Biomacromolecule structures are vital in drug development, with X-ray diffraction (XRD) traditionally used to determine their atomic structures. However, the development of force fields for diversified drug molecules has been challenging. Quantum refinement (QR) methods have shown promise in improving biomacromolecule structures, but their application has been limited due to high computational costs. To overcome this, researchers have incorporated machine learning potentials (MLPs) into multiscale ONIOM-QMMM schemes, achieving quantum mechanics-level accuracy with higher efficiency. This incorporation of machine learning into QR methods could accelerate the refinement process and provide more atomistic insights into drug development.
↧