discovered bacterial species can be detected in fecal samples. People can use one or more of the seven newly discovered bacterial species as detection markers to assess the risk that the subject is autistic.

[0073] Given that obtaining relative abundance values ​​and other quantitative detection data (such as absolute abundance or total microbial load information) are routine methods in this field, if one wants to use other quantitative detection methods to assess the risk of a subject having autism, one can refer to the description above, which will not be repeated here.

[0074] Example 7: Autism Diagnosis / Prediction System for Adolescents

[0075] Based on the above embodiments, this embodiment provides a diagnostic / predictive system for adolescent autism, including a detection module, a calculation module, and a comparison module, wherein: The detection module is used to obtain quantitative detection results of preset microbial markers in the fecal samples of the donor to be tested. The microbial markers include active rumenococcus gnavus, thermophilic streptococcus, salivarius streptococcus, Intestinibacter bartlettii, Anaerostipes hadrus, and Faecalibacterium prausnitzii.

[0076] The calculation module is used to calculate the probability that the donor to be tested is an autistic patient based on the quantitative detection results, and denoted as the autistic patient probability value.

[0077] In actual operation, the calculation module also includes a first probability module and a second probability module, wherein: the first probability module is used to substitute the relative abundance value of each single species in the microbial biomarker into the binary logistic regression equation to calculate the logarithm y of the dominance of the test subject; the second probability module is used to calculate the probability Z of the test subject being a type 2 diabetic patient based on y, Z=exp(y) / {1+exp(y)}, where exp(y) is an exponential function of y.

[0078] The comparison module is used to compare the probability value of the autism patient with a preset threshold, and to determine whether the adolescent under test has autism based on the comparison result.

[0079] Example 8: Method for constructing a prediction model

[0080] Based on the descriptions in Examples 1-7, the present invention provides a method for constructing a predictive model for adolescent autism, comprising the following steps: S1. Sample collection: Collect fecal samples from adolescents with autism and healthy adolescents according to the preset inclusion and exclusion criteria. In this step, given that different groups of people have different definitions of "healthy person," such as some people considering family members of long-lived families as healthy people (passing physical examinations), some people considering teenagers aged 20-30 as healthy people (passing physical examinations), some people considering college students of sports colleges as healthy people (passing physical examinations), etc., people can use the healthy person screening method listed in Example 1 of this invention to screen for healthy people, or they can use other standards to screen for healthy people. This embodiment does not impose any restrictions here, as long as the collected fecal samples conform to people's general understanding.

[0081] S2. Sample grouping: DNA extraction, library construction and sequencing were performed on the fecal samples of the above-mentioned adolescent autism patients and adolescent healthy individuals, respectively. The fecal samples of adolescent autism patients were assigned to the autism group, and the fecal samples of adolescent healthy individuals were assigned to the healthy individuals group. In this step, after selecting specific fecal samples from healthy individuals, people should be able to extract DNA from the fecal samples, construct libraries, and sequence them according to the preset steps in order to distinguish the differential microorganisms between the autism group and the healthy group. The specific experimental steps can be referred to the descriptions in Examples 1 to 4 above, and will not be repeated here.

[0082] S3. Identify differentially expressed microorganisms: Perform high-throughput sequencing on the autism group and the healthy group to identify differentially expressed microorganisms between the autism group and the healthy group. The differentially expressed microorganisms may include one or more of the following: active rumenococci, sludge bacterium, fecal prevostii, active rumenococci, Hodgkin's eubacterium, giant anaerobic corynebacterium, and variant rare micrococci. The steps for performing high-throughput sequencing and identifying differentially expressed microorganisms can be found in the descriptions of Examples 1-4 above, and will not be repeated here.

[0083] S4. Use the differentially expressed microorganisms as a predictive model for adolescent autism to distinguish whether the adolescent to be tested is an autistic patient.

[0084] In practical work, in conjunction with Examples 6 and 7, this step provides two methods for using the differentially expressed microorganisms as predictive models, specifically including: Referring to Example 6, the first method of using the differential microorganisms as a prediction model is as follows: S41, obtain the quantitative detection results of preset microbial markers in the fecal sample of the adolescent to be tested; S42, compare the quantitative detection results with preset thresholds, and determine whether the adolescent to be tested is an autistic patient based on the comparison results.

[0085] Referring to Example 7, the second method of using the differentially expressed microorganisms as a prediction model is as follows: S41, obtain the quantitative detection results of preset microbial markers in the fecal sample of the adolescent to be tested; S42, calculate the probability that the adolescent to be tested is an autistic patient based on the quantitative detection results, and use the probability value of the autistic patient as the quantitative detection result; S43, compare the quantitative detection result with a preset threshold, and determine whether the adolescent to be tested is an autistic patient based on the comparison result.

