Christopher T. Lee

Allosteric drug development holds promise for delivering medicines that are more selective and less toxic than those that target orthosteric sites. To date, the discovery of allosteric binding sites and lead compounds has been mostly serendipitous, achieved through high-throughput screening. Over the past decade, structural data has become more readily available for larger protein systems and more membrane protein classes (e.g., GPCRs and ion channels), which are common allosteric drug targets. In parallel, improved simulation methods now provide better atomistic understanding of the protein dynamics and cooperative motions that are critical to allosteric mechanisms. As a result of these advances, the field of predictive allosteric drug development is now on the cusp of a new era of rational structure-based computational methods. Here, we review algorithms that predict allosteric sites based on sequence data and molecular dynamics simulations, describe tools that assess the druggability of these pockets, and discuss how Markov state models and topology analyses provide insight into the relationship between protein dynamics and allosteric drug binding. In each section, we first provide an overview of the various method classes before describing relevant algorithms and software packages.

Predicting the rate of nonfacilitated permeation of solutes across lipid bilayers is important to drug design, toxicology, and signaling. These rates can be estimated using molecular dynamics simulations combined with the inhomogeneous solubility-diffusion model, which requires calculation of the potential of mean force and position-dependent diffusivity of the solute along the transmembrane axis. In this paper, we assess the efficiency and accuracy of several methods for the calculation of the permeability of a model DMPC bilayer to urea, benzoic acid, and codeine. We compare umbrella sampling, replica exchange umbrella sampling, adaptive biasing force, and multiple-walker adaptive biasing force for the calculation of the transmembrane PMF. No definitive advantage for any of these methods in their ability to predict the membrane permeability coefficient Pm was found, provided that a sufficiently long equilibration is performed. For diffusivities, a Bayesian inference method was compared to a generalized Langevin method, both being sensitive to chosen parameters and the slow relaxation of membrane defects. Agreement within 1.5 log units of the computed Pm with experiment is found for all permeants and methods. Remaining discrepancies can likely be attributed to limitations of the force field as well as slowly relaxing collective movements within the lipid environment. Numerical calculations based on model profiles show that Pm can be reliably estimated from only a few data points, leading to recommendations for calculating Pm from simulations.

Automated classification of human anatomy is an important prerequisite for many computer-aided diagnosis systems. The spatial complexity and variability of anatomy throughout the human body makes classification difficult. “Deep learning” methods such as convolutional networks (ConvNets) outperform other state-of-the-art methods in image classification tasks. In this work, we present a method for organ- or body-part-specific anatomical classification of medical images acquired using computed tomography (CT) with ConvNets. We train a ConvNet, using 4,298 separate axial 2D key-images to learn 5 anatomical classes. Key-images were mined from a hospital PACS archive, using a set of 1,675 patients. We show that a data augmentation approach can help to enrich the data set and improve classification performance. Using ConvNets and data augmentation, we achieve anatomy-specific classification error of 5.9 % and area-under-the-curve (AUC) values of an average of 0.998 in testing. We demonstrate that deep learning can be used to train very reliable and accurate classifiers that could initialize further computer-aided diagnosis.