All experiments were approved by the animal ethics committee of the University of Western Australia (Perth, Australia).

The animal model and experimental procedures were previously described (18). Briefly, 39 date-mated merino ewes were randomly assigned to six different groups of between five and eight animals to receive IA injections under ultrasound guidance. Verification of the IA injections was done by amniotic fluid electrolyte analysis. The date-mated pregnant ewes received an IA injection of an in vitro cultured strain HPA5 of UP serovar 3 (2 × 10⁵ color-changing units, CCU) (28) 42 days prior to delivery (at 82 days of gestation, which corresponds to the second trimester in humans) or Escherichia coli-derived LPS (O55:B5; Merck, Darmstadt, Germany), 10 mg in 2 ml of saline, 2 or 7 days prior to delivery (at respectively, 122 and 117 days of gestation). Previously, we have shown that the half-life time of LPS in the amniotic fluid is relatively long (1.7 days) and that the LPS amount is higher than the essential threshold of 1 mg for at least 5 days (29, 30). Chronic sustained UP infection was confirmed by positive culture of amniocentesis samples at intermediate time points and sterile amniotic fluid samples collected at cesarean delivery, as previously described (31). Two or seven days LPS exposure (prior to cesarean delivery) represents an acute inflammatory challenge. To evaluate the combined effect between these inflammatory modalities, a subgroup of chronically UP-infected ewes received IA LPS at 35 and 40 days post-UP infection (i.e., 7 or 2 days LPS exposure prior to delivery following 42 days of UP infection). A group receiving IA injections of sterile saline (2 or 7 days prior to delivery, respectively six and two animals which were pooled) served as controls (Figure 1). Fetuses were surgically delivered at 124 ± 2 days of gestational age (term gestation in sheep = 150 days), equivalent of ~30 weeks of human gestation. After delivery, fetuses were euthanized with intravenous pentobarbitone (100 mg/kg). For this experiment, fetuses of both sexes were used.

During necropsy, blood and terminal ileum samples were collected. Ileum samples were fixed in 10% formalin and embedded in paraffin, or snap frozen in liquid nitrogen. Where insufficient paraffin-embedded material was available for study, additional material was generated by paraffin embedding snap-frozen tissue samples: frozen tissue blocks were defrosted, fixed in 4% formaldehyde at room temperature overnight, and transferred to 70% ethanol prior to embedding in paraffin with the use of a vacuum infiltration processor.

The following antibodies were used for immunohistochemistry: polyclonal rabbit anti-myeloperoxidase (MPO; A0398, Dakocytomation, Glostrup, Denmark) for the identification of neutrophils, polyclonal rabbit anti-cluster of differentiation 3 (CD3; A0452, Dakocytomation) for the detection of T cells, polyclonal rabbit anti-bovine protein gene product 9.5 (PGP9.5; Z5116, Dakocytomation) for the detection of enteric neurons, polyclonal rabbit anti-doublecortin (Ab18723, Abcam, Cambridge, UK) for the detection of immature neurons, polyclonal rabbit anti-glial fibrillary acidic protein (GFAP; Zo334, Dakocytomation) to detect enteric glial cell reactivity/activation (32), and polyclonal rabbit anti-S100β (PA5-16257, Invitrogen, Carlsbad, CA, USA) as a marker for enteric glial cells.

The following secondary antibodies were used: peroxidase-conjugated polyclonal goat anti-rabbit (111-035-045, Jackson, West Grove, PA, USA) (MPO), peroxidase-conjugated polyclonal swine anti-rabbit (P0399, DakoCytomation) (doublecortin) and BrightVision+ Poly-HRP-Anti Mouse/Rabbit IgG biotin-free (ImmunoLogic, Duiven, Netherlands) (PGP9.5), and biotin-conjugated polyclonal swine anti-rabbit (E0353, DakoCytomation) (CD3, GFAP, S100β).

