RT Journal Article
SR Electronic
T1 Transfer Learning with MotifTransformers for Predicting Protein-Protein Interactions Between a Novel Virus and Humans
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2020.12.14.422772
DO 10.1101/2020.12.14.422772
A1 Jack Lanchantin
A1 Arshdeep Sekhon
A1 Clint Miller
A1 Yanjun Qi
YR 2020
UL http://biorxiv.org/content/early/2020/12/15/2020.12.14.422772.abstract
AB The novel coronavirus SARS-CoV-2, which causes Coronavirus disease 2019 (COVID-19), is a significant threat to worldwide public health. Viruses such as SARS-CoV-2 infect the human body by forming interactions between virus proteins and human proteins that compromise normal human protein-protein interactions (PPI). Current in vivo methods to identify PPIs between a novel virus and humans are slow, costly, and difficult to cover the vast interaction space. We propose a novel deep learning architecture designed for in silico PPI prediction and a transfer learning approach to predict interactions between novel virus proteins and human proteins. We show that our approach outperforms the state-of-the-art methods significantly in predicting Virus–Human protein interactions for SARS-CoV-2, H1N1, and Ebola.Competing Interest StatementThe authors have declared no competing interest.