Approaches for machine learning intermolecular interaction energies and application to energy components from symmetry adapted perturbation theory.

Accurate prediction of intermolecular interaction energies is a fundamental challenge in electronic structure theory due to their subtle character and small magnitudes relative to total molecular energies. Symmetry adapted perturbation theory (SAPT) provides rigorous quantum mechanical means for computing such quantities directly and accurately, but for a computational cost of at least O(N5), where N is the number of atoms. Here, we report machine learned models of SAPT components with a computational cost that scales asymptotically linearly, O(N). We use modified multi-target Behler-Parrinello neural networks and specialized intermolecular symmetry functions to address the idiosyncrasies of the intermolecular problem, achieving 1.2 kcal mol-1 mean absolute errors on a test set of hydrogen bound complexes including structural data extracted from the Cambridge Structural Database and Protein Data Bank, spanning an interaction energy range of 20 kcal mol-1. Additionally, we recover accurate predictions of the physically meaningful SAPT component energies, of which dispersion and induction/polarization were the easiest to predict and electrostatics and exchange-repulsion are the most difficult.

3D matched pairs: integrating ligand- and structure-based knowledge for ligand design and receptor annotation.

We describe an extension to the matched molecular pairs approach that merges pairwise activity differences with three-dimensional contextual information derived from X-ray crystal structures and binding pose predictions. The incorporation of 3D binding poses allows the direct comparison of structural changes to diverse chemotypes in particular binding pockets, facilitating the transfer of SAR from one series to another. Integrating matched pair data with the receptor structure can also highlight activity patterns within the binding site--for example, "hot spot" regions can be visualized where changes in the ligand structure are more likely to impact activity. The method is illustrated using P38α structural and activity data to generate novel hybrid ligands, identify SAR transfer networks, and annotate the receptor binding site.

Grid computing in large pharmaceutical molecular modeling.

Most major pharmaceutical companies have employed grid computing to expand their compute resources with the intention of minimizing additional financial expenditure. Historically, one of the issues restricting widespread utilization of the grid resources in molecular modeling is the limited set of suitable applications amenable to coarse-grained parallelization. Recent advances in grid infrastructure technology coupled with advances in application research and redesign will enable fine-grained parallel problems, such as quantum mechanics and molecular dynamics, which were previously inaccessible to the grid environment. This will enable new science as well as increase resource flexibility to load balance and schedule existing workloads.

Discovery informatics: its evolving role in drug discovery.

Drug discovery and development is a highly complex process requiring the generation of very large amounts of data and information. Currently this is a largely unmet informatics challenge. The current approaches to building information and knowledge from large amounts of data has been addressed in cases where the types of data are largely homogeneous or at the very least well-defined. However, we are on the verge of an exciting new era of drug discovery informatics in which methods and approaches dealing with creating knowledge from information and information from data are undergoing a paradigm shift. The needs of this industry are clear: Large amounts of data are generated using a variety of innovative technologies and the limiting step is accessing, searching and integrating this data. Moreover, the tendency is to move crucial development decisions earlier in the discovery process. It is crucial to address these issues with all of the data at hand, not only from current projects but also from previous attempts at drug development. What is the future of drug discovery informatics? Inevitably, the integration of heterogeneous, distributed data are required. Mining and integration of domain specific information such as chemical and genomic data will continue to develop. Management and searching of textual, graphical and undefined data that are currently difficult, will become an integral part of data searching and an essential component of building information- and knowledge-bases.

To measure is to know: an approach to CADD performance metrics.

With the financial and productivity challenges currently facing the pharmaceutical industry, there is constant pressure to justify resources and improve efficiency. With process-driven activities, understanding the contribution of these resources is reasonably straightforward. By contrast, measuring the contribution of knowledge workers is less obvious. Here, we present an impact-oriented approach to assessing the performance of an industrial computer-assisted drug design group. We discuss how these metrics are used to understand and optimize resource allocation in support of drug discovery programs.

Protein-ligand NOE matching: a high-throughput method for binding pose evaluation that does not require protein NMR resonance assignments.

Given the three-dimensional (3D) structure of a protein, the binding pose of a ligand can be determined using distance restraints derived from assigned intra-ligand and protein-ligand nuclear Overhauser effects (NOEs). A primary limitation of this approach is the need for resonance assignments of the ligand-bound protein. We have developed an approach that utilizes data from 3D 13C-edited, 13C/15N-filtered HSQC-NOESY spectra for evaluating ligand binding poses without requiring protein NMR resonance assignments. Only the 1H NMR assignments of the bound ligand are essential. Trial ligand binding poses are generated by any suitable method (e.g., computational docking). For each trial binding pose, the 3D 13C-edited, 13C/15N-filtered HSQC-NOESY spectrum is predicted, and the predicted and observed patterns of protein-ligand NOEs are matched and scored using a fast, deterministic bipartite graph matching algorithm. The best scoring (lowest "cost") poses are identified. Our method can incorporate any explicit restraints or protein assignment data that are available, and many extensions of the basic procedure are feasible. Only a single sample is required, and the method can be applied to both slowly and rapidly exchanging ligands. The method was applied to three test cases: one complex involving muscle fatty acid-binding protein (mFABP) and two complexes involving the leukocyte function-associated antigen 1 (LFA-1) I-domain. Without using experimental protein NMR assignments, the method identified the known binding poses with good accuracy. The addition of experimental protein NMR assignments improves the results. Our "NOE matching" approach is expected to be widely applicable; i.e., it does not appear to depend on a fortuitous distribution of binding pocket residues.