ABSTRACT
Summary Prediction and understanding of virus-host protein-protein interactions (PPIs) have relevance for the development of novel therapeutic interventions. In addition, virus-like particles open novel opportunities to deliver therapeutics to targeted cell types and tissues. Given our incomplete knowledge of PPIs on the one hand and the cost and time associated with experimental procedures on the other, we here propose a deep learning approach to predict virus-host PPIs. Our method (Siamese Tailored deep sequence Embedding of Proteins [STEP]) is based on recent deep protein sequence embedding techniques, which we integrate into a Siamese neural network. After showing the state-of-the-art performance of STEP on external datasets, we apply it to two use cases, severe acute respiratory syndrome coronavirus 2 and John Cunningham polyomavirus, to predict virus-host PPIs. Altogether our work highlights the potential of deep sequence embedding techniques originating from the field of NLP as well as explainable artificial intelligence methods for the analysis of biological sequences. Graphical Highlights • Deep learning approach (STEP) predicts virus protein to human host protein interactions• It is based on recent deep protein sequence embeddings and Siamese neural network• Prediction of PPIs of the JCV VP1 protein and of the SARS-CoV-2 spike protein• Identify parts of sequences that most likely contribute to the PPI using explainable AI The bigger picture The development of novel cell and tissue-specific therapies requires a profound knowledge about protein-protein interactions (PPIs). Identifying these PPIs with experimental approaches such as biochemical assays or yeast two-hybrid screens is cumbersome, costly, and at the same time difficult to scale. Computational approaches can help to prioritize huge amounts of possible PPIs by learning from biological sequences plus already known PPIs. In this work, we developed an approach that is based on recent deep protein sequence embedding techniques, which we integrate into a Siamese neural network architecture. We use this approach to train models by using protein sequence information and known PPIs. We apply the models to two use cases to predict virus protein to human host interactions. Altogether our work highlights the potential of deep sequence embedding techniques as well as explainable artificial intelligence methods for the analysis of biological sequence data. Protein-protein interaction (PPI) databases that include already-known PPIs represent an important resource in bioinformatics. A major challenge is to extend our knowledge of PPIs, which are highly relevant for the development of novel virus-like particles that can deliver therapeutics to targeted cells and tissues. Here, we use these PPI databases and the protein sequence information to train deep Siamese neural network architecture while using transfer learning and apply them to predict new virus-host PPIs with high accuracy.