Glucagon-like peptide-2 regulates release of chylomicrons from the intestine

Abstract

Background & aims: The intestine efficiently incorporates and rapidly secretes dietary fat as chylomicrons (lipoprotein particles comprising triglycerides, phospholipids, cholesterol, and proteins) that contain the apolipoprotein isoform apoB-48. The gut can store lipids for many hours after their ingestion, and release them in chylomicrons in response to oral glucose, sham feeding, or unidentified stimuli. The gut hormone glucagon-like peptide-2 (GLP-2) facilitates intestinal absorption of lipids, but its role in chylomicron secretion in human beings is unknown.

Methods: We performed a randomized, single-blind, cross-over study, with 2 study visits 4 weeks apart, to assess the effects of GLP-2 administration on triglyceride-rich lipoprotein (TRL) apoB-48 in 6 healthy men compared with placebo. Subjects underwent constant intraduodenal feeding, with a pancreatic clamp and primed constant infusion of deuterated leucine. In a separate randomized, single-blind, cross-over validation study, 6 additional healthy men ingested a high-fat meal containing retinyl palmitate and were given either GLP-2 or placebo 7 hours later with measurement of TRL triglyceride, TRL retinyl palmitate, and TRL apoB-48 levels.

Results: GLP-2 administration resulted in a rapid (within 30 minutes) and transient increase in the concentration of TRL apoB-48, compared with placebo (P = .03). Mathematic modeling of stable isotope enrichment and the mass of the TRL apoB-48 suggested that the increase resulted from the release of stored, presynthesized apoB-48 from the gut. In the validation study, administration of GLP-2 at 7 hours after the meal, in the absence of additional food intake, robustly increased levels of TRL triglycerides (P = .007), TRL retinyl palmitate (P = .002), and TRL apoB-48 (P = .04) compared with placebo.

Conclusions: Administration of GLP-2 to men causes the release of chylomicrons that comprise previously synthesized and stored apoB-48 and lipids. This transiently increases TRL apoB-48 levels compared with placebo. Clinical trials number at www.clinicaltrials.gov: NCT 01958775.

Trial registration: ClinicalTrials.gov NCT01958775.

Keywords: Enterocyte; Fatty Acid; Human Trial; Plasma Lipid.

Figure 1

(A) Outline of lipoprotein kinetic study (study A). Volunteers had a nasoduodenal tube inserted the day before the study. After an overnight fast, a liquid mixed macronutrient formula was infused through the nasoduodenal tube for 15 hours from 4 AM on the day of the study. A pancreatic clamp (with infusion of somatostatin, insulin, glucagon, and growth hormone) was started at 7 AM. TRL kinetics were studied with a primed, constant infusion of deuterated leucine (d3-leucine) for 10 hours starting at 9 AM. At 9 AM volunteers received a subcutaneous dose of either GLP-2 (1500 ug) or placebo. NPO, Nil per oral except water. (B) Multicompartmental model for analysis of TRL apoB-100 kinetics and TRL apoB-48 placebo treatment. Infused d3-leucine enters the plasma amino acid pool (PAA) (compartment 1). After a delay (compartment 2), it is incorporated into TRL apoB (compartment 3). Enrichment time-course curves were analyzed with the multicompartmental model to derive FCR.

Figure 2

Mean (n = 6) plasma (A) TG concentration, (B) TRL TG, (C) TRL apo-B48, and (D) TRL apoB-100 concentrations after subcutaneous administration of either GLP-2 or placebo (placebo, black diamond and dotted line; GLP-2, black square and solid line) was assessed during the course of the kinetic study. The mean AUC for the first 3 hours after either GLP-2 or placebo administration is shown in the inset for each of these parameters (placebo, white bar; GLP-2, black bar). (A) GLP-2 treatment caused a transient increase in plasma TG level with a significant increase in both AUC in the first 3 hours and peak concentration at 1 hour. ^†P = .03, *P = .03. (B) There was no change in TRL TG concentration as assessed by AUC in the first 3 hours and peak concentration at 1 hour. (C) GLP-2 treatment caused a transient increase in TRL apoB-48 concentration, with a significant increase in both AUC in the first 3 hours and peak concentration at 1 hour. ^††P = .02, **P = .02. (D) GLP-2 did not affect TRL apoB-100 concentration.

