Ensemble-Based Replica Exchange Alchemical Free Energy Methods: The Effect of Protein Mutations on Inhibitor Binding

Accurate calculation of affinity changes to the close state of influenza A M2 transmembrane domain in response to subtle structural changes of adamantyl amines using free energy perturbation methods in different lipid bilayers

Experimental binding free energies of 27 adamantyl amines against the influenza M2(22-46) WT tetramer, in its closed form at pH 8, were measured by ITC in DPC micelles. The measured Kd's range is ~44 while the antiviral potencies (IC50) range is ~750 with a good correlation between binding free energies computed with Kd and IC50 values (r = 0.76). We explored with MD simulations (ff19sb, CHARMM36m) the binding profile of complexes with strong, moderate and weak binders embedded in DMPC, DPPC, POPC or a viral mimetic membrane and using different experimental starting structures of M2. To predict accurately differences in binding free energy in response to subtle changes in the structure of the ligands, we performed 18 alchemical perturbative single topology FEP/MD NPT simulations (OPLS2005) using the BAR estimator (Desmond software) and 20 dual topology calculations TI/MD NVT simulations (ff19sb) using the MBAR estimator (Amber software) for adamantyl amines in complex with M2(22-46) WT in DMPC, DPPC, POPC. We observed that both methods with all lipids show a very good correlation between the experimental and calculated relative binding free energies (r = 0.77-0.87, mue = 0.36-0.92 kcal mol-1) with the highest performance achieved with TI/MBAR and lowest performance with FEP/BAR in DMPC bilayers. When antiviral potencies are used instead of the Kd values for computing the experimental binding free energies we obtained also good performance with both FEP/BAR (r = 0.83, mue = 0.75 kcal mol-1) and TI/MBAR (r = 0.69, mue = 0.77 kcal mol-1).

Comparison of Equilibrium and Nonequilibrium Approaches for Relative Binding Free Energy Predictions

Alchemical relative binding free energy calculations have recently found important applications in drug optimization. A series of congeneric compounds are generated from a preidentified lead compound, and their relative binding affinities to a protein are assessed in order to optimize candidate drugs. While methods based on equilibrium thermodynamics have been extensively studied, an approach based on nonequilibrium methods has recently been reported together with claims of its superiority. However, these claims pay insufficient attention to the basis and reliability of both methods. Here we report a comparative study of the two approaches across a large data set, comprising more than 500 ligand transformations spanning in excess of 300 ligands binding to a set of 14 diverse protein targets. Ensemble methods are essential to quantify the uncertainty in these calculations, not only for the reasons already established in the equilibrium approach but also to ensure that the nonequilibrium calculations reside within their domain of validity. If and only if ensemble methods are applied, we find that the nonequilibrium method can achieve accuracy and precision comparable to those of the equilibrium approach. Compared to the equilibrium method, the nonequilibrium approach can reduce computational costs but introduces higher computational complexity and longer wall clock times. There are, however, cases where the standard length of a nonequilibrium transition is not sufficient, necessitating a complete rerun of the entire set of transitions. This significantly increases the computational cost and proves to be highly inconvenient during large-scale applications. Our findings provide a key set of recommendations that should be adopted for the reliable implementation of nonequilibrium approaches to relative binding free energy calculations in ligand-protein systems.

Evaluating the ability of end-point methods to predict the binding affinity tendency of protein kinase inhibitors

Because of the high economic cost of exploring the experimental impact of mutations occurring in kinase proteins, computational approaches have been employed as alternative methods for evaluating the structural and energetic aspects of kinase mutations. Among the main computational methods used to explore the affinity linked to kinase mutations are docking procedures and molecular dynamics (MD) simulations combined with end-point methods or alchemical methods. Although it is known that end-point methods are not able to reproduce experimental binding free energy (ΔG) values, it is also true that they are able to discriminate between a better or a worse ligand through the estimation of ΔG. In this contribution, we selected ten wild-type and mutant cocrystallized EGFR-inhibitor complexes containing experimental binding affinities to evaluate whether MMGBSA or MMPBSA approaches can predict the differences in affinity between the wild type and mutants forming a complex with a similar inhibitor. Our results show that a long MD simulation (the last 50 ns of a 100 ns-long MD simulation) using the MMGBSA method without considering the entropic components reproduced the experimental affinity tendency with a Pearson correlation coefficient of 0.779 and an R2 value of 0.606. On the other hand, the correlation between theoretical and experimental ΔΔG values indicates that the MMGBSA and MMPBSA methods are helpful for obtaining a good correlation using a short rather than a long simulation period.

