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

• Published in: Journal of the American Chemical Society 2020-03, Vol.142 (9), p.4114-4120
• Main Authors: Reher, Raphael, Kim, Hyun Woo, Zhang, Chen, Mao, Huanru Henry, Wang, Mingxun, Nothias, Louis-Félix, Caraballo-Rodriguez, Andres Mauricio, Glukhov, Evgenia, Teke, Bahar, Leao, Tiago, Alexander, Kelsey L, Duggan, Brendan M, Van Everbroeck, Ezra L, Dorrestein, Pieter C, Cottrell, Garrison W, Gerwick, William H
• Format: Article
• Language: English
• Subjects: Biological Products - chemistry; Biological Products - isolation & purification; Biological Products - toxicity; Cell Line, Tumor; Cheminformatics; Cyanobacteria - chemistry; Humans; Machine Learning; Magnetic Resonance Spectroscopy; Neural Networks, Computer; Peptides, Cyclic - chemistry; Peptides, Cyclic - isolation & purification; Peptides, Cyclic - toxicity
• ISSN: 0002-7863; 1520-5126; 1520-5126
• DOI: 10.1021/jacs.9b13786

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.