Automated Adaptive Absolute Binding Free Energy Calculations

Automated On-the-Fly Optimization of Resource Allocation for Efficient Free Energy Simulations

Computing the free energy of protein-ligand binding by employing molecular dynamics (MD) simulations is becoming a valuable tool in the early stages of drug discovery. However, the cost and complexity of such simulations are often prohibitive for high-throughput studies. We present an automated workflow for the thermodynamic integration scheme with the "on-the-fly" optimization of computational resource allocation for each λ-window of both relative and absolute binding free energy simulations. This iterative workflow utilizes automatic equilibration detection and convergence testing via the Jensen-Shannon distance to determine optimal simulation stopping points in an entirely data-driven manner. It is broadly applicable to multiple free energy calculations, such as ligand binding, amino acid mutations, and others, while utilizing different estimators, e.g., free energy perturbation, BAR, MBAR, etc. We benchmark our workflow on the well-characterized systems, namely, cyclin-dependent kinase 2 and T4 lysozyme L99A/M102Q mutant, and the more flexible SARS-CoV-2 papain-like protease. We demonstrate that this proposed protocol can achieve more than 85% reduction in computational expense while maintaining similar levels of accuracy compared to other benchmarking protocols. We examine the performance of this protocol on both small and large molecular transformations. The cost-accuracy tradeoff of repeated runs is also investigated.

FEP-SPell-ABFE: An Open-Source Automated Alchemical Absolute Binding Free-Energy Calculation Workflow for Drug Discovery

The binding affinity between a drug molecule and its target, measured by the absolute binding free energy (ABFE), is a crucial factor in the lead discovery phase of drug development. Recent research has highlighted the potential of in silico ABFE predictions to directly aid drug development by allowing for the ranking and prioritization of promising candidates. This work introduces an open-source Python workflow called FEP-SPell-ABFE, designed to automate ABFE calculations with minimal user involvement. The workflow requires only three key inputs: a receptor protein structure in PDB format, candidate ligands in SDF format, and a configuration file (config.yaml) that governs both the workflow and molecular dynamics simulation parameters. It produces a ranked list of ligands along with their binding free energies in the comma-separated values (CSV) format. The workflow leverages SLURM (Simple Linux Utility for Resource Management) for automating task execution and resource allocation across the modules. A usage example and several benchmark systems for validation are provided. The FEP-SPell-ABFE workflow, along with a practical example, is publicly accessible on GitHub at https://github.com/freeenergylab/FEP-SPell-ABFE, distributed under the MIT License.

Active learning driven prioritisation of compounds from on-demand libraries targeting the SARS-CoV-2 main protease

FEgrow is an open-source software package for building congeneric series of compounds in protein binding pockets. For a given ligand core and receptor structure, it employs hybrid machine learning/molecular mechanics potential energy functions to optimise the bioactive conformers of supplied linkers and functional groups. Here, we introduce significant new functionality to automate, parallelise and accelerate the building and scoring of compound suggestions, such that it can be used for automated de novo design. We interface the workflow with active learning to improve the efficiency of searching the combinatorial space of possible linkers and functional groups, make use of interactions formed by crystallographic fragments in scoring compound designs, and introduce the option to seed the chemical space with molecules available from on-demand chemical libraries. As a test case, we target the main protease (Mpro) of SARS-CoV-2, identifying several small molecules with high similarity to molecules discovered by the COVID moonshot effort, using only structural information from a fragment screen in a fully automated fashion. Finally, we order and test 19 compound designs, of which three show weak activity in a fluorescence-based Mpro assay, but work is needed to further optimise the prioritisation of compounds for purchase. The FEgrow package and full tutorials demonstrating the active learning workflow are available at https://github.com/cole-group/FEgrow.

Narrowing the gap between machine learning scoring functions and free energy perturbation using augmented data

Machine learning offers great promise for fast and accurate binding affinity predictions. However, current models lack robust evaluation and fail on tasks encountered in (hit-to-) lead optimisation, such as ranking the binding affinity of a congeneric series of ligands, thereby limiting their application in drug discovery. Here, we address these issues by first introducing a novel attention-based graph neural network model called AEV-PLIG (atomic environment vector-protein ligand interaction graph). Second, we introduce a new and more realistic out-of-distribution test set called the OOD Test. We benchmark our model on this set, CASF-2016, and a test set used for free energy perturbation (FEP) calculations, that not only highlights the competitive performance of AEV-PLIG, but provides a realistic assessment of machine learning models with rigorous physics-based approaches. Moreover, we demonstrate how leveraging augmented data (generated using template-based modelling or molecular docking) can significantly improve binding affinity prediction correlation and ranking on the FEP benchmark (weighted mean PCC and Kendall's τ increases from 0.41 and 0.26 to 0.59 and 0.42). These strategies together are closing the performance gap with FEP calculations (FEP+ achieves weighted mean PCC and Kendall's τ of 0.68 and 0.49 on the FEP benchmark) while being  ~400,000 times faster.

Robust Automated Truncation Point Selection for Molecular Simulations

Quantities calculated from molecular simulations are often subject to an initial bias due to unrepresentative starting configurations. Initial data are usually discarded to reduce bias. Chodera's method for automated truncation point selection [J. Chem. Theory Comput. 2016, 12, 4, 1799-1805] is popular but has not been thoroughly assessed. We reformulate White's marginal standard error rule to provide a spectrum of truncation point selection heuristics that differ in their treatment of autocorrelation. These include a method effectively equivalent to Chodera's. We test these methods on ensembles of synthetic time series modeled on free energy change estimates from long absolute binding free energy calculations. Methods that more thoroughly account for autocorrelation often show late and variable truncation times, while methods that less thoroughly account for autocorrelation often show early truncation, relative to the optimal truncation point. This increases variance and bias, respectively. We recommend a method that achieves robust performance across our test sets by balancing these two extremes. None of the methods reliably detected insufficient sampling. All heuristics tested are implemented in the open-source Python package RED (github.com/fjclark/red).