Machine-learning a virus assembly fitness landscape

Realistic evolutionary fitness landscapes are notoriously difficult to construct. A recent cutting-edge model of virus assembly consists a dodecahedral capsid with $12$ corresponding packaging signals in three affinity bands. This whole genome/phenotype space consisting $3^{12}$ genomes has been explored via computationally expensive stochastic models, giving landscape terms the efficiency. Using latest machine-learning techniques by establishing neural network, we show that intensive computation can be short-circuited matter minutes astounding accuracy.