Untargeted Metabolomics Approach for the Discovery of Salinity-Related Alkaloids in a Stony Coral-Derived Fungus Aspergillus terreus

Abstract

As a part of the important species that form coral reef ecosystems, stony corals have become a potential source of pharmacologically active lead compounds for an increasing number of compounds with novel chemical structures and strong biological activity. In this study, the secondary metabolites and biological activities are reported for Aspergillus terreus C21-1, an epiphytic fungus acquired from Porites pukoensis collected from Xuwen Coral Reef Nature Reserve, China. This strain was cultured in potato dextrose broth (PDB) media and rice media with different salinities based on the OSMAC strategy. The mycelial morphology and high-performance thin layer chromatographic (HPTLC) fingerprints of the fermentation extracts together with bioautography were recorded. Furthermore, an untargeted metabolomics study was performed using principal component analysis (PCA), orthogonal projection to latent structure discriminant analysis (O-PLSDA), and feature-based molecular networking (FBMN) to analyze their secondary metabolite variations. The comprehensive results revealed that the metabolite expression in A. terreus C21-1 differed significantly between liquid and solid media. The metabolites produced in liquid medium were more diverse but less numerous compared to those in solid medium. Meanwhile, the mycelial morphology underwent significant changes with increasing salinity under PDB cultivation conditions, especially in PDB with 10% salinity. Untargeted metabolomics revealed significant differences between PDB with 10% salinity and other media, as well as between liquid and solid media. FBMN analysis indicated that alkaloids, which might be produced under high salt stress, contributed largely to the differences. The biological activities results showed that six groups of crude extracts exhibited acetylcholinesterase (AChE) inhibitory activities, along with 1,1-diphenyl-2-picrylhydrazyl (DPPH) free radical scavenging and antibacterial activities. The results of this study showed that the increase in salinity favored the production of unique alkaloid compounds by A. terreus C21-1.

Keywords: Aspergillus terreus; alkaloids; stony coral; untargeted metabolomics.

Figure 1

The morphological characteristics of Aspergillus terreus C21-1 in different media over a period of 28 days (G1–G6); 1 means the front and 2 the back of the plate.

Figure 2

HPTLC fingerprints of six crude extracts are presented in the following figures. (A) shows the UV images of experiments G1–G6 under 254 nm, with sample numbers marked below the starting line. (B) displays the UV images of G1–G6 under 365 nm. The unfolding system used was n-hexane: ethyl acetate = 3:2 (v/v). The rulers beside the TLC plate were utilized as references for calculating the Rf values.

Figure 3

The HPLC fingerprints of the six crude extracts using a UV wave length of 210 nm.

Figure 4

PCA analysis of all groups of the A. terreus C21-1.

Figure 5

(A) OPLS-DA plot (R2X: 0.730, R2Y:0.916, Q2: 0.884) of liquid medium and solid medium groups of the A. terreus C21-1 metabolic profiles. (B) OPLS−DA s−plot for liquid medium vs. solid medium groups. Dots represent individual metabolites; dots highlighted in light orange correspond to metabolites with a VIP value greater than 3.

Figure 6

(A) OPLS−DA plot (R2X: 0.983, R2Y:1.000, Q2: 0.999) of 0.3% salinity and 10% salinity groups. (B) OPLS−DA s−plot for 0.3% salinity vs. 10% salinity groups. Dots represent individual metabolites; dots highlighted in light orange correspond to metabolites with a VIP value greater than 3.

Figure 7

The metabolic profile of the features in extracts 0.3 PDB (A) and 10 PDB (B) showing their retention times, precursor ion m/z values, and intensities (exported from MSDIAL).

Figure 8

The statistics of the numbers of the total features (A), the annotated and unknown features (B), and the alkaloids (C) detected in the two crude extracts.

Figure 9

The FBMN molecular network based on positive ion MS/MS spectral similarity, showing a selection of amplified clusters. In the FBMN network, each node represents a feature marked with the mean m/z value of the parent ion, and the similarity of the secondary mass spectra between compounds was expressed by the cosine value, which was proportional to the similarity. The different colors of sections in the nodes represent different samples, i.e.,: respectively, 0.3 PDB and 10 PDB. The thickness of the connecting lines between nodes is positively correlated with the cosine value. The node size reflects the feature abundance (ion intensity). The A, B, C, D, E represent a locally enlarged view of a, b, c, d, e, respectively.