Gut Microbiota Assessment in Obese Children and Adolescents by Machine Learning Algorithms

Abstract

Gut microbiota has been recently established to play a contributory role in the development and progression of obesity, a multifactorial disease predisposing to several comorbidities. Our aim was to evaluate the gut microbiota composition by machine learning algorithms in 33 Italian obese children and adolescents. Patients were divided in 3 groups: simple obesity (n=10, mean age 11.6 +3.0, median 10.8), metabolic syndrome (n=16, mean age 13.3+3.0, median 13.5) or Prader Willi syndrome (n=7, mean age 8.3+5.3, median 8.7). Inclusion criteria were living in Northern Italy, born singleton birth, personal history negative for acute or chronic gastrointestinal diseases and/or antibiotic or probiotics administration in the previous month. As controls 17 healthy control (mean age 12.0+2.4 median 10.6) were analyzed using the same approach. Statistical analysis for sparse high-throughput sequencing data algorithm (metagenomeSeq) using cumulative sum scaling for data normalization was performed. False discovery rate adjusted p-value using zero-inflated Gaussian fit statistical model (indicated with q). Over all analyses Parasutterella resulted with a q=0.014424, the comparison between obese patients and controls was q=0.021194. In the overall analysis Acidaminococcus intestini showed q=0.039528 while the comparison in pairs of two between metabolic syndrome and controls was q=0.03979. Using the EdgeR algorithm Clostridium bartlettii abundance between Prader Willi patients and controls resulted in q=0.02189. In overall analysis Ruminococcus flavefaciens resulted q=6.1528E-17 (using the DESeq2 algorithm); in pairs analysis Ruminococcus flavefaciens showed significant difference in Prader Willi patients as compared to obese (q=0.013755) and metabolic syndrome ones (q=0.021898). In overall analysis Veillonellaceae showed a FDR q=0.029303. while its richness resulted more than 150 times higher in metabolic syndrome patients than in controls (q=0.039793 evaluated with DESeq2 algorithm). Among Veillonellaceae descendants, the Veillonella rogosae showed, on the contrary, the lowest abundance in metabolic syndrome patients as compared to other groups. In detail, Veillonella rogosae abundances were 13 (FDR q=0.014566), around 20 times (FDR q=0.010646) and >20 (FDR q=0.0025008) less abundant in metabolic syndrome patients than obese, Prader Willi patients and controls, respectively. Significant differences in gut microbiota composition was found among patients with different degrees of obesity and controls. Further, Prader Willi patients showed a peculiar microbiota assessment.