scholarly journals VirPreNet: a weighted ensemble convolutional neural network for the virulence prediction of influenza A virus using all eight segments

2020 ◽  
Author(s):  
Rui Yin ◽  
Zihan Luo ◽  
Pei Zhuang ◽  
Zhuoyi Lin ◽  
Chee Keong Kwoh
Keyword(s):  
Public Health ◽  
Neural Network ◽  
Convolutional Neural Network ◽  
Influenza A Virus ◽  
Influenza A ◽  
Lethal Dose ◽  
Influenza Viruses ◽  
Supplementary Information ◽  
Numerical Representation ◽  
Influenza A Viruses

Abstract Motivation Influenza viruses are persistently threatening public health, causing annual epidemics and sporadic pandemics. The evolution of influenza viruses remains to be the main obstacle in the effectiveness of antiviral treatments due to rapid mutations. Previous work has been investigated to reveal the determinants of virulence of the influenza A virus. To further facilitate flu surveillance, explicit detection of influenza virulence is crucial to protect public health from potential future pandemics. Results In this article, we propose a weighted ensemble convolutional neural network (CNN) for the virulence prediction of influenza A viruses named VirPreNet that uses all eight segments. Firstly, mouse lethal dose 50 is exerted to label the virulence of infections into two classes, namely avirulent and virulent. A numerical representation of amino acids named ProtVec is applied to the eight-segments in a distributed manner to encode the biological sequences. After splittings and embeddings of influenza strains, the ensemble CNN is constructed as the base model on the influenza dataset of each segment, which serves as the VirPreNet’s main part. Followed by a linear layer, the initial predictive outcomes are integrated and assigned with different weights for the final prediction. The experimental results on the collected influenza dataset indicate that VirPreNet achieves state-of-the-art performance combining ProtVec with our proposed architecture. It outperforms baseline methods on the independent testing data. Moreover, our proposed model reveals the importance of PB2 and HA segments on the virulence prediction. We believe that our model may provide new insights into the investigation of influenza virulence. Availability and implementation Codes and data to generate the VirPreNet are publicly available at https://github.com/Rayin-saber/VirPreNet. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals VirPreNet: A weighted ensemble convolutional neural network for the virulence prediction of influenza A virus using all 8 segments

2020 ◽  
Author(s):  
Rui Yin ◽  
Zihan Luo ◽  
Pei Zhuang ◽  
Zhuoyi Lin ◽  
Chee Keong Kwoh
Keyword(s):  
Public Health ◽  
Neural Network ◽  
Convolutional Neural Network ◽  
Influenza A Virus ◽  
Influenza A ◽  
Lethal Dose ◽  
Influenza Viruses ◽  
Numerical Representation ◽  
Influenza A Viruses ◽  
Linear Layer

AbstractMotivationInfluenza viruses are persistently threatening public health, causing annual epidemics and sporadic pandemics. The evolution of influenza viruses remains to be the main obstacle in the effectiveness of antiviral treatments due to rapid mutations. Previous work has been investigated to reveal the determinants of virulence of the influenza A virus. To further facilitate flu surveillance, explicit detection of influenza virulence is crucial to protect public health from potential future pandemics.ResultsIn this paper, we propose a weighted ensemble convolutional neural network for the virulence prediction of influenza A viruses named VirPreNet that uses all 8 segments. Firstly, mouse lethal dose 50 is exerted to label the virulence of infections into two classes, namely avirulent and virulent. A numerical representation of amino acids named ProtVec is applied to the 8-segments in a distributed manner to encode the biological sequences. After splittings and embeddings of influenza strains, the ensemble convolutional neural network is constructed as the base model on the influenza dataset of each segment, which serves as the VirPreNet’s main part. Followed by a linear layer, the initial predictive outcomes are integrated and assigned with different weights for the final prediction. The experimental results on the collected influenza dataset indicate that VirPreNet achieves state-of-the-art performance combining ProtVec with our proposed architecture. It outperforms baseline methods on the independent testing data. Moreover, our proposed model reveals the importance of PB2 and HA segments on the virulence prediction. We believe that our model may provide new insights into the investigation of influenza [email protected] and ImplementationCodes and data to generate the VirPreNet are publicly available at https://github.com/Rayin-saber/VirPreNet

scholarly journals An Intranasal Virus-Like Particle Vaccine Broadly Protects Mice from Multiple Subtypes of Influenza A Virus

mBio ◽  
2015 ◽  
Vol 6 (4) ◽  
Author(s):  
Louis M. Schwartzman ◽  
Andrea L. Cathcart ◽  
Lindsey M. Pujanauski ◽  
Li Qi ◽  
John C. Kash ◽  
...  
Keyword(s):  
Public Health ◽  
Influenza A Virus ◽  
Influenza A ◽  
Influenza Viruses ◽  
Significant Protection ◽  
Virus Infections ◽  
Influenza A Viruses ◽  
Virus Like Particle ◽  
Practical Strategy ◽  
Universal Influenza Vaccine

