Ecometabolomic Analysis of Wild Populations of Pilocarpus pennatifolius (Rutaceae) Using Unimodal Analyses

Abstract

Studies examining the diversity of plant specialized metabolites suggest that biotic and abiotic pressures greatly influence the qualitative and quantitative diversity found in a species. Large geographic distributions expose a species to a great variety of environmental pressures, thus providing an enormous opportunity for expression of environmental plasticity. Pilocarpus, a neotropical genus of Rutaceae, is rich in alkaloids, terpenoids, and coumarins, and is the only commercial source of the alkaloid pilocarpine for the treatment of glaucoma. Overharvesting of species in this genus for pilocarpine, has threatened natural populations of the species. The aim of this research was to understand how adaptation to environmental variation shapes the metabolome in multiple populations of the widespread species Pilocarpus pennatifolius. LCMS data from alkaloid and phenolic extracts of leaf tissue were analyzed with environmental predictors using unimodal unconstrained and constrained ordination methods for an untargeted metabolomics analysis. PLS-DA was used to further confirm the chemoecotypes of each site. The most important variables contributing to the alkaloid variation between the sites: mean temperature of wettest quarter, as well as the soil content of phosphorus, magnesium, and base saturation (V%). The most important contributing to the phenolic variation between the sites: mean temperature of the wettest quarter, temperature seasonality, calcium and soil electrical conductivity. This research will have broad implications in a variety of areas including biocontrol for pests, environmental and ecological plant physiology, and strategies for species conservation maximizing phytochemical diversity.

Keywords: Pilocarpus pennatifolius; canonical correlation analyses; chemoecotype; ecological metabolomics; ecophysiology; unimodal ordination.

FIGURE 1

Correspondence Analysis (CA) and Canonical Correspondence Analysis (CCA) for the alkaloid and phenolic extractions. (A) CA ordination plot of alkaloid extraction at the six sites with each dot representing an individual plant (average of three biological replicates) at a site (B) CCA ordination biplot of alkaloid extractions displaying environmental variables (arrows) and each site (circle with size representing the number of individuals collected) (C) CA ordination plot of phenolic extraction at the six sites with each dot representing an individual plant (average of three biological replicates) at a site (D) CCA ordination biplot of phenolic extraction displaying environmental variables (arrows) and each site (circle with size representing the number of individuals collected). Number of individuals collected and site location (A–F) is also noted in Table 1. Numerical results of CA and CCA are in Table 2. Site A is Red, Site B is Green, Site C is Dark Blue, Site D is Light Blue, Site E is Magenta, and Site F is Yellow.

FIGURE 2

Compounds-environmental variables biplot of Canonical Correspondence Analysis (CCA) for identified compounds. CCA biplot depicts environmental variables as arrows and compound optima as red triangles (IDs refer to Supplementary Tables 4, 6). From the ordination one can determine how higher levels of environmental variables affect the abundance of the compound. Compound A7’s optima, or the highest abundance of A7, occurs at higher levels of soil P, whereas compound A6 has a higher compound abundance with low soil P (A) CCA of alkaloid compounds (A1–A11) (B) CCA of coumarin compounds (C1–C8).

FIGURE 3

PLS-DA of alkaloid and phenolic extractions depicts differentiation between sites. 3D scores plot between selected PCs. The explained variances are shown in brackets. Site locations (A–F) are color-coded and ID’s refer to Table 1. (A) PLS-DA for alkaloid extraction (B) PLS-DA for phenolic extraction.

FIGURE 4

Random Forests (RF) Classification of the differentiation between sites for alkaloid and phenolic extractions. Each color represents the cumulative error rates for the RF classification of each site as a unique class/chemoecotype. A site with a smaller error rate that is stabilized with a fewer number of decision trees is considered to be more accurately distinguished as a unique chemoecotype. The overall error rate for chemoecotype classification is shown as a red line. Site locations are color coded by the legend on this graph and labeled with ID’s (A–F) as found on Table 1. The alkaloid extraction has the lowest overall error rate for classification of chemoecotypes, therefore chemoecotype groups are more easily distinguished or identified. (A) alkaloid extraction (B) phenolic extraction.