Mateo Reveiz

BoltzGen: Toward Universal Binder Design

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.

Boltz-2: Towards Accurate and Efficient Binding Affinity Prediction

Boltz-2 predicts protein–ligand affinity from its co-folded structures, nearing free-energy perturbation accuracy (average Pearson 0.66 on a 4-target FEP+ subset) at over 1000× lower compute.

GLYCO-2: a Tool to Quantify Glycan Shielding of Glycosylated Proteins with Improved Data Processing and Computation Speed

GLYCO-2 improves computational efficiency for quantifying glycan shielding of glycoproteins, revealing increased shielding in influenza HA proteins over time.

Boltz-1: Democratizing Biomolecular Interaction Modeling

Open-source Boltz-1 predicts biomolecular complex structures comparably to AlphaFold3 and Chai-1 on CASP15 and recent PDB targets; Boltz-steering lets 97% of test-set poses pass physical checks.

Vaccine-elicited and naturally elicited antibodies differ in their recognition of the HIV-1 fusion peptide

This study compares vaccine-elicited and naturally elicited antibodies' recognition of HIV-1 fusion peptide sequences, finding that naturally elicited antibodies show greater tolerance to sequence variation.