Predicting the hosts of prokaryotic viruses using GCN-based semi-supervised learning

TL;DR

This paper introduces HostG, a semi-supervised GCN-based model that improves virus host prediction accuracy by leveraging virus-virus and virus-host similarities, outperforming existing methods on simulated and real data.

Contribution

The work presents a novel semi-supervised GCN model, HostG, that effectively predicts hosts for novel viruses using a knowledge graph and minimizes calibration error during training.

Findings

HostG outperforms existing methods in host prediction accuracy.

It effectively predicts hosts from new taxa.

The model demonstrates robustness on both simulated and real datasets.

Abstract

Background: Prokaryotic viruses, which infect bacteria and archaea, are the most abundant and diverse biological entities in the biosphere. To understand their regulatory roles in various ecosystems and to harness the potential of bacteriophages for use in therapy, more knowledge of viral-host relationships is required. High-throughput sequencing and its application to the microbiome have offered new opportunities for computational approaches for predicting which hosts particular viruses can infect. However, there are two main challenges for computational host prediction. First, the empirically known virus-host relationships are very limited. Second, although sequence similarity between viruses and their prokaryote hosts have been used as a major feature for host prediction, the alignment is either missing or ambiguous in many cases. Thus, there is still a need to improve the accuracy of host prediction. Results: In this work, we present a semi-supervised learning model, named HostG, to conduct host prediction for novel viruses. We construct a knowledge graph by utilizing both virus-virus protein similarity and virus-host DNA sequence similarity. Then graph convolutional network (GCN) is adopted to exploit viruses with or without known hosts in training to enhance the learning ability. During the GCN training, we minimize the expected calibrated error (ECE) to ensure the confidence of the predictions. We tested HostG on both simulated and real sequencing data and compared its performance with other state-of-the-art methods specifcally designed for virus host classification (VHM-net, WIsH, PHP, HoPhage, RaFAH, vHULK, and VPF-Class). Conclusion: HostG outperforms other popular methods, demonstrating the efficacy of using a GCN-based semi-supervised learning approach. A particular advantage of HostG is its ability to predict hosts from new taxa.