Ian A. Watson

Experimental Designs for Selecting Molecules from Large Chemical Databases

Recent developments in high-throughput screening and combinatorial chemistry have generated interest in experimental design methods to select subsets of molecules from large chemical databases. In this manuscript three methods for selecting molecules from large databases are described:  edge designs, spread designs, and coverage designs. Two algorithms with linear time complexity that approximate spread and coverage designs are described. These algorithms can be threaded for multiprocessor systems, are compatible with any definition of molecular distance, and may be applied to very large chemical databases. For example, ten thousand molecules were selected using the maximum dissimilarity approximation to a spread design from a sixty-dimensional simulated molecular database of one million molecules in approximately 6 h on a UNIX workstation.

GPU Accelerated Support Vector Machines for Mining High-Throughput Screening Data

Support Vector Machine (SVM), one of the most promising tools in chemical informatics, is time-consuming for mining large high-throughput screening (HTS) data sets. Here, we describe a parallelization of SVM-light algorithm on a graphic processor unit (GPU), using molecular fingerprints as descriptors and the Tanimoto index as kernel function. Comparison experiments based on six PubChem Bioassay data sets show that the GPU version is 43-104x faster than SVM-light for building classification models and 112-212x over SVM-light for building regression models.

Structure-guided expansion of kinase fragment libraries driven by support vector machine models

This work outlines a new de novo design process for the creation of novel kinase inhibitor libraries. It relies on a profiling paradigm that generates a substantial amount of kinase inhibitor data from which highly predictive QSAR models can be constructed. In addition, a broad diversity of X-ray structure information is needed for binding mode prediction. This is important for scaffold and substituent site selection. Borrowing from FBDD, the process involves fragmentation of known actives, proposition of binding mode hypotheses for the fragments, and model-driven recombination using a pharmacophore derived from known kinase inhibitor structures. The support vector machine method, using Merck atom pair derived fingerprint descriptors, was used to build models from activity from 6 kinase assays. These models were qualified prospectively by selecting and testing compounds from the internal compound collection. Overall hit and enrichment rates of 82% and 2.5%, respectively, qualified the models for use in library design. Using the process, 7 novel libraries were designed, synthesized and tested against these same 6 kinases. The results showed excellent results, yielding a 92% hit rate for the 179 compounds that made up the 7 libraries. The results of one library designed to include known literature compounds, as well as an analysis of overall substituent frequency, are discussed.

Rationalizing Lead Optimization by Associating Quantitative Relevance with Molecular Structure Modification

Historically, one of the characteristic activities of the medicinal chemist has been the iterative improvement of lead compounds until a suitable therapeutic entity is achieved. Often referred to as lead optimization, this process typically takes the form of minor structural modifications to an existing lead in an attempt to ameliorate deleterious attributes while simultaneously trying to maintain or improve desirable properties. The cumulative effect of this exercise performed over the course of several decades of pharmaceutical research by thousands of trained researchers has resulted in large collections of pharmaceutically relevant chemical structures. As far as the authors are aware, this work represents the first attempt to use that data to define a framework to quantifiably catalogue and summate this information into a medicinal chemistry expert system. A method is proposed that first comprehensively mines a compendium of chemical structures compiling the structural modifications, abridges them to rectify artificially inflated support levels, and then performs an association rule mining experiment to ascribe relative confidences to each transformation. The result is a catalogue of statistically relevant structural modifications that can potentially be used in a number of pharmaceutical applications.

Open Innovation Drug Discovery (OIDD): A Potential Path to Novel Therapeutic Chemical Space

The continued development of computational and synthetic methods has enabled the enumeration or preparation of a nearly endless universe of chemical structures. Nevertheless, the ability of this chemical universe to deliver small molecules that can both modulate biological targets and have drug-like physicochemical properties continues to be a topic of interest to the pharmaceutical industry and academic researchers alike. The chemical space described by public, commercial, in-house and virtual compound collections has been interrogated by multiple approaches including biochemical, cellular and virtual screening, diversity analysis, and in-silico profiling. However, current drugs and known chemical probes derived from these efforts are contained within a remarkably small volume of the predicted chemical space. Access to more diverse classes of chemical scaffolds that maintain the properties relevant for drug discovery is certainly needed to meet the increasing demands for pharmaceutical innovation. The Lilly Open Innovation Drug Discovery platform (OIDD) was designed to tackle barriers to innovation through the identification of novel molecules active in relevant disease biology models. In this article we will discuss several computational approaches towards describing novel, biologically active, drug-like chemical space and illustrate how the OIDD program may facilitate access to previously untapped molecules that may aid in the search for innovative pharmaceuticals.

