Jack Demaray

This paper develops interpretable biophysical neural networks to predict transcriptional activation domains from protein sequences, revealing how residue properties influence both activation strength and protein abundance.

This paper introduces bridge recombinase for versatile genome editing in bacteria, achieving large insertions, inversions, and excisions across multiple phyla and gut communities.

The paper introduces NNMF, a spatially-aware method for analyzing spatial transcriptomics data, identifying multicellular patterns and spatially-variable genes in large datasets.