Enhancing automated drug substance impurity structure elucidation from tandem mass spectra through transfer learning and domain knowledge
We present a machine learning model that elucidates process impurities from synthesis via tandem mass spectra, and demonstrate how it becomes accurate enough to become a useful companion in a real-world chemical/analytical development setting.
Authors
- Jonas Kühlborn
- Julian Keupp (ORCID: https://orcid.org/0000-0001-8735-6883)
- Robert Möckel (ORCID: https://orcid.org/0000-0001-9883-9952)
- Frank J. Maier
- Emilio Dorigatti (ORCID: https://orcid.org/0000-0002-6829-7766)
- Jonathan Groß
Institutions
- Boehringer Ingelheim (Germany) (DE)
Publication Details
- Journal
- Digital Discovery
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1039/d5dd00115c
- Citations
- 1
- Primary Topic
- Spectroscopy and Chemometric Analyses
- Type
- article
- Field-Weighted Citation Impact
- 0.75