Mucin-Mimetic Glycan Arrays Integrating Machine Learning for Analyzing Receptor Pattern Recognition by Influenza a Viruses

ABSTRACTInfluenza A viruses (IAVs) exploit host glycans in airway epithelial mucosa to gain entry and initiate infection. Rapid detection of changes in IAV specificity towards host glycan classes can provide early indication of virus transmissibility and infection potential. IAVs use hemagglutinins (HA) to bind sialic acids linked to larger glycan structures and a switch in HA specificity from α2,3-to α2,6-linked sialoglycans is considered a prerequisite for viral transmission from birds to humans. While the changes in HA structure associated with the evolution of binding phenotype have been mapped, the influence of glycan receptor presentation on IAV specificity remains obscured. Here, we describe a glycan array platform which uses synthetic mimetics of mucin glycoproteins to model how receptor presentation in the mucinous glycocalyx, including glycan type and valency of the glycoconjugates and their surface density, impact IAV binding. We found that H1N1 virus produced in embryonated chicken eggs, which recognizes both receptor types, exclusively engaged mucin-mimetics carrying α2,3-linked sialic acids in their soluble form. The virus was able utilize both receptor structures when the probes were immobilized on the array; however, increasing density in the mucin-mimetic brush diminished viral adhesion. Propagation in mammalian cells produced a change in receptor pattern recognition by the virus, without altering its HA affinity, toward improved binding of α2,6-sialylated mucin mimetics and reduced sensitivity to surface crowding of the probes. Application of a support vector machine (SVM) learning algorithm as part of the glycan array binding analysis efficiently characterized this shift in binding preference and may prove useful to study the evolution of viral responses to a new host.

Download Full-text

Predicting correct serotypes using machine-learning models based on codon usage patterns of influenza A viruses

10.1101/528083 ◽

2019 ◽

Keyword(s):

Machine Learning ◽

Codon Usage ◽

Influenza A ◽

Learning Models ◽

Influenza A Viruses ◽

Ha Gene ◽

Protein Expressions ◽

Usage Patterns ◽

Gene 4 ◽

Machine Learning Models

AbstractConsistent codon usage patterns across species was supposed to be observed owing to the degeneracy of genetic code and the conservation of the translation machinery. In fact, however, codon usage vary dramatically among organisms, and the choice difference might also affect downstream protein expressions, structures as well as their functions. It is suggested that different codon usage patterns should encrypt distinct characters for a certain type of organism, and as a result, a series of machine-learning models have been constructed, not only for learning the patterns from certain species, but also for predicting the species based on given patterns. Two gene segments of influenza A virus, hemagglutinin (HA; gene 4) and neuraminidase (NA; gene 6), were so essential for the immune response of their hosts, that the serotypes of the viruses are named after their combinations. They thus become the objects of this study, and those proposed models work quite well on the designated tasks.

Download Full-text

Conservation region finding for influenza A viruses by machine learning methods of N-linked glycosylation sites and B-cell epitopes

Mathematical Biosciences ◽

10.1016/j.mbs.2019.108217 ◽

2019 ◽

Vol 315 ◽

pp. 108217 ◽

Cited By ~ 1

Author(s):

Jone-Han Liu ◽

Chi-Chang Chang ◽

Chi-Wei Chen ◽

Li-Ting Wong ◽

Yen-Wei Chu

Keyword(s):

Machine Learning ◽

B Cell ◽

Influenza A ◽

Influenza A Viruses ◽

Learning Methods ◽

B Cell Epitopes ◽

Machine Learning Methods ◽

Glycosylation Sites

Download Full-text

Machine Learning Methods for Predicting Human-Adaptive Influenza A Viruses Based on Viral Nucleotide Compositions

Molecular Biology and Evolution ◽

10.1093/molbev/msz276 ◽

2019 ◽

Vol 37 (4) ◽

pp. 1224-1236 ◽

Cited By ~ 2

Author(s):

Jing Li ◽

Sen Zhang ◽

Bo Li ◽

Yi Hu ◽

Xiao-Ping Kang ◽

...

Keyword(s):

Machine Learning ◽

Influenza A ◽

High Performance ◽

Influenza Pandemic ◽

Characteristic Curve ◽

Confusion Matrix ◽

Virus Transmission ◽

Principal Component ◽

Human Adaptation ◽

Influenza A Viruses

Abstract Each influenza pandemic was caused at least partly by avian- and/or swine-origin influenza A viruses (IAVs). The timing of and the potential IAVs involved in the next pandemic are currently unpredictable. We aim to build machine learning (ML) models to predict human-adaptive IAV nucleotide composition. A total of 217,549 IAV full-length coding sequences of the PB2 (polymerase basic protein-2), PB1, PA (polymerase acidic protein), HA (hemagglutinin), NP (nucleoprotein), and NA (neuraminidase) segments were decomposed for their codon position-based mononucleotides (12 nts) and dinucleotides (48 dnts). A total of 68,742 human sequences and 68,739 avian sequences (1:1) were resampled to characterize the human adaptation-associated (d)nts with principal component analysis (PCA) and other ML models. Then, the human adaptation of IAV sequences was predicted based on the characterized (d)nts. Respectively, 9, 12, 11, 13, 10 and 9 human-adaptive (d)nts were optimized for the six segments. PCA and hierarchical clustering analysis revealed the linear separability of the optimized (d)nts between the human-adaptive and avian-adaptive sets. The results of the confusion matrix and the area under the receiver operating characteristic curve indicated a high performance of the ML models to predict human adaptation of IAVs. Our model performed well in predicting the human adaptation of the swine/avian IAVs before and after the 2009 H1N1 pandemic. In conclusion, we identified the human adaptation-associated genomic composition of IAV segments. ML models for IAV human adaptation prediction using large IAV genomic data sets can facilitate the identification of key viral factors that affect virus transmission/pathogenicity. Most importantly, it allows the prediction of pandemic influenza.

Download Full-text