Accelerating natural product discovery with linked MS-genomics and language/transformer-based models

npj Antimicrobials and Resistance 2026 Open access

Read full text
Authors: Dillon W P Tay, Winston Lian Chye Koh, Shi Jun Ang, Zicong Marvin Wong, Yi Wee Lim, Yi Wee Lim, Elena Heng, Yu Hung Ng, Naythan Z X Yeo, Krishnan Adaikkappan, Fong Tian Wong, Yee Hwee Lim
+1 more Yee Hwee Lim
DOI: 10.1038/s44259-026-00206-7
Cited by: 1
References: 32

Abstract

Integrated chem-bio characterization of microbial strain libraries can streamline natural product discovery by prioritizing candidate producers. Here, we employ language- and transformer-based models to extract actionable insights from linked mass spectrometry (MS)-genome datasets. Our framework enables ranking of microbial producers to prioritise high-potential candidates for targeted validation. Across three representative case studies, this approach prioritized producers of diverse natural products with 75-100% precision. These findings demonstrate the transformative potential of AI-enabled chem-bio characterization to significantly accelerate natural product discovery and enable access to microbial chemical diversity beyond reference knowledge.

Fields of Study & Subjects

Microbial Natural Products and Biosynthesis Genomics and Phylogenetic Studies Microbial Metabolic Engineering and Bioproduction

Publication details

Journal / source
npj Antimicrobials and Resistance
Publisher
Springer Science and Business Media LLC
Volume
4
Issue
1
Publication date
30 April 2026
Language
EN