Hunter M. Nisonoff

This study shows that large-scale recombination can generate millions of catalytically competent PETases compatible with high-throughput screening.

This study investigates the trade-off between activity and specificity in adenine base editors using machine learning and high-throughput screening, finding that activity is the primary determinant of editing outcomes.

The paper designs active RNA-guided nucleases using AI and structure-guided methods, validated by cryo-EM and functional testing across species.

The paper develops ADhunter, a model to identify and quantify transcriptional activators in fungal genomes, expanding functional annotations across non-model species.

The paper develops an RNA language model to predict mutations that enhance RNA thermostability using a new database of RNA sequences linked to environmental temperatures.

GENTANGLE is a computational tool for designing overlapping gene pairs in microbial genomes, enabling safer genetic engineering through gene entanglements.

The paper traces the evolutionary origin of eukaryotic RNA-guided endonucleases, showing they evolved from a specific clade of bacterial IS607 TnpB enzymes.

This paper introduces a method to improve deep neural network predictions of fitness functions by leveraging sparse epistatic interactions in genetic sequences.

The paper evaluates methods for predicting protein fitness using both evolutionary and assay-labelled data, finding a simple baseline approach competitive with more complex methods.

OSPREY 3.0 improves protein design software with faster algorithms, GPU support, and a Python interface, showing accurate mutation effect predictions on protein-protein binding.