Related Experiment Video
Updated: Oct 12, 2025
09:34
A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
Published on: September 25, 2021
4.2K
Predicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning
1Electrical Engineering, City University of Hong Kong, Hong Kong, China.
BMC Biology
|November 25, 2021
Summary
Accurately predicting virus hosts is crucial for understanding ecosystems and developing phage therapy. A new semi-supervised learning model, HostG, improves virus host prediction, even for novel viruses and taxa, by using graph convolutional networks.
Area of Science:
- Microbiology
- Bioinformatics
- Computational Biology
Background:
- Prokaryotic viruses are abundant and diverse, playing key roles in ecosystems.
- Understanding virus-host relationships is vital for ecological studies and bacteriophage therapy.
- Current computational host prediction methods face challenges due to limited known relationships and ambiguous sequence similarities.
Purpose of the Study:
- To develop an accurate computational model for predicting virus hosts, especially for novel viruses.
- To improve upon existing methods for virus host classification.
Main Methods:
- A semi-supervised learning model named HostG was developed.
- A knowledge graph was constructed using virus-virus protein similarity and virus-host DNA sequence similarity.
- Graph convolutional networks (GCNs) were employed for host prediction, minimizing expected calibrated error (ECE) for confident predictions.
Main Results:
- HostG demonstrated superior performance compared to state-of-the-art methods on simulated and real sequencing data.
- The model effectively predicted hosts for novel viruses.
- HostG showed a particular advantage in predicting hosts from new taxa.
Conclusions:
- HostG's GCN-based semi-supervised learning approach is effective for virus host prediction.
- The model offers improved accuracy and the ability to predict hosts for previously uncharacterized viral taxa.
More Related Videos
Related Concept Videos
01:29Viruses of Archaea
162
Archaeal viruses play a crucial role in the ecosystems of extremophilic archaea, particularly those belonging to the phyla Euryarchaeota and Crenarchaeota. By shaping host evolution and facilitating gene transfer, these viruses influence microbial communities and contribute to genetic diversity in extreme environments. The archaea they infect thrive in acidic hot springs and hydrothermal vents characterized by high temperatures and low pH. Archaeal viruses exhibit remarkable structural...
162
01:26Size and Structure of Viral Genomes
229
Viral genomes exhibit remarkable diversity in size, structure, and composition, influencing their replication strategies and interactions with host cells. These genomes consist of either DNA or RNA and may be linear or circular. Additionally, they can be single-stranded or double-stranded, with each configuration affecting how the virus propagates within a host. RNA viruses, for instance, generally have smaller genomes than DNA viruses, a factor that contributes to their high mutation rates and...
229
01:29Viruses with RNA Genomes
216
RNA viruses are categorized into positive-strand, negative-strand, or double-stranded groups based on their genomic structure and replication mechanisms. This classification dictates how they exploit host cellular machinery for protein synthesis and replication. Some RNA viruses also utilize reverse transcription as part of their life cycle, further diversifying their replication strategies.Positive-Strand RNA VirusesPositive-strand RNA viruses have genomes that function directly as messenger...
216