From atoms to fragments: a coarse representation for efficient and functional protein design
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag172 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Leonardo V Castorina und 2 weiteren Autor:innen. Beteiligte Einrichtung: AstraZeneca UK, Cambridge, CB2 0AA, United Kingdom. Hauptthemen laut MEDLINE: Proteins, Computational Biology, Protein Engineering. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Leonardo Castorina, UKRI via the Centre for Doctoral Training in Biomedical AI. Kartic Subr, aRoyal Society University Research.
Abstract (Originalsprache)
Motivation Although deep learning has accelerated protein design, current protein representations such as sequences or full-atom structures scale non-linearly with protein length. We propose a sparse and interpretable representation for proteins, based on evolutionarily conserved fragments. Specifically, we use a curated set of 40 functional and evolutionarily conserved fragments as an alphabet to build Fragment Graphs and Fragment Sets. These fragment-based representations are both lightweight and functionally informative, capturing up to 55% more variance using fewer than 13 of the dimensions required by traditional methods. Results On a dataset of 215 functionally diverse proteins, our approach creates more coherent functional clusters than traditional sequence- and structure-based methods, even among proteins with ≤30% sequence identity. Fragment-based searches of protein databases achieve accuracies comparable to traditional methods, while using 90% fewer tokens per protein. These searches execute ∼68.7× faster than RMSD-based structural methods and ∼1.64× faster than sequence-based methods, even including fragment pre-processing overhead. Additionally, we show that our representation effectively guides RFDiffusion for protein backbone generation with functional recovery rates higher than 40%. In summary, our fragment-based representation offers a scalable and interpretable alternative for the next generation of protein design tools for backbone design, sequence design, and functional similarity searches within protein structure databases. Availability https://github.com/wells-wood-research/tessera
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- AstraZeneca UK, Cambridge, CB2 0AA, United Kingdom.
- School of Biological Sciences, The University of Edinburgh, Edinburgh, EH9 3FF, United Kingdom.
- School of Informatics, The University of Edinburgh, Edinburgh, EH8 9AB, United Kingdom.
ORCID-Profile: Leonardo V Castorina, Christopher W Wood, Kartic Subr
Förderung
- Leonardo Castorina
- UKRI via the Centre for Doctoral Training in Biomedical AI. Kartic Subr
- aRoyal Society University Research
Zitieren
APA
Castorina, L. V., Wood, C. W., & Subr, K. (2026). From atoms to fragments: a coarse representation for efficient and functional protein design. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag172
Vancouver
Castorina LV, Wood CW, Subr K. From atoms to fragments: a coarse representation for efficient and functional protein design. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag172
BibTeX
@article{Castorina2026,
author = {Castorina, Leonardo V and Wood, Christopher W and Subr, Kartic},
title = {From atoms to fragments: a coarse representation for efficient and functional protein design},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag172}
}
EUVIMED