Modulation of pathogen-induced CCL20 secretion from HT-29 human intestinal epithelial cells by commensal bacteria

Abstract

Background: Human intestinal epithelial cells (IECs) secrete the chemokine CCL20 in response to infection by various enteropathogenic bacteria or exposure to bacterial flagellin. CCL20 recruits immature dendritic cells and lymphocytes to target sites. Here we investigated IEC responses to various pathogenic and commensal bacteria as well as the modulatory effects of commensal bacteria on pathogen-induced CCL20 secretion. HT-29 human IECs were incubated with commensal bacteria (Bifidobacterium infantis or Lactobacillus salivarius), or with Salmonella typhimurium, its flagellin, Clostridium difficile, Mycobacterium paratuberculosis, or Mycobacterium smegmatis for varying times. In some studies, HT-29 cells were pre-treated with a commensal strain for 2 hr prior to infection or flagellin stimulation. CCL20 and interleukin (IL)-8 secretion and nuclear factor (NF)-kappaB activation were measured using enzyme-linked immunosorbent assays.

Results: Compared to untreated cells, S. typhimurium, C. difficile, M. paratuberculosis, and flagellin activated NF-kappaB and stimulated significant secretion of CCL20 and IL-8 by HT-29 cells. Conversely, B. infantis, L. salivarius or M. smegmatis did not activate NF-kappaB or augment CCL20 or IL-8 production. Treatment with B. infantis, but not L. salivarius, dose-dependently inhibited the baseline secretion of CCL20. In cells pre-treated with B. infantis, C. difficile-, S. typhimurium-, and flagellin-induced CCL20 were significantly attenuated. B. infantis did not limit M. Paratuberculosis-induced CCL20 secretion.

Conclusion: This study is the first to demonstrate that a commensal strain can attenuate CCL20 secretion in HT-29 IECs. Collectively, the data indicate that M. paratuberculosis may mediate mucosal damage and that B. infantis can exert immunomodulatory effects on IECs that mediate host responses to flagellin and flagellated enteric pathogens.

Figure 1

Intestinal epithelial cells secrete CCL20 differentially in response to various bacteria. Confluent HT-29 cells were treated with Salmonella typhimurium (1 × 10⁷ colony-forming units (CFU)/ml), flagellin (0.5 μg/ml), Clostridium difficile (1 × 10⁷ CFU/ml), an equal volume of their cell-free culture supernatants, Mycobacterium paratuberculosis (1 × 10⁸ CFU/ml), M. smegmatis (1 × 10⁸ CFU/ml), Bifidobacterium infantis (1 × 10⁷ CFU/ml), or Lactobacillus salivarius (1 × 10⁷ CFU/ml). CCL20 protein levels in cell culture supernatants were measured after 6 hr, 12 hr, or 24 hr as specified on the above graph. Significant levels of CCL20 were only detected after 12 hr incubation with M. paratuberculosis and after 24 hr with C. difficile. M. smegmatis, B. Infantis and L. Salivarius did not result in significant CCL20 secretion at any of the time points or concentrations used. The data are expressed as pg/ml CCL20 and represent the mean ± standard error (n = 7 independent experiments). *P < 0.05 relative to untreated cells.

Figure 2

Intestinal epithelial cells secrete interleukin (IL)-8 differentially in response to various bacteria. Confluent HT-29 cells were treated with Salmonella typhimurium (1 × 10⁷ colony-forming units (CFU)/ml), flagellin (0.5 μg/ml), Clostridium difficile (1 × 10⁷ CFU/ml), an equal volume of their cell-free culture supernatants, Mycobacterium paratuberculosis (1 × 10⁸CFU/ml), M. smegmatis (1 × 10⁸ CFU/ml), Bifidobacterium infantis (1 × 10⁷ CFU/ml), or Lactobacillus salivarius (1 × 10⁷ CFU/ml). IL-8 protein levels in cell culture supernatants were measured after 6 hr, 12 hr, or 24 hr as specified by enzyme-linked immunosorbent assay. The data are expressed as pg/ml IL-8 and represent the mean ± standard error (n = 7 independent experiments). *P < 0.05 relative to untreated cells.

