AlphaFold Database Offers Free Access to 200 Million Protein Structures
A collaboration between Google DeepMind and EMBL-EBI provides open access to over 200 million AI-predicted protein structures, dramatically accelerating biological research globally.
The AlphaFold Protein Structure Database provides open access to over 200 million protein structure predictions, significantly accelerating scientific research. Developed by Google DeepMind in partnership with EMBL's European Bioinformatics Institute (EMBL-EBI), this platform uses artificial intelligence to predict a protein's 3D structure directly from its amino acid sequence. The database offers broad coverage of UniProt, the standard repository for protein sequences and annotations.
This AI system regularly achieves accuracy that is competitive with experimental results, making it a highly valuable tool for the scientific community. Researchers have the ability to search for specific proteins or download entire proteomes, including the complete human proteome and the proteomes of 47 other key organisms important to global health. Additionally, the database includes downloads for the manually curated subset of UniProt known as Swiss-Prot.
While the system still faces some limitations, its top-ranked performance in the CASP14 competition demonstrates its immediate potential to advance biological understanding. For research applications that extend beyond the current database offerings, scientists are able to generate their own predictions using the freely available open-source code. The platform also provides online training courses and comprehensive FAQs to help users integrate these structural predictions into their work.