Optimal strategies for virtual screening of induced-fit and flexible target in the 2015 D3R Grand Challenge

In Silico Screening and Experimental Validation of Novel MexAB-OprM Efflux Pump Inhibitors of Pseudomonas aeruginosa

The emergence of multidrug-resistant Pseudomonas aeruginosa possesses a significant public health concern. Constitutively expressed MexAB-OprM efflux pumps in P. aeruginosa significantly contribute to its resistance to a variety of antibiotics. The development of efflux pump inhibitors (EPIs) has emerged as an attractive strategy in reversing antibiotic resistance. In this study, structure-based virtual screening techniques were used for the identification of new MexAB-OprM efflux inhibitors. The predicted poses were thoroughly filtered by induced fit docking procedures followed by in vitro microbiological assays for the validation of in silico results. Two compounds, NSC-147850 and NSC-112703, were able to restore tetracycline susceptibility in MexAB-OprM overexpressing Pseudomonas aeruginosa ATCC® 27853™ strain. This correlation observed between in silico screening and positive efflux inhibitory activity in vitro suggests that NSC-147850 and NSC-112703 have potential as EPIs and may be effective in combination therapy against drug-resistant strains of P. aeruginosa.

Mebendazole's Conformational Space and Its Predicted Binding to Human Heat-Shock Protein 90

Recent experimental evidence suggests that mebendazole, a popular antiparasitic drug, binds to heat shock protein 90 (Hsp90) and inhibits acute myeloid leukemia cell growth. In this study we use quantum mechanics (QM), molecular similarity, and molecular dynamics (MD) calculations to predict possible binding poses of mebendazole to the adenosine triphosphate (ATP) binding site of Hsp90. Extensive conformational searches and minimization of the five mebendazole tautomers using the MP2/aug-cc-pVTZ theory level resulted in 152 minima. Mebendazole-Hsp90 complex models were subsequently created using the QM optimized conformations and protein coordinates obtained from experimental crystal structures that were chosen through similarity calculations. Nine different poses were identified from a total of 600 ns of explicit solvent, all-atom MD simulations using two different force fields. All simulations support the hypothesis that mebendazole is able to bind to the ATP binding site of Hsp90.

Affinity prediction using deep learning based on SMILES input for D3R grand challenge 4

Modern molecular docking comprises the prediction of pose and affinity. Prediction of docking poses is required for affinity prediction when three-dimensional coordinates of the ligand have not been provided. However, a large number of feature engineering is required for existing methods. In addition, there is a need for a robust model for the sequential combination of pose and affinity prediction due to the probabilistic deviation of the ligand position issue. We propose a pipeline using a bipartite graph neural network and transfer learning trained on a re-docking dataset. We evaluated our model on the released data from drug design data resource grand challenge 4 (D3R GC4). The two target protein data provided by the challenge have different patterns. The model outperformed the best participant by 9% on the BACE target protein from stage 2. Further, our model showed competitive performance on the CatS target protein.

Preliminary modelling as the first stage of targeted organic synthesis

The review aims to present a classification and applicability analysis of methods for preliminary molecular modelling for targeted organic, catalytic and biocatalytic synthesis. The following three main approaches are considered as a primary classification of the methods: modelling of the target – ligand coordination without structural information on both the target and the resulting complex; calculations based on experimentally obtained structural information about the target; and dynamic simulation of the target – ligand complex and the reaction mechanism with calculation of the free energy of the reaction. The review is meant for synthetic chemists to be used as a guide for building an algorithm for preliminary modelling and synthesis of structures with specified properties.

The bibliography includes 353 references.

Three-Dimensional Convolutional Neural Networks and a Cross-Docked Data Set for Structure-Based Drug Design

One of the main challenges in drug discovery is predicting protein-ligand binding affinity. Recently, machine learning approaches have made substantial progress on this task. However, current methods of model evaluation are overly optimistic in measuring generalization to new targets, and there does not exist a standard data set of sufficient size to compare performance between models. We present a new data set for structure-based machine learning, the CrossDocked2020 set, with 22.5 million poses of ligands docked into multiple similar binding pockets across the Protein Data Bank, and perform a comprehensive evaluation of grid-based convolutional neural network (CNN) models on this data set. We also demonstrate how the partitioning of the training data and test data can impact the results of models trained with the PDBbind data set, how performance improves by adding more lower-quality training data, and how training with docked poses imparts pose sensitivity to the predicted affinity of a complex. Our best performing model, an ensemble of five densely connected CNNs, achieves a root mean squared error of 1.42 and Pearson R of 0.612 on the affinity prediction task, an AUC of 0.956 at binding pose classification, and a 68.4% accuracy at pose selection on the CrossDocked2020 set. By providing data splits for clustered cross-validation and the raw data for the CrossDocked2020 set, we establish the first standardized data set for training machine learning models to recognize ligands in noncognate target structures while also greatly expanding the number of poses available for training. In order to facilitate community adoption of this data set for benchmarking protein-ligand binding affinity prediction, we provide our models, weights, and the CrossDocked2020 set at https://github.com/gnina/models.

