EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Transformer-based deep learning for predicting protein properties in the life sciences

Abel Chandra iD, Laura Tünnermann, Tommy Löfstedt, Regina Gratz iD

eLife · 18.01.2023 · 12

DOI: 10.7554/elife.82819 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift eLife, online erschienen am 18.01.2023. Verfasst von Abel Chandra und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computing Science, Umeå University, Umeå, Sweden. Hauptthemen laut MEDLINE: Deep Learning, Biological Science Disciplines. Die Arbeit wurde bisher 204-mal zitiert (Crossref) und nennt 164 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Kempestiftelserna.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent developments in deep learning, coupled with an increasing number of sequenced proteins, have led to a breakthrough in life science applications, in particular in protein property prediction. There is hope that deep learning can close the gap between the number of sequenced proteins and proteins with known properties based on lab experiments. Language models from the field of natural language processing have gained popularity for protein property predictions and have led to a new computational revolution in biology, where old prediction results are being improved regularly. Such models can learn useful multipurpose representations of proteins from large open repositories of protein sequences and can be used, for instance, to predict protein properties. The field of natural language processing is growing quickly because of developments in a class of models based on a particular model—the Transformer model. We review recent developments and the use of large-scale Transformer models in applications for predicting protein characteristics and how such models can be used to predict, for example, post-translational modifications. We review shortcomings of other deep learning models and explain how the Transformer models have quickly proven to be a very promising way to unravel information hidden in the sequences of amino acids.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningBiological Science DisciplinesAmino Acid SequenceAmino AcidsLanguage

Stichwörter der Autor:innen

computational biologydeep learninglife sciencesmachine learningprotein property predictionsystems biologytransformers

Substanzen

Amino Acids

Autor:innen und Institutionen

  • Department of Computing Science, Umeå University, Umeå, Sweden.
  • Umeå Plant Science Centre (UPSC), Department of Forest Genetics and Plant Physiology, Swedish University of Agricultural Sciences, Umeå, Sweden.
  • Department of Forest Ecology and Management, Swedish University of Agricultural Sciences, Umeå, Sweden.

ORCID-Profile: Abel Chandra, Regina Gratz

Förderung

  • Kempestiftelserna

Zitieren

APA

Chandra, A., Tünnermann, L., Löfstedt, T., & Gratz, R. (2023). Transformer-based deep learning for predicting protein properties in the life sciences. eLife, 12. https://doi.org/10.7554/elife.82819

Vancouver

Chandra A, Tünnermann L, Löfstedt T, Gratz R. Transformer-based deep learning for predicting protein properties in the life sciences. eLife. 2023;12. doi:10.7554/elife.82819

BibTeX
@article{Chandra2023,
  author = {Chandra, Abel and Tünnermann, Laura and Löfstedt, Tommy and Gratz, Regina},
  title = {Transformer-based deep learning for predicting protein properties in the life sciences},
  journal = {eLife},
  year = {2023},
  volume = {12},
  doi = {10.7554/elife.82819}
}
Kostenlos starten →