Virtual Screening in the Cloud Identifies Potent and Selective ROS1 Kinase Inhibitors.

ROS1 rearrangements account for 1-2% of non-small cell lung cancer patients, yet there are no specifically designed, selective ROS1 therapies in the clinic. Previous knowledge of potent ROS1 inhibitors with selectivity over TrkA, a selected antitarget, enabled virtual screening as a hit finding approach in this project. The ligand-based virtual screening was focused on identifying molecules with a similar 3D shape and pharmacophore to the known actives. To that end, we turned to the AstraZeneca virtual library, estimated to cover 1015 synthesizable make-on-demand molecules. We used cloud computing-enabled FastROCS technology to search the enumerated 1010 subset of the full virtual space. A small number of specific libraries were prioritized based on the compound properties and a medicinal chemistry assessment and further enumerated with available building blocks. Following the docking evaluation to the ROS1 structure, the most promising hits were synthesized and tested, resulting in the identification of several potent and selective series. The best among them gave a nanomolar ROS1 inhibitor with over 1000-fold selectivity over TrkA and, from the preliminary established SAR, these have the potential to be further optimized. Our prospective study describes how conceptually simple shape-matching approaches can identify potent and selective compounds by searching ultralarge virtual libraries, demonstrating the applicability of such workflows and their importance in early drug discovery.

Virtual Screening Expands the Non-Natural Amino Acid Palette for Peptide Optimization.

Peptides are an important modality in drug discovery. While current peptide optimization focuses predominantly on the small number of natural and commercially available non-natural amino acids, the chemical spaces available for small molecule drug discovery are in the billions of molecules. In the present study, we describe the development of a large virtual library of readily synthesizable non-natural amino acids that can power the virtual screening protocols and aid in peptide optimization. To that end, we enumerated nearly 380 thousand amino acids and demonstrated their vast chemical diversity compared to the 20 natural and commercial residues. Furthermore, we selected a diverse ten thousand amino acid subset to validate our virtual screening workflow on the Keap1-Neh2 complex model system. Through in silico mutations of Neh2 peptide residues to those from the virtual library, our docking-based protocol identified a number of possible solutions with a significantly higher predicted affinity toward the Keap1 protein. This protocol demonstrates that the non-natural amino acid chemical space can be massively extended and virtually screened with a reasonable computational cost.

Virtual Screening in the Cloud: How Big Is Big Enough?

Virtual screening is a standard tool in Computer-Assisted Drug Design (CADD). Early in a project, it is typical to use ligand-based similarity search methods to find suitable hit molecules. However, the number of compounds which can be screened and the time required are usually limited by computational resources. We describe here a high-throughput virtual screening project using 3D similarity (FastROCS) and automated evaluation workflows on Orion, a cloud computing platform. Cloud resources make this approach fully scalable and flexible, allowing the generation and search of billions of virtual molecules, and give access to an explicit 3D virtual chemistry space not available before. We discuss the impact of the size of the search space with respect to finding novel chemical hits and the size of the required hit list, as well as computational and economical aspects of resource scaling.

Scaffold hopping by fragment replacement.

This work describes a data driven method for scaffold hopping by fragment replacement. A search database of scaffolds is created by cutting bonds of existing compounds in a combinatorial fashion. Three-dimensional structures of the scaffolds are then generated and made searchable based on the relative orientation of the broken bonds using an auxiliary index file. The retrieved scaffolds are ranked using volume overlap and electrostatic similarity scores. A similar approach has been used before in the program CAVEAT and others. The present work introduces a novel indexing scheme for the attachment vector geometry, which allows for fast searching. A scaffold shape descriptor is defined, which allows for queries with a single attachment vector (R-groups) and improves the shape similarity between the query and the suggested replacement fragments. The program, called Scaffold Hopping, is shown to retrieve relevant bioisosteric replacement scaffolds for a set of example queries in a reasonable time frame, making the program suitable to be used in drug design work.

MIMUMBA revisited: torsion angle rules for conformer generation derived from X-ray structures.

A method has been developed which automatically generates SMARTS patterns for four-atomic torsional fragments, searches experimental structures in the Cambridge Crystallographic Database, and obtains rules for preferred torsion angles in drug-size molecules. These rules can be used for exhaustive conformational analysis using the popular conformer generator OMEGA. This approach results in an overall improvement of quality and coverage of conformational space when comparing conformer ensembles generated by this method with results obtained by using the default OMEGA setup. In particular, the percentage of structures with at least one conformation closer than 0.5 A to the X-ray structure improves from 84% to 92% in a test set of 11 027 experimental structures from the CSD. Moreover, the average RMS distance of the closest conformation to the X-ray structure improves from 0.30 to 0.22 A.

"In-house likeness": comparison of large compound collections using artificial neural networks.

Binary classification models able to discriminate between data sets of compounds are useful tools in a range of applications from compound acquisition to library design. In this paper we investigate the ability of artificial neural networks to discriminate between compound collections from various sources aiming at developing an "in-house likeness" scoring scheme (i.e. in-house vs external compounds) for compound acquisition. Our analysis shows atom-type based Ghose-Crippen fingerprints in combination with artificial neural networks to be an efficient way to construct such filters. A simple measure of the chemical overlap between different compound collections can be derived using the output scores from the neural net models.

Comparison of support vector machine and artificial neural network systems for drug/nondrug classification.

Support vector machine (SVM) and artificial neural network (ANN) systems were applied to a drug/nondrug classification problem as an example of binary decision problems in early-phase virtual compound filtering and screening. The results indicate that solutions obtained by SVM training seem to be more robust with a smaller standard error compared to ANN training. Generally, the SVM classifier yielded slightly higher prediction accuracy than ANN, irrespective of the type of descriptors used for molecule encoding, the size of the training data sets, and the algorithm employed for neural network training. The performance was compared using various different descriptor sets and descriptor combinations based on the 120 standard Ghose-Crippen fragment descriptors, a wide range of 180 different properties and physicochemical descriptors from the Molecular Operating Environment (MOE) package, and 225 topological pharmacophore (CATS) descriptors. For the complete set of 525 descriptors cross-validated classification by SVM yielded 82% correct predictions (Matthews cc = 0.63), whereas ANN reached 80% correct predictions (Matthews cc = 0.58). Although SVM outperformed the ANN classifiers with regard to overall prediction accuracy, both methods were shown to complement each other, as the sets of true positives, false positives (overprediction), true negatives, and false negatives (underprediction) produced by the two classifiers were not identical. The theory of SVM and ANN training is briefly reviewed.