Can Free Energy Perturbation Simulations Coupled with Replica-Exchange Molecular Dynamics Study Ligands with Distributed Binding Sites?

Free energy perturbation coupled with replica exchange with solute tempering (FEP/REST) offers a rigorous approach to compute relative free energy changes for ligands. To determine the applicability of FEP/REST for the ligands with distributed binding poses, we considered two alchemical transformations involving three putative inhibitors I0, I1, and I2 of the Venezuelan equine encephalitis virus nuclear localization signal sequence binding to the importin-α (impα) transporter protein. I0 → I1 and I0 → I2 transformations, respectively, increase or decrease the polarity of the parent molecule. Our objective was three-fold─(i) to verify FEP/REST technical performance and convergence, (ii) to estimate changes in binding free energy ΔΔG, and (iii) to determine the utility of FEP/REST simulations for conformational binding analysis. Our results are as follows. First, our FEP/REST implementation properly follows FEP/REST formalism and produces converged ΔΔG estimates. Due to ligand inherent unbinding, the better FEP/REST strategy lies in performing multiple independent trajectories rather than extending their length. Second, I0 → I1 and I0 → I2 transformations result in overall minor changes in inhibitor binding free energy, slightly strengthening the affinity of I1 and weakening that of I2. Electrostatic interactions dominate binding interactions, determining the enthalpic changes. The two transformations cause opposite entropic changes, which ultimately govern binding affinities. Importantly, we confirm the validity of FEP/REST free energy estimates by comparing them with our previous REST simulations, directly probing binding of three ligands to impα. Third, we established that FEP/REST simulations can sample binding ensembles of ligands. Thus, FEP/REST can be applied (i) to study the energetics of the ligand binding without defined poses and showing minor differences in affinities |ΔΔG| ≲ 0.5 kcal/mol and (ii) to collect ligand binding conformational ensembles.

Enhanced Configurational Sampling Approaches to Alchemical Ligand Binding Free Energy Simulations: Current Status and Challenges

Ligand binding free energy simulations (LB-FES) have been routine tasks in modern drug discovery campaign. A long-standing challenge for LB-FES is the difficulty in adequately sampling nontrivial environmental reorganizations in response to ligand binding. Therefore, various enhanced configurational sampling (ECS) approaches were devised to speed up fluctuations of relevant slow degrees of freedom (SDOF) and ensure simulation convergence. However, in contrast to the achievements in parametrization, software performance, and workflow automation, efficient ECS methodology suitable for high throughput screening remains in an early stage of development. Here, a review of ECS developments with LB-FES is presented, revisiting current approaches and underlining the major technical pitfalls and challenges. This Perspective focuses on alchemical LB-FES on account of their predominant role in high throughput drug screening as well as the established partnership with ECS. The critical aspects of designing ECS approaches, from both theoretical and applied perspectives, are described. This work is intended to provide a contemporary review of the scientific, technical, and practical issues associated with the accelerating convergence of alchemical LB-FES.

