Towards Interpreting Zoonotic Potential of Betacoronavirus Sequences With Attention
This work addresses the challenge of predicting zoonotic transmission risks for public health and virology, though it appears incremental as it builds on existing deep learning methods.
The researchers tackled the problem of distinguishing zoonotic potential in newly discovered betacoronaviruses, achieving a 94% accuracy using an attention-enhanced LSTM classifier on conserved viral proteins.
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 a 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.