Alphafold has recently added the proteome of nearly all the WHO priority pathogens to their library of highly accurate prediction of protein structures. AlphaFold is an AI system developed by DeepMind that predicts a protein’s 3D structure from its amino acid sequence. DeepMind and EMBL’s European Bioinformatics Institute (EMBL-EBI) have partnered to make these predictions freely available to the scientific community.
The database will be expanded during 2022 to cover a large proportion of all catalogued proteins (the over 100 million in UniRef90).
AlphaFold DB currently provides predicted structures for the organisms listed on this webpage, as well as the majority of Swiss-Prot. You can download a prediction for an individual UniProt accession by visiting the corresponding structure page (example: https://www.alphafold.ebi.ac.uk/entry/F4HVG8).
For downloading all predictions for a given species, use the download links below. Note that this option is only available on the desktop version of the site.
These uncompressed archive files (.tar) contain all the available compressed PDB and mmCIF files (.gz) for a reference proteome. In the case of proteins longer than 2700 amino acids (aa), AlphaFold provides 1400aa long, overlapping fragments. For example, Titin has predicted fragment structures named as Q8WZ42-F1 (residues 1–1400), Q8WZ42-F2 (residues 201–1600), etc. These fragments are currently only available in these proteome archive files, not on the website.
For downloading all predictions for all species, visit the FTP site: ftp://ftp.ebi.ac.uk/pub/databases/alphafold
More on the AlphaFold Protein Structure Database webpage.