[0086] In practice, a Z-score greater than 0.5 indicates a higher probability that the subject has adolescent autism; a Z-score less than 0.5 indicates a lower probability; and a Z-score of 0.5 suggests the subject may be a patient or have autism, requiring further testing using methods such as mental health assessments and medication. Furthermore, the closer the Z-score is to 0.5, the more necessary it is to utilize additional testing methods.

[0087] Example 9: Diagnosing whether a test sample is a adolescent with autism

[0088] If it is necessary to diagnose whether a person under test is an adolescent with autism, in addition to conventional testing methods such as ultrasound examination, serum liver enzyme test, and liver tissue biopsy, medical staff can also use the methods or products described in Examples 1 to 11 above to diagnose the person under test, in order to assist medical staff in making a more accurate judgment: (1) If, after continuous observation over multiple time periods, the content of one or more of the following bacteria is found to be high (compared to the mean and standard deviation of the autism group in Table 4), or even shows a significant increasing trend, then the adolescent being tested is more likely to be autistic.

[0089] (2) If, after observation over multiple consecutive periods, the content of one or more Streptococcus salivarius in the test subject is found to be high (compared to the mean and standard deviation of the healthy group in Table 4), then the test subject adolescent is more likely to be a healthy person.

[0090] (3) If, after observation over multiple consecutive periods, the person being tested does not exhibit the patterns described in (1) and (2) above, then medical staff can combine [the above information with further details]. Figure 1 According to Table 4, a preliminary judgment is made on whether the adolescent under test is autistic; (4) If medical staff want to more accurately determine whether the person to be tested is an adolescent with autism, they can calculate the probability that the adolescent to be tested is an autism patient based on the quantitative detection results of 6 single bacterial species (such as relative abundance values) and the technical solutions described in Examples 5 to 7.

[0091] e. Results and Analysis Based on the results of Examples 4 and 5, it can be seen that for single bacterial species, *Ruminococcus virens* has the highest AUC value (approximately 0.908), while *Corynebacterium praecox* has the lowest AUC value (approximately 0.774). For mimicry markers, the AUC value is approximately 0.963, the optimal cutoff value is approximately 0.521, the sensitivity is approximately 0.935, and the specificity is 0.967.

[0092] The AUC of the six microbial markers identified in this application is all greater than 75%. One or more of the six microbial markers can be used as detection markers for the diagnosis of adolescent autism. At the same time, since this invention only requires the collection of fecal samples from the test subjects, this invention is not only completely non-invasive, but also highly accurate, and can be used to diagnose whether the test adolescents (fecal samples) have autism.

[0093] Based on the results obtained from the description in Table 3 above and the calculation formula for the probability of disease Z, it can be seen that the calculation formula for calculating the probability of disease in the sample to be tested, which is summarized in this application, is basically correct and can be used to diagnose the risk and probability of disease in the sample to be tested. The probability of disease in Table 3 above may not fully meet the diagnostic criteria. This is because the intestinal sample of the person to be tested may produce false positive or false negative results. Further testing using other methods is required, including blood routine tests, diagnostic physical signs, etc.

[0094] Conclusion and explanation: 1. By Figures 1-3 As shown in Table 2, any one of the six newly discovered single bacterial species in this application can be used as a microbial biomarker for adolescent autism. Each single bacterial species has sensitivity and specificity for adolescent autism. Therefore, the microbial biomarker for adolescent autism can be selected from any one or more of the six newly discovered single bacterial species in this application.

[0095] 2. As shown in Table 3, it is normal for only one or a few species of bacteria to be detected when testing intestinal samples. This is because there are individual differences. The probability Z of disease in this application is calculated. Therefore, even if a sample contains only a single species of bacteria, this application can still calculate the probability that the sample to be tested has adolescent autism.

[0096] 3. Predictive effect: The AUC value of the mimicry marker (a marker formed by the combination of 6 single bacterial species) (approximately 0.963) is higher than that of the single bacteria. The AUC value of the four single bacterial species Ruminococcus gnavus, Streptococcus thermophilus, Streptococcus salivarius, and Intestinibacter bartlettii combined together is 0.973.

[0097] 4. All six newly discovered bacterial species in this application can be used as detection variables. They all have high specificity and sensitivity, and the AUC of all six microbial markers is greater than 75%. One or more of the six microbial markers can be used as detection markers for the diagnosis of adolescent autism.

