Discovery of potent inhibitors of α-synuclein aggregation using structure-based iterative learning.
Published version
Peer-reviewed
Repository URI
Repository DOI
Type
Change log
Authors
Abstract
Machine learning methods hold the promise to reduce the costs and the failure rates of conventional drug discovery pipelines. This issue is especially pressing for neurodegenerative diseases, where the development of disease-modifying drugs has been particularly challenging. To address this problem, we describe here a machine learning approach to identify small molecule inhibitors of α-synuclein aggregation, a process implicated in Parkinson's disease and other synucleinopathies. Because the proliferation of α-synuclein aggregates takes place through autocatalytic secondary nucleation, we aim to identify compounds that bind the catalytic sites on the surface of the aggregates. To achieve this goal, we use structure-based machine learning in an iterative manner to first identify and then progressively optimize secondary nucleation inhibitors. Our results demonstrate that this approach leads to the facile identification of compounds two orders of magnitude more potent than previously reported ones.
Description
Acknowledgements: This work was supported by the UKRI (10059436, 10061100), which funded R.I.H., E.A.A., Z.F.B., A.A., M.N., R.C.G., R.S., A.P., S.C., P.S., T.P.J.K. and M.V. Grant RF1NS110437 funded B.G. Grant #AI001086 from the Division of Intramural Research of the NIAID funded B.C., P.A. and A.S. We thank K. Stott, from the Biophysics Facility, Department of Biochemistry, University of Cambridge, for her assistance in using these facilities. The authors thank L. Sakhnini for help with mass spectrometry work and H. Greer for assisting with the TEM and the EPSRC Underpinning Multi-User Equipment Call (EP/P030467/1) for funding the TEM. We also thank ARCHER, MARCOPOLO and CIRCE high-performance computing resources for the computer time. Z.F.B. acknowledges the Federation of European Biochemical Societies (FEBS) for financial support (LTF). S.C. acknowledges the Singapore Ministry of Health’s National Medical Research Council under its Open Fund-Young Individual Research Grant (OF-YIRG) (MOH-001132-00) for support. P.S. is a Royal Society University Research Fellow (URF\R1\201461) and acknowledges funding from UKRI EPSRC (EP/X024733/1). Parts of the figures were created with BioRender.com.
Funder: UKRI (10059436, 10061100)
Keywords
Journal Title
Conference Name
Journal ISSN
1552-4469
