Classical molecular dynamics (MD) and Quantum Mechanical (QM) MD have both been used to investigate the dynamics of the bio-molecular systems for many years. Classical MD provides this more efficiently using an empirical energy function, while QM MD determines energies and electron densities through solving the Schrodinger equation. While classical MD uses fixed molecular topologies, QM MD allows us to see the formation and breakage of covalent bonds, changes in protonation and tautomerization, and shows how reactions occur. Researchers, however, have found a way to achieve QM accuracy with near-classical efficiency with Anakin-Mi (ANI) forcefield. ANI uses a neural network to predict a system’s energy, given only a set of atoms and their positions. A potential called ANI-1 was then developed through ANI by being trained on a subset of GDB databases ( Human Genome Databases). We used this potential to predict forces for out well-characterized host-guest system. The force from each atom propagates the system forward in time. We then can run unbinding and binding simulations to view the reactions that take place when in bounded and unbounded states. Although this is slower than classical MD, this method paves the way for more accurate simulations to be used during drug discovery. We particularly expect this method to help improve the selectivity of covalent inhibitors, by modeling covalent attachment to target and off-target proteins.