Enhancing automated drug substance impurity structure elucidation from tandem mass spectra through transfer learning and domain knowledge
Year: 2025
Type: article
Abstract: 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.
Source: Digital Discovery
DOI: 10.1039/d5dd00115c
Authors: Emilio Dorigatti, Jonathan Groß, Jonas Kühlborn, Robert Möckel, Frank Maier, Julian Keupp
Institution: Boehringer Ingelheim (Germany)
Language: English
Subfield: Spectroscopy
Field: Chemistry
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4412643172