Related Experiment Video
Updated: Sep 28, 2025
07:55
Generation of Escape Variants of Neutralizing Influenza Virus Monoclonal Antibodies
Published on: August 29, 2017
11.9K
End-to-end antigenic variant generation for H1N1 influenza HA protein using sequence to sequence models
Mohamed Elsayed Abbas1,2, Zhu Chengzhang1,3,2, Ahmed Fathalla4
1School of Computer Science and Engineering, Central South University, Changsha, China.
Plos One
|March 28, 2022
Summary
A new deep learning model generates influenza A virus antigenic variants, accelerating vaccine development. This approach accurately predicts hemagglutinin protein changes, crucial for public health surveillance.
Area of Science:
- Virology
- Computational Biology
- Public Health
Background:
- Influenza A virus variants pose a significant public health risk, with potential for lethal outbreaks.
- Current methods for predicting viral antigenicity often rely on classification techniques and are time-consuming.
- Antigenic shift and drift, driven by surface protein changes, enable influenza A to evade host immunity.
Purpose of the Study:
- To develop a novel deep learning model for generating antigenic variants of the influenza A virus.
- To address the limitations of existing methods in terms of time and labor for identifying antigenic pairs.
- To create a model that generates the hemagglutinin (HA) protein of antigenic variants, a capability lacking in current literature.
Main Methods:
- Utilized an end-to-end deep learning methodology.
- Employed a sequence-to-sequence architecture to generate viral antigenic variants.
- Generated the HA protein of antigenic variants based on the influenza A virus surface protein.
Main Results:
- The proposed model achieved a mean accuracy of 97.57% in generating antigenic variants.
- The BLEU score was used to evaluate the generated HA protein against actual variants.
- The model successfully generated the HA protein of influenza A virus antigenic variants.
Conclusions:
- The developed deep learning model offers a significant advancement in predicting influenza A virus antigenicity.
- This approach can substantially reduce the time and effort required for identifying antigenic pairs.
- The model's high accuracy supports its potential application in public health surveillance and rapid vaccine development.
Related Concept Videos
02:28Leaky Scanning
5.3K
During most eukaryotic translation processes, the small 40S ribosome subunit scans an mRNA from its 5' end until it encounters the first start AUG codon. The large 60S ribosomal subunit then joins the smaller one to initiate protein synthesis. The location of the translation initiation is largely determined by the nucleotides near the start codon as there may be multiple translation initiation sites present on the mRNA. Marilyn Kozak discovered that the sequence RCCAUGG (where R...
5.3K
00:36Viral Mutations
33.9K
A mutation is a change in the sequence of bases of DNA or RNA in a genome. Some mutations occur during replication of the genome due to errors made by the polymerase enzymes that replicate DNA or RNA. Unlike DNA polymerase, RNA polymerase is prone to errors because it is not capable of “proofreading” its work. Viruses with RNA-based genomes, like HIV, therefore accrue mutations faster than viruses with DNA-based genomes. Because mutation and recombination provide the raw material...
33.9K