Gabriel Foley

Systematic Regional Bias is Widespread in ChIP-seq

The paper identifies systematic regional bias in ChIP-seq data across multiple experiments and proposes metrics to improve data integration.

Learning the Language of Phylogeny with MSA Transformer

This study evaluates how MSA Transformer captures evolutionary distance and epistasis in protein sequences, showing it can reconstruct phylogenetic trees consistent with maximum likelihood methods.

Codon language model scores provide information beyond protein language models for missense variant interpretation

The paper shows that codon-level scores from the CaLM model provide additional information for missense variant interpretation beyond protein-level representations.

Do Protein Language Models Learn Phylogeny?

This study evaluates protein language models' ability to infer phylogenetic relationships without explicit training, finding they perform well in low- and high-gap settings and capture broader evolutionary relationships.

Optimal Phylogenetic Reconstruction of Insertion and Deletion Events

This paper introduces a Mixed-Integer Programming approach to optimally reconstruct indel events in phylogenetic trees, outperforming existing methods in accuracy and efficiency.

Engineering indel and substitution variants of diverse and ancient enzymes using Graphical Representation of Ancestral Sequence Predictions (GRASP)

The paper introduces GRASP, a method for ancestral sequence reconstruction that handles large datasets and indels, demonstrating its ability to generate biologically active enzyme ancestors.