{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["17(1)"],"submitter":["Morin L"],"pubmed_abstract":["Automatic extraction of molecules from scientific literature plays a crucial role in accelerating research across fields ranging from drug discovery to materials science. Patent documents, in particular, contain molecular information in visual form, which is often inaccessible through traditional text-based searches. In this work, we introduce SubGrapher, a method for the visual fingerprinting of molecule and Markush structure images. Unlike conventional Optical Chemical Structure Recognition (OCSR) models that attempt to reconstruct full molecular graphs, SubGrapher focuses on extracting fingerprints directly from images. Using learning-based instance segmentation, SubGrapher identifies functional groups and carbon backbones, constructing a substructure-based fingerprint that enables the "],"journal":["Journal of cheminformatics"],"pagination":["149"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12482248"],"repository":["biostudies-literature"],"pubmed_title":["Subgrapher: visual fingerprinting of chemical structures."],"pmcid":["PMC12482248"],"pubmed_authors":["Morin L","Meijer GI","Van Gool L","Staar PWJ","Weber V"],"additional_accession":[]},"is_claimable":false,"name":"Subgrapher: visual fingerprinting of chemical structures.","description":"Automatic extraction of molecules from scientific literature plays a crucial role in accelerating research across fields ranging from drug discovery to materials science. Patent documents, in particular, contain molecular information in visual form, which is often inaccessible through traditional text-based searches. In this work, we introduce SubGrapher, a method for the visual fingerprinting of molecule and Markush structure images. Unlike conventional Optical Chemical Structure Recognition (OCSR) models that attempt to reconstruct full molecular graphs, SubGrapher focuses on extracting fingerprints directly from images. Using learning-based instance segmentation, SubGrapher identifies functional groups and carbon backbones, constructing a substructure-based fingerprint that enables the ","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Sep","modification":"2026-06-03T23:34:02.812Z","creation":"2026-05-03T03:11:41.666Z"},"accession":"S-EPMC12482248","cross_references":{"pubmed":["41024145"],"doi":["10.1186/s13321-025-01091-4"]}}