OrgNet+: towards robust protein stability prediction with convolutional neural networks
Bioinformatics · 01.07.2026 · 42 (Supplement_1)
DOI: 10.1093/bioinformatics/btag258 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 07.07.2026. Verfasst von Anastasia Sarycheva und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Science, Constructor University Bremen gGmbH, Bremen 28759, Germany. Hauptthemen laut MEDLINE: Proteins, Computational Biology, Software. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Motivation Predicting the effect of single-point mutations on protein stability is a central problem in molecular biology and protein engineering. Recent structure-based deep learning methods, particularly 3D convolutional neural networks (3D CNNs), have achieved strong predictive performance by leveraging high-resolution protein structures. However, proteins exist as heterogeneous conformational ensembles rather than single static structures, and the impact of conformational flexibility on structure-based ΔΔG predictors remains poorly characterized. Consequently, current models may yield unstable or even contradictory predictions when evaluated across alternative, yet equally plausible, conformations of the same protein. Results We introduce OrgNet+, a conformational ensemble-aware and orientation-gnostic framework that explicitly incorporates protein structure flexibility during training. OrgNet+ is trained on augmented datasets comprising diverse conformational ensembles generated using a comprehensive set of molecular modelling methods: normal mode analysis, molecular dynamics, Monte-Carlo simulations, and a generative deep learning model. Across all ensemble types, OrgNet+ substantially reduces intra-ensemble prediction variance while simultaneously improving predictive accuracy. The improved performance extends to standard single-reference-structure benchmarks, even though OrgNet+ was trained exclusively on conformational ensembles and never exposed to the reference experimental structures. Availability and implementation OrgNet+ is available at https://github.com/i-Molecule/OrgNet.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Science, Constructor University Bremen gGmbH, Bremen 28759, Germany.
- Constructor Labs, Bremen 28759, Germany.
ORCID-Profile: Petr Popov
Zitieren
APA
Sarycheva, A., Shumilov, A., & Popov, P. (2026). OrgNet+: towards robust protein stability prediction with convolutional neural networks. Bioinformatics, 42(Supplement_1). https://doi.org/10.1093/bioinformatics/btag258
Vancouver
Sarycheva A, Shumilov A, Popov P. OrgNet+: towards robust protein stability prediction with convolutional neural networks. Bioinformatics. 2026;42(Supplement_1). doi:10.1093/bioinformatics/btag258
BibTeX
@article{Sarycheva2026,
author = {Sarycheva, Anastasia and Shumilov, Aleksandr and Popov, Petr},
title = {OrgNet+: towards robust protein stability prediction with convolutional neural networks},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {Supplement_1},
doi = {10.1093/bioinformatics/btag258}
}
EUVIMED