vHULK, a New Tool for Bacteriophage Host Prediction Based on Annotated Genomic Features and Neural Networks

Amgarten, Deyvid; Iha, Bruno Koshin Vázquez; Piroupo, Carlos Morais; Silva, da; Setúbal, João Carlos

doi:10.1089/phage.2021.0016

Cited by 10 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2022 )—much higher than the sensitivity observed in our study (52.2 per cent). In contrast, their reported genus-level accuracies for VHMN (31.1 per cent) and RaFAH (71.3 per cent) (see Figure 6 in Amgarten et al. 2022 ) were much lower than those observed here (91.7 per cent and 95.1 per cent, respectively)—a difference that may be caused by the low diversity of taxa investigated.…”

Section: Resultscontrasting

confidence: 90%

“…In a follow-up study, the same authors developed CHERRY and demonstrated prediction accuracies ranging from less than 20 per cent (for the alignment-based PHIST) to ∼40 per cent (vHULK and VHMN) to almost 80 per cent (CHERRY) at the species-level and from ∼35 per cent–40 per cent (PHIST, PHP, VPF-Class, and WIsH) to ∼60 per cent–70 per cent (HostG, RaFAH, VHMN, and vHULK) to more than 80 per cent (CHERRY) at the genus-level (see Figure 4B in Shang and Sun 2022 ). The authors of vHULK self-reported accuracies of 95.2 per cent and 99.1 per cent for E. coli and G. terrae at the genus-level, with 81.9 per cent and 90.1 per cent sensitivity and 97.1 per cent and 99.8 per cent specificity, respectively (see Table 3 in Amgarten et al. 2022 )—much higher than the sensitivity observed in our study (52.2 per cent).…”

Section: Resultscontrasting

confidence: 78%

“…In contrast to confirmatory tools which are generally based on a single type of information (such as exact sequence matches or k -mer profiles), several of the exploratory tools included in this study—CHERRY ( Shang and Sun 2022 ), HostG ( Shang and Sun 2021 ), RaFAH ( Coutinho et al. 2021 ), vHULK ( Amgarten et al. 2022 ), VHMN ( Wang et al.…”

Section: Resultsmentioning

confidence: 99%

“…2017 ), as well as the exploratory tools CHERRY v.1.0 ( Shang and Sun 2022 ), HostG v.1.0 ( Shang and Sun 2021 ), Random Forest Assignment of Hosts (RaFAH) v.1.0 ( Coutinho et al. 2021 ), viral Host UnveiLing Kit (vHULK) v.2.0 ( Amgarten et al. 2022 ), VirHostMatcher-Net (VHMN) v.1.0 ( Wang et al.…”

Section: Methodsmentioning

confidence: 99%

See 3 more Smart Citations

Computational host range prediction—The good, the bad, and the ugly

Howell,

Versoza,

Pfeifer

2023

Virus Evolution

View full text Add to dashboard Cite

The rapid emergence and spread of antimicrobial resistance across the globe have prompted the usage of bacteriophages (i.e., viruses that infect bacteria) in a variety of applications ranging from agriculture to biotechnology and medicine. In order to effectively guide the application of bacteriophages in these multifaceted areas, information about their host ranges – that is the bacterial strains or species that a bacteriophage can successfully infect and kill – is essential. Utilizing 16 broad-spectrum (polyvalent) bacteriophages with experimentally validated host ranges, we here benchmark the performance of 11 recently developed computational host range prediction tools that provide a promising and highly scalable supplement to traditional, but laborious, experimental procedures. We show that machine- and deep-learning approaches offer the highest levels of accuracy and precision – however, their predominant predictions at the species- or genus-level render them ill-suited for applications outside of an ecosystems metagenomics framework. In contrast, only moderate sensitivity (<80%) could be reached at the strain-level, albeit at low levels of precision (<40%). Taken together, these limitations demonstrate that there remains room for improvement in the active scientific field of in silico host prediction to combat the challenge of guiding experimental designs to identify the most promising bacteriophage candidates for any given application.

show abstract

Section: Resultscontrasting

confidence: 90%

Section: Resultscontrasting

confidence: 78%

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Computational host range prediction—The good, the bad, and the ugly

Howell,

Versoza,

Pfeifer

2023

Virus Evolution

View full text Add to dashboard Cite

show abstract

“…In Boeckaerts’s study [ 54 ], they employed random forest as optimal machine learning methods to predict bacteriophage hosts based on sequences of annotated RBP. RBP can be considered as a signal for PHI with the basic that RBP can recognize specific bacterial receptors on the bacterial cell surface and is regarded as the determinant for the specificity of phage infection [ 55 ]. This RBP-based method took nucleotide sequences along with protein sequence and structure data as comprehensive features basing on bacterial and viral sequences annotated as RBP protein rather than whole-genome sequences, and assigned query phage to the class of a specific bacterial host species in the constructed RBP database.…”

Section: Methods For Phi Predictionmentioning

confidence: 99%

Advances in phage–host interaction prediction: in silico method enhances the development of phage therapies

Nie,

Qiu,

Wei

et al. 2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

Phages can specifically recognize and kill bacteria, which lead to important application value of bacteriophage in bacterial identification and typing, livestock aquaculture and treatment of human bacterial infection. Considering the variety of human-infected bacteria and the continuous discovery of numerous pathogenic bacteria, screening suitable therapeutic phages that are capable of infecting pathogens from massive phage databases has been a principal step in phage therapy design. Experimental methods to identify phage–host interaction (PHI) are time-consuming and expensive; high-throughput computational method to predict PHI is therefore a potential substitute. Here, we systemically review bioinformatic methods for predicting PHI, introduce reference databases and in silico models applied in these methods and highlight the strengths and challenges of current tools. Finally, we discuss the application scope and future research direction of computational prediction methods, which contribute to the performance improvement of prediction models and the development of personalized phage therapy.

show abstract

Freshwater Viral Metagenome Analyses Targeting dsDNA Viruses

Moon,

Cho

2023

Methods in Molecular Biology

View full text Add to dashboard Cite

vHULK, a New Tool for Bacteriophage Host Prediction Based on Annotated Genomic Features and Neural Networks

Cited by 10 publications

References 31 publications

Computational host range prediction—The good, the bad, and the ugly

Computational host range prediction—The good, the bad, and the ugly

Advances in phage–host interaction prediction: in silico method enhances the development of phage therapies

Freshwater Viral Metagenome Analyses Targeting dsDNA Viruses

Contact Info

Product

Resources

About