TY - GEN

T1 - An Artificial Neural Network Based Ensemble Model for Predicting Antigenic Variants: Application of Reduced Amino Acid Alphabets and Word2Vec

T2 - 2022 8th Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS)

AU - Forghani, Majid

AU - Khachay, Michael

AU - Firstkov, Artyom

AU - Ramsay, Edward

N1 - This study was funded by the Russian Foundation for Basic Research (RFBR), project number 19-31-60025. Michael Khachay and Artyom Firstkov were funded by the Ural Mathematical Center with the financial support of the Ministry of Education and Science of the Russian Federation (Agreement number 075-02-2022-874).

PY - 2022/12/28

Y1 - 2022/12/28

N2 - Assessment of antigenic similarity between strains of the influenza virus is a crucial factor when planning vaccine compositions. To perform this, a gold-standard laboratory procedure, hemagglutination inhibition assay, is conventionally used. Despite its theoretical importance and accuracy, this procedure suffers from several shortcomings, including high time consumption. Therefore, various computer-aided and mathematical methods have been developed to acquire earlier knowledge on the antigenic characteristics of currently circulating viruses. In this paper, we introduce a state-of-the-art ensemble artificial neural network model based on features derived from multi-representation of antigenicity. Generally, each feature is generated from an optimized convolutional neural network whose input describes the genetic difference between viruses in a specific numerical space. The space is determined based on embedding of the genetic sequence by a reduced amino acid alphabet and the Word2Vec framework. Our experiments indicated that the proposed model outperformed approaches from the literature by achieving an accuracy level of 0.933 for the HINI subtype. This implies possible application of our model as a promising exploratory tool in practical tasks of virus control. © 2022 IEEE.

AB - Assessment of antigenic similarity between strains of the influenza virus is a crucial factor when planning vaccine compositions. To perform this, a gold-standard laboratory procedure, hemagglutination inhibition assay, is conventionally used. Despite its theoretical importance and accuracy, this procedure suffers from several shortcomings, including high time consumption. Therefore, various computer-aided and mathematical methods have been developed to acquire earlier knowledge on the antigenic characteristics of currently circulating viruses. In this paper, we introduce a state-of-the-art ensemble artificial neural network model based on features derived from multi-representation of antigenicity. Generally, each feature is generated from an optimized convolutional neural network whose input describes the genetic difference between viruses in a specific numerical space. The space is determined based on embedding of the genetic sequence by a reduced amino acid alphabet and the Word2Vec framework. Our experiments indicated that the proposed model outperformed approaches from the literature by achieving an accuracy level of 0.933 for the HINI subtype. This implies possible application of our model as a promising exploratory tool in practical tasks of virus control. © 2022 IEEE.

UR - http://www.scopus.com/inward/record.url?partnerID=8YFLogxK&scp=85149437293

U2 - 10.1109/ICSPIS56952.2022.10044061

DO - 10.1109/ICSPIS56952.2022.10044061

M3 - Conference contribution

SN - 978-166547623-2

SP - 1

EP - 6

BT - Proceedings - 2022 8th International Iranian Conference on Signal Processing and Intelligent Systems, ICSPIS 2022

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 28 December 2022 through 29 December 2022

ER -