Andrew Savinov

This study uses AI to design protein fragments that regulate biomolecular condensates, showing success in multiple targets and revealing new interaction mechanisms.

An all-atom diffusion model unifying biomolecular structure prediction and sequence-structure generation designs experimentally validated nanobodies, mini-proteins, and linear or cyclic peptides across 26 diverse targets.

This paper introduces FragFold, a computational method using AlphaFold to predict inhibitory protein fragments, showing high accuracy in predicting binding and inhibitory activity.

The paper assesses the functional impact of sequence motifs in yeast 3' UTRs using random sequence libraries, revealing context-dependent regulatory effects.