Accurate Prediction of Virus-Host Protein-Protein Interactions via a Siamese Neural Network Using Deep Protein Sequence Embeddings

• Published in: bioRxiv 2022-05
• Main Authors: Madan, Sumit, Demina, Victoria, Stapf, Marcus, Ernst, Oliver, Froehlich, Holger
• Format: Article
• Language: English
• Subjects: Amino acid sequence; Bioinformatics; Deep learning; Embedding; Neural networks; Neurotransmitters; Predictions; Protein interaction; Proteins; Severe acute respiratory syndrome coronavirus 2; Spike protein; Therapeutic applications; Therapeutic targets; Virus-like particles; Viruses; VP1 protein
• ISSN: 2692-8205
• DOI: 10.1101/2022.05.31.494170

Prediction and understanding of tissue-specific virus-host interactions have relevance for the development of novel therapeutic interventions strategies. In addition, virus-like particles (VLPs) open novel opportunities to deliver therapeutic compounds to targeted cell types and tissues. Given our incomplete knowledge of virus-host interactions on one hand and the cost and time associated with experimental procedures on the other, we here propose a novel deep learning approach to predict virus-host protein-protein interactions (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 architecture. After evaluating the high prediction performance of STEP in comparison to an existing method, we apply it to two use cases, SARS-CoV-2 and John Cunningham polyomavirus (JCV), to predict virus protein to human host interactions. For the SARS-CoV-2 spike protein our method predicts an interaction with the sigma 2 receptor, which has been suggested as a drug target. As a second use case, we apply STEP to predict interactions of the JCV VP1 protein showing an enrichment of PPIs with neurotransmitters, which are known to function as an entry point of the virus into glial brain cells. In both cases we demonstrate how recent techniques from the field of Explainable AI (XAI) can be employed to identify those parts of a pair of sequences, which most likely contribute to the protein-protein interaction. Altogether our work highlights the potential of deep sequence embedding techniques originating from the field of natural language processing as well as XAI methods for the analysis of biological sequences. We have made our method publicly available via GitHub. Competing Interest Statement V.D., M.S., and O.E. are employees of Neuway Pharma GmbH. The company funded the work presented in this paper, but had no influence on scientific results.