Formalin-fixed terminal ileum was embedded in paraffin and 4 μm sections were cut. After deparaffinization and rehydration, endogenous peroxidase activity was blocked with 0.3% H₂O₂ diluted in phosphorylated buffer saline (PBS, pH 7.4). Antigen retrieval was performed with citrate buffer for CD3, PGP9.5, doublecortin, and S100β stainings. Non-specific binding was blocked for 30 min at room temperature with 10% normal goat serum (NGS) in PBS (MPO), 5% NGS in PBS (doublecortin), or 5% bovine serum albumin (BSA) in PBS (CD3, GFAP, and S100β). For PGP9.5, non-specific binding was blocked for 10 min at room temperature with 20% fetal calf serum (FCS). Thereafter, sections were incubated with the primary antibody of interest and subsequently incubated with the respective secondary antibody. MPO, PGP9.5, and doublecortin were detected by using a peroxidase-conjugated secondary antibody and antibodies against CD3, GFAP, and S100β were detected with avidin–biotin complex (Vectastain Elite ABC kit, Bio-connect, Huissen, Netherlands). Substrate staining was performed for MPO with 3-amino-9-ethylcarbazole (AEC; Merck, Darmstadt, Germany). Immunoreactivity for CD3 and GFAP was detected by using nickel-DAB. Immunoreactivity for PGP9.5, doublecortin, and S100β was detected by using DAB. Hematoxylin (MPO, PGP9.5, doublecortin, and S100β) or nuclear fast red (CD3 and GFAP) was used as a counterstain for nuclei.

H&E slides were analyzed by two independent investigators blinded to the experimental setup to assess damage of the terminal ileum. A scoring system from 0 to 4 was used to describe the severity of histological injury. Scoring was as follows: 0, no damage; 1, disrupted epithelial lining, but no loss of enterocytes; 2, disrupted epithelial lining, mild enterocyte loss from the villus tips; 3, disrupted epithelial lining, moderate enterocyte loss from villus tips, some debris in the lumen; and 4, abundant enterocyte loss from villus tips, abundant debris in the lumen, and severe shedding of villus tips.

The stained tissue sections were scanned with the Ventana iScan HT slide scanner (Ventana Medical Systems, Oro Valley, AZ, USA). Of these images, viewed with Panoramic Viewer (version 1.15.4, 3DHISTECH, Budapest, Hungary), random images of regions of interest were taken (×200).

Two investigators blinded to the study groups counted the MPO- and CD3-positive cells in three to five non-overlapping high-power fields in the mucosa and submucosa. The average MPO- and CD3-positive cells per area are reported for each animal. The percentage of area in the submucosal and myenteric ganglia positively stained for PGP9.5, doublecortin, GFAP, and S100β was determined in five non-overlapping high-power fields using Leica QWin Pro software (version 3.4.0, Leica Microsystems, Mannheim, Germany) by an investigator blinded to the study groups. Relative area staining was calculated by dividing the positively stained areas of the ganglia of the submucosal or myenteric plexus by the total area of the muscle layer. The data are expressed as fold increase over the control value.

RNA was extracted from snap-frozen terminal ileum tissue using TRI reagent (Invitrogen)/chloroform extraction. Isolated RNA was DNase treated to remove possible contamination with genomic DNA by using the RQ1 RNase-Free DNase kit (Promega, Madison, WI, USA) and afterwards reverse transcribed into cDNA using oligo(dT)12–18 primers (Invitrogen) and Moloney murine leukemia virus (M-MLV) reverse transcriptase (Invitrogen). Quantitative real-time PCR (qPCR) reactions were performed with a LightCycler 480 Instrument (Roche Applied Science, Basel, Switzerland) using the SensiMix™ SYBR® No-ROX kit (Bioline, London, UK) for 45 cycles. The mRNA levels of IL-1β, IL-6, IL-10, tumor necrosis factor alpha (TNF-α), and interleukin-1 receptor-associated kinase 3 (IRAK3) were determined to assess inflammation of the terminal ileum. The mRNA levels of neuronal nitric oxide synthase (nNOS) and choline acetyltransferase (CHAT) were determined to assess the motility signaling functions of the ENS using LinRegPCR software (version 2016.0, Heart Failure Research Center, Academic Medical Center, Amsterdam, Netherlands). The geometric mean of the mRNA levels of three reference genes [ribosomal protein S15 (RPS15), glyceraldehyde 3-phosphate dehydrogenase (GAPDH), and peptidylprolyl isomerase A (PPIA)] were calculated and used as a normalization factor. The data are expressed as fold increase over the control value. The primer sequences are shown in Table 1.

Data are presented as median with interquartile range. Statistical analyses were performed using GraphPad Prism (version 6.01, GraphPad Software Inc., La Jolla, CA, USA). A non-parametric Kruskal–Wallis test followed by Dunn's post hoc test was used to analyze statistically significant group differences. Differences were considered statistically significant at p < 0.05. Given the relatively small animal numbers per group, we also reported actual p values between p ≥ 0.05 and p < 0.10 and interpreted these as potentially biologically relevant. This assumption will decrease the chance of a type II error, but increases the chance of a type I error.