Cross-docking benchmark for automated pose and ranking prediction of ligand binding

Significant efforts have been devoted in the last decade to improving molecular docking techniques to predict both accurate binding poses and ranking affinities. Some shortcomings in the field are the limited number of standard methods for measuring docking success and the availability of widely accepted standard data sets for use as benchmarks in comparing different docking algorithms throughout the field. In order to address these issues, we have created a Cross-Docking Benchmark server. The server is a versatile cross-docking data set containing 4,399 protein-ligand complexes across 95 protein targets intended to serve as benchmark set and gold standard for state-of-the-art pose and ranking prediction in easy, medium, hard, or very hard docking targets. The benchmark along with a customizable cross-docking data set generation tool is available at http://disco.csb.pitt.edu. We further demonstrate the potential uses of the server in questions outside of basic benchmarking such as the selection of the ideal docking reference structure.

Defining the Kv2.1-syntaxin molecular interaction identifies a first-in-class small molecule neuroprotectant

The neuronal cell death-promoting loss of cytoplasmic K+ following injury is mediated by an increase in Kv2.1 potassium channels in the plasma membrane. This phenomenon relies on Kv2.1 binding to syntaxin 1A via 9 amino acids within the channel intrinsically disordered C terminus. Preventing this interaction with a cell and blood-brain barrier-permeant peptide is neuroprotective in an in vivo stroke model. Here a rational approach was applied to define the key molecular interactions between syntaxin and Kv2.1, some of which are shared with mammalian uncoordinated-18 (munc18). Armed with this information, we found a small molecule Kv2.1-syntaxin-binding inhibitor (cpd5) that improves cortical neuron survival by suppressing SNARE-dependent enhancement of Kv2.1-mediated currents following excitotoxic injury. We validated that cpd5 selectively displaces Kv2.1-syntaxin-binding peptides from syntaxin and, at higher concentrations, munc18, but without affecting either synaptic or neuronal intrinsic properties in brain tissue slices at neuroprotective concentrations. Collectively, our findings provide insight into the role of syntaxin in neuronal cell death and validate an important target for neuroprotection.

A network-centric approach to drugging TNF-induced NF-κB signaling

Target-centric drug development strategies prioritize single-target potency in vitro and do not account for connectivity and multi-target effects within a signal transduction network. Here, we present a systems biology approach that combines transcriptomic and structural analyses with live-cell imaging to predict small molecule inhibitors of TNF-induced NF-κB signaling and elucidate the network response. We identify two first-in-class small molecules that inhibit the NF-κB signaling pathway by preventing the maturation of a rate-limiting multiprotein complex necessary for IKK activation. Our findings suggest that a network-centric drug discovery approach is a promising strategy to evaluate the impact of pharmacologic intervention in signaling.

Chemical perturbation of specific protein–protein interactions is notoriously difficult, yet necessary when complete inhibition of a signalling pathway is detrimental to the cell. Here, the authors use a systems approach and identify two first-in-class small molecules that specifically inhibit TNF-induced NF-κB activation.

Predicting protein targets for drug-like compounds using transcriptomics

An expanded chemical space is essential for improved identification of small molecules for emerging therapeutic targets. However, the identification of targets for novel compounds is biased towards the synthesis of known scaffolds that bind familiar protein families, limiting the exploration of chemical space. To change this paradigm, we validated a new pipeline that identifies small molecule-protein interactions and works even for compounds lacking similarity to known drugs. Based on differential mRNA profiles in multiple cell types exposed to drugs and in which gene knockdowns (KD) were conducted, we showed that drugs induce gene regulatory networks that correlate with those produced after silencing protein-coding genes. Next, we applied supervised machine learning to exploit drug-KD signature correlations and enriched our predictions using an orthogonal structure-based screen. As a proof-of-principle for this regimen, top-10/top-100 target prediction accuracies of 26% and 41%, respectively, were achieved on a validation of set 152 FDA-approved drugs and 3104 potential targets. We then predicted targets for 1680 compounds and validated chemical interactors with four targets that have proven difficult to chemically modulate, including non-covalent inhibitors of HRAS and KRAS. Importantly, drug-target interactions manifest as gene expression correlations between drug treatment and both target gene KD and KD of genes that act up- or down-stream of the target, even for relatively weak binders. These correlations provide new insights on the cellular response of disrupting protein interactions and highlight the complex genetic phenotypes of drug treatment. With further refinement, our pipeline may accelerate the identification and development of novel chemical classes by screening compound-target interactions.

