Behavioral metabolomics: how behavioral data can guide metabolomics research on neuropsychiatric disorders

Abstract

Introduction: Metabolomics produces vast quantities of data but determining which metabolites are the most relevant to the disease or disorder of interest can be challenging.

Objectives: This study sought to demonstrate how behavioral models of psychiatric disorders can be combined with metabolomics research to overcome this limitation.

Methods: We designed a preclinical, untargeted metabolomics procedure, that focuses on the determination of central metabolites relevant to substance use disorders that are (a) associated with changes in behavior produced by acute drug exposure and (b) impacted by repeated drug exposure. Untargeted metabolomics analysis was carried out on liquid chromatography-mass spectrometry data obtained from 336 microdialysis samples. Samples were collected from the medial striatum of male Sprague-Dawley (N = 21) rats whilst behavioral data were simultaneously collected as part of a (±)-3,4-methylenedioxymethamphetamine (MDMA)-induced behavioral sensitization experiment. Analysis was conducted by orthogonal partial least squares, where the Y variable was the behavioral data, and the X variables were the relative concentrations of the 737 detected features.

Results: MDMA and its derivatives, serotonin, and several dopamine/norepinephrine metabolites were the greatest predictors of acute MDMA-produced behavior. Subsequent univariate analyses showed that repeated MDMA exposure produced significant changes in MDMA metabolism, which may contribute to the increased abuse liability of the drug as a function of repeated exposure.

Conclusion: These findings highlight how the inclusion of behavioral data can guide metabolomics data analysis and increase the relevance of the results to the phenotype of interest.

Keywords: Addiction; Behavior; LCMS; MDMA; Metabolomics; Sensitization.

Fig. 1

Results of PCA on LC-MS metabolomics data collected from 336 microdialysis samples. a) 3D scores plot of the first three components with samples shaded according to acute MDMA dose (baseline [BL; green], 0.0 [blue], 5.0 [yellow], 10.0 [red] mg/kg). Ellipse/sphere represents Hotelling T2 (95%). b) Histogram showing variable loadings for component 3 as a function of retention time. R²X values of each component are shown at the bottom of each graph

Fig. 2

Results of the OPLS model assessing variables predictive of locomotor activity. a) Scores plot showing samples shaded according to acute MDMA dose (baseline [BL; green], 0.0 [blue], 5.0 [yellow], 10.0 [red]). Ellipse represents Hotelling T2 (95%). b) Loadings plot with variables of interest highlighted in red as determined by predictive-VIP scores > 1 and orthogonal-VIP scores < 1. R²X values of each component are shown at the bottom of each graph

Fig. 3

Mean (± standard error of the mean) locomotor activity and relative concentration of select metabolites of interest as a function of time and MDMA pre-treatment group. MDMA 0.0, 5.0, and 10.0 mg/kg i.p. was administered at 120, 240, and 360 min, respectively. ^aID based on external standards. ^bID based on MS/MS fragmentation data. ^cID based on mass and adduct pattern. *p < .05, **p < .01, ***p < .001, ****p < .0001 compared to control; two-way ANOVA followed by Šidák-corrected multiple comparisons

Fig. 4

a) Q-TOF-ESI MS/MS spectra of benzoylated MDMA, MDA, HMMA, and 3-MT at 10, 20, and 40 eV collision energies. b) Proposed fragmentation of MDMA, MDA, HMMA, and 3-MT

Fig. 5

Primary metabolic pathways of MDMA and the CYP enzymes involved in both rats (R) and humans (H) (de la Torre & Farré, 2004)