Machine learning of fecal metabolites of children with autism spectrum disorder during microbiota transfer therapy

Fatir Qureshi, James Adams, Kathryn Hanagan, Dae Wook Kang, Rosa Krajmalnik-Brown, Juergen Hahn

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Introduction: Autism spectrum disorder (ASD) encompasses a large group of early onset neurological conditions thatresult in impairments in social behavior and communication, which are estimated to affect 1 in 54 children under theage of 8 in the United States (Maenner et al., 2020). Although diagnosis of this disorder is only made throughbehavioral evaluations, many systems of the body are strongly affected in this condition. A diverse range ofphysiological mechanisms have been observed to be perturbed in ASD including the immune, endocrine, andgastrointestinal (GI) systems (Rossignol, D. A., and Frye, R., 2012). Notably, the prevalence of GI symptoms co-occurring with ASD (~46%) lends significant credence to investigating the relationship of ASD to the gastrointestinalsystem (Fry et al., 2015). Furthermore, the microbiota of individuals with ASD, both with and without the presence ofthis co-occurring condition, has consistently been observed to be distinct from their typically-developing (TD) peers(Hughes et al., 2018). Thus, in recent years, there have been growing efforts related to studying the effect of the microbiome on the Gut-Brain Axis in the context of ASD etiology. The use of microbiota transfer therapy (MTT) has shown considerablepotential in its capability to alleviate not only symptoms associated with GI complications, but also in some cases toreduce the severity of certain behavioral symptoms in children with ASD. For example, Kang et al. (2017)demonstrated in an open-label study that through MTT, there was an 80% reduction in GI symptoms and a 24% initialreduction in core ASD symptoms, with greater improvement in ASD symptoms at a two-year follow-up (Kang et al2019). ASD children who underwent MTT were also observed to undergo changes in their plasma metabolite profilesto more closely resemble those of their typically developing peers (Adams et al., 2019). This work subsequently builds on this MTT study by focusing on fecal samples taken from these participants. Thepurpose of this work was to examine the differences in gut metabolites between children with ASD and GI problemsvs. typically developing children without GI problems, and determine the effects of gut microbiota transfer therapy onthe fecal metabolites of the ASD group. Towards this purpose, both multivariate and univariate statistical analysis wasapplied. The development of a classification model based on metabolite panels could in turn be used to validateunderlying metabolic change stemming from treatment. Methods The study involved 38 children, aged 7-16 years, with 18 professionally diagnosed with ASD (verified with the AutismDiagnostic Interview-Revised) and 20 determined to be TD. The participants with ASD were required to have moderateto severe GI problems, while the TD participants were required to be without GI disorders. The study consisted of 2weeks of preparing ASD participants for MTT, 8 weeks of MTT treatment followed by 8 weeks of evaluation posttreatment. TD participants did not undergo any treatment, but had fecal samples collected at the same time as ASDparticipants at the start of the study. Fecal samples were taken at four time points from the participants with ASD.Parents were instructed to freeze these sample immediately after collection for up to 3 days, and the samples werethen transported to Arizona State University on dry ice where they were stored in a -80 °C freezer. Initial fecalsamples were collected from all participants at Week 0. Samples were taken from ASD participants at the Week 3mark from the beginning of the treatment (after about 5 days of microbiota transplant) and at the end of MTT treatment(Week 10). The ASD group was sampled again 8 weeks after all treatment ceased (Week 18). Once the study concluded, aliquots of the fecal samples were shipped overnight on dry ice to Metabolon (Durham, NC,USA). Both the control and autism samples were blinded and randomized prior to being shipped. Metabolon utilizedultrahigh performance liquid chromatography-tandem mass spectroscopy (UHPLC-MS/MS) instruments for obtainingmetabolomic information on 669 metabolites. In order to ensure continuous distribution of values across allparticipants, metabolites with fewer than 40% of measurements above the detection limit were removed fromsubsequent analysis. Univariate analysis was performed on each of