Combined Free-Energy Calculation and Machine Learning Methods for Understanding Ligand Unbinding Kinetics

The determination of drug residence times, which define the time an inhibitor is in complex with its target, is a fundamental part of the drug discovery process. Synthesis and experimental measurements of kinetic rate constants are, however, expensive and time consuming. In this work, we aimed to obtaindrug residence times computationally. Furthermore, we propose a novel algorithm to identify molecular design objectives based on ligand unbinding kinetics. We designed an enhanced sampling technique to accurately predict the free-energy profiles of theligand unbinding process, focusing on the free-energy barrier forunbinding. Our methodfirst identifies unbinding paths determin-ing a corresponding set of internal coordinates (ICs) that formcontacts between the protein and the ligand; it then iterativelyupdates these interactions during a series of biased molecular dynamics (MD) simulations to reveal the ICs that are important forthe whole of the unbinding process. Subsequently, we performedfinite-temperature string simulations to obtain the free-energybarrier for unbinding using the set of ICs as a complex reaction coordinate. Importantly, we also aimed to enable the further designof drugs focusing on improved residence times. To this end, we developed a supervised machine learning (ML) approach with inputsfrom unbiaseddownhilltrajectories initiated near the transition state (TS) ensemble of the string unbinding path. We demonstratethat our ML method can identify key ligand-protein interactions driving the system through the TS. Some of the most importantdrugs for cancer treatment are kinase inhibitors. One of these kinase targets is cyclin-dependent kinase 2 (CDK2), an appealingtarget for anticancer drug development. Here, we tested our method using two different CDK2 inhibitors for the potential furtherdevelopment of these compounds. We compared the free-energy barriers obtained from our calculations with those observed inavailable experimental data. We highlighted important interactions at the distal ends of the ligands that can be targeted for improvedresidence times. Our method provides a new tool to determine unbinding rates and to identify key structural features of the inhibitors that can be used as starting points for novel design strategies in drug discovery

Automated summary

In this study, computational methods were used to determine drug residence times and identify key structural features of inhibitors. The researchers proposed a novel algorithm and developed a machine learning model, which showed potential in predicting unbinding rates and identifying key ligand-protein interactions. The method was tested using CDK2 inhibitors, and important interactions for improving residence times were identified.