SureChEMBL in 2026: an open database of chemical and biomedical annotations from the patent literature.

SureChEMBL’s redesigned platform now contains 31 million chemical structures and 1 million biomedical entity annotations extracted from 44 million chemically annotated patent documents.

• Why it matters: Patent literature often reveals drug-discovery chemistry and biology before scientific publications, but its scale and nonmachine-readable chemical representations make automated analysis difficult.
• What they did: The team rebuilt SureChEMBL with modern extraction, chemistry registration, search, and data-delivery workflows, plus large-scale reprocessing of the historical corpus via a unified standardization pipeline.
• The result: Automatically generated biomedical annotations link patent chemistry to genes, proteins, diseases, and mechanisms, enabling access via the website, API, and downloadable Bulk Data.