EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PUFFIN: protein unit discovery with functional supervision

Gökçe Uludoğan iD, Buse Giledereli, Elif Ozkirimli iD, Arzucan Özgür

Bioinformatics · 01.07.2026 · 42 (Supplement_1)

DOI: 10.1093/bioinformatics/btag265 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 07.07.2026. Verfasst von Gökçe Uludoğan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Boğaziçi University, Bebek, Istanbul, 34342, Turkey. Hauptthemen laut MEDLINE: Proteins, Computational Biology. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Research Council, European Research Council Executive Agency.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Proteins carry out biological functions through the coordinated action of groups of residues organized into structural arrangements. These arrangements, which we refer to as protein units, exist at an intermediate scale, being larger than individual residues yet smaller than entire proteins. A deeper understanding of protein function can be achieved by identifying these units and their associations with function. However, existing approaches either focus on residue-level signals, rely on curated annotations, or segment protein structures without incorporating functional information, thereby limiting interpretable analysis of structure–function relationships. Results We introduce PUFFIN, a data-driven framework for discovering protein units by jointly learning structural partitioning and functional supervision. PUFFIN represents proteins as residue-level structure graphs and applies a graph neural network with a structure-aware pooling mechanism that partitions each protein into multiresidue units, with functional supervision that shapes the partition. We show that the learned units are structurally coherent, exhibit organized associations with molecular function, and show meaningful correspondence with curated InterPro annotations. Together, these results demonstrate that PUFFIN provides an interpretable framework for analyzing structure–function relationships using learned protein units and their statistical function associations. Availability and implementation We made our source code available at github.com/boun-tabi-lifelu/puffin.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsComputational BiologyGraph Neural NetworksDatabases, ProteinStructure-Activity RelationshipProtein Conformation

Substanzen

Proteins

Autor:innen und Institutionen

  • Department of Computer Engineering, Boğaziçi University, Bebek, Istanbul, 34342, Turkey.
  • Roche Informatics, F. Hoffmann-La Roche AG, Basel, 4070, Switzerland.

ORCID-Profile: Gökçe Uludoğan, Elif Ozkirimli

Förderung

  • European Research Council
  • European Research Council Executive Agency

Zitieren

APA

Uludoğan, G., Giledereli, B., Ozkirimli, E., & Özgür, A. (2026). PUFFIN: protein unit discovery with functional supervision. Bioinformatics, 42(Supplement_1). https://doi.org/10.1093/bioinformatics/btag265

Vancouver

Uludoğan G, Giledereli B, Ozkirimli E, Özgür A. PUFFIN: protein unit discovery with functional supervision. Bioinformatics. 2026;42(Supplement_1). doi:10.1093/bioinformatics/btag265

BibTeX
@article{Uludoan2026,
  author = {Uludoğan, Gökçe and Giledereli, Buse and Ozkirimli, Elif and Özgür, Arzucan},
  title = {PUFFIN: protein unit discovery with functional supervision},
  journal = {Bioinformatics},
  year = {2026},
  volume = {42},
  number = {Supplement_1},
  doi = {10.1093/bioinformatics/btag265}
}
Kostenlos starten →