NAMDis a molecular dynamics program designed for high-performance simulations of very large biological objects on CPU- and GPU-based architectures. NAMD offers scalable performance on petascale parallel supercomputers consisting of hundreds of thousands of cores, as well as on inexpensive commodity clusters commonly found in academic environments. It is written in C++ and leans on Charm++ parallel objects for optimal performance on low-latency architectures. NAMD is a versatile, multipurpose code that gathers state-of-the-art algorithms to carry out simulations in apt thermodynamic ensembles, using the widely popular CHARMM, AMBER, OPLS, and GROMOS biomolecular force fields. Here, we review the main features of NAMD that allow both equilibrium and enhanced-sampling molecular dynamics simulations with numerical efficiency. We describe the underlying concepts utilized by NAMD and their implementation, most notably for handling long-range electrostatics; controlling the temperature, pressure, and pH; applying external potentials on tailored grids; leveraging massively parallel resources in multiple-copy simulations; and hybrid quantum-mechanical/molecular-mechanical descriptions. We detail the variety of options offered by NAMD for enhanced-sampling simulations aimed at determining free-energy differences of either alchemical or geometrical transformations and outline their applicability to specific problems. Last, we discuss the roadmap for the development of NAMD and our current efforts toward achieving optimal performance on GPU-based architectures, for pushing back the limitations that have prevented biologically realistic billion-atom objects to be fruitfully simulated, and for making large-scale simulations less expensive and easier to set up, run, and analyze. NAMD is distributed free of charge with its source code at www.ks.uiuc.edu.

Scalable molecular dynamics on CPU and GPU architectures with NAMD.

Molecular Dynamics Simulation for All.

This review discusses the many roles atomistic computer simulations of macromolecular (for example, protein) receptors and their associated small-molecule ligands can play in drug discovery, including the identification of cryptic or allosteric binding sites, the enhancement of traditional virtual-screening methodologies, and the direct prediction of small-molecule binding energies. The limitations of current simulation methodologies, including the high computational costs and approximations of molecular forces required, are also discussed. With constant improvements in both computer power and algorithm design, the future of computer-aided drug design is promising; molecular dynamics simulations are likely to play an increasingly important role.

/pdf/molecular-dynamics-simulations-and-drug-discovery-1wu2ajeo71.pdf

Molecular dynamics simulations and drug discovery

Designing tight-binding ligands is a primary objective of small-molecule drug discovery. Over the past few decades, free-energy calculations have benefited from improved force fields and sampling algorithms, as well as the advent of low-cost parallel computing. However, it has proven to be challenging to reliably achieve the level of accuracy that would be needed to guide lead optimization (∼5× in binding affinity) for a wide range of ligands and protein targets. Not surprisingly, widespread commercial application of free-energy simulations has been limited due to the lack of large-scale validation coupled with the technical challenges traditionally associated with running these types of calculations. Here, we report an approach that achieves an unprecedented level of accuracy across a broad range of target classes and ligands, with retrospective results encompassing 200 ligands and a wide variety of chemical perturbations, many of which involve significant changes in ligand chemical structures. In addition, we have applied the method in prospective drug discovery projects and found a significant improvement in the quality of the compounds synthesized that have been predicted to be potent. Compounds predicted to be potent by this approach have a substantial reduction in false positives relative to compounds synthesized on the basis of other computational or medicinal chemistry approaches. Furthermore, the results are consistent with those obtained from our retrospective studies, demonstrating the robustness and broad range of applicability of this approach, which can be used to drive decisions in lead optimization.

/pdf/accurate-and-reliable-prediction-of-relative-ligand-binding-2xur9551c2.pdf

Accurate and Reliable Prediction of Relative Ligand Binding Potency in Prospective Drug Discovery by Way of a Modern Free-Energy Calculation Protocol and Force Field

Molecular mechanics Poisson-Boltzmann surface area (MM/PBSA) and molecular mechanics generalized Born surface area (MM/GBSA) are arguably very popular methods for binding free energy prediction since they are more accurate than most scoring functions of molecular docking and less computationally demanding than alchemical free energy methods. MM/PBSA and MM/GBSA have been widely used in biomolecular studies such as protein folding, protein-ligand binding, protein-protein interaction, etc. In this review, methods to adjust the polar solvation energy and to improve the performance of MM/PBSA and MM/GBSA calculations are reviewed and discussed. The latest applications of MM/GBSA and MM/PBSA in drug design are also presented. This review intends to provide readers with guidance for practically applying MM/PBSA and MM/GBSA in drug design and related research fields.