Figure 3

(A) Mean TRL apoB-100 enrichment for the duration of the study for placebo and GLP-2 are depicted. Both model generated curves (placebo, dotted line; GLP-2, solid line) and actual data are shown (placebo, black diamond; GLP-2, black square). MFL: Mole fraction labeled. (B) Steady state multi-compartmental modeling was carried out to assess TRL apoB-100 FCR (fractional catabolic rate) and PR (production rate) (placebo, white bars; GLP-2, black bars). There were no significant differences in either FCR or PR between GLP-2 and placebo treatments. (C) Mean TRL apoB-48 enrichment for the duration of the study for placebo and GLP-2 treatments are depicted. Both models generated curves (placebo, dotted line; GLP-2, solid line) and actual data are shown (placebo, black diamond; GLP-2, black square).

Figure 4

(A, B) Non-steady state modeling of TRL apoB-48 kinetics after GLP-2 administration (Hypothesis 1) was carried out. This model hypothesizes that GLP-2 transiently increases TRL apoB-48 de novo synthesis (production rate, PR) and the FCR is constant over time. TRL apoB-48 concentrations (A, solid line) and TRL apoB-48 enrichment (B, solid line) predicted by this model are compared to actual values (black squares). This hypothesis was consistent with the observed transient increase in TRL apoB-48 concentration, but it predicted that TRL apoB-48 enrichment was much higher than the actual values during the early time points. (C, D) Non-steady state modeling of TRL apoB-48 kinetics after GLP-2 administration (Hypothesis 2) was carried out. This model hypothesizes that GLP-2 transiently decreases TRL apoB-48 FCR and the PR of de novo synthesized apoB-48 is constant over time. TRL apoB-48 concentrations (C, solid line) and TRL apoB-48 enrichment (D, solid line) predicted by this model are compared to actual values (black squares). This hypothesis was consistent with the measured TRL apoB-48 enrichment, but was inconsistent with measured TRL apoB-48 concentrations. (E, F) Non-steady state modeling of TRL apoB-48 kinetics after GLP-2 administration (Hypothesis 3) was carried out. This model predicts that GLP-2 transiently releases unlabelled TRL apoB-48 into the circulation and the PR of newly synthesized apoB-48 and FCR are constant over time. TRL apoB-48 concentrations (E, solid line) and TRL apoB-48 enrichment (F, solid line) predicted by this model are compared to actual values (black squares). This hypothesis was consistent with both the measured TRL apoB-48 concentrations and enrichments.

Figure 5

(A) Outline of Study B. Volunteers ingested a liquid meal along with 120,000 IU of vitamin A (retinyl palmitate) at 7 am (T = −7 hours). At 2 pm (T = 0 hours) volunteers received a subcutaneous dose of either GLP-2 (1500 mcg) or placebo and blood sampling was performed for a further 3 hours until 5 pm (T = 3 hours). No food was permitted after ingestion of the meal at 7 am until 5 pm. Representative (n = 1) concentration curve of (B) plasma triglyceride (TG), (C) triglyceride rich lipoprotein (TRL) TG, and (D) TRL retinyl palmitate from a single volunteer (placebo, black diamond and dotted line; GLP-2, black square and solid line) following ingestion of the liquid meal containing retinyl palmitate at −7 hours. GLP-2 or placebo was administered at 0 hours. GLP-2 acutely increased the concentration or all of these parameters for approximately 2 hours following its administration.

Figure 6

(A–D) Bar charts illustrating the mean (n = 6) incremental AUC curve vs time (with the T = 0 hour concentration taken as the baseline) (positive bars above zero indicate an increase in concentration and negative bars below zero indicate a decrease in concentration) for the first 3 hours after administration of either GLP-2 or placebo at T = 0 (placebo, white bar and black outline; GLP-2, black bar) for the following parameters: (A) plasma TG, (B) TRL TG, (C) TRL retinyl palmitate, and (D) TRL apoB-48. GLP-2 significantly increased plasma TG (^‡P = .01), TRL TG (^‡‡P .007), TRL retinyl palmitate (^‡‡‡P = .002), and TRL apoB-48 (^¶P = .04) concentrations compared with a decrease in these parameters with placebo. (E) Mean concentration curves of chylomicron retinyl palmitate immediately before (T = 0 hours) and up to 60 minutes after administration of GLP-2 and placebo (placebo, black diamond and dotted line; GLP-2, black square and solid line) (n = 5). GLP-2 significantly increased the chylomicron retinyl palmitate concentration at 60 minutes (^¶¶P = .003).