Differences in the Gut Microbiome of Young Adults with Schizophrenia Spectrum Disorder: Using Machine Learning to Distinguish Cases from Controls

While an association between the gut microbiome and schizophrenia spectrum disorders (SSD) has been suggested, the existing evidence is still inconclusive. To this end, we analyzed bacteria and bacterial genes in feces from 52 young adult SSD patients and 52 controls using fecal shotgun metagenomic sequencing. Compared to controls, young SSD patients were found to have significantly lower α-diversity and different β-diversity both regarding bacterial species (i.e., taxonomic diversity) and bacterial genes (i.e., functional diversity). Furthermore, the α-diversity measures 'Pielou's evenness' and 'Shannon' were significantly higher for both bacterial species, bacterial genes encoding enzymes and gut brain modules in young SSD patients on antipsychotic treatment (young SSD not on antipsychotics=9 patients, young SSD on antipsychotics=43 patients). We also applied machine learning classifiers to distinguish between young SSD patients and healthy controls based on their gut microbiome. Results showed that taxonomic and functional data classified young SSD individuals with an accuracy of ≥ 70% and with an area under the receiver operating characteristic curve (AUROC) of ≥ 0.75. Differential abundance analysis on the most important features in the classifier models revealed that most of the species with higher abundance in young SSD patients had their natural habitat in the oral cavity. In addition, many of the modules with higher abundance in young SSD patients were amino acid biosynthesis modules. Moreover, the abundances of gut-brain modules of butyrate synthesis and acetate degradation were lower in the SSD patients compared to controls. Collectively, our findings continue to support the presence of gut microbiome alterations in SSD and provide support for the use of machine learning algorithms to distinguish patients from controls based on gut microbiome profiles.