SignalP 6.0 predicts all five types of signal peptides using protein language models
Felix TeufelSection for Bioinformatics, Department of Health Technology, Technical University of Denmark, Kongens Lyngby, DenmarkJosé Juan Almagro ArmenterosNovo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, DenmarkAlexander Rosenberg JohansenDepartment of Computer Science, Stanford University, Stanford, CA, USAMagnús Halldór GíslasonCenter for Genomic Medicine, Rigshospitalet (Copenhagen University Hospital), Copenhagen, DenmarkSilas Irby PihlSection for Bioinformatics, Department of Health Technology, Technical University of Denmark, Kongens Lyngby, DenmarkKonstantinos D. TsirigosEMBL-EBI, Wellcome Genome Campus, Cambridge, UKOle WintherCenter for Genomic Medicine, Rigshospitalet (Copenhagen University Hospital), Copenhagen, DenmarkSøren BrunakNovo Nordisk Foundation Center for Protein Research, Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, DenmarkGunnar von HeijneScience for Life Laboratory, Stockholm University, Solna, SwedenHenrik NielsenSection for Bioinformatics, Department of Health Technology, Technical University of Denmark, Kongens Lyngby, Denmark
2022en
ABI
Аннотация
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.
Перевод пока недоступен
Идентификаторы
Цитирования и источники
Цитирований: 2Использованных источников: 0