Samantha Petti

This paper introduces two methods, SLED and GTD, to infer modular structure in genotype-phenotype maps by combining epistasis and pleiotropy, showing they yield similar modular architectures in yeast data.

The paper uses joint QTL mapping to analyze pleiotropy patterns across structured environments in budding yeast, revealing genetic interactions influenced by environmental relationships.

The paper establishes the relationship between Gaussian process priors and regularized regression in sequence-to-function mapping, showing how to construct regularizers that correspond to explicit Gaussian process priors and characterize implicit function space priors.

This paper applies attention-based models to predict phenotype from genotype, showing improved performance in epistatic regimes and enabling transfer learning across environments.

The paper introduces a new structural alphabet for protein structure search that improves accuracy when combined with existing methods.

The paper introduces interpretable Gaussian process models for sequence-function relationships, capturing epistasis and achieving superior predictive performance on large biological datasets.

SoftAlign is an end-to-end protein structure alignment method that improves accuracy over existing tools while being compatible with other alignment strategies.

This paper introduces a differentiable Smith-Waterman algorithm to jointly learn multiple sequence alignments and downstream tasks, showing improvements in contact prediction and structure prediction.

The paper introduces two new methods for splitting biological sequence data into training and test sets to improve benchmarking by ensuring test sequences are dissimilar to training sequences.