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

Transfer learning to leverage larger datasets for improved prediction of protein stability changes

Henry Dieckhaus iD, Michael Brocidiacono, Nicholas Z Randolph iD, Brian Kuhlman iD

Proceedings of the National Academy of Sciences · 06.02.2024 · 121 (6)

DOI: 10.1073/pnas.2314853121 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 29.01.2024. Verfasst von Henry Dieckhaus und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biochemistry and Biophysics, University of North Carolina School of Medicine, Chapel Hill, NC 27599. Hauptthemen laut MEDLINE: Neural Networks, Computer, Proteins. Die Arbeit wurde bisher 246-mal zitiert (Crossref) und nennt 44 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, NSF | EDU | Division of Graduate Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Amino acid mutations that lower a protein’s thermodynamic stability are implicated in numerous diseases, and engineered proteins with enhanced stability can be important in research and medicine. Computational methods for predicting how mutations perturb protein stability are, therefore, of great interest. Despite recent advancements in protein design using deep learning, in silico prediction of stability changes has remained challenging, in part due to a lack of large, high-quality training datasets for model development. Here, we describe ThermoMPNN, a deep neural network trained to predict stability changes for protein point mutations given an initial structure. In doing so, we demonstrate the utility of a recently released megascale stability dataset for training a robust stability model. We also employ transfer learning to leverage a second, larger dataset by using learned features extracted from ProteinMPNN, a deep neural network trained to predict a protein’s amino acid sequence given its three-dimensional structure. We show that our method achieves state-of-the-art performance on established benchmark datasets using a lightweight model architecture that allows for rapid, scalable predictions. Finally, we make ThermoMPNN readily available as a tool for stability prediction and design.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerProteinsAmino Acid SequenceProtein StabilityMachine Learning

Stichwörter der Autor:innen

deep learningpoint mutationprotein stabilitytransfer learning

Substanzen

Proteins

Autor:innen und Institutionen

  • Department of Biochemistry and Biophysics, University of North Carolina School of Medicine, Chapel Hill, NC 27599.
  • Division of Chemical Biology and Medicinal Chemistry, University of North Carolina Eshelman School of Pharmacy, Chapel Hill, NC 27599.
  • Department of Bioinformatics and Computational Biology, University of North Carolina School of Medicine, Chapel Hill, NC 27599.
  • Lineberger Comprehensive Cancer Center, University of North Carolina School of Medicine, Chapel Hill, NC 27599.

ORCID-Profile: Henry Dieckhaus, Nicholas Z Randolph, Brian Kuhlman

Förderung

  • NIGMS NIH HHS
  • HHS | NIH | National Institute of General Medical Sciences
  • NSF | EDU | Division of Graduate Education

Zitieren

APA

Dieckhaus, H., Brocidiacono, M., Randolph, N. Z., & Kuhlman, B. (2024). Transfer learning to leverage larger datasets for improved prediction of protein stability changes. Proceedings of the National Academy of Sciences, 121(6). https://doi.org/10.1073/pnas.2314853121

Vancouver

Dieckhaus H, Brocidiacono M, Randolph NZ, Kuhlman B. Transfer learning to leverage larger datasets for improved prediction of protein stability changes. Proceedings of the National Academy of Sciences. 2024;121(6). doi:10.1073/pnas.2314853121

BibTeX
@article{Dieckhaus2024,
  author = {Dieckhaus, Henry and Brocidiacono, Michael and Randolph, Nicholas Z and Kuhlman, Brian},
  title = {Transfer learning to leverage larger datasets for improved prediction of protein stability changes},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2024},
  volume = {121},
  number = {6},
  doi = {10.1073/pnas.2314853121}
}
Kostenlos starten →