Figure 3

Bacterial-induced NF-kB DNA binding activity in intestinal epithelial cells. HT-29 cells were untreated, or were exposed to Salmonella typhimurium (1 × 10⁷ colony forming units (CFU)/ml), flagellin (0.5 μg/ml), Clostridium difficile (1 × 10⁷ CFU/ml), or Mycobacterium paratuberculosis (1 × 10⁷ or 1 × 10⁸ CFU/ml) for 1 hr. The DNA binding activity of NF-κB p65 in HT-29 nuclear extracts was determined using an enzyme-linked immunosorbent assay-based transcription factor assay. The positive control Jurkat nuclear extract provided with the kit was used to verify assay specificity in competition assays with wild-type or mutated NF-κB oligonucleotides. The data represent the mean absorbance readings ± standard error of five separate experiments. P < 0.05 relative to untreated cells.

Figure 4

Bifidobacterium infantis attenuates the baseline secretion of CCL20 in HT-29 cells. (a) Confluent HT-29 monolayers were treated with B. infantis at doses of 1 × 10⁵, 1 × 10⁶, or 1 × 10⁷ colony-forming units/ml, and CCL20 levels were measured after 6 hr. B. infantis caused a dose-dependent inhibition of baseline CCL20 secretion by confluent HT-29 monolayers. (b) Confluent HT-29 cells were treated with 1 × 10⁷/ml live B. infantis or L. salivarius, or an equivalent dose of formalin-killed bacteria. CCL20 levels were measured after 6 hr. Both live and formalin-killed B. infantis, but not L. salivarius, restrained the baseline secretion of CCL20 by HT-29 cells. The data are expressed as CCL20 protein levels relative to untreated control cells and represent the mean ± standard error (n = 5 independent experiments). *P < 0.05 compared with untreated monolayers.

Figure 5

Bifidobacterium infantis limits Salmonella typhimurium- and flagellin-induced CCL20 secretion. (a) Confluent HT-29 monolayers were pre-treated for 2 hr with 1 × 10⁷/ml live B. infantis or Lactobacillus salivarius, or an equivalent dose of formalin-killed B. infantis prior to infection with S. typhimurium. CCL20 levels were measured 6 hr after infection. Both live and formalin-killed B. infantis restrained S. typhimurium induced CCL20 secretion (*P < 0.05 compared with S. typhimurium-infected HT-29 cells). The data are expressed as pg/ml CCL20 protein and represent the mean ± standard error (n = 8 independent experiments). (b) Confluent HT-29 monolayers were pre-treated for 2 hr with live B. infantis at doses of 1 × 10⁵, 1 × 10⁶, or 1 × 10⁷ colony-forming units/ml (left panel) or 1 × 10⁷/ml formalin-killed B. infantis (right panel). Subsequently, cells were treated with 0.5 μg/ml flagellin for 6 hr. Pre-treatment with 1 × 10⁷ live and formalin-killed significantly inhibited flagellin-induced CCL20 secretion (*P < 0.05 relative to flagellin-treated HT-29 cells). The data are expressed as CCL20 protein levels relative to flagellin-treated cells and represent the mean ± standard error (n = 7 independent experiments).

Figure 6

Bifidobacterium infantis attenuates Clostridium difficile-induced CCL20 secretion. Confluent HT-29 monolayers were pre-treated for 2 hr with 1 × 10⁷ colony-forming units/ml (CFU/ml) live B. infantis or Lactobacillus salivarius prior to infection with 1 × 10⁷ CFU/ml C. difficile bacteria or an equal volume of their cell-free supernatants, or 1 × 10⁸ CFU/ml Mycobacterium paratuberculosis. CCL20 levels were measured 12 hr or 24 hr post-treatment as indicated. B. infantis, but not L. salivarius, restrained C. difficile-induced CCL20 secretion (*P < 0.05 compared with C. difficile- treated HT-29 cells). B. infantis did not limit M. paratuberculosis-induced CCL20 secretion. The data are expressed as per cent of pathogen-induced CCL20 secretion and represent the mean ± standard error (n = 6 independent experiments).