Marissa A. Zintel

The paper designs functional transcriptional activation domains using machine learning and experimental validation, finding that over 90% of predicted sequences work in yeast.

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.

The paper shows that function can be conserved in transcriptional activation domains without sequence conservation through evolutionary turnover of key residues.

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