High-Throughput Ligand Dissociation Kinetics Predictions Using Site Identification by Ligand Competitive Saturation DOI
Wenbo Yu, Shashi Kumar,

Mingtian Zhao

и другие.

Journal of Chemical Theory and Computation, Год журнала: 2025, Номер unknown

Опубликована: Апрель 26, 2025

The dissociation or off rate, koff, of a drug molecule has been shown to be more relevant efficacy than affinity for selected systems, motivating the development predictive computational methodologies. These are largely based on enhanced-sampling molecular dynamics (MD) simulations that come at high cost limiting their utility design where large number ligands need evaluated. To overcome this, presented is combined physics- and machine learning (ML)-based approach uses physics-based site identification by ligand competitive saturation (SILCS) method enumerate potential pathways calculate free-energy profiles along those pathways. calculated with properties used as features train ML models, including tree neural network approaches, predict koff values. protocol developed validated using 329 13 proteins showing robustness workflow built upon SILCS profiles. resulting SILCS-Kinetics offers highly efficient study kinetics, providing powerful tool facilitate ability generate quantitative estimates atomic functional groups contributions dissociation.

Язык: Английский

High-Throughput Ligand Dissociation Kinetics Predictions Using Site Identification by Ligand Competitive Saturation DOI
Wenbo Yu, Shashi Kumar,

Mingtian Zhao

и другие.

Journal of Chemical Theory and Computation, Год журнала: 2025, Номер unknown

Опубликована: Апрель 26, 2025

The dissociation or off rate, koff, of a drug molecule has been shown to be more relevant efficacy than affinity for selected systems, motivating the development predictive computational methodologies. These are largely based on enhanced-sampling molecular dynamics (MD) simulations that come at high cost limiting their utility design where large number ligands need evaluated. To overcome this, presented is combined physics- and machine learning (ML)-based approach uses physics-based site identification by ligand competitive saturation (SILCS) method enumerate potential pathways calculate free-energy profiles along those pathways. calculated with properties used as features train ML models, including tree neural network approaches, predict koff values. protocol developed validated using 329 13 proteins showing robustness workflow built upon SILCS profiles. resulting SILCS-Kinetics offers highly efficient study kinetics, providing powerful tool facilitate ability generate quantitative estimates atomic functional groups contributions dissociation.

Язык: Английский

Процитировано

0