End-Point Binding Free Energy Calculation with MM/PBSA and MM/GBSA: Strategies and Applications in Drug Design

Alchemical free energy methods for drug discovery: progress and challenges

Here, we give an overview of the protein- ligand binding portion of the Statistical Assessment of Modeling of Proteins and Ligands 4 (SAMPL4) challenge, which focused on predicting binding of HIV integrase inhibitors in the catalytic core domain. The challenge encompassed three components—a small ''virtual screen- ing'' challenge, a binding mode prediction component, and a small affinity prediction component. Here, we give summary results and statistics concerning the performance of all submissions at each of these challenges. Virtual screening was particularly challenging here in part because, in contrast to more typical virtual screening test sets, the inactive compounds were tested because they were thought to be likely binders, so only the very top predictions per- formed significantly better than random. Pose prediction was also quite challenging, in part because inhibitors in the set bind to three different sites, so even identifying the correct binding site was challenging. Still, the best methods managed low root mean squared deviation predictions in many cases. Here, we give an overview of results, highlight some features of methods which worked particularly well, and refer the interested reader to papers in this issue which describe specific submissions for additional details.

/pdf/blind-prediction-of-hiv-integrase-binding-from-the-sampl4-3ft80ppb5n.pdf

Blind prediction of HIV integrase binding from the SAMPL4 challenge

Identification of gene expression state of a cancer patient from routine pathology imaging and characterization of its phenotypic effects have significant clinical and therapeutic implications. However, prediction of expression of individual genes from whole slide images (WSIs) is challenging due to co-dependent or correlated expression of multiple genes. Here, we use a purely data-driven approach to first identify groups of genes with co-dependent expression and then predict their status from (WSIs) using a bespoke graph neural network. These gene groups allow us to capture the gene expression state of a patient with a small number of binary variables that are biologically meaningful and carry histopathological insights for clinically and therapeutic use cases. Prediction of gene expression state based on these gene groups allows associating histological phenotypes (cellular composition, mitotic counts, grading, etc.) with underlying gene expression patterns and opens avenues for gaining significant biological insights from routine pathology imaging directly. Graphical Abstract Highlights Data-driven discovery of co-expressing gene groups in breast caner Histological imaging based prediction of gene groups via deep learning Identification of phenotypic correlates of gene-expression in histological imaging Clinical and therapeutic impact of gene groups and their visual patterns identified

/pdf/data-driven-modelling-of-gene-expression-states-in-breast-2s3ign3t.pdf

Data-Driven Modelling of Gene Expression States in Breast Cancer and their Prediction from Routine Whole Slide Images

High accuracy medical image classiﬁcation can be limited by the costs of acquiring more data as well as the time and expertise needed to label existing images. In this paper, we apply active learning to medical image classiﬁcation, a method which aims to maximise model performance on a minimal subset from a larger pool of data. We present a new active learning framework, based on deep reinforcement learning, to learn an active learning query strategy to label images based on predictions from a convolutional neural network. Our framework modiﬁes the deep-Q network formulation, allowing us to pick data based additionally on geometric arguments in the latent space of the classiﬁer, allowing for high accuracy multi-class classiﬁcation in a batch-based active learning setting, enabling the agent to label datapoints that are both diverse and about which it is most uncertain. We apply our framework to two medical imaging datasets and compare with standard query strategies as well as the most recent reinforcement learning based active learning approach for image classiﬁcation.

Deep reinforced active learning for multi-class image classification

Image-based profiling techniques have become increasingly popular over the past decade for their applications in target identification, mechanism-of-action inference, and assay development. These techniques have generated large datasets of cellular morphologies, which are typically used to investigate the effects of small molecule perturbagens. In this work, we extend the impact of such dataset to improving quantitative structure-activity relationship (QSAR) models by introducing Molecule-Morphology Contrastive Pretraining (MoCoP), a framework for learning multi-modal representation of molecular graphs and cellular morphologies. We scale MoCoP to approximately 100K molecules and 600K morphological profiles using data from the JUMP-CP Consortium and show that MoCoP consistently improves performances of graph neural networks (GNNs) on molecular property prediction tasks in ChEMBL20 across all dataset sizes. The pretrained GNNs are also evaluated on internal GSK pharmacokinetic data and show an average improvement of 2.6% and 6.3% in AUPRC for full and low data regimes, respectively. Our findings suggest that integrating cellular morphologies with molecular graphs using MoCoP can significantly improve the performance of QSAR models, ultimately expanding the deep learning toolbox available for QSAR applications.

/pdf/molecule-morphology-contrastive-pretraining-for-transferable-vu8ah0gp.pdf

Kim Branson

Papers

Alchemical free energy methods for drug discovery: progress and challenges

Blind prediction of HIV integrase binding from the SAMPL4 challenge

Data-Driven Modelling of Gene Expression States in Breast Cancer and their Prediction from Routine Whole Slide Images

Deep reinforced active learning for multi-class image classification

Molecule-Morphology Contrastive Pretraining for Transferable Molecular Representation