DepoScope: Accurate phage depolymerase annotation and domain delineation using large language models

DepoScope: точная аннотация деполимераз фагов и определение границ доменов с использованием больших языковых моделей
Michiel Stock, Bernard De Baets C, Rafael Sanjuán, Pilar Domingo‐Calap, Yves Briers, Dimitri Boeckaerts, Robby Concha-Eloko
2024-08-05

ESM-2INPHAREDconvolutional neural networkdomain delineationphage depolymerase annotation
Abstract 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 precisely identify depolymerase sequences and their enzymatic domains. 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 are subsequently used to train DepoScope. Our work is the first approach that combines sequence-level predictions with amino-acid-level predictions for an accurate depolymerase detection and functional domain identification. In that way, we believe that DepoScope can enhance our understanding of phage-host interactions at the level of depolymerases. Summary with Key Messages Phage depolymerases are proteins that play a crucial role in the first step of a phage replication cycle. As a result, they are both important from a biological perspective and a therapeutical perspective. Current methods to accurately annotate phage depolymerases and their associated enzymatic domains remains challenging due to their inherent high sequence diversity. We have developed DepoScope, a language-based artificial intelligence model that can accurately identify phage depolymerases and their specific enzymatic domains. We provide full public access to the DepoScope code and database to give broad access to the research community and promote further research.
1
DepoScope addresses the challenge of highly diverse depolymerase sequences and is presented as the first approach combining sequence- and residue-level predictions for this task.
2
DepoScope combines a fine-tuned ESM-2 protein language model with a convolutional neural network to annotate phage depolymerases and delineate their enzymatic domains.
3
The authors curated a high-quality training dataset from the INPHARED phage genome database using sequential filtering procedures.
4
The method performs both sequence-level depolymerase detection and amino-acid-level functional domain identification in a unified approach.
5
The study created a dedicated database of polysaccharide-degrading domains to support depolymerase annotation and domain delineation.

bacteriophage depolymerases and their enzymatic domains

accurate sequence-level depolymerase annotation and amino-acid-level enzymatic domain delineation

Publication Details
Publication Date
2024-08-05
Journal
Publisher
ISSN
Cited by
41
Access Type
Author Information
Authors
Michiel Stock
Bernard De Baets C
Rafael Sanjuán
Pilar Domingo‐Calap
Yves Briers
Dimitri Boeckaerts
Robby Concha-Eloko
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%