TY - JOUR
T1 - SignalP 5.0 improves signal peptide predictions using deep neural networks
AU - Almagro Armenteros, José Juan
AU - Tsirigos, Konstantinos D
AU - Sønderby, Casper Kaae
AU - Petersen, Thomas Nordahl
AU - Winther, Ole
AU - Brunak, Søren
AU - von Heijne, Gunnar
AU - Nielsen, Henrik
PY - 2019/4
Y1 - 2019/4
N2 - Signal peptides (SPs) are short amino acid sequences in the amino terminus of many newly synthesized proteins that target proteins into, or across, membranes. Bioinformatic tools can predict SPs from amino acid sequences, but most cannot distinguish between various types of signal peptides. We present a deep neural network-based approach that improves SP prediction across all domains of life and distinguishes between three types of prokaryotic SPs.
AB - Signal peptides (SPs) are short amino acid sequences in the amino terminus of many newly synthesized proteins that target proteins into, or across, membranes. Bioinformatic tools can predict SPs from amino acid sequences, but most cannot distinguish between various types of signal peptides. We present a deep neural network-based approach that improves SP prediction across all domains of life and distinguishes between three types of prokaryotic SPs.
KW - Algorithms
KW - Amino Acid Sequence
KW - Archaeal Proteins/classification
KW - Bacterial Proteins/classification
KW - Biotechnology
KW - Computational Biology
KW - Eukaryota/genetics
KW - Neural Networks, Computer
KW - Protein Sorting Signals/genetics
KW - Sequence Analysis, Protein
KW - Software
U2 - 10.1038/s41587-019-0036-z
DO - 10.1038/s41587-019-0036-z
M3 - Journal article
C2 - 30778233
SN - 1087-0156
VL - 37
SP - 420
EP - 423
JO - Nature Biotechnology
JF - Nature Biotechnology
IS - 4
ER -