EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Beyond native sequence recovery: Improved modeling of the sequence-energy landscape of protein structures

Foster Birnbaum iD, Amy E Keating iD

Proceedings of the National Academy of Sciences · 07.07.2026 · 123 (27)

DOI: 10.1073/pnas.2535494123 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 02.07.2026. Verfasst von Foster Birnbaum und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biology, Massachusetts Institute of Technology, Cambridge, MA 02139. Hauptthemen laut MEDLINE: Proteins, Computational Biology. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIGMS NIH HHS, HHS | NIH | National Institute of General Medical Sciences (NIGMS).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Computational protein design using machine learning models has advanced rapidly since the introduction of AlphaFold2. There is now a suite of tools that enable in silico design of proteins with desired structures and properties. Most design workflows require fitting a designed backbone with a sequence that stabilizes it, and many machine learning sequence design models have been proposed. These models are trained to recover the native sequence paired with a known structure, a task known as native sequence recovery (NSR). Here, we demonstrate the limitations of optimizing a sequence design model only for NSR. We show that NSR is often misaligned with more important metrics of model performance: the compatibility of the generated sequence with the desired fold and the ability of the model to predict the energetic effects of mutations. We introduce PottsMPNN, which is trained to generate a Potts energy function consisting of single-residue and residue-pair terms from a protein backbone, and we demonstrate that learning a Potts model reduces NSR but improves sequence generation and energy prediction. We also trained PottsMPNN with noised backbone structures and multiple sequence alignments. In tests on held-out data, NSR decreased, but the quality of the designed sequences and energy predictions improved. By demonstrating the limitations of optimizing for NSR and the effectiveness of strategies that avoid NSR overoptimization, our work advances sequence design and highlights future directions for the broader protein design field.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProteinsComputational BiologyModels, MolecularProtein ConformationMachine LearningAmino Acid SequenceProtein FoldingProtein Engineering

Stichwörter der Autor:innen

deep learningprotein designsequence designsequence–structure compatibilitystability prediction

Substanzen

Proteins

Autor:innen und Institutionen

  • Department of Biology, Massachusetts Institute of Technology, Cambridge, MA 02139.
  • Computational and Systems Biology, Massachusetts Institute of Technology, Cambridge, MA 02139.
  • Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139.

ORCID-Profile: Foster Birnbaum, Amy E Keating

Förderung

  • NIGMS NIH HHS
  • HHS | NIH | National Institute of General Medical Sciences (NIGMS)

Zitieren

APA

Birnbaum, F., & Keating, A. E. (2026). Beyond native sequence recovery: Improved modeling of the sequence-energy landscape of protein structures. Proceedings of the National Academy of Sciences, 123(27). https://doi.org/10.1073/pnas.2535494123

Vancouver

Birnbaum F, Keating AE. Beyond native sequence recovery: Improved modeling of the sequence-energy landscape of protein structures. Proceedings of the National Academy of Sciences. 2026;123(27). doi:10.1073/pnas.2535494123

BibTeX
@article{Birnbaum2026,
  author = {Birnbaum, Foster and Keating, Amy E},
  title = {Beyond native sequence recovery: Improved modeling of the sequence-energy landscape of protein structures},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2026},
  volume = {123},
  number = {27},
  doi = {10.1073/pnas.2535494123}
}
Kostenlos starten →