Convolutional Neural Network Based Approach to In Silico Non-Anticipating Prediction of Antigenic Distance for Influenza Virus

Forghani, Majid; Khachay, Michael

doi:10.3390/v12091019

Cited by 14 publications

(10 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From Table 3, it is observed that threshold 0.4 seems to be a good choice for modeling the antigenic variants. Compared with previous studies [10,11], our results indicate a high degree of accuracy, especially for H3N2, which suggests potential application in the field of public health.…”

Section: Resultscontrasting

confidence: 39%

“…They demonstrated that incorporating the structural context of protein can enhance antigenic evolution prediction. Additionally, Forghani and Khachay [10] carried out a principal component analysis on AAindex1 and introduced 11 indices that explained 91% of the total variation in the database. The new indices are further used to encode HA protein sequence and create an input tensor fed into a convolutional neural network.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reduced amino acid alphabet-based encoding and its impact on modeling influenza antigenic evolution

Forghani

Firstkov

AlyanNezhadi

et al. 2022

Russian Journal of Infection and Immunity

View full text Add to dashboard Cite

Currently, vaccination is one of the most efficient ways to control and prevent influenza infection. Vaccine production largely relies on the results of laboratory assays, including hemagglutination inhibition and microneutralization assays, which are time-consuming and laborious. Viruses can escape from the immune response that results in the need to revise and update vaccines biannually. The hemagglutination inhibition assay can measure how effectively antibodies against a reference strain bind and block an antigen of the test strain. Various computer-aided models have been developed to optimize candidate vaccine strain selection. A general problem in modeling of antigenic evolution is the representation of genetic sequences for input into the research model. Our motivation stems from the well-known problem of encoding genetic information for modeling antigenic evolution. This paper introduces a two-fold encoding approach based on reduced amino acid alphabet and amino acid index databases called AAindex. We propose to apply a simplified amino acid alphabet in modeling of antigenic evolution. A simplified alphabet, also called a sub-alphabet or reduced amino acid alphabet, implies to use the 20 amino acids being clustered and divided into amino acid groups. The proposed encoding allows to redefine mutations termed for amino acid groups located in reduced alphabets. We investigated 40 reduced amino acid sets and their performance in modeling antigenic evolution. The experimental results indicate that the proposed reduced amino acid alphabets can achieve the performance of the standard alphabet in its accuracy. Moreover, these alphabets provide deeper insight into various aspects of the relationship between mutation and antigenic variation. By checking identified high-impact sites in the Influenza Research Database, we found that not only antigenic sites have a significant influence on antigenicity, but also other amino acids located in close proximity. The results indicate that all selected non-antigenic sites are related to immune responses. According to the Influenza Research Database, these have been experimentally determined to be T-cell epitopes, B-cell epitopes, and MHC-binding epitopes of different classes. This highlighted a caveat: while simulating antigenic evolution, the model should consider not only the genetic information on antigenic sites, but also that of neighboring positions, as they may indirectly impact antigenicity. Additionally, our findings indicate that structural and charge characteristics are the most beneficial in modeling antigenic evolution, which is in agreement with previous studies.

show abstract

Section: Resultscontrasting

confidence: 39%

Section: Introductionmentioning

confidence: 99%

Reduced amino acid alphabet-based encoding and its impact on modeling influenza antigenic evolution

Forghani

Firstkov

AlyanNezhadi

et al. 2022

Russian Journal of Infection and Immunity

View full text Add to dashboard Cite

show abstract

“…The computational model is trained on influenza H3N2 subtype data and utilized antigenic cartography. Forghani et al [ 38 ] used physicochemical properties of the constituent amino acids with the help of PCA as a dimensionality reduction technique, to create a sequence encoding. The obtained sequence encoding is fed to a convolutional neural network to predict the antigenic distance for the H1N1 influenza virus subtype.…”

Section: Related Workmentioning

confidence: 99%

End-to-end antigenic variant generation for H1N1 influenza HA protein using sequence to sequence models

et al. 2022

View full text Add to dashboard Cite

The growing risk of new variants of the influenza A virus is the most significant to public health. The risk imposed from new variants may have been lethal, as witnessed in the year 2009. Even though the improvement in predicting antigenicity of influenza viruses has rapidly progressed, few studies employed deep learning methodologies. The most recent literature mostly relied on classification techniques, while a model that generates the HA protein of the antigenic variant is not developed. However, the antigenic pair of influenza virus A can be determined in a laboratory setup, the process needs a tremendous amount of time and labor. Antigenic shift and drift which are caused by changes in surface protein favored the influenza A virus in evading immunity. The high frequency of the minor changes in the surface protein poses a challenge to identifying the antigenic variant of an emerging virus. These changes slow down vaccine selection and the manufacturing process. In this vein, the proposed model could help save the time and efforts exerted to identify the antigenic pair of the influenza virus. The proposed model utilized an end-to-end learning methodology relying on deep sequence-to-sequence architecture to generate the antigenic variant of a given influenza A virus using surface protein. Employing the BLEU score to evaluate the generated HA protein of the antigenic variant of influenza virus A against the actual variant, the proposed model achieved a mean accuracy of 97.57%.

show abstract

“…Although in most cases, the representation of evolutionary history in terms of point mutations is quite informative, sometimes it is required to consider a more complex genetic signature (or motif) to well describe a phenotype. As an example, most of the models for predicting antigenic evolution rely on complex patterns at antigenic sites [6]. Studies have shown that non-antigenic sites located in the vicinity of antigenic sites also impact antigenicity.…”

Section: Introductionmentioning

confidence: 99%

Visualization of the Evolutionary Trajectory: Application of Reduced Amino Acid Alphabets and Word2Vec Embedding

Forghani

Firstkov

Vasev

et al. 2022

Proceedings of the 32nd International Conference on Computer Graphics and Vision

Self Cite

View full text Add to dashboard Cite

Analysis of viral evolution is a key element of epidemiological surveillance and control. One of the fundamental tools which is widely used to illustrate evolutionary history is the phylogenetic tree. Recently, we have proposed an alternative visualization for the phylogenetic tree using the evolutionary trajectory of its taxa. An evolutionary trajectory is a path starting from a taxon and ending at the root of the tree. In this paper, we propose an embedding of tree nodes by encoding their genetic sequence using a reduced amino acid alphabet and employing the Word2Vec framework. The suggested visualization maintains the phylogenetic relationship between nodes, while their proximity in 3D space depends on three factors: the type of reduced amino acid alphabet; fixed-length genetic patterns used in Word2Vec; and the neighbor effect of adjacent signatures. The results of our experiments showed that the majority of evolutionary history can be described in the embedded space. Moreover, they suggest potential application of our approach as an explanatory tool in studying various aspects: evolutionary dynamics; evolutionary deviation of viral variants; and phylogenetic characteristics, such as formation of new clades. Besides the usual local analysis of point mutations, the developed framework enables studying these aspects based on a more comprehensive global context, including neighboring effects, genetic signatures.

show abstract

Convolutional Neural Network Based Approach to In Silico Non-Anticipating Prediction of Antigenic Distance for Influenza Virus

Cited by 14 publications

References 56 publications

Reduced amino acid alphabet-based encoding and its impact on modeling influenza antigenic evolution

Reduced amino acid alphabet-based encoding and its impact on modeling influenza antigenic evolution

End-to-end antigenic variant generation for H1N1 influenza HA protein using sequence to sequence models

Visualization of the Evolutionary Trajectory: Application of Reduced Amino Acid Alphabets and Word2Vec Embedding

Contact Info

Product

Resources

About