Clustering the protein universe of life using DIAMOND DeepClust

Nature Methods 2026 Open access

Read full text
Authors: Benjamin Buchfink, Emile Barbe, Haim Ashkenazy, Klaus Reuter, J. Alexander Kennedy, Hajk‐Georg Drost
DOI: 10.1038/s41592-026-03030-z
Cited by: 7
References: 47

Abstract

Relating billions of proteins across the tree of life remains a challenging task for comparative biosphere genomics and artificial intelligence-driven structure prediction. Here we present DIAMOND DeepClust, a cascaded, ultra-fast clustering method enabling planetary-scale organization of protein space, scaling to trillions of sequences while retaining sensitivity at low identity. Aggregating 19 billion biosphere proteins into 544 million nonsingleton clusters, we show that using our DeepClust database, available for download, can enhance structure prediction with AlphaFold2.

Fields of Study & Subjects

Machine Learning in Bioinformatics Protein Structure and Dynamics Genomics and Phylogenetic Studies

Publication details

Journal / source
Nature Methods
Publisher
Springer Science and Business Media LLC
Volume
23
Issue
4
Pages
724–727
Publication date
24 March 2026
Language
EN