Predicting Zoonotic Risk of Influenza A Viruses from Host Tropism Protein Signature Using Random Forest.
Ontology highlight
ABSTRACT:
SUBMITTER: Eng CLP
PROVIDER: S-EPMC5485959 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundMajority of influenza A viruses reside and circulate among animal populations, seldom infecting humans due to host range restriction. Yet when some avian strains do acquire the ability to overcome species barrier, they might become adapted to humans, replicating efficiently and causing diseases, leading to potential pandemic. With the huge influenza A virus reservoir in wild birds, it is a cause for concern when a new influenza strain emerges with the ability to cross host species barrier, as shown in light of the recent H7N9 outbreak in China. Several influenza proteins have been shown to be major determinants in host tropism. Further understanding and determining host tropism would be important in identifying zoonotic influenza virus strains capable of crossing species barrier and infecting humans.ResultsIn this study, computational models for 11 influenza proteins have been constructed using the machine learning algorithm random forest for prediction of host tropism. The prediction models were trained on influenza protein sequences isolated from both avian and human samples, which were transformed into amino acid physicochemical properties feature vectors. The results were highly accurate prediction models (ACC>96.57; AUC>0.980; MCC>0.916) capable of determining host tropism of individual influenza proteins. In addition, features from all 11 proteins were used to construct a combined model to predict host tropism of influenza virus strains. This would help assess a novel influenza strain's host range capability.ConclusionsFrom the prediction models constructed, all achieved high prediction performance, indicating clear distinctions in both avian and human proteins. When used together as a host tropism prediction system, zoonotic strains could potentially be identified based on different protein prediction results. Understanding and predicting host tropism of influenza proteins lay an important foundation for future work in constructing computation models capable of directly predicting interspecies transmission of influenza viruses. The models are available for prediction at http://fluleap.bic.nus.edu.sg.
| S-EPMC4290784 | biostudies-literature
Project description:Zoonotic influenza A viruses constantly pose a health threat to humans as novel strains occasionally emerge from the avian population to cause human infections. Many past epidemic as well as pandemic strains have originated from avian species. While most viruses are restricted to their primary hosts, zoonotic strains can sometimes arise from mutations or reassortment, leading them to acquire the capability to escape host species barrier and successfully infect a new host. Phylogenetic analyses and genetic markers are useful in tracing the origins of zoonotic infections, but there are still no effective means to identify high risk strains prior to an outbreak. Here we show that distinct host tropism protein signatures can be used to identify possible zoonotic strains in avian species which have the potential to cause human infections. We have discovered that influenza A viruses can now be classified into avian, human, or zoonotic strains based on their host tropism protein signatures. Analysis of all influenza A viruses with complete proteome using the host tropism prediction system, based on machine learning classifications of avian and human viral proteins has uncovered distinct signatures of zoonotic strains as mosaics of avian and human viral proteins. This is in contrast with typical avian or human strains where they show mostly avian or human viral proteins in their signatures respectively. Moreover, we have found that zoonotic strains from the same influenza outbreaks carry similar host tropism protein signatures characteristic of a common ancestry. Our results demonstrate that the distinct host tropism protein signature in zoonotic strains may prove useful in influenza surveillance to rapidly identify potential high risk strains circulating in avian species, which may grant us the foresight in anticipating an impending influenza outbreak.
| S-EPMC4767729 | biostudies-literature
Project description:Mortality is an unfortunately common outcome of extremely and very preterm birth. Existing clinical prediction models capture mortality risk at birth but fail to account for the remainder of the hospital course. Infants born < 32 weeks gestation with complete physiologic and clinical data were included in this retrospective study. Mortality risk was quantified by conventional means (clinical factors) using the CRIB-II score and the optimal logistic regression model. A random forest (RF) model was trained using a subset of the cohort, labeling data within 6 h of death as "worry." The model was then tested using the remaining infants. A total of 275 infants were included in the study with a mean gestational age of 27 weeks, mean birth weight of 929 g, 49% female, and a mortality rate of 21%. The CRIB-II and logistic regression models had acceptable performance with sensitivities of 71% and 80% AUC scores of 0.78 and 0.84, respectively. The RF model had superior performance with a sensitivity of 88% and an AUC of 0.93. A random forest model which incorporates fixed clinical factors with the influence of aberrancies in subsequent physiology has superior performance for mortality prediction compared to conventional models.
| S-EPMC8012581 | biostudies-literature
Project description:Host-virus associations have co-evolved under ecological and evolutionary selection pressures that shape cross-species transmission and spillover to humans. Observed virus-host associations provide relevant context for newly discovered wildlife viruses to assess knowledge gaps in host-range and estimate pathways for potential human infection. Using models to predict virus-host networks, we predicted the likelihood of humans as hosts for 513 newly discovered viruses detected by large-scale wildlife surveillance at high-risk animal-human interfaces in Africa, Asia, and Latin America. Predictions indicated that novel coronaviruses are likely to infect a greater number of host species than viruses from other families. Our models further characterize novel viruses through prioritization scores and directly inform surveillance targets to identify host ranges for newly discovered viruses.
| S-EPMC9390964 | biostudies-literature
Project description:Hepatitis E virus (HEV), the causative agent of hepatitis E, is an understudied but important pathogen. HEV typically causes self-limiting acute viral hepatitis, however chronic infection with neurological and other extrahepatic manifestations has increasingly become a significant clinical problem. The discovery of swine HEV from pigs and demonstration of its zoonotic potential led to the genetic identification of very diverse HEV strains from more than a dozen other animal species. HEV strains from pig, rabbit, deer, camel, and rat have been shown to cross species barriers and infect humans. Zoonotic HEV infections through consumption of raw or undercooked animal meat or direct contact with infected animals have been reported. The discovery of a large number of animal HEV variants does provide an opportunity to develop useful animal models for HEV. In this mini-review, we discuss recent advances in HEV host range, and cross-species and zoonotic transmission.
