Galectin-3 as a Therapeutic Target for NSAID-Induced Intestinal Ulcers

Abstract

Non-steroidal anti-inflammatory drugs (NSAIDs) induce ulcers in the gastrointestinal tract, including the stomach and small intestine. NSAID-induced gastric ulcers can be prevented by taking acid-neutralizing/inhibitory drugs and cytoprotective agents. In contrast, there are no medicines to control NSAID-induced small intestinal ulcers, which are accompanied by a mucosal invasion of bacteria and subsequent activation of immune cells. Galectin-3 (Gal3), an endogenous lectin, has anti-microbial and pro-inflammatory functions. In the small intestine, since Gal3 is highly expressed in epithelial cells constitutively and macrophages inducibly, the Gal3 level can affect microbiota composition and macrophage activation. We hypothesized that the modulation of Gal3 expression could be beneficial in NSAID-induced intestinal ulcers. Using Gal3 knockout (Gal3KO) mice, we determined whether Gal3 could be a therapeutic target in NSAID-induced intestinal ulcers. Following the administration of indomethacin, an NSAID, we found that small intestinal ulcers were less severe in Gal3KO mice than in wild-type (WT) mice. We also found that the composition of intestinal microbiota was different between WT and Gal3KO mice and that bactericidal antibiotic polymyxin B treatment significantly suppressed NSAID-induced ulcers. Furthermore, clodronate, a macrophage modulator, attenuated NSAID-induced ulcers. Therefore, Gal3 could be an exacerbating factor in NSAID-induced intestinal ulcers by affecting the intestinal microbiota population and macrophage activity. Inhibition of Gal3 may be a therapeutic strategy in NSAID-induced intestinal ulcers.

Clinical trial registration: www.ClinicalTrials.gov, identifier NCT03832946.

Keywords: 16S rRNA; PAS stain; adverse effect; animal model; cyclooxygenase-2 inhibitors; gastrointestinal flora; microbiome; small intestine.

FIGURE 1

Galectin-3 (Gal3) and mucin staining. (A) We conducted immunohistochemistry with anti-Gal3 antibody (BioLegend, San Diego, CA, United States) using a Histofine SAB-PO kit (Nichirei Biosciences; Tokyo, Japan), in 4-μm thick small intestine sections of wild-type (WT) and Gal3 knockout (Gal3KO) mice. Gal3 was stained brown, and nuclei were counterstained with hematoxylin (blue). In WT mice, we found moderate Gal3 staining in the cytoplasm of enterocytes (EC, black arrows) and intense staining of mononuclear cells (red arrowheads) in the lamina propria (LP). In the Peyer’s patch (PP), Gal3 positive cells were detected in the subepithelial dome region (SED), but not in the germinal center (GC). Gal3KO mice had no Gal3 positive cells. The middle grayscale panels were shown to indicate anatomical structures. EP, epithelium. (B) Periodic acid-Schiff (PAS) staining of intestine sections of WT and Gal3KO mice. The cytoplasm of goblet cells (black arrowheads) and the luminal surface of enterocytes were stained purple-magenta due to the presence of mucins.

FIGURE 2

Indomethacin (Indo)-induced small intestinal ulcers. We treated WT and Gal3KO mice with Indo, and 18 h later, harvested the small intestines (n = 7 per group). We determined the Indo concentration 5 mg/kg body weight by “Human equivalent dose calculation” (42). Indo (FUJIFILM Wako, Osaka, Japan) was solved in a 0.5% NaHCO₃ solution and administrated to non-fasted mice by using a stomach tube. (A) We opened the small intestine along the anti-mesenteric side, and took macroscopic images with a scale by a digital camera (Canon, Tokyo, Japan). Representative macroscopic images of the jejunum from WT (ulcer score = 3) and Gal3KO mice (ulcer score = 0). Bar = 10 mm. (B) The ulcer severity was assessed using the ulcer score (23) with modification. The macroscopic ulceration areas were captured and quantified by an ImageJ software (NIH, Bethesda, MD, United States) and summed per jejunum. The entire jejunum areas were similar in all mice examined and were around 1,200 mm². We used the modified ulcer score as follows: 0 = no lesion, 1 = less than 5 mm², 2 = 5∼20 mm², 3 = 21∼40 mm², 4 = 41∼70 mm², and 5 = more than 71 mm². *P < 0.05 by the Mann–Whitney U test. (C) Small intestine lesions, 18 h after Indo administration. We stained formalin-fixed paraffin sections with hematoxylin and eosin, anti-F4/80 antibody (AbD Serotec, Kidlington, United Kingdom) for macrophages, and anti-Ly6G antibody (BD Biosciences, San Jose, CA, United States) for neutrophils. Bar = 50 μm.

FIGURE 3

Fecal occult blood (FOB) of Indo-administered mice. FOB levels were higher in Indo-administered WT mice (○) than in Gal3KO mice (●). Without Indo administration, FOB was not detectable in WT mice (△) or Gal3KO mice (▲). +Indo groups, n = 7; –Ind groups, n = 3. *P < 0.05 WT+Indo versus Gal3KO+Indo by the Student t-test; count per second. FOB level was determined as described previously (43). Feces were suspended in distilled water and centrifuged at 12,000 × g. The supernatant was mixed with the luminol reagent (FUJIFILM Wako), and then chemiluminescence was measured by a luminometer (Wallac ARVO SX 1420 multilabel counter, PerkinElmer, Waltham, MA, United States).

FIGURE 4

Glucuronidase activity of fecal bacteria. Fecal suspension from naïve WT (○) and Gal3KO mice (●) were prepared (n = 7). To determine β-glucuronidase activities, we incubated 20 μL of the fecal suspension with 180 μL of the reaction mixture containing 1 mM p-nitrophenyl-β-D-glucuronide, 50 mM HEPES-HCl (pH 7.4), and 37.2 mM 2-mercaptoethanol at 37°C for 30 min. The optical density (OD) was measured at 405 nm every 5 min (24). ΔOD: OD changes per 1 min.

FIGURE 5

Small intestinal microbial reduction by antibiotics and Indo-induced intestinal ulcers in WT mice. We treated WT mice with unabsorbable antibiotics, polymyxin B (PolyB, 0.5 mg/mL, Pfizer Inc., New York, NY, United States) or neomycin (Neo, 1 mg/mL, Thermo Fisher Scientific, Waltham, MA, United States) in drinking water. (A) On day 6, we killed mice and harvested small intestinal contents. We prepared suspensions of the contents in water and conducted Gram staining (FUJIFILM Wako). (B) On day 6, Indo was administrated, and 18 h later, we harvested, rinsed the small intestine, and took macroscopic images (n = 5). Representative images of the jejunum. Bar = 10 mm. (C) PolyB-treated mice had lower ulcer scores than the control (Con) and Neo-treated mice. Ulcer severities were determined by the modified ulcer scores. **P < 0.01; *P < 0.05 by the ANOVA with post hoc Tukey test.

FIGURE 6

Clodronate injection and Indo-induced intestinal ulcers in WT mice. We injected clodronate (Clod) intraperitoneally into WT mice. The next day, we administered Indo and killed mice 18 h later. We harvested and rinsed the small intestines, and took macroscopic images (n = 5). (A) Representative images of the jejunum from Indo-administered mice without Clod treatment (+Indo) showed more severe ulcers than mice treated with Clod (Clod+Indo). Bar = 10 mm. (B) Ulcer severities were determined by the modified ulcer scores. *P < 0.05 by the Mann–Whitney U test.