ACES: Optimized Alchemically Enhanced Sampling

We present an alchemical enhanced sampling (ACES) method implemented in the GPU-accelerated AMBER free energy MD engine. The methods hinges on the creation of an "enhanced sampling state" by reducing or eliminating selected potential energy terms and interactions that lead to kinetic traps and conformational barriers while maintaining those terms that curtail the need to otherwise sample large volumes of phase space. For example, the enhanced sampling state might involve transforming regions of a ligand and/or protein side chain into a noninteracting "dummy state" with internal electrostatics and torsion angle terms turned off. The enhanced sampling state is connected to a real-state end point through a Hamiltonian replica exchange (HREMD) framework that is facilitated by newly developed alchemical transformation pathways and smoothstep softcore potentials. This creates a counterdiffusion of real and enhanced-sampling states along the HREMD network. The effect of a differential response of the environment to the real and enhanced-sampling states is minimized by leveraging the dual topology framework in AMBER to construct a counterbalancing HREMD network in the opposite alchemical direction with the same (or similar) real and enhanced sampling states at inverted end points. The method has been demonstrated in a series of test cases of increasing complexity where traditional MD, and in several cases alternative REST2-like enhanced sampling methods, are shown to fail. The hydration free energy for acetic acid was shown to be independent of the starting conformation, and the values for four additional edge case molecules from the FreeSolv database were shown to have a significantly closer agreement with experiment using ACES. The method was further able to handle different rotamer states in a Cdk2 ligand identified as fractionally occupied in crystal structures. Finally, ACES was applied to T4-lysozyme and demonstrated that the side chain distribution of V111χ1 could be reliably reproduced for the apo state, bound to p-xylene, and in p-xylene→ benzene transformations. In these cases, the ACES method is shown to be highly robust and superior to a REST2-like enhanced sampling implementation alone.

Predicting antibiotic resistance in complex protein targets using alchemical free energy methods

Drug resistant Mycobacterium tuberculosis, which mostly results from single nucleotide polymorphisms in antibiotic target genes, poses a major threat to tuberculosis treatment outcomes. Relative binding free energy (RBFE) calculations can rapidly predict the effects of mutations, but this approach has not been tested on large, complex proteins. We use RBFE calculations to predict the effects of M. tuberculosis RNA polymerase and DNA gyrase mutations on rifampicin and moxifloxacin susceptibility respectively. These mutations encompass a range of amino acid substitutions with known effects and include large steric perturbations and charged moieties. We find that moderate numbers (n = 3-15) of short RBFE calculations can predict resistance in cases where the mutation results in a large change in the binding free energy. We show that the method lacks discrimination in cases with either a small change in energy or that involve charged amino acids, and we investigate how these calculation errors may be decreased.

Predicting the mutation effects of protein–ligand interactions via end-point binding free energy calculations: strategies and analyses

Protein mutations occur frequently in biological systems, which may impact, for example, the binding of drugs to their targets through impairing the critical H-bonds, changing the hydrophobic interactions, etc. Thus, accurately predicting the effects of mutations on biological systems is of great interests to various fields. Unfortunately, it is still unavailable to conduct large-scale wet-lab mutation experiments because of the unaffordable experimental time and financial costs. Alternatively, in silico computation can serve as a pioneer to guide the experiments. In fact, numerous pioneering works have been conducted from computationally cheaper machine-learning (ML) methods to the more expensive alchemical methods with the purpose to accurately predict the mutation effects. However, these methods usually either cannot result in a physically understandable model (ML-based methods) or work with huge computational resources (alchemical methods). Thus, compromised methods with good physical characteristics and high computational efficiency are expected. Therefore, here, we conducted a comprehensive investigation on the mutation issues of biological systems with the famous end-point binding free energy calculation methods represented by MM/GBSA and MM/PBSA. Different computational strategies considering different length of MD simulations, different value of dielectric constants and whether to incorporate entropy effects to the predicted total binding affinities were investigated to provide a more accurate way for predicting the energetic change upon protein mutations. Overall, our result shows that a relatively long MD simulation (e.g. 100 ns) benefits the prediction accuracy for both MM/GBSA and MM/PBSA (with the best Pearson correlation coefficient between the predicted ∆∆G and the experimental data of ~ 0.44 for a challenging dataset). Further analyses shows that systems involving large perturbations (e.g. multiple mutations and large number of atoms change in the mutation site) are much easier to be accurately predicted since the algorithm works more sensitively to the large change of the systems. Besides, system-specific investigation reveals that conformational adjustment is needed to refine the micro-environment of the manually mutated systems and thus lead one to understand why longer MD simulation is necessary to improve the predicting result. The proposed strategy is expected to be applied in large-scale mutation effects investigation with interpretation.

