Authors
- Gonçalo Bernardes
Instituto de Medicina Molecular, Lisboa and Department of Chemistry, University of Cambridge ,
- Tiago Rodrigues ,
- Markus Werner ,
- Jakob Roth ,
- Eduardo H. G. da Cruz ,
- Marta C. Marques ,
- Susana A. Lobo ,
- Andreas Koeberle ,
- Francisco Corzana ,
- Eufrânio N. da Silva Júnior ,
- Oliver Werz
Abstract
Chemical matter with often-discarded moieties entails opportunities for drug discovery. Relying on orthogonal ligand-centric machine learning methods, targets were consensually identified as potential counterparts for the fragment-like natural product β-lapachone. Resorting to a comprehensive range of biophysical and biochemical assays, the natural product was validated as a potent, ligand efficient, allosteric and reversible modulator of 5-lipoxygenase (5-LO). Moreover, we provide a rationale for 5-LO-inhibiting chemotypes inspired in the β-lapachone scaffold through a focused analogue library. This work demonstrates the power of artificial intelligence technologies to deconvolute complex phenotypic readouts of clinically relevant chemical matter, leverage natural product-based drug discovery, as an alternative and/or complement to chemoproteomics and as a viable approach for systems pharmacology studies.
Content

Supplementary material
