Markus A. Lill

This study identifies three druggable targets in Plasmodium falciparum gametocytes using high-throughput screening and reveals resistance mechanisms for one compound.

This paper introduces a generative deep neural network to efficiently sample protein-ligand dynamics, enabling accurate and rapid generation of complexes with full flexibility.

This study evaluates whether deep learning models for co-folding adhere to physical principles in predicting protein-ligand interactions and finds they show discrepancies under perturbations, suggesting overfitting.

This paper introduces a distance-aware Transformer model that enhances ligand-based virtual screening by capturing 3D shape similarity, enabling efficient screening of large compound databases.

PanScreen assesses off-target liabilities of small molecules using structure-based modeling and deep learning, offering accurate predictions and insights into potential modes of action.

This paper evaluates dataset quality and splitting techniques for predicting protein-ligand binding affinities, introducing a tool (po-sco) and showing improved model performance with better data practices.