Foldseek enables fast and sensitive comparisons of large structure sets. It reaches sensitivities similar to state-of-the-art structural aligners while being at least 20,000 times faster.

A new algorithm called FoldSeek (van Kempen et al. 2024) efficiently clustered over 214 million protein structures from the AlphaFold database into only 2.30 million clusters, significantly reducing the data by almost 100 times! You can group the data points together to obtain only the non-repetitive, meaningful representative structures for each group. This reduction is possible due to the intrinsic patterns shared across many protein types.

Structural analysis poses a significant time challenge, contrasting with the swiftness of sequence analysis. The authors of FoldSeek highlight this disparity: “Searching with a single query structure through a database with 100 million protein structures would take the popular TM-align tool a month on one CPU core, and an all-versus-all comparison would take 10 millennia on a 1,000-core cluster. Sequence searching is four to five orders of magnitude faster: an all-versus-all comparison of 100 million sequences would take MMseqs2 only around a week on the same cluster” (van Kempen et al. 2024). In contrast, their algorithm, FoldSeek, drastically accelerates structural comparisons while maintaining sensitivity. This speed enhancement, achieved through the development of a 3Di alphabet, facilitates large-scale structural analysis. Unlike conventional methods like CLE, 3D-BLAST, and Protein Blocks, which describe the protein backbone, 3Di characterizes interactions between closely placed residue pairs in 3D space.

The AlphaFold Protein Structure Database (AFDB), co-developed by Google DeepMind and EMBL-EBI, has significantly enhanced its search capabilities by integrating Foldseek into all its entries. Users can now perform structure-based searches against the Protein Data Bank (PDB), which houses experimentally determined structures, and the AlphaFold Database.

The PDB collection is updated weekly to incorporate the latest releases from the Worldwide Protein Data Bank, ensuring users can always access the most current entries for their searches. Additionally, searching against AlphaFold models involves using a curated AFDB collection clustered at 50% sequence identity, termed AFDB50. This optimisation reduces redundancy in the searches by focusing on searching against representatives of clusters with homologous proteins.

Foldseek introduces GPU support for monomer and multimer search, improved profile search and ProstT5 integration, new databases, several performance improvements and bug fixes.