Vincent Zoete

This paper optimizes AlphaFold3 for rapid and reliable structural modeling of antibodies and T-cell receptors, achieving 45-fold faster MSA phase and 3.6-fold faster inference.

The paper improves the molecular docking algorithm Attracting Cavities, enhancing its speed, sampling, and versatility while demonstrating better performance compared to AutoDock Vina.

This study compares co-folding and docking methods for drug design, finding that physics-based docking outperforms co-folding for novel ligands and provides physical rationale for binding.

The paper introduces a domain-centric method using physico-chemical properties to classify proteins, improving accuracy over traditional phylogeny-based approaches.

The paper develops a method combining machine learning and reverse screening to predict cancer cell line responses to cytotoxic molecules, achieving 71% accuracy in identifying experimental targets.

This paper introduces OiiSTER-map, a 2D heatmap to evaluate molecular quality in generative chemistry by combining bioactivity and structural features, aiming to improve drug discovery assessment.

The paper introduces TCR specificity profiles to identify key determinants of TCR-epitope recognition and shows their ability to predict cross-reactivity and interpret machine learning models.

This paper introduces TCRfp, a method converting TCR 3D structures into 1D fingerprints for high-throughput repertoire analysis and epitope recognition prediction.

The paper uses phage display and machine learning to discover TCRs specific to cancer antigens, identifying functional TCRs from large repertoires.

The paper redirects TCR specificity in regulatory T cells toward class I HLA antigens to enhance tissue-specific homing in Type 1 Diabetes.

The paper identifies a dominant monoallelic PAK2 variant causing Knobloch syndrome type 2 with intellectual disability and retinal degeneration.