QDCRNet: Quantum dilated convolutional recurrent network for virus detection using gene expression data.

Area of Science:

• Bioinformatics
• Computational Biology
• Genomics

Background:

• Viral infections pose significant global health risks, necessitating accurate and rapid detection methods.
• Current diagnostic challenges include non-specific symptoms, variable viral expression, and testing delays.
• Effective virus identification is crucial for timely treatment and controlling disease transmission.

Purpose of the Study:

• To develop and evaluate a novel deep learning model for precise virus detection using gene expression data.
• To address limitations in current viral diagnostic approaches through advanced computational methods.

Main Methods:

• Gene expression data underwent Box-Cox transformation.
• Feature selection was performed using Gower distance and mutual information to identify relevant genomic regions.
• Virus detection was achieved using the Quantum Dilated Convolutional Recurrent Network (QDCRNet), integrating Quantum Dilated Convolutional Neural Network (QDCNN) and Deep Recurrent Neural Network (DRNN).

Main Results:

• The QDCRNet model demonstrated high performance in virus detection.
• Achieved an accuracy of 90.80%, sensitivity of 90.50%, and specificity of 90.40%.

Conclusions:

• The QDCRNet model offers a powerful and accurate solution for virus detection from gene expression data.
• This approach has the potential to significantly improve the speed and precision of diagnosing viral infections.