Alchemical Free Energy Estimators and Molecular Dynamics Engines: Accuracy, Precision, and Reproducibility

The binding free energy between a ligand and its target protein is an essential quantity to know at all stages of the drug discovery pipeline. Assessing this value computationally can offer insight into where efforts should be focused in the pursuit of effective therapeutics to treat a myriad of diseases. In this work, we examine the computation of alchemical relative binding free energies with an eye for assessing reproducibility across popular molecular dynamics packages and free energy estimators. The focus of this work is on 54 ligand transformations from a diverse set of protein targets: MCL1, PTP1B, TYK2, CDK2, and thrombin. These targets are studied with three popular molecular dynamics packages: OpenMM, NAMD2, and NAMD3 alpha. Trajectories collected with these packages are used to compare relative binding free energies calculated with thermodynamic integration and free energy perturbation methods. The resulting binding free energies show good agreement between molecular dynamics packages with an average mean unsigned error between them of 0.50 kcal/mol. The correlation between packages is very good, with the lowest Spearman's, Pearson's and Kendall's tau correlation coefficients being 0.92, 0.91, and 0.76, respectively. Agreement between thermodynamic integration and free energy perturbation is shown to be very good when using ensemble averaging.

Large Scale Study of Ligand-Protein Relative Binding Free Energy Calculations: Actionable Predictions from Statistically Robust Protocols

The accurate and reliable prediction of protein-ligand binding affinities can play a central role in the drug discovery process as well as in personalized medicine. Of considerable importance during lead optimization are the alchemical free energy methods that furnish an estimation of relative binding free energies (RBFE) of similar molecules. Recent advances in these methods have increased their speed, accuracy, and precision. This is evident from the increasing number of retrospective as well as prospective studies employing them. However, such methods still have limited applicability in real-world scenarios due to a number of important yet unresolved issues. Here, we report the findings from a large data set comprising over 500 ligand transformations spanning over 300 ligands binding to a diverse set of 14 different protein targets which furnish statistically robust results on the accuracy, precision, and reproducibility of RBFE calculations. We use ensemble-based methods which are the only way to provide reliable uncertainty quantification given that the underlying molecular dynamics is chaotic. These are implemented using TIES (Thermodynamic Integration with Enhanced Sampling). Results achieve chemical accuracy in all cases. Ensemble simulations also furnish information on the statistical distributions of the free energy calculations which exhibit non-normal behavior. We find that the "enhanced sampling" method known as replica exchange with solute tempering degrades RBFE predictions. We also report definitively on numerous associated alchemical factors including the choice of ligand charge method, flexibility in ligand structure, and the size of the alchemical region including the number of atoms involved in transforming one ligand into another. Our findings provide a key set of recommendations that should be adopted for the reliable application of RBFE methods.

Pandemic drugs at pandemic speed: infrastructure for accelerating COVID-19 drug discovery with hybrid machine learning- and physics-based simulations on high-performance computers

The race to meet the challenges of the global pandemic has served as a reminder that the existing drug discovery process is expensive, inefficient and slow. There is a major bottleneck screening the vast number of potential small molecules to shortlist lead compounds for antiviral drug development. New opportunities to accelerate drug discovery lie at the interface between machine learning methods, in this case, developed for linear accelerators, and physics-based methods. The two in silico methods, each have their own advantages and limitations which, interestingly, complement each other. Here, we present an innovative infrastructural development that combines both approaches to accelerate drug discovery. The scale of the potential resulting workflow is such that it is dependent on supercomputing to achieve extremely high throughput. We have demonstrated the viability of this workflow for the study of inhibitors for four COVID-19 target proteins and our ability to perform the required large-scale calculations to identify lead antiviral compounds through repurposing on a variety of supercomputers.

