EUVIMEDSkopri EUVIMED
Open access

Validation of de novo designed water‐soluble and transmembrane β‐barrels by in silico folding and melting

Alvaro Martin Hermosilla iD, Carolin Berner, Sergey Ovchinnikov, Anastassia A Vorobieva iD

Protein Science · 2024-07 · 33 (7)

DOI: 10.1002/pro.5033 ↗

At a glance

Journal article in Protein Science, 2024-07. Written by Alvaro Martin Hermosilla and 3 co-authors. Institution: Structural Biology Brussels, Vrije Universiteit Brussel, Brussels, Belgium. Major MEDLINE topics: Protein Folding, Solubility, Membrane Proteins. Cited 17 times so far (Crossref); 47 references. The full text is freely available in PubMed Central. Funded by: Vlaams Instituut voor Biotechnologie, National Science Foundation, Federation of European Biochemical Societies.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

In silico validation of de novo designed proteins with deep learning (DL)‐based structure prediction algorithms has become mainstream. However, formal evidence of the relationship between a high‐quality predicted model and the chance of experimental success is lacking. We used experimentally characterized de novo water‐soluble and transmembrane β‐barrel designs to show that AlphaFold2 and ESMFold excel at different tasks. ESMFold can efficiently identify designs generated based on high‐quality (designable) backbones. However, only AlphaFold2 can predict which sequences have the best chance of experimentally folding among similar designs. We show that ESMFold can generate high‐quality structures from just a few predicted contacts and introduce a new approach based on incremental perturbation of the prediction (“in silico melting”), which can reveal differences in the presence of favorable contacts between designs. This study provides a new insight on DL‐based structure prediction models explainability and on how they could be leveraged for the design of increasingly complex proteins; in particular membrane proteins which have historically lacked basic in silico validation tools.

Subjects

MeSH terms (MEDLINE)

Protein FoldingSolubilityMembrane ProteinsWaterComputer SimulationModels, MolecularProtein Conformation, beta-StrandDeep LearningAlgorithms

Author keywords

AlphaFold2ESMFoldde novo designmembrane proteinstructure predictionβ‐Sheet

Substances

Membrane ProteinsWater

Authors and institutions

  • Structural Biology Brussels, Vrije Universiteit Brussel, Brussels, Belgium.
  • VIB-VUB Center for Structural Biology, Brussels, Belgium.
  • John Harvard Distinguished Science Fellowship Program, Harvard University, Cambridge, Massachusetts, USA.
  • VIB Center for AI and Computational Biology, Belgium.

ORCID profiles: Alvaro Martin Hermosilla, Anastassia A Vorobieva

Funding

  • Vlaams Instituut voor Biotechnologie
  • National Science Foundation
  • Federation of European Biochemical Societies
  • NIH HHS
  • National Institutes of Health

Cite

APA

Hermosilla, A. M., Berner, C., Ovchinnikov, S., & Vorobieva, A. A. (2024). Validation of de novo designed water‐soluble and transmembrane β‐barrels by in silico folding and melting. Protein Science. https://doi.org/10.1002/pro.5033

Vancouver

Hermosilla AM, Berner C, Ovchinnikov S, Vorobieva AA. Validation of de novo designed water‐soluble and transmembrane β‐barrels by in silico folding and melting. Protein Science. 2024. doi:10.1002/pro.5033

BibTeX
@article{Hermosilla2024,
  author = {Hermosilla, Alvaro Martin and Berner, Carolin and Ovchinnikov, Sergey and Vorobieva, Anastassia A},
  title = {Validation of de novo designed water‐soluble and transmembrane β‐barrels by in silico folding and melting},
  journal = {Protein Science},
  year = {2024},
  doi = {10.1002/pro.5033}
}
Start for free →