• Modeling the structure of various viruses in the form of directed weighted graphs. • Presenting a feature extraction algorithm based on complex networks metrics. • The impact of the eigen-vector, input centrality and output centrality measures of specific nucleotide triplets within genes associated with particular virus types. • The independence of the proposed approach's performance from the length or type of virus genetic data. • Utilizing an interpretable classifier with the ability to relate findings to genetic concepts by extracting rules.