Sarah F. Gurev

The paper investigates factors determining effective reassortment in orthohantaviruses, finding that ecological overlap and molecular compatibility are key for reassortant establishment.

The paper models SARS-CoV-2 evolution during the pandemic, finding that immune escape became more important than infectivity as variants evolved.

This paper evaluates variant effect prediction models on viruses, showing that state-of-the-art models underperform on viral proteins compared to alignment-based models, especially in low-sequence regimes.

RNAGym provides a benchmarking framework for RNA fitness, secondary structure, and tertiary structure prediction using diverse datasets and standardized assays.

The paper designs SARS-CoV-2 Spike proteins with novel mutations to evaluate vaccine effectiveness against future viral variants using a deep learning model.

This paper introduces a de-biasing method for sequence models of protein fitness to improve predictions of functional variants far from natural sequences.