Recent developments in multiscale free energy simulations

Physics-based free energy simulations enable the rigorous calculation of properties, such as conformational equilibria, solvation or binding free energies. While historically most applications have occurred at the atomistic level of resolution, a range of advances in the past years make it possible now to reliably cross the temporal, spatial and theory scales for the modeling of complex systems or the efficient prediction of results at the accuracy level of expensive quantum-mechanical calculations. In this mini-review, we discuss recent methodological advances as well as opportunities opened up by the introduction of machine learning approaches, which tackle the diverse challenges across the different scales, improve the accuracy and feasibility, and push the boundaries of multiscale free energy simulations.

Recent Developments in Free Energy Calculations for Drug Discovery

The grand challenge in structure-based drug design is achieving accurate prediction of binding free energies. Molecular dynamics (MD) simulations enable modeling of conformational changes critical to the binding process, leading to calculation of thermodynamic quantities involved in estimation of binding affinities. With recent advancements in computing capability and predictive accuracy, MD based virtual screening has progressed from the domain of theoretical attempts to real application in drug development. Approaches including the Molecular Mechanics Poisson Boltzmann Surface Area (MM-PBSA), Linear Interaction Energy (LIE), and alchemical methods have been broadly applied to model molecular recognition for drug discovery and lead optimization. Here we review the varied methodology of these approaches, developments enhancing simulation efficiency and reliability, remaining challenges hindering predictive performance, and applications to problems in the fields of medicine and biochemistry.

Structural basis for the hyperthermostability of an archaeal enzyme induced by succinimide formation

Stability of proteins from hyperthermophiles (organisms existing under boiling water conditions) enabled by a reduction of conformational flexibility is realized through various mechanisms. A succinimide (SNN) arising from the post-translational cyclization of the side chains of aspartyl/asparaginyl residues with the backbone amide -NH of the succeeding residue would restrain the torsion angle Ψ and can serve as a new route for hyperthermostability. However, such a succinimide is typically prone to hydrolysis, transforming to either an aspartyl or β-isoaspartyl residue. Here, we present the crystal structure of Methanocaldococcus jannaschii glutamine amidotransferase and, using enhanced sampling molecular dynamics simulations, address the mechanism of its increased thermostability, up to 100°C, imparted by an unexpectedly stable succinimidyl residue at position 109. The stability of SNN109 to hydrolysis is seen to arise from its electrostatic shielding by the side-chain carboxylate group of its succeeding residue Asp110, as well as through n → π^∗ interactions between SNN109 and its preceding residue Glu108, both of which prevent water access to SNN. The stable succinimidyl residue induces the formation of an α-turn structure involving 13-atom hydrogen bonding, which locks the local conformation, reducing protein flexibility. The destabilization of the protein upon replacement of SNN with a Φ-restricted prolyl residue highlights the specificity of the succinimidyl residue in imparting hyperthermostability to the enzyme. The conservation of the succinimide-forming tripeptide sequence (E(N/D)(E/D)) in several archaeal GATases strongly suggests an adaptation of this otherwise detrimental post-translational modification as a harbinger of thermostability.

Rapid and accurate estimation of protein-ligand relative binding affinities using site-identification by ligand competitive saturation

Predicting relative protein-ligand binding affinities is a central pillar of lead optimization efforts in structure-based drug design. The site identification by ligand competitive saturation (SILCS) methodology is based on functional group affinity patterns in the form of free energy maps that may be used to compute protein-ligand binding poses and affinities. Presented are results obtained from the SILCS methodology for a set of eight target proteins as reported originally in Wang et al. (J. Am. Chem. Soc., 2015, 137, 2695-2703) using free energy perturbation (FEP) methods in conjunction with enhanced sampling and cycle closure corrections. These eight targets have been subsequently studied by many other authors to compare the efficacy of their method while comparing with the outcomes of Wang et al. In this work, we present results for a total of 407 ligands on the eight targets and include specific analysis on the subset of 199 ligands considered previously. Using the SILCS methodology we can achieve an average accuracy of up to 77% and 74% when considering the eight targets with their 199 and 407 ligands, respectively, for rank-ordering ligand affinities as calculated by the percent correct metric. This accuracy increases to 82% and 80%, respectively, when the SILCS atomic free energy contributions are optimized using a Bayesian Markov-chain Monte Carlo approach. We also report other metrics including Pearson's correlation coefficient, Pearlman's predictive index, mean unsigned error, and root mean square error for both sets of ligands. The results obtained for the 199 ligands are compared with the outcomes of Wang et al. and other published works. Overall, the SILCS methodology yields similar or better-quality predictions without a priori need for known ligand orientations in terms of the different metrics when compared to current FEP approaches with significant computational savings while additionally offering quantitative estimates of individual atomic contributions to binding free energies. These results further validate the SILCS methodology as an accurate, computationally efficient tool to support lead optimization and drug discovery.

