Many computer programmes can predict protein-protein interaction grounded with an amino acid sequence, although they tend to focus on species-specific interactions rather than cross-species ones. Homogeneous protein interaction prediction algorithms fail to find interactions between proteins from different species. In this research, we constructed an artificial intelligence deep learning model to encode the frequency of consecutive amino acids in a protein sequence. The deep learning model predicts human-viral protein interactions. The study used an artificial intelligence deep learning model and protein annotations to predict human-virus protein interactions. A simple but effective representation technique for predicting inter-species protein-protein interactions. The representation approach has several advantages, such as improving model performance, generating feature vectors, and applying the same representation to diverse protein types. The results of simulation show that the proposed method achieves an accuracy of 98% than other methods.