Roux-en-Y Gastric Bypass Surgery Induces Early Plasma Metabolomic and Lipidomic Alterations in Humans Associated with Diabetes Remission

Abstract

Roux-en-Y gastric bypass (RYGB) is an effective method to attain sustained weight loss and diabetes remission. We aimed to elucidate early changes in the plasma metabolome and lipidome after RYGB. Plasma samples from 16 insulin-resistant morbidly obese subjects, of whom 14 had diabetes, were subjected to global metabolomics and lipidomics analysis at pre-surgery and 4 and 42 days after RYGB. Metabolites and lipid species were compared between time points and between subjects who were in remission and not in remission from diabetes 2 years after surgery. We found that the variables that were most discriminatory between time points were decanoic acid and octanoic acid, which were elevated 42 days after surgery, and sphingomyelins (18:1/21:0 and 18:1/23:3), which were at their lowest level 42 days after surgery. Insulin levels were lower at 4 and 42 days after surgery compared with pre-surgery levels. At 4 days after surgery, insulin levels correlated positively with metabolites of branched chain and aromatic amino acid metabolism and negatively with triglycerides with long-chain fatty acids. Of the 14 subjects with diabetes prior to surgery, 7 were in remission 2 years after surgery. The subjects in remission displayed higher pre-surgery levels of tricarboxylic acid cycle intermediates and triglycerides with long-chain fatty acids compared with subjects not in remission. Thus, metabolic alterations are induced soon after surgery and subjects with diabetes remission differ in the metabolic profiles at pre- and early post-surgery time points compared to patients not in remission.

Fig 1. Partial least square discriminant analysis of lipidomic and metabolomic profiles of the subjects (n = 16).

(A) Score plot showing clustering of subjects based on metabolomic and (B) lipidomic profiles at pre-surgery and 4 and 42 days after surgery. (C) Top 20 metabolites and (D) lipid species with their variable importance in projection (VIP) scores and relative abundance at pre-surgery and 4 and 42 days after surgery. LysoPC = lysophosphatidylcholine; PC = phosphatidylcholine; PE = phosphatidylethanolamine; SM = sphingomyelin; TG = triglycerides.

Fig 2. Spearman rank correlations of (A) metabolites (B) lipid species with insulin levels at 4 and 42 days after RYGB.

*p<0.05; **p<0.01. LysoPE = lysophosphatidylethanolamine; PC = phosphatidylcholine; PE = phosphatidylethanolamine; SM = sphingomyelin; TG = triglycerides.

Fig 3. Metabolites at (A) pre (B) 4 days and (C) 42 days after surgery and lipids at (D) pre (E) 4 days and (F) 42 days after surgery that differed significantly between patients in diabetes remission and not in remission.

*p<0.05; **p<0.01; ***p<0.001. LysoPC = lysophosphatidylcholine; N-REM = patients not in diabetes remission; PC = phosphatidylcholine; PE = phosphatidylethanolamine; REM = patients in diabetes remission; SM = sphingomyelin; TG = triglycerides.