The effect of protein mutations on drug binding suggests ensuing personalised drug selection

The advent of personalised medicine promises a deeper understanding of mechanisms and therefore therapies. However, the connection between genomic sequences and clinical treatments is often unclear. We studied 50 breast cancer patients belonging to a population-cohort in the state of Qatar. From Sanger sequencing, we identified several new deleterious mutations in the estrogen receptor 1 gene (ESR1). The effect of these mutations on drug treatment in the protein target encoded by ESR1, namely the estrogen receptor, was achieved via rapid and accurate protein-ligand binding affinity interaction studies which were performed for the selected drugs and the natural ligand estrogen. Four nonsynonymous mutations in the ligand-binding domain were subjected to molecular dynamics simulation using absolute and relative binding free energy methods, leading to the ranking of the efficacy of six selected drugs for patients with the mutations. Our study shows that a personalised clinical decision system can be created by integrating an individual patient's genomic data at the molecular level within a computational pipeline which ranks the efficacy of binding of particular drugs to variant proteins.

Uncertainty quantification in classical molecular dynamics

Molecular dynamics simulation is now a widespread approach for understanding complex systems on the atomistic scale. It finds applications from physics and chemistry to engineering, life and medical science. In the last decade, the approach has begun to advance from being a computer-based means of rationalizing experimental observations to producing apparently credible predictions for a number of real-world applications within industrial sectors such as advanced materials and drug discovery. However, key aspects concerning the reproducibility of the method have not kept pace with the speed of its uptake in the scientific community. Here, we present a discussion of uncertainty quantification for molecular dynamics simulation designed to endow the method with better error estimates that will enable it to be used to report actionable results. The approach adopted is a standard one in the field of uncertainty quantification, namely using ensemble methods, in which a sufficiently large number of replicas are run concurrently, from which reliable statistics can be extracted. Indeed, because molecular dynamics is intrinsically chaotic, the need to use ensemble methods is fundamental and holds regardless of the duration of the simulations performed. We discuss the approach and illustrate it in a range of applications from materials science to ligand-protein binding free energy estimation. This article is part of the theme issue 'Reliability and reproducibility in computational science: implementing verification, validation and uncertainty quantification in silico'.

Assessing the sequence dependence of pyrimidine-pyrimidone (6-4) photoproduct in a duplex double-stranded DNA: A pitfall for microsecond range simulation

Sequence dependence of the (6-4) photoproduct conformational landscape when embedded in six 25-bp duplexes is evaluated along extensive unbiased and enhanced (replica exchange with solute tempering, REST2) molecular dynamics simulations. The structural reorganization as the central pyrimidines become covalently tethered is traced back in terms of non-covalent interactions, DNA bending, and extrusion of adenines of the opposite strands. The close sequence pattern impacts the conformational landscape around the lesion, inducing different upstream and downstream flexibilities. Moreover, REST2 simulations allow us to probe structures possibly important for damaged DNA recognition.

