# Machine-learning a virus assembly fitness landscape

## TL;DR

This paper demonstrates that machine learning, specifically neural networks, can rapidly and accurately predict the fitness landscape of virus assembly, significantly reducing computational effort compared to traditional stochastic models.

## Contribution

The study introduces a neural network approach to efficiently approximate the virus assembly fitness landscape, replacing costly stochastic simulations.

## Key findings

- Neural networks can predict assembly efficiency with high accuracy.
- The approach reduces computation time from hours to minutes.
- It enables rapid exploration of complex genotype-phenotype spaces.

## Abstract

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