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

Teufel F, Almagro Armenteros JJ, Johansen AR, GĂ­slason MH, Pihl SI, Tsirigos KD, Winther O, Brunak S, von Heijne G, Nielsen H

Nat. Biotechnol. 40 (7) 1023-1025 [2022-07-00; online 2022-01-03]

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.

PubMed 34980915

DOI 10.1038/s41587-021-01156-3

Crossref 10.1038/s41587-021-01156-3

pmc: PMC9287161
pii: 10.1038/s41587-021-01156-3


Publications 9.5.1