Structure prediction of protein-ligand complexes from sequence information with Umol.

Protein-ligand docking is an established tool in drug discovery and development to narrow down potential therapeutics for experimental testing. However, a high-quality protein structure is required and often the protein is treated as fully or partially rigid. Here we develop an AI system that can predict the fully flexible all-atom structure of protein-ligand complexes directly from sequence information.

Oxidatively-mediated in silico epimerization of a highly amyloidogenic segment in the human calcitonin hormone (hCT).

In order to study the effects of peptide exposure to oxidative attack, we chose a model reaction in which the hydroxyl radical discretely abstracts a hydrogen atom from the α-carbon of each residue of a highly amyloidogenic region in the human calcitonin hormone, hCT. Based on a combined Molecular Mechanics / Quantum Mechanics approach, the extended and folded L- and D-configuration and radical intermediate hCT peptides were optimized to obtain their compactness, secondary structure and relative thermodynamic data. The results suggest that the epimerization of residues is generally an exergonic process that can explain the cumulative nature of molecular aging.