Scoring amino acid mutation to predict pandemic risk of avian influenza virus

Based on CRISPR-Cas13a system, to establish a rapid visual detection method for avian influenza viruses

To rapidly, specifically, and sensitively detect avian influenza virus (AIV), this research established a visual detection method of recombinase-aided amplification (RAA) based on Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR) and CRISPR associated proteins 13a (Cas13a) system. In this study, specific primers and CRISPR RNA (crRNA) were designed according to the conservative sequence of AIV Nucleprotein (NP) gene. RAA technology was used to amplify the target sequence, and the amplification products were visually detected by lateral flow dipstick (LFD). The specificity, sensitivity, and reproducibility of RAA-CRISPR-Cas13a-LFD were evaluated. At the same time, this method and polymerase chain reaction (PCR)-agarose electrophoresis method were used to detect clinical samples, and the coincidence rate of the two detection methods was calculated. The results showed that the RAA-CRISPR-Cas13a-LFD method could achieve specific amplification of the target gene fragments, and the detection results could be visually observed through the LFD. Meanwhile, there was no cross-reaction with infectious bronchitis virus (IBV), infectious laryngotracheitis virus (ILTV), and Newcastle disease virus (NDV). The sensitivity reached 100 copies/μL, which was 1,000-fold higher than that of PCR-agarose electrophoresis method. The coincidence rate of clinical tests was 98.75 %, and the total reaction time was ~1 h. The RAA-CRISPR-Cas13a-LFD method established in this study had the advantages of rapid, simple, strong specificity, and high sensitivity, which provided a new visual method for AIV detection.

Evolution of the North American Lineage H7 Avian Influenza Viruses in Association with H7 Virus's Introduction to Poultry

The incursions of H7 subtype low-pathogenicity avian influenza virus (LPAIV) from wild birds into poultry and its mutations to highly pathogenic avian influenza virus (HPAIV) have been an ongoing concern in North America. Since 2000, 10 phylogenetically distinct H7 virus outbreaks from wild birds have been detected in poultry, six of which mutated to HPAIV. To study the molecular evolution of the H7 viruses that occurs when changing hosts from wild birds to poultry, we performed analyses of the North American H7 hemagglutinin (HA) genes to identify amino acid changes as the virus circulated in wild birds from 2000 to 2019. Then, we analyzed recurring HA amino acid changes and gene constellations of the viruses that spread from wild birds to poultry. We found six HA amino acid changes occurring during wild bird circulation and 10 recurring changes after the spread to poultry. Eight of the changes were in and around the HA antigenic sites, three of which were supported by positive selection. Viruses from each H7 outbreak had a unique genotype, with no specific genetic group associated with poultry outbreaks or mutation to HPAIV. However, the genotypes of the H7 viruses in poultry outbreaks tended to contain minor genetic groups less observed in wild bird H7 viruses, suggesting either a biased sampling of wild bird AIVs or a tendency of having reassortment with minor genetic groups prior to the virus's introduction to poultry. IMPORTANCE Wild bird-origin H7 subtype avian influenza viruses are a constant threat to commercial poultry, both directly by the disease they cause and indirectly through trade restrictions that can be imposed when the virus is detected in poultry. It is important to understand the genetic basis of why the North American lineage H7 viruses have repeatedly crossed the species barrier from wild birds to poultry. We examined the amino acid changes in the H7 viruses associated with poultry outbreaks and tried to determine gene reassortment related to poultry adaptation and mutations to HPAIV. The findings in this study increase the understanding of the evolutionary pathways of wild bird AIV before infecting poultry and the HA changes associated with adaptation of the virus in poultry.

Using amino acid features to identify the pathogenicity of influenza B virus

BACKGROUND

Influenza B virus can cause epidemics with high pathogenicity, so it poses a serious threat to public health. A feature representation algorithm is proposed in this paper to identify the pathogenicity phenotype of influenza B virus.

METHODS

The dataset included all 11 influenza virus proteins encoded in eight genome segments of 1724 strains. Two types of features were hierarchically used to build the prediction model. Amino acid features were directly delivered from 67 feature descriptors and input into the random forest classifier to output informative features about the class label and probabilistic prediction. The sequential forward search strategy was used to optimize the informative features. The final features for each strain had low dimensions and included knowledge from different perspectives, which were used to build the machine learning model for pathogenicity identification.

RESULTS

The 40 signature positions were achieved by entropy screening. Mutations at position 135 of the hemagglutinin protein had the highest entropy value (1.06). After the informative features were directly generated from the 67 random forest models, the dimensions for class and probabilistic features were optimized as 4 and 3, respectively. The optimal class features had a maximum accuracy of 94.2% and a maximum Matthews correlation coefficient of 88.4%, while the optimal probabilistic features had a maximum accuracy of 94.1% and a maximum Matthews correlation coefficient of 88.2%. The optimized features outperformed the original informative features and amino acid features from individual descriptors. The sequential forward search strategy had better performance than the classical ensemble method.

