Gabriella O. Estevam

Learning inhibitor interactions from protein deep mutational scanning data and deep learning models

The paper benchmarks AI models for predicting mutational effects and drug-target affinity using deep mutational scanning data, finding that current models fail to capture inhibitor-dependent fitness landscapes.

Autoregulation of the MET Receptor Tyrosine Kinase by its Intracellular Juxtamembrane Domain

This study identifies a role for the MET juxtamembrane domain in accelerating kinase activation through an allosteric mechanism, with implications for MET-driven cancer therapies.

Mapping kinase domain resistance mechanisms for the MET receptor tyrosine kinase via deep mutational scanning

The paper uses deep mutational scanning to analyze MET kinase domain mutations and their resistance to 11 inhibitors, identifying resistance and sensitizing mutations and improving prediction with a protein language model.

Engineering of CRISPR-Cas PAM recognition using deep learning of vast evolutionary data

This paper introduces Protein2PAM, a deep learning model that predicts CRISPR-Cas PAM specificity from protein sequences, enabling the design of Cas variants with tailored PAM recognition.

Rosace: a robust deep mutational scanning analysis framework employing position and mean-variance shrinkage

Rosace improves analysis of deep mutational scanning data by using Bayesian shrinkage and position information, outperforming existing methods in simulations and real data.

Conserved regulatory motifs in the juxtamembrane domain and kinase N-lobe revealed through deep mutational scanning of the MET receptor tyrosine kinase domain.