DeepPeptide predicts cleaved peptides in proteins using conditional random fields

Abstract Motivation Peptides are ubiquitous throughout life and involved in a wide range of biological processes, ranging from neural signaling in higher organisms to antimicrobial peptides in bacteria. Many peptides are generated post-translationally by cleavage of precursor proteins and can thus n...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Bioinformatics (Oxford, England) England), 2023-10, Vol.39 (10)
Hauptverfasser: Teufel, Felix, Refsgaard, Jan Christian, Madsen, Christian Toft, Stahlhut, Carsten, Grønborg, Mads, Winther, Ole, Madsen, Dennis
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Abstract Motivation Peptides are ubiquitous throughout life and involved in a wide range of biological processes, ranging from neural signaling in higher organisms to antimicrobial peptides in bacteria. Many peptides are generated post-translationally by cleavage of precursor proteins and can thus not be detected directly from genomics data, as the specificities of the responsible proteases are often not completely understood. Results We present DeepPeptide, a deep learning model that predicts cleaved peptides directly from the amino acid sequence. DeepPeptide shows both improved precision and recall for peptide detection compared to previous methodology. We show that the model is capable of identifying peptides in underannotated proteomes. Availability and implementation DeepPeptide is available online at ku.biolib.com/DeepPeptide.
ISSN:1367-4811
1367-4803
1367-4811
DOI:10.1093/bioinformatics/btad616