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

Felix Teufel; José Juan Almagro Armenteros; Alexander Rosenberg Johansen; Magnús Halldór Gíslason; Silas Irby Pihl; Konstantinos D. Tsirigos; Ole Winther; Søren Brunak; Gunnar von Heijne; Henrik Nielsen

doi:10.1038/s41587-021-01156-3

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

Felix Teufel, José Juan Almagro Armenteros, Alexander Rosenberg Johansen, Magnús Halldór Gíslason, Silas Irby Pihl, Konstantinos D. Tsirigos, Ole Winther, Søren Brunak, Gunnar von Heijne, Henrik Nielsen^*

^*Corresponding author for this work

Research output: Contribution to journal › Comment/debate › Research

976 Citations (Scopus)

36 Downloads (Pure)

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.

Original language	English
Journal	Nature Biotechnology
Volume	40
Pages (from-to)	1023-1025
ISSN	1087-0156
DOIs	https://doi.org/10.1038/s41587-021-01156-3
Publication status	Published - 2022

Bibliographical note

Publisher Copyright:
© 2022, The Author(s).

Access to Document

10.1038/s41587-021-01156-3Licence: CC BY

FulltextFinal published version, 2.53 MBLicence: CC BY

Cite this

SignalP 6.0 predicts all five types of signal peptides using protein language models. / Teufel, Felix; Almagro Armenteros, José Juan; Johansen, Alexander Rosenberg; Gíslason, Magnús Halldór; Pihl, Silas Irby; Tsirigos, Konstantinos D.; Winther, Ole ; Brunak, Søren; von Heijne, Gunnar; Nielsen, Henrik.

In: Nature Biotechnology, Vol. 40, 2022, p. 1023-1025.

Research output: Contribution to journal › Comment/debate › Research

Teufel, Felix ; Almagro Armenteros, José Juan ; Johansen, Alexander Rosenberg ; Gíslason, Magnús Halldór ; Pihl, Silas Irby ; Tsirigos, Konstantinos D. ; Winther, Ole ; Brunak, Søren ; von Heijne, Gunnar ; Nielsen, Henrik. / SignalP 6.0 predicts all five types of signal peptides using protein language models. In: Nature Biotechnology. 2022 ; Vol. 40. pp. 1023-1025.

@article{3728c1fabbe2420da524ea4ab74e8bd3,

title = "SignalP 6.0 predicts all five types of signal peptides using protein language models",

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.",

author = "Felix Teufel and {Almagro Armenteros}, {Jos{\'e} Juan} and Johansen, {Alexander Rosenberg} and G{\'i}slason, {Magn{\'u}s Halld{\'o}r} and Pihl, {Silas Irby} and Tsirigos, {Konstantinos D.} and Ole Winther and S{\o}ren Brunak and {von Heijne}, Gunnar and Henrik Nielsen",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s).",

year = "2022",

doi = "10.1038/s41587-021-01156-3",

language = "English",

volume = "40",

pages = "1023--1025",

journal = "Nature Biotechnology",

issn = "1087-0156",

publisher = "nature publishing group",

}

TY - JOUR

T1 - SignalP 6.0 predicts all five types of signal peptides using protein language models

AU - Teufel, Felix

AU - Almagro Armenteros, José Juan

AU - Johansen, Alexander Rosenberg

AU - Gíslason, Magnús Halldór

AU - Pihl, Silas Irby

AU - Tsirigos, Konstantinos D.

AU - Winther, Ole

AU - Brunak, Søren

AU - von Heijne, Gunnar

AU - Nielsen, Henrik

PY - 2022

Y1 - 2022

N2 - 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.

AB - 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.

U2 - 10.1038/s41587-021-01156-3

DO - 10.1038/s41587-021-01156-3

M3 - Comment/debate

C2 - 34980915

AN - SCOPUS:85122179157

VL - 40

SP - 1023

EP - 1025

JO - Nature Biotechnology

JF - Nature Biotechnology

SN - 1087-0156

ER -