Transfer learning via multi-scale convolutional neural layers for human-virus protein-protein interaction prediction

To complement experimental efforts, machine learning-based computational methods are playing an important role to predict human-virus protein-protein interactions (PPIs). To predict interactions between human and viral proteins, we combine evolutionary sequence profile features of interacting proteins with a Siamese convolutional neural network (CNN) architecture and a multi-layer perceptron, allowing us to outperform various feature encodings-based machine learning and state-of-the-art prediction methods. As our main contribution, we introduce a transfer learning method that reliably predicts interactions in a target human-virus domain based on training in a source human-virus domain. Finally, we utilize our transfer learning method to predict human-SARS-CoV-2 PPIs, indicating that our predictions are topologically and functionally similar to experimentally known interactions.