SureChEMBL

Chemical Structure Information in Patents

SureChEMBL is a publicly available large-scale resource containing compounds extracted from the full text, images and attachments of patent documents. The data are extracted from the patent literature according to an automated text and image-mining pipeline on a daily basis. SureChEMBL provides access to a previously unavailable, open and timely set of annotated compound-patent associations, complemented with sophisticated combined structure and keyword-based search capabilities against the compound repository and patent document corpus. Additionally , SureChEMBL makes use of NLP (Natural Language Processing) to automatically annotate genes and diseases in the patent text. Given the wealth of knowledge hidden in patent documents, analysis of SureChEMBL data has immediate applications in drug discovery, medicinal chemistry and other commercial areas of chemical science.

As of September 2024, the database contains 28.5 million compounds extracted from 28 million patent documents.