Noninvasive stool-based detection of infant gastrointestinal development using gene expression profiles from exfoliated epithelial cells

Abstract

We have developed a novel molecular methodology that utilizes stool samples containing intact sloughed epithelial cells to quantify intestinal gene expression profiles in the developing human neonate. Since nutrition exerts a major role in regulating neonatal intestinal development and function, our goal was to identify gene sets (combinations) that are differentially regulated in response to infant feeding. For this purpose, fecal mRNA was isolated from exclusively breast-fed (n = 12) and formula-fed (n = 10) infants at 3 mo of age. Linear discriminant analysis was successfully used to identify the single genes and the two- to three-gene combinations that best distinguish the feeding groups. In addition, putative "master" regulatory genes were identified using coefficient of determination analysis. These results support our premise that mRNA isolated from stool has value in terms of characterizing the epigenetic mechanisms underlying the developmentally regulated transcriptional activation/repression of genes known to modulate gastrointestinal function. As larger data sets become available, this methodology can be extended to validation and, ultimately, identification of the main nutritional components that modulate intestinal maturation and function.

Fig. 1.

Linear discriminant analysis (LDA) phenotype classification using the genes endothelial PAS domain-containing protein 1 (hypoxia-inducible factor 2α, EPAS1) and uncoupling protein 2 (UCP2) provides the best-performing 2-gene feature set. Classification is between breast-fed (○) and formula-fed (△) infants (see Table 2 for additional details). Axes represent normalized intensity values of the indicated genes. Note clear separation between the groups, except for 1 outlier.

Fig. 2.

LDA phenotype classification using the genes EPAS1, forkhead box protein E3 (FOXE3), and synaptophysin (SYP) provides the best-performing 3-gene feature set. The 3-dimensional LDA hyperplane discriminates between breast-fed (○) and formula-fed (▵) infants (see Table 2 for additional details). Axes represent normalized intensity values of the corresponding genes. Note clear separation between the groups, except for 1 outlier (the same infant outlier in Fig. 1).

Fig. 3.

Association between expression patterns of genes (triple predictors) was determined using coefficient of determination (CoD). CoD measures the degree to which the transcriptional levels of an observed gene set can be used to improve the prediction of the transcriptional state of a target gene relative to the best-possible prediction in the absence of observations. Examples for the strong single-gene classifiers in Table 2, excluding tight junction protein 1 (TJP1), are shown. NR5A2, nuclear receptor subfamily 5, group A, member 2; NR3C1, nuclear receptor subfamily 3, group C, member 1; PCDH7, protocadherin 7; ITGB2, integrin-β₂; EPIM, epimorphin; BAD, Bcl2 antagonist of cell death.