Dataset of protein-ligand complexes now available in the Registry of Open Data on AWS

The article announces the release of a comprehensive dataset of over 16,000 protein-ligand complexes (PLCs) in the AWS Registry of Open Data, created through a collaboration between IIIT-Hyderabad, Intel, AWS, and Insilico Medicine.

• Dataset provides molecular dynamics trajectories and binding energy estimates for protein-ligand interactions
• Aimed at supporting machine learning and drug discovery research
• Generated using massive computational resources on AWS, scaling up to 300,000 vCPUs
• Utilized GROMACS for simulations and Amazon EC2, ParallelCluster, and FSx for Lustre for infrastructure
• Freely accessible with no transfer or storage fees

The dataset is intended to help computational researchers analyze protein-ligand interactions, potentially accelerating drug discovery processes by providing rich, dynamic molecular interaction data.