ABSTRACTInfluenza virus infections are a global public health problem, with a significant impact of morbidity and mortality from both annual epidemics and pandemics. The current strategy for preventing annual influenza is to develop a new vaccine each year against specific circulating virus strains. Because these vaccines are unlikely to protect against an antigenically divergent strain or a new pandemic virus with a novel hemagglutinin (HA) subtype, there is a critical need for vaccines that protect against all influenza A viruses, a so-called “universal” vaccine. Here we show that mice were broadly protected against challenge with a wide variety of lethal influenza A virus infections (94% aggregate survival following vaccination) with a virus-like particle (VLP) vaccine cocktail. The vaccine consisted of a mixture of VLPs individually displaying H1, H3, H5, or H7 HAs, and vaccinated mice showed significant protection following challenge with influenza viruses expressing 1918 H1, 1957 H2, and avian H5, H6, H7, H10, and H11 hemagglutinin subtypes. These experiments suggest a promising and practical strategy for developing a broadly protective “universal” influenza vaccine.IMPORTANCEThe rapid and unpredictable nature of influenza A virus evolution requires new vaccines to be produced annually to match circulating strains. Human infections with influenza viruses derived from animals can cause outbreaks that may be associated with high mortality, and such strains may also adapt to humans to cause a future pandemic. Thus, there is a large public health need to create broadly protective, or “universal,” influenza vaccines that could prevent disease from a wide variety of human and animal influenza A viruses. In this study, a noninfectious virus-like particle (VLP) vaccine was shown to offer significant protection against a variety of influenza A viruses in mice, suggesting a practical strategy to develop a universal influenza vaccine.

scholarly journals Unseasonal Transmission of H3N2 Influenza A Virus During the Swine-Origin H1N1 Pandemic

2010 ◽  
Vol 84 (11) ◽  
pp. 5715-5718 ◽  
Author(s):  
Elodie Ghedin ◽  
David E. Wentworth ◽  
Rebecca A. Halpin ◽  
Xudong Lin ◽  
Jayati Bera ◽  
...  
Keyword(s):  
New York ◽  
Influenza A Virus ◽  
Influenza A ◽  
New York State ◽  
The United States ◽  
Influenza Viruses ◽  
Influenza A Viruses ◽  
York State ◽  
Low Incidence ◽  
H3n2 Influenza

ABSTRACT The initial wave of swine-origin influenza A virus (pandemic H1N1/09) in the United States during the spring and summer of 2009 also resulted in an increased vigilance and sampling of seasonal influenza viruses (H1N1 and H3N2), even though they are normally characterized by very low incidence outside of the winter months. To explore the nature of virus evolution during this influenza “off-season,” we conducted a phylogenetic analysis of H1N1 and H3N2 sequences sampled during April to June 2009 in New York State. Our analysis revealed that multiple lineages of both viruses were introduced and cocirculated during this time, as is typical of influenza virus during the winter. Strikingly, however, we also found strong evidence for the presence of a large transmission chain of H3N2 viruses centered on the south-east of New York State and which continued until at least 1 June 2009. These results suggest that the unseasonal transmission of influenza A viruses may be more widespread than is usually supposed.

scholarly journals Influenza A Virus Inhibits RSV Infection via a Two-Wave Expression of IFIT Proteins

Viruses ◽  
2020 ◽  
Vol 12 (10) ◽  
pp. 1171
Author(s):  
Yaron Drori ◽  
Jasmine Jacob-Hirsch ◽  
Rakefet Pando ◽  
Aharona Glatman-Freedman ◽  
Nehemya Friedman ◽  
...  
Keyword(s):  
Influenza A Virus ◽  
Influenza A ◽  
Influenza Viruses ◽  
Mass Spectrometry Analysis ◽  
Influenza A Viruses ◽  
Rsv Infection ◽  
Syncytial Virus ◽  
Mouse Lungs

