EUVIMEDObjevte EUVIMED
Crossref

VoroIF‐GNN : Voronoi tessellation‐derived protein–protein interface assessment using a graph neural network

Kliment Olechnovič iD, Česlovas Venclovas iD

Proteins: Structure, Function, and Bioinformatics · 2023-12 · 91 (12) · 1879-1888

DOI: 10.1002/prot.26554 ↗

At a glance

Journal article in Proteins: Structure, Function, and Bioinformatics, published online on 2023-07-21. Written by Kliment Olechnovič and 1 co-authors. Institution: Institute of Biotechnology, Life Sciences Center, Vilnius University, Vilnius, Lithuania. Major MEDLINE topics: Proteins, Neural Networks, Computer. Cited 51 times so far (Crossref); 33 references. Funded by: Research Council of Lithuania, Lietuvos Mokslo Taryba.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

We present VoroIF‐GNN (Voronoi InterFace Graph Neural Network), a novel method for assessing inter‐subunit interfaces in a structural model of a protein–protein complex, relying solely on the input structure without any additional information. Given a multimeric protein structural model, we derive interface contacts from the Voronoi tessellation of atomic balls, construct a graph of those contacts, and predict the accuracy of every contact using an attention‐based GNN. The contact‐level predictions are then summarized to produce whole interface‐level scores. VoroIF‐GNN was blindly tested for its ability to estimate the accuracy of protein complexes during CASP15 and showed strong performance in selecting the best multimeric model out of many. The method implementation is freely available at https://kliment-olechnovic.github.io/voronota/expansion_js/ .

Subjects

MeSH terms (MEDLINE)

ProteinsNeural Networks, ComputerModels, Molecular

Author keywords

CASPVoronoi tessellationestimation of model accuracygraph neural networkprotein-protein complexquality assessment

Substances

Proteins

Authors and institutions

  • Institute of Biotechnology, Life Sciences Center, Vilnius University, Vilnius, Lithuania.

ORCID profiles: Kliment Olechnovič, Česlovas Venclovas

Funding

  • Research Council of Lithuania
  • Lietuvos Mokslo Taryba

Cite

APA

Olechnovič, K., & Venclovas, Č. (2023). VoroIF‐GNN : Voronoi tessellation‐derived protein–protein interface assessment using a graph neural network. Proteins: Structure, Function, and Bioinformatics, 91(12), 1879-1888. https://doi.org/10.1002/prot.26554

Vancouver

Olechnovič K, Venclovas Č. VoroIF‐GNN : Voronoi tessellation‐derived protein–protein interface assessment using a graph neural network. Proteins: Structure, Function, and Bioinformatics. 2023;91(12):1879-1888. doi:10.1002/prot.26554

BibTeX
@article{Olechnovi2023,
  author = {Olechnovič, Kliment and Venclovas, Česlovas},
  title = {VoroIF‐GNN : Voronoi tessellation‐derived protein–protein interface assessment using a graph neural network},
  journal = {Proteins: Structure, Function, and Bioinformatics},
  year = {2023},
  volume = {91},
  number = {12},
  pages = {1879--1888},
  doi = {10.1002/prot.26554}
}
Start for free →