Balancing Pharmacodynamics and Pharmacokinetics in SARS-CoV-2 Mpro Inhibitors through Machine Learning and Molecular Dynamics

The main protease (M_pro) is a validated therapeutic target for inhibiting SARS-CoV-2 replication. Few lead compounds have advanced clinically due to difficulty in optimizing both target affinity and drug-like properties.  In order to address this challenge, we integrated machine learning (ML) and molecular dynamics (MD) simulations to investigate the balance between pharmacodynamic (PD) and PK properties in M_pro inhibitor design. We developed ML models to classify M_pro inhibitors using experimental IC₅₀ data, combining molecular descriptors with structural insights from MD simulations. Our Support Vector Machine (SVM) model achieved strong performance (training accuracy = 0.84, ROC AUC = 0.91; test accuracy = 0.79, ROC AUC = 0.86), while our logistic regression model (training accuracy = 0.78, ROC AUC = 0.85; test accuracy = 0.76, ROC AUC = 0.83). Notably, PK descriptors often exhibited opposing trends to binding affinity: hydrophilic features enhanced binding affinity but compromised PK properties, whereas hydrogen bonding, hydrophobic and π–π interactions in subsites S2 and S3/S4 are fundamental for binding affinity. Our findings highlight the need for a balanced approach in M_pro inhibitor design, strategically targeting these subsites may balance PD and PK properties. This study provides a computational framework for rational M_pro inhibitor discovery, combining ML and MD to investigate the complex interplay between enzyme inhibition and drug–likeness. These insights may guide in hit-to-lead optimization of the novel next-generation M_pro inhibitors of the SARS-CoV-2 with preclinical and clinical potential.