Structure–Kinetic Relationship for Drug Design Revealed by a PLS Model with Retrosynthesis-Based Pre-Trained Molecular Representation and Molecular Dynamics Simulation

[Image: see text] Drug design based on kinetic properties is growing in application. Here, we applied retrosynthesis-based pre-trained molecular representation (RPM) in machine learning (ML) to train 501 inhibitors of 55 proteins and successfully predicted the dissociation rate constant (k(off)) values of 38 inhibitors from an independent dataset for the N-terminal domain of heat shock protein 90α (N-HSP90). Our RPM molecular representation outperforms other pre-trained molecular representations such as GEM, MPG, and general molecular descriptors from RDKit. Furthermore, we optimized the accelerated molecular dynamics to calculate the relative retention time (RT) for the 128 inhibitors of N-HSP90 and obtained the protein–ligand interaction fingerprints (IFPs) on their dissociation pathways and their influencing weights on the k(off) value. We observed a high correlation among the simulated, predicted, and experimental −log(k(off)) values. Combining ML, molecular dynamics (MD) simulation, and IFPs derived from accelerated MD helps design a drug for specific kinetic properties and selectivity profiles to the target of interest. To further validate our k(off) predictive ML model, we tested our model on two new N-HSP90 inhibitors, which have experimental k(off) values and are not in our ML training dataset. The predicted k(off) values are consistent with experimental data, and the mechanism of their kinetic properties can be explained by IFPs, which shed light on the nature of their selectivity against N-HSP90 protein. We believe that the ML model described here is transferable to predict k(off) of other proteins and will enhance the kinetics-based drug design endeavor.