Jeliazko R. Jeliazkov

Humatch provides fast, gene-specific humanisation of antibody heavy and light chains using CNNs, aligning with experimental data and reducing immunogenic risks.

The paper shows that simple computational methods like BLOSUM can create diverse, binder-enriched antibody libraries better than deep learning approaches.

This paper demonstrates that inverting ESMFold can generate more native-like and expressive protein sequences compared to AFDesign, but with higher memory usage.

The paper presents a framework for ensuring reproducibility in bio-macromolecular modeling through automated benchmarks and a test server, demonstrating its utility for Rosetta and other tools.