Indirect Similarity Based Methods for Effective Scaffold-Hopping in Chemical Compounds

Methods that can screen large databases to retrieve a structurally diverse set of compounds with desirable bioactivity properties are critical in the drug discovery and development process. This paper presents a set of such methods that are designed to find compounds that are structurally different to a certain query compound while retaining its bioactivity properties (scaffold hops). These methods utilize various indirect ways of measuring the similarity between the query and a compound that take into account additional information beyond their structure-based similarities. The set of techniques that are presented capture these indirect similarities using approaches based on analyzing the similarity network formed by the query and the database compounds. Experimental evaluation shows that most of these methods substantially outperform previously developed approaches both in terms of their ability to identify structurally diverse active compounds as well as active compounds in general.

Dissimilarity-based approaches to compound acquisition

The concept of molecular diversity has been integrated in drug discovery efforts for many years. Applications of molecular diversity have been used to identify compounds for screening and to select compounds to augment proprietary collections. These early efforts were crude and suffered from a number of faults, but their evolution has, over the years, led to an improvement in the computational procedures used to identify new commercial compounds for acquisition. Although not much has recently been written about modern methods for augmenting compound collections, this activity is still a very relevant and important task to those involved with the development of compound collections. This review focuses on the process and software used to identify compounds deemed worthy of acquisition.

Evaluating the performances of quantitative structure-retention relationship models with different sets of molecular descriptors and databases for high-performance liquid chromatography predictions

Quantitative structure-retention relationship (QSRR) models were studied for two databases: one with 151 compounds and the other with 1719 compounds. In both cases, the three modeling methods employed (multiple linear regression, partial least squares, and random forests) provided similar prediction results with regard to root-mean-square error of prediction. The reversed-phase retention related seven molecular descriptors provided better models for the smaller dataset, while the use of over 2000 molecular descriptors generated better models for the larger dataset. The QSRR models were then validated with a mixture of an active pharmaceutical ingredient and its four process/degradation impurities. Finally, classification of compounds based on similar logD profiles before QSRR modeling improved chromatographic predictability for the models used. The results showed that database composition had a desirable effect on prediction accuracy for certain input molecules.

The Proximal Lilly Collection: Mapping, Exploring and Exploiting Feasible Chemical Space

Venturing into the immensity of the small molecule universe to identify novel chemical structure is a much discussed objective of many methods proposed by the chemoinformatics community. To this end, numerous approaches using techniques from the fields of computational de novo design, virtual screening and reaction informatics, among others, have been proposed. Although in principle this objective is commendable, in practice there are several obstacles to useful exploitation of the chemical space. Prime among them are the sheer number of theoretically feasible compounds and the practical concern regarding the synthesizability of the chemical structures conceived using in silico methods. We present the Proximal Lilly Collection initiative implemented at Eli Lilly and Co. with the aims to (i) define the chemical space of small, drug-like compounds that could be synthesized using in-house resources and (ii) facilitate access to compounds in this large space for the purposes of ongoing drug discovery efforts. The implementation of PLC relies on coupling access to available synthetic knowledge and resources with chemo/reaction informatics techniques and tools developed for this purpose. We describe in detail the computational framework supporting this initiative and elaborate on the characteristics of the PLC virtual collection of compounds. As an example of the opportunities provided to drug discovery researchers by easy access to a large, realistically feasible virtual collection such as the PLC, we describe a recent application of the technology that led to the discovery of selective kinase inhibitors.

Knowledge-Based Strategy to Improve Ligand Pose Prediction Accuracy for Lead Optimization

Accurately predicting how a small molecule binds to its target protein is an essential requirement for structure-based drug design (SBDD) efforts. In structurally enabled medicinal chemistry programs, binding pose prediction is often applied to ligands after a related compounds crystal structure bound to the target protein has been solved. In this article, we present an automated pose prediction protocol that makes extensive use of existing X-ray ligand information. It uses spatial restraints during docking based on maximum common substructure (MCS) overlap between candidate molecule and existing X-ray coordinates of the related compound. For a validation data set of 8784 docking runs, our protocols pose prediction accuracy (80-82%) is almost two times higher than that of one unbiased docking method software (43%). To demonstrate the utility of this protocol in a project setting, we show its application in a chronological manner for a number of internal drug discovery efforts. The accuracy and applicability of this algorithm (>70% of cases) to medicinal chemistry efforts make this the approach of choice for pose prediction in lead optimization programs.