CONCLUSIONS

The optimized informative features had the best performance and were used to build a predictive model so as to identify the phenotype of influenza B virus with high pathogenicity and provide early risk warning for disease control.

Predicting Cross-Species Infection of Swine Influenza Virus with Representation Learning of Amino Acid Features

Swine influenza viruses (SIVs) can unforeseeably cross the species barriers and directly infect humans, which pose huge challenges for public health and trigger pandemic risk at irregular intervals. Computational tools are needed to predict infection phenotype and early pandemic risk of SIVs. For this purpose, we propose a feature representation algorithm to predict cross-species infection of SIVs. We built a high-quality dataset of 1902 viruses. A feature representation learning scheme was applied to learn feature representations from 64 well-trained random forest models with multiple feature descriptors of mutant amino acid in the viral proteins, including compositional information, position-specific information, and physicochemical properties. Class and probabilistic information were integrated into the feature representations, and redundant features were removed by feature space optimization. High performance was achieved using 20 informative features and 22 probabilistic information. The proposed method will facilitate SIV characterization of transmission phenotype.

Influenza virus genotype to phenotype predictions through machine learning: a systematic review

Background: There is great interest in understanding the viral genomic predictors of phenotypic traits that allow influenza A viruses to adapt to or become more virulent in different hosts. Machine learning techniques have demonstrated promise in addressing this critical need for other pathogens because the underlying algorithms are especially well equipped to uncover complex patterns in large datasets and produce generalizable predictions for new data. As the body of research where these techniques are applied for influenza A virus phenotype prediction continues to grow, it is useful to consider the strengths and weaknesses of these approaches to understand what has prevented these models from seeing widespread use by surveillance laboratories and to identify gaps that are underexplored with this technology. Methods and Results: We present a systematic review of English literature published through 15 April 2021 of studies employing machine learning methods to generate predictions of influenza A virus phenotypes from genomic or proteomic input. Forty-nine studies were included in this review, spanning the topics of host discrimination, human adaptability, subtype and clade assignment, pandemic lineage assignment, characteristics of infection, and antiviral drug resistance. Conclusions: Our findings suggest that biases in model design and a dearth of wet laboratory follow-up may explain why these models often go underused. We, therefore, offer guidance to overcome these limitations, aid in improving predictive models of previously studied influenza A virus phenotypes, and extend those models to unexplored phenotypes in the ultimate pursuit of tools to enable the characterization of virus isolates across surveillance laboratories.

Maintaining proper health records improves machine learning predictions for novel 2019-nCoV

Background

An ongoing outbreak of a novel coronavirus (2019-nCoV) pneumonia continues to affect the whole world including major countries such as China, USA, Italy, France and the United Kingdom. We present outcome (‘recovered’, ‘isolated’ or ‘death’) risk estimates of 2019-nCoV over ‘early’ datasets. A major consideration is the likelihood of death for patients with 2019-nCoV.

Method

Accounting for the impact of the variations in the reporting rate of 2019-nCoV, we used machine learning techniques (AdaBoost, bagging, extra-trees, decision trees and k-nearest neighbour classifiers) on two 2019-nCoV datasets obtained from Kaggle on March 30, 2020. We used ‘country’, ‘age’ and ‘gender’ as features to predict outcome for both datasets. We included the patient’s ‘disease’ history (only present in the second dataset) to predict the outcome for the second dataset.

Results

The use of a patient’s ‘disease’ history improves the prediction of ‘death’ by more than sevenfold. The models ignoring a patent’s ‘disease’ history performed poorly in test predictions.

Conclusion

Our findings indicate the potential of using a patient’s ‘disease’ history as part of the feature set in machine learning techniques to improve 2019-nCoV predictions. This development can have a positive effect on predictive patient treatment and can result in easing currently overburdened healthcare systems worldwide, especially with the increasing prevalence of second and third wave re-infections in some countries.

