Molecular Dynamics Simulation Data of Five BRAF V600E Inhibitor Complexes: AI-Designed Small Molecules in Oncology

Background & ContextThis dataset comprises molecular dynamics (MD) simulations of four novel BRAF V600E inhibitor complexes, designed using REINVENT 4, an advanced AI/ML framework integrating reinforcement learning (RL) and transfer learning (TL). The BRAF V600E mutation is a critical therapeutic target in melanoma, thyroid carcinoma, and colorectal cancer, but existing inhibitors face challenges like drug resistance and off-target toxicity. These simulations validate the binding stability and dynamics of AI-generated inhibitors, offering insights for structure-based drug optimization.Data ContentThe dataset includes:Topology Files (*.top, *.gro) – Essential for simulation reproducibility.Trajectory Files (e.g., *.xtc, *.trr) – Full MD trajectories for all replicates.Simulation Parameters – Force field (e.g., AMBER/CHARMM), temperature, pressure, and integration steps.Potential ApplicationsDrug Discovery: Benchmarking AI-designed inhibitors against known BRAF inhibitors.Structural Biology: Studying protein-ligand stability and conformational dynamics.Machine Learning: Training predictive models for binding affinity or resistance mutations.