Pablo Gaínza

The paper predicts over 1,400 CRBN-compatible β-hairpin G-loop proteins and validates 22 neosubstrates, redefining rules for molecular glue-induced degradation.

The paper develops caffeine-inducible systems for controlling gene expression in human cells using humanized protein components and demonstrates their use in inducible gene expression in T-cells.

This study identifies a novel binding mechanism of G3BP2 to CRBN through an unconventional site, expanding the understanding of CRBN's neosubstrate recognition.

This paper designs proteins that target neosurfaces from protein-ligand complexes using a deep learning approach, validated experimentally against three drug-bound protein complexes.

Mammalian display of CRISPR-introduced trastuzumab mutant libraries trains a network that picks antigen binders out of a hundred-million-variant virtual library; 30 of 30 tested variants bound.

The paper introduces MaSIF, a geometric deep learning framework to predict biomolecular interactions by learning interaction fingerprints from protein molecular surfaces.

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.