Stool phospholipid signature is altered by diet and tumors

Abstract

Intake of saturated fat is a risk factor for ulcerative colitis (UC) and colon cancer. Changes in the microbiota have been implicated in the development of UC and colon cancer. The host and the microbiota generate metabolites that may contribute to or reflect disease pathogenesis. We used lipid class specific quantitative mass spectrometry to assess the phospholipid (PL) profile (phosphatidylcholine [PC], phosphatidylethanolamine [PE], phosphatidylinositol [PI], phosphatidylserine [PS]) of stool from mice fed a high fat (HFD) or control diet with or without induction of colitis-associated tumors using azoxymethane and dextran sodium sulfate. The microbiota was assessed using qPCR for several bacterial groups. Colitis-associated tumors were associated with reduced bulk PI and PE levels in control diet fed mice compared to untreated mice. Significant decreases in the relative quantities of several PC species were found in colitis-associated tumor bearing mice fed either diet. Statistical analysis of the PL profile revealed distinct clustering by treatment group. Partial least squares regression analysis found that the relative quantities of the PS class profile best predicted bacterial abundance of Clostridium leptum and Prevotella groups. Abundance of selected PL species correlated with bacterial group quantities. Thus, we have described that a HFD and colitis-associated tumors are associated with changes in phospholipids and may reflect host-microbial interactions and disease states.

Figure 1. Schematic of analysis groups in study.

Figure 2. Outcome of feeding a HFD and tumor induction.

A) Weight change over the course of the 10 week experiment. Weight change from the beginning of the experiment is plotted. Significance determined by Two-Way ANOVA compared to Ctl diet no Tx. Bonferroni post-hoc test. B) Length of excised colons was measured (cm). Bars represent means ±SD. Significance determined by unpaired t test compared to untreated dietary control. C) Tumors were visually counted in the colons of mice at the end of the treatment period. Bars represent means ±SD. Significance determined by unpaired t-test. Ctl diet AOM-DSS n = 4, HFD AOM-DSS n = 6. D) Representative electrospray ionization mass spectrometric analyses of phospholipid class. Arrows represents the internal standard. Precursor ion scan (PIS) for PC was conducted in positive ion mode with internal standard at 650.14 m/z. Precursor ion scan for PE was conducted in negative ion mode with internal standard at 742.58 m/z. Precursor ion scan for PI was conducted in negative ion mode with internal standard at 860.96 m/z. Representative neutral loss scan (NLS) for PS was conducted in negative ion mode with internal standard at 787.45 m/z. Significance demonstrated as ***p<0.001, **p<0.01, *p<0.05.

Figure 3. Quantities and distribution of lipid classes recovered from stool samples.

Calculated pmol/g stool values for all detected peaks (both identified and unidentified) from representative class specific spectra were summed for each class of phospholipid. A) The bulk amount of each phospholipid class as determined above is graphed for each treatment group. Comparisons between untreated and AOM-DSS treated animals were analyzed by unpaired t-test. Bars represent mean ± SD, p values as indicated. B) The normalized pmol quantities of PLs were graphed. Chain lengths were summed and similar lengths combined to reduce complexity. Simpson's reciprocal diversity index for each treatment was calculated to determine α diversity. Bars represent means.

Figure 4. Distinct group clustering and signature expression profile of stool phospholipids.

A–E) Partial least squares – discriminant analysis was performed on the PL profile of all the treatment groups combined (A) or in specific comparisons (B–E). Plots were generated using Multibase add-in for Excel. Bar graphs were generated using the relative pmol/g normalized stool weight quantities of the identified PL species from all four PL classes. B–E) Relative quantities of PLs were compared between treatment groups. The top 30 differential relative quantities between the treatment groups analyzed are presented. Bars represent mean ± SD. Each class of PL was analyzed separately. Significance determined by Two-way ANOVA, Bonferroni post-hoc test, **** = p<0.0001, *** = p<0.001, ** = p<0.01, * = p<0.05.

Figure 5. Low frequency species map.

Phospholipid species that were present at low frequencies (less than 50%) in at least one of the four treatment groups were assembled into a list. Species that were not present in at least half of the samples in any one other group were removed. The frequency occurrence of each species was mapped by CIMminer. Phospholipid species and treatment groups were clustered by Euclidean distance.

Figure 6. Correlations of relative bacterial abundance with PL levels.

A) Relative quantities of bacterial groups were assessed in stool of treatment groups by qPCR. B) Partial least squares – discriminant analysis to determine grouping and clustering of samples was performed on ARISA data from stool samples. C) Partial-least squares regression was performed using the relative quantities of lipid species to predict the relative quantity of bacterial groups. The PS lipid class was the best predictor of bacterial group relative quantities. Significance of correlation between the observed and estimated values computed by partial least squares regression was determined by Pearson correlation. D) Significantly correlated PL species and bacterial groups (by Pearson correlation) were assembled into a list. The non-linear R² value for the interaction between PL species quantities and bacterial quantities were then manually manipulated to reflect the direction of the interaction. These values were mapped by a one-matrix heat map (CIMminer). Phospholipids and bacterial groups were clustered by Euclidean distance.