EUVIMEDEUVIMED entdecken
Crossref

ERIS2: A deep-learning platform for predicting mutation-induced protein stability changes

Srinivasan Ekambaram, Debarshi Kundu, Swaroop Ghosh, Nikolay V Dokholyan

Structure · 2026-10

DOI: 10.1016/j.str.2026.10.003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Structure, 2026-10. Verfasst von Srinivasan Ekambaram und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, University of Virginia, School of Medicine, Charlottesville, VA 22903, USA. Die Arbeit nennt 52 Literaturangaben. Gefördert von: National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurately predicting changes in protein thermodynamic stability upon mutation is a fundamental challenge in protein engineering and therapeutics. Deep learning has improved prediction, but many models remain limited by small, imbalanced training data and poor generalization across mutation types. Here, we present ERIS2, an attention-convolutional deep learning framework that integrates contextual sequence embeddings with atomistic and residue-level structural features from experimental protein structures to predict mutation-induced stability changes. Trained on large-scale experimental measurements combined with curated ProTherm data, a 5-fold ERIS2 ensemble achieved Pearson correlation coefficients of 0.69 on S461, 0.51 on S669, and 0.60 on S96, three blind-test datasets sequence-disjoint from all training configurations, and showed negligible anti-symmetry bias on Ssym forward and reverse pairs. ERIS2 is freely available as a structure-based web server without registration, providing a robust framework for protein stability prediction and advancing computational tools for protein engineering and therapeutic design.

Schlagwörter

Stichwörter der Autor:innen

ESM2attentiondeep learningmutation effectspoint mutationsprotein language modelprotein stabilitystructural featuresweb serverΔΔG prediction

Autor:innen und Institutionen

  • Department of Neurology, University of Virginia, School of Medicine, Charlottesville, VA 22903, USA.
  • Department of Computer Science and Engineering, Penn State University, University Park, PA 16802, USA.
  • School of Electrical Engineering and Computer Science, Penn State University, University Park, PA 16802, USA. Electronic address: szg212@psu.edu.
  • Department of Neurology, University of Virginia, School of Medicine, Charlottesville, VA 22903, USA; Department of Neuroscience, University of Virginia, School of Medicine, Charlottesville, VA 22903, USA; Department of…

Förderung

  • National Institutes of Health

Zitieren

APA

Ekambaram, S., Kundu, D., Ghosh, S., & Dokholyan, N. V. (2026). ERIS2: A deep-learning platform for predicting mutation-induced protein stability changes. Structure. https://doi.org/10.1016/j.str.2026.10.003

Vancouver

Ekambaram S, Kundu D, Ghosh S, Dokholyan NV. ERIS2: A deep-learning platform for predicting mutation-induced protein stability changes. Structure. 2026. doi:10.1016/j.str.2026.10.003

BibTeX
@article{Ekambaram2026,
  author = {Ekambaram, Srinivasan and Kundu, Debarshi and Ghosh, Swaroop and Dokholyan, Nikolay V},
  title = {ERIS2: A deep-learning platform for predicting mutation-induced protein stability changes},
  journal = {Structure},
  year = {2026},
  doi = {10.1016/j.str.2026.10.003}
}
Kostenlos starten →