Julia Fukuyama

Entrenchment of germline amino-acid differences in antibody affinity maturation

This study uses deep learning to detect entrenchment in antibody germline genes, revealing epistatic constraints from both intra-chain and genetically uncoupled partners.

Separating selection from mutation in antibody language models

This paper introduces a model that separates mutation and selection processes in antibody language models to improve prediction of mutation effects on antibody function.

Nucleotide context models outperform protein language models for predicting antibody affinity maturation

This study compares nucleotide context models and protein language models for predicting antibody affinity maturation, finding nucleotide-based models perform better.

Thrifty wide-context models of B cell receptor somatic hypermutation

The paper develops 'thrifty' models of somatic hypermutation using convolutions on 3-mer embeddings, showing they outperform 5-mer models with fewer parameters.

A decomposition of a phylogenetically-informed distance into basal and terminal components

The paper decomposes a phylogenetically-informed distance into basal and terminal components, showing that basal structure dominates and demonstrates applications in simulated and real datasets.