Influenza viruses and respiratory syncytial virus (RSV) are respiratory viruses that primarily circulate worldwide during the autumn and winter seasons. Seasonal surveillance has shown that RSV infection generally precedes influenza. However, in the last four winter seasons (2016–2020) an overlap of the morbidity peaks of both viruses was observed in Israel, and was paralleled by significantly lower RSV infection rates. To investigate whether the influenza A virus inhibits RSV, human cervical carcinoma (HEp2) cells or mice were co-infected with influenza A and RSV. Influenza A inhibited RSV growth, both in vitro and in vivo. Mass spectrometry analysis of mouse lungs infected with influenza A identified a two-wave pattern of protein expression upregulation, which included members of the interferon-induced protein with the tetratricopeptide (IFITs) family. Interestingly, in the second wave, influenza A viruses were no longer detectable in mouse lungs. In addition, knockdown and overexpression of IFITs in HEp2 cells affected RSV multiplicity. In conclusion, influenza A infection inhibits RSV infectivity via upregulation of IFIT proteins in a two-wave modality. Understanding the immune system involvement in the interaction between influenza A and RSV viruses will contribute to the development of future treatment strategies against these viruses.

IFN-κ suppresses the replication of influenza A viruses through the IFNAR-MAPK-Fos-CHD6 axis

2020 ◽  
Vol 13 (626) ◽  
pp. eaaz3381 ◽  
Author(s):  
Yongquan He ◽  
Weihui Fu ◽  
Kangli Cao ◽  
Qian He ◽  
Xiangqing Ding ◽  
...  
Keyword(s):  
Influenza A Virus ◽  
Influenza A ◽  
Influenza Viruses ◽  
Mitogen Activated Protein Kinase ◽  
Type I Interferons ◽  
Type I ◽  
Influenza A Viruses ◽  
Human Lung Cells ◽  
Avian Influenza A Virus ◽  
Factor C

Type I interferons (IFNs) are the first line of defense against viral infection. Using a mouse model of influenza A virus infection, we found that IFN-κ was one of the earliest responding type I IFNs after infection with H9N2, a low-pathogenic avian influenza A virus, whereas this early induction did not occur upon infection with the epidemic-causing H7N9 virus. IFN-κ efficiently suppressed the replication of various influenza viruses in cultured human lung cells, and chromodomain helicase DNA binding protein 6 (CHD6) was the major effector for the antiviral activity of IFN-κ, but not for that of IFN-α or IFN-β. The induction of CHD6 required both of the type I IFN receptor subunits IFNAR1 and IFNAR2, the mitogen-activated protein kinase (MAPK) p38, and the transcription factor c-Fos but was independent of signal transducer and activator of transcription 1 (STAT1) activity. In addition, we showed that pretreatment with IFN-κ protected mice from lethal influenza viral challenge. Together, our findings identify an IFN-κ–specific pathway that constrains influenza A virus and provide evidence that IFN-κ may have potential as a preventative and therapeutic agent against influenza A virus.

scholarly journals H5N1 Influenza A Virus PB1-F2 Relieves HAX-1-Mediated Restriction of Avian Virus Polymerase PA in Human Lung Cells

2018 ◽  
Vol 92 (11) ◽  
pp. e00425-18 ◽  
Author(s):  
B. Mazel-Sanchez ◽  
I. Boal-Carvalho ◽  
F. Silva ◽  
R. Dijkman ◽  
M. Schmolke
Keyword(s):  
Influenza A Virus ◽  
Influenza A ◽  
Influenza Viruses ◽  
Zoonotic Transmission ◽  
Restriction Factor ◽  
Influenza A Viruses ◽  
Human Lung Cells ◽  
Enzymatic Function ◽  
H5n1 Influenza ◽  
Avian Origin

ABSTRACTHighly pathogenic influenza A viruses (IAV) from avian hosts were first reported to directly infect humans 20 years ago. However, such infections are rare events, and our understanding of factors promoting or restricting zoonotic transmission is still limited. One accessory protein of IAV, PB1-F2, was associated with pathogenicity of pandemic and zoonotic IAV. This short (90-amino-acid) peptide does not harbor an enzymatic function. We thus identified host factors interacting with H5N1 PB1-F2, which could explain its importance for virulence. PB1-F2 binds to HCLS1-associated protein X1 (HAX-1), a recently identified host restriction factor of the PA subunit of IAV polymerase complexes. We demonstrate that the PA of a mammal-adapted H1N1 IAV is resistant to HAX-1 imposed restriction, while the PA of an avian-origin H5N1 IAV remains sensitive. We also showed HAX-1 sensitivity for PAs of A/Brevig Mission/1/1918 (H1N1) and A/Shanghai/1/2013 (H7N9), two avian-origin zoonotic IAV. Inhibition of H5N1 polymerase by HAX-1 can be alleviated by its PB1-F2 through direct competition. Accordingly, replication of PB1-F2-deficient H5N1 IAV is attenuated in the presence of large amounts of HAX-1. Mammal-adapted H1N1 and H3N2 viruses do not display this dependence on PB1-F2 for efficient replication in the presence of HAX-1. We propose that PB1-F2 plays a key role in zoonotic transmission of avian H5N1 IAV into humans.IMPORTANCEAquatic and shore birds are the natural reservoir of influenza A viruses from which the virus can jump into a variety of bird and mammal host species, including humans. H5N1 influenza viruses are a good model for this process. They pose an ongoing threat to human and animal health due to their high mortality rates. However, it is currently unclear what restricts these interspecies jumps on the host side or what promotes them on the virus side. Here we show that a short viral peptide, PB1-F2, helps H5N1 bird influenza viruses to overcome a human restriction factor of the viral polymerase complex HAX-1. Interestingly, we found that human influenza A virus polymerase complexes are already adapted to HAX-1 and do not require this function of PB1-F2. We thus propose that a functional full-length PB1-F2 supports direct transmission of bird viruses into humans.

