Oscar A. MacLean

Protein language models learn the underlying accessibility of mutations alongside protein fitness landscapes

This study evaluates how protein language models capture mutational processes and fitness landscapes, finding that explicit mutational accessibility improves predictions while historical biases degrade performance.

Understanding the emergence of the influenza A/H3N2 K subclade in its historical and evolutionary context

The paper investigates the emergence of the influenza A/H3N2 K subclade, finding limited antigenic change and age-dependent vaccine responses, suggesting non-antigenic selection pressures.

A Machine Learning Framework to Identify the Correlates of Disease Severity in Acute Arbovirus Infection

This study uses machine learning to identify key viral and host processes associated with varying severity in bluetongue virus infection in sheep.

Conserved recombination patterns across coronavirus subgenera

The paper identifies conserved recombination patterns across six coronavirus subgenera and links them to transcriptional regulatory sequences and sequence features.