Large-scale transcriptome mining enables macrocyclic diversification and improved bioactivity of the stephanotic acid scaffold

Abstract

Nearly 10,000 plant species are represented by RNA-seq datasets in the NCBI sequence read archive, which are difficult to search in unassembled format due to database size. Here, we optimize RNA-seq assembly to transform most of this public RNA-seq data to a searchable database for biosynthetic gene discovery. We test our transcriptome mining pipeline towards the diversification of moroidins, which are plant ribosomally-synthesized and posttranslationally-modified peptides (RiPPs) biosynthesized from copper-dependent peptide cyclases. Moroidins are bicyclic compounds with a conserved stephanotic acid scaffold, which becomes cytotoxic to non-small cell lung adenocarcinoma cells with an additional C-terminal macrocycle. We discover moroidin analogs with second ring structures diversified at the crosslink and the non-crosslinked residues including a moroidin analog from water chickweed, which exhibits higher cytotoxicity against lung adenocarcinoma cells than moroidin. Our study expands stephanotic acid-type peptides to grasses, Lowiaceae, mints, pinks, and spurges while demonstrating that large-scale transcriptome mining can broaden the medicinal chemistry toolbox for chemical and biological exploration of eukaryotic RiPP lead structures.

Fig. 1. Transcriptome mining of plant RiPPs.

a General workflow of transcriptomics-guided discovery of plant RiPPs including de novo assembly of NGS data as a challenging step addressed in this work. b Chemical structures of stephanotic acid-type burpitides. c The moroidin scaffold. d Moroidin precursor peptide KjaBURP from Kerria japonica. Moroidin core peptides are highlighted in red and blue color. Sequence highlighted in gray was not assembled with the BURP domain by SOAPdenovo-trans in 1kp database. BURP-domain sequence is underlined. e Comparison of unassembled and assembled RNA-seq data search for discovery of stephanotic acid-type burpitides. f Transcriptome mining workflow of this study with either (1) Sequenceserver-based tblastn search or (2) commandline PHI-BLAST search. sp. species, FDR false discovery rate. Source data are provided as a Source Data file.

Fig. 2. Characterization of stephanotic acid-burpitides with a Trp-Val-crosslinked second ring.

a Glechoma hederacea in the University of Michigan Arboretum. b Glechomanin detection in methanolic leaf extracts of G. hederacea and of transgenic N. benthamiana 6 days after infiltration with Agrobacterium tumefaciens LBA4404 pEAQ-HT-GheBURP. c Glechomanin structure. d Key HMBC signals of glechomanin side-chain-crosslinks. e Orchidantha maxillarioides plant in Missouri botanical garden. f Glechomanin detection in methanolic leaf extract of transgenic N. benthamiana 6 days after infiltration with A. tumefaciens LBA4404 pEAQ-HT-OmaBURP1-1xQLFVWGW. EIC: extracted ion chromatogram. Source data are provided as a Source Data file.

Fig. 3. Characterization of stephanotic acid-burpitides with a Tyr-Phe-crosslinked second ring.

a Mercurialis annua from University of Michigan herbarium. b Mercurialin detection in methanolic leaf extracts of M. annua and of transgenic N. benthamiana 6 days after infiltration with A. tumefaciens LBA4404 pEAQ-HT-ManBURP. c Mercurialin structure. d Key HMBC correlations of mercurialin side-chain-crosslinks. EIC: extracted ion chromatogram. Source data are provided as a Source Data file.

Fig. 4. Characterization of moroidin burpitides in pinks and grasses.

a Second-ring sequence diversity of moroidin cores in transcriptomics-derived fused burpitide cyclases. b Stellaria aquatica. c LC-MS characterization of moroidin-QLLVWRNH in S. aquatica and transgenic N. benthamiana after 6 days of expression of SaqBURP-1xQLLVWRNH. d Moroidin-QLLVWRNH structure. e Sacciolepis striata. Photo credit: Larry Allain, U.S. Geological Survey. f LC-MS characterization of moroidin-QLLVWRNH in S. striata and in transgenic N. benthamiana after 6 days of expression of SstBURP-4xQLLVWRNH. EIC: extracted ion chromatogram. Source data are provided as a Source Data file.

Fig. 5. Bioactivity of moroidin-QLLVWRNH.

a In vitro anticancer assays of moroidin-QLLVWRNH. Cell viability in six human cancer cell lines is plotted for the peptide across ten concentrations: H1299 (non-small cell lung cancer), U2OS (osteosarcoma), LNCaP (prostate cancer), HUH-7 (hepatoma), A549 (lung carcinoma), and H1437 (non-small cell lung adenocarcinoma). The data points represent the mean of triplicate samples (n = 3) and error bars represent one standard error of the mean. b In vitro counterscreen of moroidin-QLLVWRNH in three non-cancerous cell lines is plotted for the peptide across ten concentrations: HFF (human foreskin fibroblast), IMR-90 (human lung fibroblast), and MEF (mouse embryonic fibroblast). The data points represent the mean of triplicate samples (n = 3) and error bars represent one standard error of the mean. Corresponding IC₅₀ values of (a and b) are listed. Source data are provided as a Source Data file.

Fig. 6. Phylogenetic distribution of characterized stephanotic acid-type burpitides in flowering plants.

Displayed phylogenetic resolution are plant orders. See Supplementary Table 15 for species information. ANA: Amborellales, Nymphaeales, and Austrobaileyales clade; x: any proteinogenic amino acid.