A Convolutional Neural Network-Based Approach for the Rapid Annotation of Molecularly Diverse Natural Products

Abstract

This report describes the first application of the novel NMR-based machine learning tool “Small Molecule Accurate Recognition Technology” (SMART 2.0) for mixture analysis and subsequent accelerated discovery and characterization of new natural products. The concept was applied to the extract of a filamentous marine cyanobacterium known to be a prolific producer of cytotoxic natural products. This environmental Symploca extract was roughly fractionated, and then prioritized and guided by cancer cell cytotoxicity, NMR-based SMART 2.0, and MS2-based molecular networking. This led to the isolation and rapid identification of a new chimeric swinholide-like macrolide, symplocolide A, as well as the annotation of swinholide A, samholides A–I, and several new derivatives. The planar structure of symplocolide A was confirmed to be a structural hybrid between swinholide A and luminaolide B by 1D/2D NMR and LC-MS2 analysis. A second example applies SMART 2.0 to the characterization of structurally novel cyclic peptides, and compares this approach to the recently appearing “atomic sort” method. This study exemplifies the revolutionary potential of combined traditional and deep learning-assisted analytical approaches to overcome longstanding challenges in natural products drug discovery.

Sarcaglarols A—D, Lindenane−Monoterpene Heterodimers from Sarcandra glabra Based on Molecular Networks

“…[ 12 ] This visualization tool can facilitate the isolation of target compounds as well as dereplication of known one. [ 13‐14 ] In recent years, the efficient discoveries of two novel disesquiterpenoid from Ainsliaea macrocephala , [ 15 ] two unusual selaginellin analogues and eight new diarylfluorene derivatives from Selaginella tamariscina , [ 16 ] and nine new polyacetylated 18‐norspirostanol saponins from Trillium tschonoskii were all guided by the molecular networking strategy. [ 17 ] In the light of our interest in lindenane‐type sesquiterpene heteropolymers, especially the type of lindenane− normonoterpene conjugates with a peroxide bridge (sarglaperoxides A and B), which we isolated from S. glabra , [ 6 ] a traditional Chinese medicine (TCM) widely used, and mainly used to treat inflammation and traumatic injuries, [ 18 ] we thus envisaged using molecular networks, combined with our standard compounds, to directionally search our target heterodimers from S. glabra .…”

Cheminformatics in Natural Product‐based Drug Discovery

“…Another study successfully employed a convolutional neural network-based approach for the rapid identification of new NPs from a filamentous marine cyanobacterium. [53] A different approach is taken by the NP-StructurePredictor. [54] Based solely on targeted molecular weights derived from m/z values obtained by liquid chromatography-MS, this tool produces a rank-ordered list of likely NP structures.…”

From Ocean to Medicine: Pharmaceutical Applications of Metabolites from Marine Bacteria

“…The SMART technology in combination with GNPS was successfully applied recently to the discovery of symplocolide A ( 73 ), a new chimeric swinholide-like macrolide with cytotoxic properties against the NCI-H460 human lung cancer cell line obtained from extracts of the filamentous marine cyanobacterium Symploca sp. [ 173 ].…”