ORIGAMI: Orientation-Aware Graph Neural Network for Assessing Multimeric Interfaces of Protein Complex Structures
Journal of Chemical Information and Modeling · 2026
DOI: 10.1021/acs.jcim.6c00988 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2026. Verfasst von Xinyu Wang und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Virginia Tech, Blacksburg, Virginia24061, United States. Hauptthemen laut MEDLINE: Graph Neural Networks, Proteins, Computational Biology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, Division of Biological Infrastructure, National Institute of General Medical Sciences.
Abstract (Originalsprache)
Deep-learning-based protein structure prediction methods have led to a paradigm shift in computational structural biology, yet reliably assessing the quality of computationally predicted multimeric structures remains challenging. Recent methods have demonstrated the benefits of employing graph neural networks for assessing multimeric interfaces of protein complexes but ignore geometric orientational features naturally occurring in 3-dimensional protein conformational space and act only on scalar weights. We present ORIGAMI, an orientation-aware graph neural network for assessing multimeric interfaces of protein complex structures that leverages both scalar and 3D vector node representations to perform symmetry-aware geometric operations while maintaining SO(3)-equivariance, capturing fine-grained orientational relationships between residues across protein–protein interfaces to estimate the interface local distance difference test (iLDDT) score. Tested on targets from multiple rounds of Critical Assessment of Structure Prediction (CASP) challenges, ORIGAMI achieves superior performance across multiple interface quality assessment benchmarks, with particularly strong gains in the expanded CASP16 interface-level evaluation and in controlled comparisons against both nonequivariant and equivariant graph neural network baselines. It also demonstrates robust cross-metric generalization by reproducing superposition-based DockQ scores with high fidelity, despite being trained only to estimate the superposition-free iLDDT score. ORIGAMI is freely available at https://github.com/Bhattacharya-Lab/ORIGAMI.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Computer Science, Virginia Tech, Blacksburg, Virginia24061, United States.
ORCID-Profile: Debswapna Bhattacharya
Förderung
- NIGMS NIH HHS
- Division of Biological Infrastructure
- National Institute of General Medical Sciences
Zitieren
APA
Wang, X., & Bhattacharya, D. (2026). ORIGAMI: Orientation-Aware Graph Neural Network for Assessing Multimeric Interfaces of Protein Complex Structures. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c00988
Vancouver
Wang X, Bhattacharya D. ORIGAMI: Orientation-Aware Graph Neural Network for Assessing Multimeric Interfaces of Protein Complex Structures. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.6c00988
BibTeX
@article{Wang2026,
author = {Wang, Xinyu and Bhattacharya, Debswapna},
title = {ORIGAMI: Orientation-Aware Graph Neural Network for Assessing Multimeric Interfaces of Protein Complex Structures},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
doi = {10.1021/acs.jcim.6c00988}
}
EUVIMED