Machine Learning-Based Bioactivity Classification of Natural Products Using LC-MS/MS Metabolomics

The rediscovery of known drug classes represents a major
challenge in natural products drug discovery. Compound rediscovery
inhibits the ability of researchers to explore novel natural products
and wastes significant amounts of time and resources. This study introduces
a novel machine learning framework that can effectively characterize
the bioactivity of natural products by leveraging liquid chromatography
tandem mass spectrometry and untargeted metabolomics analysis. This
accelerates natural product drug discovery by addressing the challenge
of dereplicating previously discovered bioactive compounds. Utilizing
the SIRIUS 5 metabolomics software suite and in-silico-generated fragmentation spectra, we have trained a ML model capable
of predicting a compound’s drug class. This approach enables
the rapid identification of bioactive scaffolds from LC-MS/MS data,
even without reference experimental spectra. The model was trained
on a diverse set of molecular fingerprints generated by SIRIUS 5 to
effectively classify compounds based on their core pharmacophores.
Our model robustly classified 21 diverse bioactive drug classes, achieving
accuracies greater than 93% on experimental spectra. This study underscores
the potential of ML combined with MFPs to dereplicate bioactive natural
products based on pharmacophore, streamlining the discovery process
and expediting improved methods of isolating novel antibacterial and
antifungal agents.