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

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 specifically 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.

Phage–bacterial contig association prediction with a convolutional neural network

“…Several state-of-the-art tools are available for phage–host association prediction, including PHP ( Lu et al , 2021 ), HoPhage (consisting of HoPhage-G and HoPhage-S) ( Tan et al , 2022 ), VPF-Class ( Pons et al , 2021 ), VHM-Net ( Wang et al , 2020 ), vHULK ( Amgarten et al , 2020 ), RaFAH ( Coutinho et al , 2021 ) and HostG ( Shang and Sun, 2021 ). Each of these tools has its own limitations making it unsuitable for the question of predicting phage–host contig associations in natural metagenomic settings.…”

“…On the other hand, ContigNet can also take the whole phage and host genomes as input because it supports contigs with any length. We compared its performance with other methods on the whole genomes according to the experimental steps described in Shang and Sun (2021) by testing the methods on the whole dataset and the dataset with only phage–host pairs without alignment results. And the results are shown in Figures 11 and 12 .…”

“…Therefore, it is important to understand the association relationship between phages and their hosts. Several computational methods have been developed to assign viruses to their putative hosts ( Ahlgren et al , 2017 ; Amgarten et al , 2020 ; Coutinho et al , 2021 ; Galiez et al , 2017 ; Lu et al , 2021 ; Pons et al , 2021 ; Shang and Sun, 2021 ; Tan et al , 2022 ; Wang et al , 2020 ), most of which assign phages to their hosts of known bacterial genomes or at certain taxonomic levels ( Amgarten et al , 2020 ; Coutinho et al , 2021 ; Pons et al , 2021 ; Shang and Sun, 2021 ; Tan et al , 2022 ; Wang et al , 2020 ) except VirHostMatcher (VHM) ( Ahlgren et al , 2017 ) and WIsH ( Galiez et al , 2017 ).…”

“…vHULK ( Amgarten et al , 2020 ) applied deep neural networks to the phage–host prediction problem using features extracted from phage sequences as input. The latest proposed method HostG ( Shang and Sun, 2021 ) used a graph convolutional networks to take both phage–host and phage–phage relationships into consideration, and the alignment scores were used to aid the construction of the relationships. However, these predefined features extracted from sequences alone are not suitable to train complicated models to predict contig–contig relationship.…”

Accurate identification of bacteriophages from metagenomic data using Transformer

“…In this work, we present a method, named PhaMer, to identify phage contigs from metagenomic data. Because previous works have shown the importance of protein composition for phage classification [ 24 , 25 ], we employ a contextualized embedding model from natural language processing (NLP) to learn protein-associated patterns in phages. Specifically, by converting a sequence into a sentence composed of protein-based tokens, we employ the embedding model to learn both the protein composition and also their associations in phage sequences.…”