TIES 20: Relative Binding Free Energy with a Flexible Superimposition Algorithm and Partial Ring Morphing

The TIES (Thermodynamic Integration with Enhanced Sampling) protocol is a formally exact alchemical approach in computational chemistry to the calculation of relative binding free energies. The validity of TIES relies on the correctness of matching atoms across compared pairs of ligands, laying the foundation for the transformation along an alchemical pathway. We implement a flexible topology superimposition algorithm which uses an exhaustive joint-traversal for computing the largest common component(s). The algorithm is employed to enable matching and morphing of partial rings in the TIES protocol along with a validation study using 55 transformations and five different proteins from our previous work. We find that TIES 20 with the RESP charge system, using the new superimposition algorithm, reproduces the previous results with mean unsigned error of 0.75 kcal/mol with respect to the experimental data. Enabling the morphing of partial rings decreases the size of the alchemical region in the dual-topology transformations resulting in a significant improvement in the prediction precision. We find that increasing the ensemble size from 5 to 20 replicas per λ window only has a minimal impact on the accuracy. However, the non-normal nature of the relative free energy distributions underscores the importance of ensemble simulation. We further compare the results with the AM1-BCC charge system and show that it improves agreement with the experimental data by slightly over 10%. This improvement is partly due to AM1-BCC affecting only the charges of the atoms local to the mutation, which translates to even fewer morphed atoms, consequently reducing issues with sampling and therefore ensemble averaging. TIES 20, in conjunction with the enablement of ring morphing, reduces the size of the alchemical region and significantly improves the precision of the predicted free energies.

Rapid, accurate, precise and reproducible ligand-protein binding free energy prediction

A central quantity of interest in molecular biology and medicine is the free energy of binding of a molecule to a target biomacromolecule. Until recently, the accurate prediction of binding affinity had been widely regarded as out of reach of theoretical methods owing to the lack of reproducibility of the available methods, not to mention their complexity, computational cost and time-consuming procedures. The lack of reproducibility stems primarily from the chaotic nature of classical molecular dynamics (MD) and the associated extreme sensitivity of trajectories to their initial conditions. Here, we review computational approaches for both relative and absolute binding free energy calculations, and illustrate their application to a diverse set of ligands bound to a range of proteins with immediate relevance in a number of medical domains. We focus on ensemble-based methods which are essential in order to compute statistically robust results, including two we have recently developed, namely thermodynamic integration with enhanced sampling and enhanced sampling of MD with an approximation of continuum solvent. Together, these form a set of rapid, accurate, precise and reproducible free energy methods. They can be used in real-world problems such as hit-to-lead and lead optimization stages in drug discovery, and in personalized medicine. These applications show that individual binding affinities equipped with uncertainty quantification may be computed in a few hours on a massive scale given access to suitable high-end computing resources and workflow automation. A high level of accuracy can be achieved using these approaches.

Hit-to-lead and lead optimization binding free energy calculations for G protein-coupled receptors

We apply the hit-to-lead ESMACS (enhanced sampling of molecular dynamics with approximation of continuum solvent) and lead-optimization TIES (thermodynamic integration with enhanced sampling) methods to compute the binding free energies of a series of ligands at the A1 and A2A adenosine receptors, members of a subclass of the GPCR (G protein-coupled receptor) superfamily. Our predicted binding free energies, calculated using ESMACS, show a good correlation with previously reported experimental values of the ligands studied. Relative binding free energies, calculated using TIES, accurately predict experimentally determined values within a mean absolute error of approximately 1 kcal mol-1. Our methodology may be applied widely within the GPCR superfamily and to other small molecule-receptor protein systems.

Repulsive Soft-Core Potentials for Efficient Alchemical Free Energy Calculations

In alchemical free energy (FE) simulations, annihilation and creation of atoms are generally achieved with the soft-core potential that shifts the interparticle separations. While this soft-core potential eliminates the numerical instability occurring near the two end states of the transformation, it makes the hybrid Hamiltonian vary nonlinearly with respect to the parameter λ, which interpolates between the Hamiltonians representing the two end states. This complicates FE estimation by Bennett acceptance ratio (BAR), free energy perturbation (FEP), and thermodynamic integration (TI) methods, thus reducing their calculation efficiency. In this work, we develop a new type of repulsive soft-core potential, called Gaussian soft-core (GSC) potential, with two parameters controlling its maximum and width. The main advantage of this potential is the linearity of the hybrid Hamiltonian with respect to λ, thus permitting the direct application of BAR, FEP, TI, and other variant FE methods. The accuracy and efficiency of the GSC potential are demonstrated by comparing the free energies of annihilation determined for 13 small molecules and an alchemical mutation of a protein side chain. In addition, in combination with a TI integrand (∂H/∂λ) estimation strategy, we show that GSC can considerably reduce the number of λ simulations compared to the commonly used separation-shifted soft-core potential.