| S-EPMC7854786 | biostudies-literature
Project description:Timely identification of emerging antigenic variants is critical to influenza vaccine design. The accuracy of a sequence-based antigenic prediction method relies on the choice of amino acids substitution matrices. In this study, we first compared a comprehensive 95 substitution matrices reflecting various amino acids properties in predicting the antigenicity of influenza viruses by a random forest model. We then proposed a novel algorithm called joint random forest regression (JRFR) to jointly consider top substitution matrices. We applied JRFR to human H3N2 seasonal influenza data from 1968 to 2003. A 10-fold cross-validation shows that JRFR outperforms other popular methods in predicting antigenic variants. In addition, our results suggest that structure features are most relevant to influenza antigenicity. By restricting the analysis to data involving two adjacent antigenic clusters, we inferred a few key amino acids mutation driving the 11 historical antigenic drift events, pointing to experimentally validated mutations. Finally, we constructed an antigenic cartography of all H3N2 viruses with hemagglutinin (the glycoprotein on the surface of the influenza virus responsible for its binding to host cells) sequence available from NCBI flu database, and showed an overall correspondence and local inconsistency between genetic and antigenic evolution of H3N2 influenza viruses.
| S-EPMC5431489 | biostudies-literature
Project description:Newly emerging influenza viruses continue to threaten public health. A rapid determination of the host range of newly discovered influenza viruses would assist in early assessment of their risk. Here, we attempted to predict the host of influenza viruses using the Support Vector Machine (SVM) classifier based on the word vector, a new representation and feature extraction method for biological sequences. The results show that the length of the word within the word vector, the sequence type (DNA or protein) and the species from which the sequences were derived for generating the word vector all influence the performance of models in predicting the host of influenza viruses. In nearly all cases, the models built on the surface proteins hemagglutinin (HA) and neuraminidase (NA) (or their genes) produced better results than internal influenza proteins (or their genes). The best performance was achieved when the model was built on the HA gene based on word vectors (words of three-letters long) generated from DNA sequences of the influenza virus. This results in accuracies of 99.7% for avian, 96.9% for human and 90.6% for swine influenza viruses. Compared to the method of sequence homology best-hit searches using the Basic Local Alignment Search Tool (BLAST), the word vector-based models still need further improvements in predicting the host of influenza A viruses.
| S-EPMC5518728 | biostudies-literature
Project description:Within the field of retrovirus, our knowledge of foamy viruses (FV) is still limited. Their unique replication strategy and mechanism of viral persistency needs further research to gain understanding of the virus-host interactions, especially in the light of the recent findings suggesting their ancient origin and long co-evolution with their nonhuman hosts. Unquestionably, the most studied member is the primate/prototype foamy virus (PFV) which was originally isolated from a human (designated as human foamy virus, HFV), but later identified as chimpanzee origin; phylogenetic analysis clearly places it among other Old World primates. Additionally, the study of non-simian animal FVs can contribute to a deeper understanding of FV-host interactions and development of other animal models. The review aims at highlighting areas of special interest regarding the structure, biology, virus-host interactions and interspecies transmission potential of primate as well as non-primate foamy viruses for gaining new insights into FV biology.
| S-EPMC3798896 | biostudies-literature
Project description:Zoonotic viruses, such as HIV, Ebola virus, coronaviruses, influenza A viruses, hantaviruses, or henipaviruses, can result in profound pathology in humans. In contrast, populations of the reservoir hosts of zoonotic pathogens often appear to tolerate these infections with little evidence of disease. Why are viruses more dangerous in one species than another? Immunological studies investigating quantitative and qualitative differences in the host-virus equilibrium in animal reservoirs will be key to answering this question, informing new approaches for treating and preventing zoonotic diseases. Integrating an understanding of host immune responses with epidemiological, ecological, and evolutionary insights into viral emergence will shed light on mechanisms that minimize fitness costs associated with viral infection, facilitate transmission to other hosts, and underlie the association of specific reservoir hosts with multiple emerging viruses. Reservoir host studies provide a rich opportunity for elucidating fundamental immunological processes and their underlying genetic basis, in the context of distinct physiological and metabolic constraints that contribute to host resistance and disease tolerance.
| S-EPMC4390999 | biostudies-literature
Project description:Background: Understanding the location and cell-type specific binding of Transcription Factors (TFs) is important in the study of gene regulation. Computational prediction of TF binding sites is challenging, because TFs often bind only to short DNA motifs and cell-type specific co-factors may work together with the same TF to determine binding. Here, we consider the problem of learning a general model for the prediction of TF binding using DNase1-seq data and TF motif description in form of position specific energy matrices (PSEMs). Methods: We use TF ChIP-seq data as a gold-standard for model training and evaluation. Our contribution is a novel ensemble learning approach using random forest classifiers. In the context of the ENCODE-DREAM in vivo TF binding site prediction challenge we consider different learning setups. Results: Our results indicate that the ensemble learning approach is able to better generalize across tissues and cell-types compared to individual tissue-specific classifiers or a classifier built based upon data aggregated across tissues. Furthermore, we show that incorporating DNase1-seq peaks is essential to reduce the false positive rate of TF binding predictions compared to considering the raw DNase1 signal. Conclusions: Analysis of important features reveals that the models preferentially select motifs of other TFs that are close interaction partners in existing protein protein-interaction networks. Code generated in the scope of this project is available on GitHub: https://github.com/SchulzLab/TFAnalysis (DOI: 10.5281/zenodo.1409697).
| S-EPMC6823902 | biostudies-literature