scholarly journals Efficient whole genome sequencing of influenza A viruses

2019 ◽  
Author(s):  
Marina Escalera-Zamudio ◽  
Ana Georgina Cobián-Güemes ◽  
Blanca Taboada ◽  
Irma López-Martínez ◽  
Joel Armando Vázquez-Pérez ◽  
...  
Keyword(s):  
Whole Genome Sequencing ◽  
Influenza A Virus ◽  
Genome Sequencing ◽  
Influenza A ◽  
Genetic Material ◽  
Influenza Viruses ◽  
Epidemiological Surveillance ◽  
Clinical Samples ◽  
Whole Genome ◽  
Influenza A Viruses

ABSTRACTThe constant threat of emergence for novel pathogenic influenza A viruses with pandemic potential, makes full-genome characterization of circulating influenza viral strains a high priority, allowing detection of novel and re-assorting variants. Sequencing the full-length genome of influenza A virus traditionally required multiple amplification rounds, followed by the subsequent sequencing of individual PCR products. The introduction of high-throughput sequencing technologies has made whole genome sequencing easier and faster. We present a simple protocol to obtain whole genome sequences of hypothetically any influenza A virus, even with low quantities of starting genetic material. The complete genomes of influenza A viruses of different subtypes and from distinct sources (clinical samples of pdmH1N1, tissue culture-adapted H3N2 viruses, or avian influenza viruses from cloacal swabs) were amplified with a single multisegment reverse transcription-PCR reaction and sequenced using Illumina sequencing platform. Samples with low quantity of genetic material after initial PCR amplification were re-amplified by an additional PCR using random primers. Whole genome sequencing was successful for 66% of the samples, whilst the most relevant genome segments for epidemiological surveillance (corresponding to the hemagglutinin and neuraminidase) were sequenced with at least 93% coverage (and a minimum 10x) for 98% of the samples. Low coverage for some samples is likely due to an initial low viral RNA concentration in the original sample. The proposed methodology is especially suitable for sequencing a large number of samples, when genetic data is urgently required for strains characterization, and may also be useful for variant analysis.

scholarly journals Influenza B viruses exhibit lower within-host diversity than influenza A viruses in human hosts

2019 ◽  
Author(s):  
Andrew L. Valesano ◽  
William J. Fitzsimmons ◽  
John T. McCrone ◽  
Joshua G. Petrie ◽  
Arnold S. Monto ◽  
...  
Keyword(s):  
Genetic Diversity ◽  
Influenza A Virus ◽  
Influenza A ◽  
Evolutionary Dynamics ◽  
Influenza Viruses ◽  
Influenza B Virus ◽  
Influenza B ◽  
Influenza A Viruses ◽  
Community Based ◽  
B Virus

