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

Felix G Teufel Jose Juan Almagro ArmenterosAlexander Rosenberg JohansenMagnús Halldór GíslasonSilas Irby PihlKonstantinos D Tsirigos Ole Winther Soren Brunak Gunnar von Heijne Henrik Nielsen

Published in: Nature biotechnology (2022)

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.

Keyphrases

amino acid
machine learning
big data
electronic health record
artificial intelligence
autism spectrum disorder
deep learning
protein protein
gram negative
data analysis
wastewater treatment
antibiotic resistance genes