[0098] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions, and improvements made by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the invention.

Claims

1. A prediction system related to autism in adolescents, characterized in that, include: The detection module is used to obtain the quantitative detection results of preset microbial markers in the fecal sample of the donor to be tested, the microbial markers including active rumenococcus gnavus and / or thermophilic streptococcus thermophilus. The comparison module is used to compare the quantitative detection results with a preset threshold, and determine whether the adolescent under test has autism based on the comparison results.

2. The prediction system of claim 1, wherein, The microbial markers also include Streptococcus salivarius and / or Enterobacter bartlettii.

3. The prediction system of claim 1 or 2, wherein, The microbial markers also include Anaerostipes hadrus and Faecalibacterium prausnitzii.

4. A gut microbiota-based system for predicting autism in adolescents, characterized by: include: The detection module is used to obtain quantitative detection results of preset microbial markers in the fecal samples of the donor to be tested. The microbial markers include active rumenococcus gnavus, thermophilic streptococcus, salivarius streptococcus, Intestinibacter bartlettii, Anaerostipes hadrus, and Faecalibacterium prausnitzii. The calculation module is used to calculate the probability that the donor to be tested is an autistic patient based on the quantitative detection results, and denoted as the autistic patient probability value; The comparison module is used to compare the probability value of the autism patient with a preset threshold, and determine whether the adolescent under test has autism based on the comparison result.

5. The adolescent autism prediction system of claim 4, wherein: The calculation module further includes a first probability module and a second probability module, wherein: The first probability module is used to substitute the relative abundance value of each single species in the microbial biomarker into the binary logistic regression equation to calculate the logarithm y of the dominance of the test object; The second probability module is used to calculate the probability Z of the subject being a type 2 diabetes patient based on y, Z = exp(y) / {1 + exp(y)}, where exp(y) is an exponential function of y.

6. The adolescent autism prediction system according to claim 5, characterized in that: The formula for the binary logistic regression equation is: y=A+B1×x1+B2×X2+B3×X3+B4×X4+B5×X5+B6×X6+B7×X7; Where A is the intercept term, B1 to B6 are the regression coefficients of the independent variables; x1 is the relative abundance value of *Streptococcus salivarius*, x2 is the relative abundance value of *Streptococcus thermophilus*, x3 is the relative abundance value of *Anaerostipes hadrus*, x4 is the relative abundance value of *Ruminococcus gnavus*, x5 is the relative abundance value of *Faecalibacterium prausnitzii*, and x6 is the relative abundance value of *Intestinibacter bartlettii*.

7. The adolescent autism prediction system according to claim 6, characterized in that: A is -0.5175, B1 is 45.2045, B2 is -10.6914, B3 is -45.7213, B4 is -23.2247, B5 is -0.2721, and B6 is -27.

796.

8. A method for constructing a predictive model for adolescent autism, characterized in that, The method for constructing the prediction model includes the following steps: Fecal samples were collected from adolescents with autism and healthy adolescents according to the pre-set inclusion and exclusion criteria. Fecal samples from adolescents with autism were designated as the autism group, and fecal samples from healthy adolescents were designated as the healthy group. High-throughput sequencing was performed on the autism group and the healthy group to identify differentially expressed microorganisms between the autism group and the healthy group, wherein the differentially expressed microorganisms include the microbial biomarkers described in the prediction system of any one of claims 1 to 3; The differentially expressed microorganisms were used as a predictive model for adolescent autism to determine whether the adolescents under test had autism.

9. The construction method according to claim 8, characterized in that, The use of the differentially expressed microorganisms as a predictive model for adolescent autism includes: Obtain quantitative detection results of pre-defined microbial markers in fecal samples from the donor to be tested; The quantitative detection results are compared with a preset threshold, and the donor to be tested is determined to be either an autistic patient or an inefficient donor based on the comparison results.

10. The construction method according to claim 8, characterized in that, The use of the differentially expressed microorganisms as a predictive model for adolescent autism includes: Quantitative detection results of preset microbial markers in fecal samples from the donor to be tested are obtained. The microbial markers include active rumenococcus gnavus, thermophilic streptococcus, salivarius streptococcus, Intestinibacter bartlettii, Anaerostipes hadrus, and Faecalibacterium prausnitzii. The probability that the donor to be tested is an autistic patient is calculated based on the quantitative test results, and the probability value of the autistic patient is used as the quantitative test result; The quantitative detection results are compared with a preset threshold, and the results are used to determine whether the adolescent under test has autism.

Images