DepoScope: Accurate phage depolymerase annotation and domain delineation using large language models
PLOS Computational Biology · 05.08.2024 · 20 (8) · e1011831
DOI: 10.1371/journal.pcbi.1011831 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 05.08.2024. Verfasst von Robby Concha-Eloko und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Integrative Systems Biology (I2SysBio), Universitat de Valencia-CSIC, Paterna, Spain. Hauptthemen laut MEDLINE: Bacteriophages, Computational Biology. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Flemish Government under the “Onderzoeksprogramma Articiële Intelligentie (AI) Vlaanderen” program, Conselleria d’Innovació, Universitats, Ciència i Societat Digital (Generalitat Valenciana, Ramón y Cajal.
Abstract (Originalsprache)
Bacteriophages (phages) are viruses that infect bacteria. Many of them produce specific enzymes called depolymerases to break down external polysaccharide structures. Accurate annotation and domain identification of these depolymerases are challenging due to their inherent sequence diversity. Hence, we present DepoScope, a machine learning tool that combines a fine-tuned ESM-2 model with a convolutional neural network to identify depolymerase sequences and their enzymatic domains precisely. To accomplish this, we curated a dataset from the INPHARED phage genome database, created a polysaccharide-degrading domain database, and applied sequential filters to construct a high-quality dataset, which is subsequently used to train DepoScope. Our work is the first approach that combines sequence-level predictions with amino-acid-level predictions for accurate depolymerase detection and functional domain identification. In that way, we believe that DepoScope can greatly enhance our understanding of phage-host interactions at the level of depolymerases.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Institute for Integrative Systems Biology (I2SysBio), Universitat de Valencia-CSIC, Paterna, Spain.
- KERMIT, Department of Data Analysis and Mathematical Modelling, Ghent University, Ghent, Belgium.
- Laboratory of Applied Biotechnology, Department of Biotechnology, Ghent University, Ghent, Belgium.
ORCID-Profile: Bernard De Baets, Dimitri Boeckaerts
Förderung
- Flemish Government under the “Onderzoeksprogramma Articiële Intelligentie (AI) Vlaanderen” program
- Conselleria d’Innovació, Universitats, Ciència i Societat Digital (Generalitat Valenciana
- Ramón y Cajal
- Vlaamse Overheid
- Conselleria de Innovación, Universidades, Ciencia y Sociedad Digital, Generalitat Valenciana
- Agencia Estatal de Investigación
- European Society of Clinical Microbiology and Infectious Diseases
- Fonds Wetenschappelijk Onderzoek
Zitieren
APA
Concha-Eloko, R., Stock, M., De Baets, B., Briers, Y., Sanjuán, R., Domingo-Calap, P., & Boeckaerts, D. (2024). DepoScope: Accurate phage depolymerase annotation and domain delineation using large language models. PLOS Computational Biology, 20(8), e1011831. https://doi.org/10.1371/journal.pcbi.1011831
Vancouver
Concha-Eloko R, Stock M, De Baets B, Briers Y, Sanjuán R, Domingo-Calap P, et al. DepoScope: Accurate phage depolymerase annotation and domain delineation using large language models. PLOS Computational Biology. 2024;20(8):e1011831. doi:10.1371/journal.pcbi.1011831
BibTeX
@article{ConchaEloko2024,
author = {Concha-Eloko, Robby and Stock, Michiel and De Baets, Bernard and Briers, Yves and Sanjuán, Rafael and Domingo-Calap, Pilar and Boeckaerts, Dimitri},
title = {DepoScope: Accurate phage depolymerase annotation and domain delineation using large language models},
journal = {PLOS Computational Biology},
year = {2024},
volume = {20},
number = {8},
pages = {e1011831},
doi = {10.1371/journal.pcbi.1011831}
}
EUVIMED