AI-assisted interpretation of Markush structures in pharmaceutical patents: a review of emerging tools, datasets, and challenges

Abstract Automated interpretation of Markush structures widely used in pharmaceutical patents to claim large families of related compounds remains challenging due to non-machine-readable structure images, variable R-groups, dependency rules, scaffold diversity, and heterogeneous claim language. Chal...

Full description

Bibliographic Details

Main Authors:	Jennifer M. Umbles Hayes, Emmanuel O. Olawode, Anietie Andy, Edmund Essah Ameyaw
Format:	Artigo
Language:	Inglês
Published:	BMC 2026-04-01
Series:	Journal of Cheminformatics
Subjects:	Markush claims Cheminformatics Patent analytics Information extraction Large language models (LLMs) Multimodal learning
Online Access:	https://doi.org/10.1186/s13321-026-01172-y
Tags:	Add Tag No Tags, Be the first to tag this record!