Víctor S. Batista

Humanized Anti-PD-1 Antibodies Generated Using The Conditional Kernel-Elastic Autoencoder

This paper uses a machine learning model to generate new anti-PD-1 antibodies with improved potency, validated through molecular dynamics simulations and experimental testing.

Label-Free AI-Classification of Subcellular Organelles Based on Optical Photothermal Infrared Images

This paper uses machine learning to classify subcellular organelles from infrared images, achieving accurate identification of several organelles but not all.

Rewiring V-type and K-type enzyme allostery through subunit interface mutations

This paper identifies specific interfacial residues in IGPS that modulate allosteric regulation through structural and dynamic changes induced by targeted mutations.

Crystal structure and molecular dynamics simulations of rademikibart Fab-IL-4Rα complex reveal biochemical basis for next-generation potent IL-4Rα inhibition in type 2 allergic and inflammatory diseases

This paper determines the crystal structure of rademikibart Fab-IL-4Rα complex and performs MD simulations to show its superior binding and inhibition of IL-4R compared to dupilumab.

Dynamic and structural insights into allosteric regulation on MKP5 a dual-specificity phosphatase

This study investigates the allosteric regulation of MKP5 by identifying the role of residue Y435 in maintaining the structural integrity of the allosteric pocket and its interaction with p38 MAPK and JNK.

QOBRA: A Quantum Operator-Based Autoencoder for De Novo Molecular Design

QOBRA is a quantum autoencoder for de novo molecular design that generates valid, novel molecules from limited datasets, demonstrating the potential of quantum computing in molecular synthesis.

Allosteric Modulation of MIF-2 Structure, Catalysis, and Biological Signaling via Cysteine Residues and a Small Molecule, Ebselen

This study investigates how Ebselen modulates MIF-2 structure, catalysis, and signaling through cysteine residues, revealing its impact on trimer stability and function.

T-ALPHA: A Hierarchical Transformer-Based Deep Neural Network for Protein-Ligand Binding Affinity Prediction With Uncertainty-Aware Self-Learning for Protein-Specific Alignment

T-ALPHA predicts protein-ligand binding affinity using a hierarchical transformer model and uncertainty-aware self-learning, outperforming existing methods and working with predicted structures.