On Calculating Free Energy Differences Using Ensembles of Transition Paths

The free energy of a process is the fundamental quantity that determines its spontaneity or propensity at a given temperature. In particular, the binding free energy of a drug candidate to its biomolecular target is used as an objective quantity in drug design. Recently, binding kinetics—rates of association (k_on) and dissociation (k_off)—have also demonstrated utility for their ability to predict efficacy and in some cases have been shown to be more predictive than the binding free energy alone. Some methods exist to calculate binding kinetics from molecular simulations, although these are typically more difficult to calculate than the binding affinity as they depend on details of the transition path ensemble. Assessing these rate constants can be difficult, due to uncertainty in the definition of the bound and unbound states, large error bars and the lack of experimental data. As an additional consistency check, rate constants from simulation can be used to calculate free energies (using the log of their ratio) which can then be compared to free energies obtained experimentally or using alchemical free energy perturbation. However, in this calculation it is not straightforward to account for common, practical details such as the finite simulation volume or the particular definition of the “bound” and “unbound” states. Here we derive a set of correction terms that can be applied to calculations of binding free energies using full reactive trajectories. We apply these correction terms to revisit the calculation of binding free energies from rate constants for a host-guest system that was part of a blind prediction challenge, where significant deviations were observed between free energies calculated with rate ratios and those calculated from alchemical perturbation. The correction terms combine to significantly decrease the error with respect to computational benchmarks, from 3.4 to 0.76 kcal/mol. Although these terms were derived with weighted ensemble simulations in mind, some of the correction terms are generally applicable to free energies calculated using physical pathways via methods such as Markov state modeling, metadynamics, milestoning, or umbrella sampling.

Combining Machine Learning and Enhanced Sampling Techniques for Efficient and Accurate Calculation of Absolute Binding Free Energies

Calculating absolute binding free energies is challenging and important. In this paper, we test some recently developed metadynamics-based methods and develop a new combination with a Hamiltonian replica-exchange approach. The methods were tested on 18 chemically diverse ligands with a wide range of different binding affinities to a complex target; namely, human soluble epoxide hydrolase. The results suggest that metadynamics with a funnel-shaped restraint can be used to calculate, in a computationally affordable and relatively accurate way, the absolute binding free energy for small fragments. When used in combination with an optimal pathlike variable obtained using machine learning or with the Hamiltonian replica-exchange algorithm SWISH, this method can achieve reasonably accurate results for increasingly complex ligands, with a good balance of computational cost and speed. An additional benefit of using the combination of metadynamics and SWISH is that it also provides useful information about the role of water in the binding mechanism.

Accuracy and Precision of Alchemical Relative Free Energy Predictions with and without Replica-Exchange

A systematic and statistically robust protocol is applied for the evaluation of free energy calculations with and without replica-exchange. The protocol is based on ensemble averaging to generate accurate assessments of the uncertainties in the predictions. Comparison is made between FEP+ and TIES-free energy perturbation and thermodynamic integration with enhanced sampling-the latter with and without the so-called "enhanced sampling" based on replica-exchange protocols. Standard TIES performs best for a reference set of targets and compounds; no benefits accrue from replica-exchange methods. Evaluation of FEP+ and TIES with REST-replica-exchange with solute tempering-reveals a systematic and significant underestimation of free energy differences in FEP+, which becomes increasingly large for long duration simulations, is confirmed by extensive analysis of previous publications, and raises a number of questions pertaining to the accuracy of the predictions with the REST technique not hitherto discussed.