2020
DOI: 10.3390/v12091019
|View full text |Cite
|
Sign up to set email alerts
|

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

Abstract: Evaluation of the antigenic similarity degree between the strains of the influenza virus is highly important for vaccine production. The conventional method used to measure such a degree is related to performing the immunological assays of hemagglutinin inhibition. Namely, the antigenic distance between two strains is calculated on the basis of HI assays. Usually, such distances are visualized by using some kind of antigenic cartography method. The known drawback of the HI assay is that it is rather time-consu… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
9
1

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
2
1

Relationship

2
7

Authors

Journals

citations
Cited by 14 publications
(10 citation statements)
references
References 56 publications
0
9
1
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%
See 1 more Smart Citation
“…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%
“…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%
“…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%