Journal article
SignalP 5.0 improves signal peptide predictions using deep neural networks
Bayesian modeling, Machine learning, Molecular Evolution, and Metagenomics, Bioinformatics, Department of Health Technology, Technical University of Denmark1
Bioinformatics, Department of Health Technology, Technical University of Denmark2
Department of Health Technology, Technical University of Denmark3
University of Copenhagen4
National Food Institute, Technical University of Denmark5
Research Group for Genomic Epidemiology, National Food Institute, Technical University of Denmark6
Integrative Systems Biology, Bioinformatics, Department of Health Technology, Technical University of Denmark7
Stockholm University8
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.
Language: | English |
---|---|
Publisher: | Nature Publishing Group US |
Year: | 2019 |
Pages: | 420-423 |
Journal subtitle: | Science and Business of Biotechnology |
ISSN: | 15461696 and 10870156 |
Types: | Journal article |
DOI: | 10.1038/s41587-019-0036-z |
ORCIDs: | Tsirigos, Konstantinos D. , Petersen, Thomas Nordahl , Nielsen, Henrik , 0000-0002-1966-3205 and 0000-0003-0316-5866 |