Predicting the mutational drivers of future SARS-CoV-2 variants of concern

SARS-CoV-2 evolution threatens vaccine- and natural infection-derived immunity, and the efficacy of therapeutic antibodies. Herein we sought to predict Spike amino acid changes that could contribute to future variants of concern. We tested the importance of features comprising epidemiology, evolution, immunology, and neural network-based protein sequence modeling. This resulted in identification of the primary biological drivers of SARS-CoV-2 intra-pandemic evolution. We found evidence that resistance to population-level host immunity has increasingly shaped SARS-CoV-2 evolution over time. We identified with high accuracy mutations that will spread, at up to four months in advance, across different phases of the pandemic. Behavior of the model was consistent with a plausible causal structure wherein epidemiological variables integrate the effects of diverse and shifting drivers of viral fitness. We applied our model to forecast mutations that will spread in the future, and characterize how these mutations affect the binding of therapeutic antibodies. These findings demonstrate that it is possible to forecast the driver mutations that could appear in emerging SARS-CoV-2 variants of concern. This modeling approach may be applied to any pathogen with genomic surveillance data, and so may address other rapidly evolving pathogens such as influenza, and unknown future pandemic viruses.

Evolutionary velocity with protein language models

Predicting the order of biological homologs is a fundamental task in evolutionary biology. For protein evolution, this order is often determined by first arranging sequences into a phylogenetic tree, which has limiting assumptions and can suffer from substantial ambiguity. Here, we demonstrate how machine learning algorithms called language models can learn mutational likelihoods that predict the directionality of evolution, thereby enabling phylogenetic analysis that addresses key limitations of existing methods. Our main conceptual advance is to construct a "vector field" of protein evolution through local evolutionary predictions that we refer to as evolutionary velocity (evo-velocity). We show that evo-velocity can successfully predict evolutionary order at vastly different timescales, from viral proteins evolving over years to eukaryotic proteins evolving over geologic eons. Evo-velocity also yields new evolutionary insights, predicting strategies of viral-host immune escape, resolving conflicting theories on the evolution of serpins, and revealing a key role of horizontal gene transfer in the evolution of eukaryotic glycolysis. In doing so, our work suggests that language models can learn sufficient rules of natural protein evolution to enable evolutionary predictability.