articleNature BiotechnologyJan 3, 2022HYBRID OA

SignalP 6.0 predicts all five types of signal peptides using protein language models

FTFelix TeufelJJJosé Juan Almagro ArmenterosARAlexander Rosenberg JohansenMHMagnús Halldór GíslasonSISilas Irby Pihl

ETH Zurich · Technical University of Denmark · +8 more institutions

PubMed
Indexed incrossrefpubmed

Abstract

Signal peptides (SPs) are short amino acid sequences that control protein secretion and translocation in all living organisms. SPs can be predicted from sequence data, but existing algorithms are unable to detect all known types of SPs. We introduce SignalP 6.0, a machine learning model that detects all five SP types and is applicable to metagenomic data.

Citation impact

2,686
total citations
FWCI
211.97
Percentile
100%
References
36
Citations per year

Authors

10
  • FT
    Felix TeufelCorresponding

    ETH Zurich, Technical University of Denmark

  • JJ
    José Juan Almagro Armenteros

    University of Copenhagen, Novo Nordisk Foundation

  • AR
    Alexander Rosenberg Johansen

    Stanford University

  • MH
    Magnús Halldór Gíslason

    Copenhagen University Hospital, Rigshospitalet

  • SI
    Silas Irby Pihl

    Technical University of Denmark

Topics & keywords

Keywords
  • Signal peptide
  • Secretion
  • Secretory protein
  • Peptide sequence
  • Protein sequencing
  • SIGNAL (programming language)
  • Protein Sorting Signals
No related works found for this paper.

Funding