Read the declaration and add your name.

Data‑Rich, Insight‑Poor? —LXXIX Kim et al.’s Folddisco paper is easy to misread.

Folddisco enables protein structural motif search in million scale databases.

Folddisco enables protein structural motif search in million scale databases.

Folddisco enables protein structural motif search in million scale databases.

Foldseek clustered 820M AlphaFold DB + ESMatlas structures

Mirdita Lab builds scalable bioinformatics methods.

Protein structure prediction breakthroughs, notably AlphaFold2 and ESMfold, have led to an unprecedented influx of computationally derived structures. The AlphaFold Protein Structure Database now prov...

Microbes are ubiquitous on Earth, forming microbiomes that sustain macroscopic life and biogeochemical cycles. Microbial dispersion, driven by natural processes and human activities, interconnects mic...

Detecting similar protein structural motifs, functionally crucial short 3D patterns, in large structure collections is computationally prohibitive. Therefore, we developed Folddisco, which overcomes this through an index of position-independent geometric features, including side-chain orientation, combined with a rarity-based scoring system. Folddisco indexes 53 million AFDB50 structures into 1.45 terabyte within 24 hours, enabling rapid detection of discontinuous or segment motifs. Folddisco is more accurate and storage-efficient than state-of-the-art methods, while being an order of magnitude faster. Folddisco is free software available at folddisco.foldseek.com and a webserver at https://search.foldseek.com/folddisco. ### Competing Interest Statement M.S. acknowledges outside interest in Stylus Medicine. The remaining authors declare no competing interests. National Research Foundation of Korea, https://ror.org/013aysd81, 2020M3A9G7103933, RS-2021-NR061659, RS-2021-NR056571, RS-2024-00396026, RS-2023-00250470 Novo Nordisk Foundation, https://ror.org/04txyc737, NNF24SA0092560

Abstract. Tailor-made enzymes empower a wide range of versatile applications, although searching for the desirable enzymes often requires high throughput s