Key Role of the Influenza A Virus PA Gene Segment in the Emergence of Pandemic Viruses

Influenza A viruses (IAVs) are a significant human pathogen that cause seasonal epidemics and occasional pandemics. Avian waterfowl are the natural reservoir of IAVs, but a wide range of species can serve as hosts. Most IAV strains are adapted to one host species and avian strains of IAV replicate poorly in most mammalian hosts. Importantly, IAV polymerases from avian strains function poorly in mammalian cells but host adaptive mutations can restore activity. The 2009 pandemic H1N1 (H1N1pdm09) virus acquired multiple mutations in the PA gene that activated polymerase activity in mammalian cells, even in the absence of previously identified host adaptive mutations in other polymerase genes. These mutations in PA localize within different regions of the protein suggesting multiple mechanisms exist to activate polymerase activity. Additionally, an immunomodulatory protein, PA-X, is expressed from the PA gene segment. PA-X expression is conserved amongst many IAV strains but activity varies between viruses specific for different hosts, suggesting that PA-X also plays a role in host adaptation. Here, we review the role of PA in the emergence of currently circulating H1N1pdm09 viruses and the most recent studies of host adaptive mutations in the PA gene that modulate polymerase activity and PA-X function.

Using the spike protein feature to predict infection risk and monitor the evolutionary dynamic of coronavirus

BACKGROUND

Coronavirus can cross the species barrier and infect humans with a severe respiratory syndrome. SARS-CoV-2 with potential origin of bat is still circulating in China. In this study, a prediction model is proposed to evaluate the infection risk of non-human-origin coronavirus for early warning.

METHODS

The spike protein sequences of 2666 coronaviruses were collected from 2019 Novel Coronavirus Resource (2019nCoVR) Database of China National Genomics Data Center on Jan 29, 2020. A total of 507 human-origin viruses were regarded as positive samples, whereas 2159 non-human-origin viruses were regarded as negative. To capture the key information of the spike protein, three feature encoding algorithms (amino acid composition, AAC; parallel correlation-based pseudo-amino-acid composition, PC-PseAAC and G-gap dipeptide composition, GGAP) were used to train 41 random forest models. The optimal feature with the best performance was identified by the multidimensional scaling method, which was used to explore the pattern of human coronavirus.

RESULTS

The 10-fold cross-validation results showed that well performance was achieved with the use of the GGAP (g = 3) feature. The predictive model achieved the maximum ACC of 98.18% coupled with the Matthews correlation coefficient (MCC) of 0.9638. Seven clusters for human coronaviruses (229E, NL63, OC43, HKU1, MERS-CoV, SARS-CoV, and SARS-CoV-2) were found. The cluster for SARS-CoV-2 was very close to that for SARS-CoV, which suggests that both of viruses have the same human receptor (angiotensin converting enzyme II). The big gap in the distance curve suggests that the origin of SARS-CoV-2 is not clear and further surveillance in the field should be made continuously. The smooth distance curve for SARS-CoV suggests that its close relatives still exist in nature and public health is challenged as usual.

CONCLUSIONS

The optimal feature (GGAP, g = 3) performed well in terms of predicting infection risk and could be used to explore the evolutionary dynamic in a simple, fast and large-scale manner. The study may be beneficial for the surveillance of the genome mutation of coronavirus in the field.

Control of avian influenza in China: Strategies and lessons

In recent decades, multiple subtypes (i.e. H9N2, H5N1 and H7N9) of avian influenza virus (AIV) have become widespread in China, which has caused enormous economic losses and posed considerable threats to public health. In this review, with the aim to provide insights into and guidelines for the control of AIV spread in China and globally in the future, we analysed the reasons why AIV has persisted in China based on socio-economic features, including poultry biosecurity, live bird markets, live bird transportation, wild birds, poultry waterfowl, poultry density, poultry population and infected birds. We also described the present status of the AIV subtypes H9, H5 and H7 in China to elucidate the effectiveness of the strategies currently employed in China (i.e. culling, mass vaccination and biosecurity improvement) to control the disease based on a literature review and our unpublished surveillance data collected over a 12-year period from 2007 to 2018. We then summarized the lessons to be learned from the control experience in China, including whether culling of infected birds is of limited value for disease control and whether improved biosecurity is a better option than culling and vaccination for the long-term control of AIV, and when the vaccine strain should be updated.

Inventory of molecular markers affecting biological characteristics of avian influenza A viruses

Avian influenza viruses (AIVs) circulate globally, spilling over into domestic poultry and causing zoonotic infections in humans. Fortunately, AIVs are not yet capable of causing sustained human-to-human infection; however, AIVs are still a high risk as future pandemic strains, especially if they acquire further mutations that facilitate human infection and/or increase pathogenesis. Molecular characterization of sequencing data for known genetic markers associated with AIV adaptation, transmission, and antiviral resistance allows for fast, efficient assessment of AIV risk. Here we summarize and update the current knowledge on experimentally verified molecular markers involved in AIV pathogenicity, receptor binding, replicative capacity, and transmission in both poultry and mammals with a broad focus to include data available on other AIV subtypes outside of A/H5N1 and A/H7N9.