There was a higher intestinal damage score for all experimental groups compared to the control (p < 0.005 for the 7 days LPS group, p < 0.05 for the 42 days UP group and 42 days UP + 7 days LPS group, and p = 0.06 for the 42 days UP + 2 days LPS group all compared to the control; Figure 2), except for the animals exposed to 2 days of LPS. Pre-exposure with UP did not augment mucosal injury in the LPS-treated groups.

A statistically significant increase in MPO-positive cells was seen in the mucosa 7 days after LPS exposure compared to the control (p < 0.05; Figure 3). Chronic UP infection also caused an elevation of mucosal MPO-positive cells compared to the control (p = 0.08; Figure 3). Furthermore, combining these two inflammatory insults resulted in an increased mucosal MPO-positive cell count compared to the control (p < 0.005; Figure 3), and this experimental group tended to be increased when compared to the UP + 2 days LPS-exposed group (p = 0.07; Figure 3). LPS exposure 2 days prior to delivery was insufficient to induce mucosal MPO-positive cell infiltration. Pre-exposure to UP in combination with LPS administration did not alter the number of mucosal MPO-positive cells compared to LPS alone, both after 2 and 7 days.

While chronic UP infection and acute LPS exposure 2 days pre-delivery did not have any effect on mucosal CD3-positive T cell presence, those animals receiving LPS 7 days pre-delivery (both uninfected and chronic UP-infected groups) as well as chronic UP-infected animals receiving LPS 2 days pre-delivery all showed apparent elevated levels of CD3-positive T cell infiltration (Figure 4). However, the only comparison to achieve p < 0.05 significance was that of uninfected and chronic UP-infected animals receiving LPS 2 days pre-delivery (Figure 4).

For investigation of submucosal inflammation, there was an increase of MPO-positive cells in the 7 days LPS group and submucosal MPO-positive cells tended to be increased in the chronic UP infection group compared to the control (p < 0.05 and p = 0.06; Figure 5). Additional acute LPS insult (2 or 7 days pre-delivery) in chronic UP-infected animals resulted in increased variability and loss of significance in the MPO cell infiltration compared to 2 or 7 days of LPS alone.

The greatest increase of submucosal CD3-positive cells was observed in 2 day LPS-exposed chronic UP-infected animals, which was significantly increased compared to the control or acute 2 day LPS stimulation alone (both p < 0.05; Figure 6) and appeared more potent than in chronic UP-infected animals receiving LPS at 7 days pre-delivery (p = 0.08; Figure 6).

Examination of underlying cytokine levels revealed increased IL-1β mRNA levels only in the uninfected or chronic UP-infected animals when LPS was administered 2 days pre-delivery (p < 0.05 compared to the 7 days LPS group, p < 0.01 compared to the 42 days UP group, p < 0.05 compared to the 42 days UP + 7 days LPS group, and p < 0.05 compared to the control, respectively; Figure 7A), whereas IL-1β mRNA levels had dropped to baseline again if LPS was administered 7 days pre-delivery (Figure 7A). IL-6 and IL-10 mRNA levels were not altered (data not shown), and the only group showing apparent TNF-α mRNA level elevation was that of the chronic UP-infected animals additionally receiving LPS 2 days pre-delivery (p = 0.07; Figure 7B).

IRAK3 mRNA levels were increased significantly only in animals exposed to 2 days of LPS alone compared to the control (p < 0.05; Figure 7C).

The PGP9.5-positive surface area in the submucosal plexus tended to be decreased in animals chronically infected for 42 days with UP compared to the control (p = 0.08; Figure 8). Similarly, chronic UP-infected animals had a diminished PGP9.5-positive surface area in the myenteric plexus (p < 0.05; Figure 8). Doublecortin-positive surface areas were not altered in either the submucosal or the myenteric plexus (data not shown).

In the submucosal plexus, the GFAP-positive surface area tended to be increased in groups receiving LPS either 2 or 7 days pre-delivery compared to the control (p = 0.07 and p = 0.09; Figure 9), while in the myenteric plexus, the GFAP-positive surface area was only increased in the group receiving LPS 7 days pre-delivery compared to the control (p < 0.05; Figure 9). For both of these regions, concomitant chronic infection by UP appeared to mute these effects.

S100β-positive surface areas were unaltered in the submucosal plexus for all conditions (data not shown), while in the myenteric plexus, the S100β-positive surface area was significantly decreased in the chronic UP-infected group compared to the control (p < 0.05; Figure 10), but this effect appeared to be counteracted by acute stimulation by LPS at either 2 or 7 days pre-delivery. No differences in nNOS and CHAT expression were observed between the groups (data not shown).

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. The handling editor declared a past co-authorship with several of the authors TW, BK.