the remaining 583 metabolites by finding the areaunder the receiver operator curve (AUROC) for classifying between the ASD and TD cohorts at Week 0. Dependingupon what type of distribution the metabolites followed, a Wilcoxon signed-rank test or a paired t-test was performedon to determine if the ASD cohort significantly changed from Week 0 to Week 18. Using Fisher discriminant analysis (FDA), the 165 metabolites that had been identified as having an AUROC valueabove 0.60 were used to develop a multivariate model for distinguishing between the ASD and TD cohorts. Anexhaustive search was performed through all possible combinations of 2, 3, and 4 of the remaining metabolites todetermine the models which best separate the ASD and TD groups at Week 0, as determined by AUROC. A 5-metabolite model was developed by iterating through all possible 1000 top 4-metabolite models augmented by each ofthe 161 remaining metabolites. An optimized model for each metabolite number was selected based upon theaccuracy attained via leave-one-out cross validation. The optimized models were subsequently applied to ASDmeasurements taken at Week 3, Week 10, and Week 18 to examine the effects of MTT. Using kernel densityestimation, the probability density function of each model was computed. Results and Discussion Preliminary analysis using univariate methods revealed that none of the individual fecal metabolites achieved anAUROC greater than 0.8, which generally indicates poor applicability for classification. The highest univariate AUROCvalue was 0.77, corresponding to carnitine. It was observed that 10.9% of the 165 metabolites with AUROC greaterthan 0.60 significantly changed following the MTT therapy when comparing the ASD group before and after treatment.Approximately 68% of the variance observed in the fecal metabolome can be explained by the gut microbiome, whichunderscores the potential impact MTT can have on reshaping metabolite concentrations observed (Zierer et al., 2018). All optimized multivariate models using 3 or more elements were able to achieve an AUROC greater than 0.9,highlighting that a multivariate analysis can provide better classification than what can be determined using univariateanalysis alone. There were two distinct models that were identified using five separate metabolites as having achievedthe same accuracy (94.6%) after cross-validation. The constituent metabolites in these panels were largely identical(imidazole propionate, theobromine, hydroxyproline, 2-hydroxy-3-methylvalerate) apart from one containing indole andthe other adenosine. The effectiveness of the 5-metabolite fecal models for classification changed significantly beforeand after MTT. The type II error rate was initially observed to be 5% for both models but was observed to be 56% 8weeks after MTT was completed, thereby indicating that distinguishing between the ASD and TD cohort is not reliablypossible after MTT. Conclusion This study investigated differences in fecal metabolites between a group of children diagnosed with ASD and GIsymptoms and their typically developing peers with no history of GI symptoms in the context of MTT. Prior to beginningtreatment, the univariate analysis demonstrated that individual fecal metabolites had limited potential to distinguishbetween ASD+GI and TD cohorts. However, multivariate metabolite models showed the potential of fecal metabolitepanels to effectively classify ASD and TD children. Following MTT, 10.9% of metabolites that most greatly differedbetween the ASD and TD groups significantly changed. The multivariate models that had been developed prior totreatment were also unable to effectively classify between both groups. The metabolites in question that shiftedprior/post treatment may point to possible metabolite/cellular mechanisms that may be implicated in ASD, and theclassification panel could potentially serve to validate the efficacy of a course of MTT treatment.

Original languageEnglish (US)
Title of host publication2020 Virtual AIChE Annual Meeting
PublisherAmerican Institute of Chemical Engineers
ISBN (Electronic)9780816911141
StatePublished - 2020
Event2020 AIChE Annual Meeting - Virtual, Online
Duration: Nov 16 2020Nov 20 2020

Publication series

NameAIChE Annual Meeting, Conference Proceedings


Conference2020 AIChE Annual Meeting
CityVirtual, Online

ASJC Scopus subject areas

  • General Chemical Engineering
  • General Chemistry


Dive into the research topics of 'Machine learning of fecal metabolites of children with autism spectrum disorder during microbiota transfer therapy'. Together they form a unique fingerprint.

Cite this