Jan K. Marzinek, Peter J. Bond, Guoping Lian, Yanyan Zhao, Lujia Han, Massimo G. Noro, Efstratios N. Pistikopoulos, Athanasios Mantalaris

Free energy prediction of ligand binding to macromolecules using explicit solvent molecular dynamics (MD) simulations is computationally very expensive. Recently, we reported a linear correlation between the binding free energy obtained via umbrella sampling (US) versus the rupture force from steered molecular dynamics (SMD) simulations for epigallocatechin-3-gallate (EGCG) binding to α-helical rich keratin. This linear correlation suggests a potential route for fast free-energy predictions using SMD alone. In this work, the generality of the linear correlation is further tested for several ligands interacting with the α-helical motif of keratin. These molecules have significantly varying properties i.e. octanol/water partition coefficient (logP), and/or overall charges (oleic acid, catechin, Fe(2+), citric acid, hydrogen citrate, dihydrogen citrate and citrate). Using the constant loading rate of our previous study of the keratin-EGCG system, we observe that the linear correlation for keratin-EGCG can be extended to other uncharged molecules where interactions are governed by hydrogen bonds and/or a combination of hydrogen bonds and hydrophobic forces. For molecules where interactions with the keratin helix are governed primarily by electrostatics between charged molecules, a second, alternative linear correlation model is derived. Whilst further investigations are needed to expand the molecular space and build a fully predictive model, the current approach represents a promising methodology for fast free energy predictions based on short SMD simulations (requiring picoseconds to nanoseconds of sampling) for defined biomolecular systems.