Deep recurrent neural network with fractional addax optimization algorithm for influenza virus host prediction

Abstract

The accurate prediction of the host of influenza viruses is a significant challenge in bioinformatics, as it is crucial for understanding viral transmission dynamics and host-virus interactions. This research

• •
  Introduces a novel approach for predicting the host of influenza viruses by leveraging protein sequences.
• •
  Extraction of features, including sequence length, Amino Acid Composition (AAC), Dipeptide Composition (DPC), Tripeptide Composition (TPC), aromaticity, secondary structure fraction, and entropy from protein sequence.
• •
  Addresses the data imbalance and improves model generalization, the oversampling technique is applied for data augmentation.

The prediction model employs a Deep Recurrent Neural Network (DRNN) optimized by Fractional Addax Optimization 34 Algorithm (FAOA), a hybrid of Addax Optimization Algorithm (AOA) and Fractional Concept (FC), designed to perform 35 influenza virus host prediction. The model's performance is evaluated using metrics, such as Matthews's Correlation 36 Coefficient (MCC), F1-Score, and Mean Squared Error (MSE). Experimental results demonstrate that the DRNN_FAOA 37 model significantly outperforms existing methods, achieving the highest MCC of 0.937, F1-Score of 0.917, and the 38 lowest MSE of 0.038. The proposed DRNN_FAOA model's ability to accurately predict influenza virus hosts suggests its 39 potential as a robust model in virus-host prediction.