AlphaFold database expands to over 200 million predicted structures, nearly every catalogued protein

Google DeepMind/AlphaFold

DeepMind and EMBL-EBI expanded the free AlphaFold Protein Structure Database more than 200-fold, from nearly 1 million to over 200 million predicted structures, covering almost every catalogued protein. In its first year AlphaFold had been used by more than half a million researchers.

• Expanded from ~1 million to >200 million predicted structures, covering nearly all catalogued proteins.
• Over 500,000 researchers from 190 countries have accessed the database.
• Structures integrated into major datasets: Ensembl, UniProt, OpenTargets.
• All 200+ million structures available for bulk download via Google Cloud Public Datasets.