Towards Interpreting Zoonotic Potential of Betacoronavirus Sequences with Attention

Abstract

Current methods for viral discovery target evolutionarily conserved proteins that accurately identify virus families but remain unable to distinguish the zoonotic potential of newly discovered viruses. Here, we apply an attention-enhanced long-short-term memory (LSTM) deep neural net classifier to a highly conserved viral protein target to predict zoonotic potential across betacoronaviruses. The classifier performs with 94% accuracy. Analysis and visualization of attention at the sequence and structure-level features indicate possible association between important protein-protein interactions governing viral replication in zoonotic betacoronaviruses and zoonotic transmission.