Gina El Nesr

The paper evaluates protein foundation models using NMR chemical shifts to identify their limitations and introduces a model that predicts its own error.

This paper demonstrates that deep learning can accurately design RNA pseudoknots, achieving results comparable to human experts in a competition.

Makeshift provides a lightweight Python package for accessing and analyzing NMR data, enabling reproducible and scalable analysis of biomolecular dynamics and chemical environments.

Trained on missing NMR amide assignments in the Biological Magnetic Resonance Data Bank, Dyna-1 (ESM-3 layer 22 embeddings) predicts micro-to-millisecond conformational exchange seen in relaxation data.

This paper introduces dEVA, a framework for de novo metalloenzyme design, achieving high catalytic activity without natural templates.

This paper introduces Caliby, a sequence design method that conditions on structural ensembles to improve designability while reducing native sequence recovery.

The paper designs bispecific antibodies that retain neutralization activity against multiple SARS-CoV-2 variants, including Omicron subvariants.