AbstractInfluenza B virus undergoes seasonal antigenic drift more slowly than influenza A, but the reasons for this difference are unclear. While the evolutionary dynamics of influenza viruses play out globally, they are fundamentally driven by mutation, reassortment, drift, and selection within individual hosts. These processes have recently been described for influenza A virus, but little is known about the evolutionary dynamics of influenza B virus (IBV) at the level of individual infections and transmission events. Here we define the within-host evolutionary dynamics of influenza B virus by sequencing virus populations from naturally-infected individuals enrolled in a prospective, community-based cohort over 8176 person-seasons of observation. Through analysis of high depth-of-coverage sequencing data from samples from 91 individuals with influenza B, we find that influenza B virus accumulates lower genetic diversity than previously observed for influenza A virus during acute infections. Consistent with studies of influenza A viruses, the within-host evolution of influenza B viruses is characterized by purifying selection and the general absence of widespread positive selection of within-host variants. Analysis of shared genetic diversity across 15 sequence-validated transmission pairs suggests that IBV experiences a tight transmission bottleneck similar to that of influenza A virus. These patterns of local-scale evolution are consistent with influenza B virus’ slower global evolutionary rate.ImportanceThe evolution of influenza virus is a significant public health problem and necessitates the annual evaluation of influenza vaccine formulation to keep pace with viral escape from herd immunity. Influenza B virus is a serious health concern for children, in particular, yet remains understudied compared to influenza A virus. Influenza B virus evolves more slowly than influenza A, but the factors underlying this are not completely understood. We studied how the within-host diversity of influenza B virus relates to its global evolution by sequencing viruses from a community-based cohort. We found that influenza B virus populations have lower within-host genetic diversity than influenza A virus and experience a tight genetic bottleneck during transmission. Our work provides insights into the varying dynamics of influenza viruses in human infection.

scholarly journals FluPhenotype—a one-stop platform for early warnings of the influenza A virus

2020 ◽  
Vol 36 (10) ◽  
pp. 3251-3253 ◽  
Author(s):  
Congyu Lu ◽  
Zena Cai ◽  
Yuanqiang Zou ◽  
Zheng Zhang ◽  
Wenjun Chen ◽  
...  
Keyword(s):  
Drug Resistance ◽  
Amino Acid ◽  
Influenza A ◽  
Genetic Relationships ◽  
Influenza Viruses ◽  
Supplementary Information ◽  
Influenza A Viruses ◽  
One Stop ◽  
Related Amino Acid ◽  
Early Warnings

Abstract Motivation Newly emerging influenza viruses keep challenging global public health. To evaluate the potential risk of the viruses, it is critical to rapidly determine the phenotypes of the viruses, including the antigenicity, host, virulence and drug resistance. Results Here, we built FluPhenotype, a one-stop platform to rapidly determinate the phenotypes of the influenza A viruses. The input of FluPhenotype is the complete or partial genomic/protein sequences of the influenza A viruses. The output presents five types of information about the viruses: (i) sequence annotation including the gene and protein names as well as the open reading frames, (ii) potential hosts and human-adaptation-associated amino acid markers, (iii) antigenic and genetic relationships with the vaccine strains of different HA subtypes, (iv) mammalian virulence-related amino acid markers and (v) drug resistance-related amino acid markers. FluPhenotype will be a useful bioinformatic tool for surveillance and early warnings of the newly emerging influenza A viruses. Availability and implementation It is publicly available from: http://www.computationalbiology.cn : 18888/IVEW. Supplementary information Supplementary data are available at Bioinformatics online.

Tempel: time-series mutation prediction of influenza A viruses via attention-based recurrent neural networks

2020 ◽  
Vol 36 (9) ◽  
pp. 2697-2704 ◽  
Author(s):  
Rui Yin ◽  
Emil Luusua ◽  
Jan Dabrowski ◽  
Yu Zhang ◽  
Chee Keong Kwoh
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Recurrent Neural Networks ◽  
Influenza A ◽  
Sequence Data ◽  
Predictive Performance ◽  
Influenza Viruses ◽  
Supplementary Information ◽  
Influenza A Viruses ◽  
Mutation Prediction

Abstract Motivation Influenza viruses are persistently threatening public health, causing annual epidemics and sporadic pandemics. The evolution of influenza viruses remains to be the main obstacle in the effectiveness of antiviral treatments due to rapid mutations. The goal of this work is to predict whether mutations are likely to occur in the next flu season using historical glycoprotein hemagglutinin sequence data. One of the major challenges is to model the temporality and dimensionality of sequential influenza strains and to interpret the prediction results. Results In this article, we propose an efficient and robust time-series mutation prediction model (Tempel) for the mutation prediction of influenza A viruses. We first construct the sequential training samples with splittings and embeddings. By employing recurrent neural networks with attention mechanisms, Tempel is capable of considering the historical residue information. Attention mechanisms are being increasingly used to improve the performance of mutation prediction by selectively focusing on the parts of the residues. A framework is established based on Tempel that enables us to predict the mutations at any specific residue site. Experimental results on three influenza datasets show that Tempel can significantly enhance the predictive performance compared with widely used approaches and provide novel insights into the dynamics of viral mutation and evolution. Availability and implementation The datasets, source code and supplementary documents are available at: https://drive.google.com/drive/folders/15WULR5__6k47iRotRPl3H7ghi3RpeNXH. Supplementary information Supplementary data are available at Bioinformatics online.

Sign in / Sign up

Export Citation Format

Share Document