Tempel: time-series mutation prediction of influenza A viruses via attention-based recurrent neural networks

Abstract

Motivation Influenza viruses are persistently threatening public health, causing annual epidemics and sporadic pandemics. The evolution of influenza viruses remains to be the main obstacle in the effectiveness of antiviral treatments due to rapid mutations. The goal of this work is to predict whether mutations are likely to occur in the next flu season using historical glycoprotein hemagglutinin sequence data. One of the major challenges is to model the temporality and dimensionality of sequential influenza strains and to interpret the prediction results. Results In this article, we propose an efficient and robust time-series mutation prediction model (Tempel) for the mutation prediction of influenza A viruses. We first construct the sequential training samples with splittings and embeddings. By employing recurrent neural networks with attention mechanisms, Tempel is capable of considering the historical residue information. Attention mechanisms are being increasingly used to improve the performance of mutation prediction by selectively focusing on the parts of the residues. A framework is established based on Tempel that enables us to predict the mutations at any specific residue site. Experimental results on three influenza datasets show that Tempel can significantly enhance the predictive performance compared with widely used approaches and provide novel insights into the dynamics of viral mutation and evolution. Availability and implementation The datasets, source code and supplementary documents are available at: https://drive.google.com/drive/folders/15WULR5__6k47iRotRPl3H7ghi3RpeNXH. Supplementary information Supplementary data are available at Bioinformatics online.

Predictive modeling of COVID-19 death cases in Pakistan

“…Different methods have often been adopted for modelling pathogens that transpire in recurrent or repeated cycles, for instance, seasonal virus, for which a variety of researches have been released which utilized time-series demonstration to forecast possible epidemics. In ( Song et al, 2016 ), and ARIMA ( Adhikari & Agrawal, 2013 ) method was built to predict the regular occurrence of infection in China for 2012, whereas in ( Yin et al, 2020 ), a predictive time series method (Tempel) was projected for influenza change estimation. Further sources include research by Lee et al ( Lee et al, 2017 ), who developed a time series method utilizing daily virus-linked tweet totals and used it to deliver instantaneous infection distribution evaluation.…”

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

“…Among them are protein structure prediction [39], gene expression regulation [40][41][42], predicting the sequence specificities [43], and protein classification [44]. Recently, deep learning has been applied to predict the mutation of the influenza virus [45], pathogenicity classification of H5 avian influenza [46], as well as time-series modeling for the recently emerging COVID-19 outbreak [47]. An inevitable problem in omics research is the representation of raw biological sequences, that is, amino acid sequence, as a network input.…”

IAV-CNN: a 2D convolutional neural network model to predict antigenic variants of influenza A virus

“…The influenza virus surface glycoproteins hemagglutinin (HA) is the main target for host immunity [6]. However, the accumulation of mutations on HA proteins results in the emergence of novel antigenic variants that can not be effectively inhibited by antibodies, posing great challenges for vaccine design [7]. Developing rapid and robust methods to determine influenza antigenicity is critical to influenza vaccine design and flu surveillance.…”