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

2022/07/01 by Felix Teufel, José Juan Almagro Armenteros, Alexander Rosenberg Johansen +7 · 39 citations
Biochemistry, Genetics and Molecular Biology · #Machine Learning in Bioinformatics #Genomics and Phylogenetic Studies #RNA and protein synthesis mechanisms

paper · doi:10.3929/ethz-b-000524414

openalex publication_date 2022/07/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• Immunopeptidomics reveals determinants of Mycobacterium tuberculosis antigen presentation on MHC class I
• Reverse vaccinology for hookworms: a rational selection of vaccinable antigens against parasitic nematodes
• Intersecting experimental evolution and CRISPR screens to identify novel toxin resistance loci
• Proteomic analyses reveal the key role of gene co-option in the evolution of the scaly-foot snail scleritome
• Improving Signal and Transit Peptide Predictions Using AlphaFold2-predicted Protein Structures
• Functional diversification of a wild potato immune receptor at its center of origin
• CCDC134 controls TLR biogenesis through the ER chaperone Gp96
• Finding functional motifs in protein sequences with deep learning and natural language models
• InterPro in 2022
• Guiding questions to avoid data leakage in biological machine learning applications
• Beyond venomous fangs: Uloboridae spiders have lost their venom but not their toxicity
• Are protein language models the new universal key?
• A type II secreted subtilase from commensal rhizobacteria cleaves immune elicitor peptides and suppresses flg22-induced immune activation
• Linear motifs regulating protein secretion, sorting and autophagy in Leishmania parasites are diverged with respect to their host equivalents
• Saccharibacteria deploy two distinct type IV pili, driving episymbiosis, host competition, and twitching motility
• Purification and characterization of a novel antibacterial peptide against Clostridium perfringens
• Mapping the ultrastructural topology of the corynebacterial cell surface
• Mapping the ultrastructural topology of the corynebacterial cell surface
• Degradation Behavior of Aliphatic–Aromatic Polyesters: from Microplastic-free Composting to Enzyme-Driven Recycling Possibility
• C‐terminal anchor endolysins—proposing a third class of tailed bacteriophage endolysins
• Haptophyte-infecting viruses change the genome condensing proteins of dinoflagellates
• Comprehensive prediction and analysis of human protein essentiality based on a pretrained large language model
• Codon language embeddings provide strong signals for protein engineering
• DeepTMHMM predicts alpha and beta transmembrane proteins using deep neural networks
• Understanding the substrate recognition and catalytic mechanism of 2-O-methyl fucosidases from glycoside hydrolase family 139
• An ecological-evolutionary perspective on the genomic diversity and habitat preferences of the Acidobacteriota
• Massive experimental quantification allows interpretable deep learning of protein aggregation
• Functional diversification of dietary plant small molecules by the gut microbiome
• Localization of heme biosynthesis in the diatom Phaeodactylum tricornutum and differential expression of multi-copy enzymes
• iMFP-LG: Identify Novel Multi-functional Peptides Using Protein Language Models and Graph-based Deep Learning
• HPClas: A data‐driven approach for identifying halophilic proteins based on catBoost
• Food production from air: gas precision fermentation with hydrogen-oxidising bacteria
• Bioinformatic discovery of type 11 secretion system (T11SS) cargo across the Proteobacteria
• A new paradigm for outer membrane protein biogenesis in the Bacteroidota
• A third type of PETase from the marine Halopseudomonas lineage
• TropiCODB: A multi-omics resource for supporting biodesign in tropical crops
• Oxidative cleavage of methyl-esterified pectic homogalacturonan by an AA17 lytic polysaccharide monooxygenase from Phytophthora infestans
• In situ structure of a bacterial flagellar motor at subnanometre resolution reveals adaptations for increased torque
• Multi-omics characterization of a lytic phage targeting Listeria monocytogenes
• Investigations on genomic, topological and structural properties of diguanylate cyclases involved in Vibrio cholerae biofilm signalling using in silico techniques: Promising drug targets in combating cholera

Related

• SignalP 6.0 predicts all five types of signal peptides using protein language models
• Machine Learning for Protein Function
• Combined Genome and Protein Statistical Features Improved the Prediction of Genes Encoding Antimicrobial Peptides: A Machine Learning Based Approach
• S 2 ‐ PepAnalyst : A Web Tool for Predicting Plant Small Signalling Peptides
• Finding functional motifs in protein sequences with deep learning and natural language models