Bioactive compounds often disrupt cellular gene expression in ways that are difficult to predict. While the correlation between a cellular response after treatment with a small molecule and the knockdown of its target protein should be simple to establish, in practice this goal has been difficult to achieve. The main challenges are that data are noisy, drugs are not intended to be active in all cell types, and signals from a bona fide target(s) may be obscured by correlations with knockdowns of other proteins in the same pathway(s). Here, we find that a random forest classification model can detect meaningful correlational patterns when gene expression profiles after compound treatment and gene knockdowns in four or more cell lines are compared. When this approach is enriched by a structure-based screen, novel drug-target interactions can be predicted. We then validated new ligand-protein interactions for four difficult targets. Although the initial compounds are not especially potent in vitro, they are capable of disrupting their target pathway in the cell to an extent that generates a significant and characteristic gene expression profile. Collectively, our studies provide insight on cell-level transcriptomic responses to pharmaceutical intervention and the use of these patterns for target identification. In addition, the method provides a novel drug discovery pipeline to test chemistries without a priori knowledge of their target(s).

A facile consensus ranking approach enhances virtual screening robustness and identifies a cell-active DYRK1α inhibitor

BACKGROUND

Virtual screening is vital for contemporary drug discovery but striking performance fluctuations are commonly encountered, thus hampering error-free use. Results and Methodology: A conceptual framework is suggested for combining screening algorithms characterized by orthogonality (docking-scoring calculations, 3D shape similarity, 2D fingerprint similarity) into a simple, efficient and expansible python-based consensus ranking scheme. An original experimental dataset is created for comparing individual screening methods versus the novel approach. Its utilization leads to identification and phosphoproteomic evaluation of a cell-active DYRK1α inhibitor.

CONCLUSION

Consensus ranking considerably stabilizes screening performance at reasonable computational cost, whereas individual screens are heavily dependent on calculation settings. Results indicate that the novel approach, currently available as a free online tool, is highly suitable for prospective screening by nonexperts.

Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges

Advanced mathematics, such as multiscale weighted colored subgraph and element specific persistent homology, and machine learning including deep neural networks were integrated to construct mathematical deep learning models for pose and binding affinity prediction and ranking in the last two D3R Grand Challenges in computer-aided drug design and discovery. D3R Grand Challenge 2 focused on the pose prediction, binding affinity ranking and free energy prediction for Farnesoid X receptor ligands. Our models obtained the top place in absolute free energy prediction for free energy set 1 in stage 2. The latest competition, D3R Grand Challenge 3 (GC3), is considered as the most difficult challenge so far. It has five subchallenges involving Cathepsin S and five other kinase targets, namely VEGFR2, JAK2, p38-α, TIE2, and ABL1. There is a total of 26 official competitive tasks for GC3. Our predictions were ranked 1st in 10 out of these 26 tasks.

Improving small molecule virtual screening strategies for the next generation of therapeutics

The new generation of post-genomic targets, such as protein-protein interactions (PPIs), often require new chemotypes not well represented in current compound libraries. This is one reason for why traditional high throughput screening (HTS) approaches are not more successful in delivering medicinal chemistry starting points for PPIs. In silico screening methods of an expanded chemical space are then potential alternatives for developing novel chemical probes to modulate PPIs. In this review, we report on the state-of-the-art pipelines for virtual screening, emphasizing prospectively validated methods capable of addressing the challenge of drugging difficult targets in the human interactome. Collectively, we show that optimal strategies for structure based virtual screening vary depending on receptor structure and degree of flexibility.

Lessons learned in induced fit docking and metadynamics in the Drug Design Data Resource Grand Challenge 2

Two of the major ongoing challenges in computational drug discovery are predicting the binding pose and affinity of a compound to a protein. The Drug Design Data Resource Grand Challenge 2 was developed to address these problems and to drive development of new methods. The challenge provided the 2D structures of compounds for which the organizers help blinded data in the form of 35 X-ray crystal structures and 102 binding affinity measurements and challenged participants to predict the binding pose and affinity of the compounds. We tested a number of pose prediction methods as part of the challenge; we found that docking methods that incorporate protein flexibility (Induced Fit Docking) outperformed methods that treated the protein as rigid. We also found that using binding pose metadynamics, a molecular dynamics based method, to score docked poses provided the best predictions of our methods with an average RMSD of 2.01 Å. We tested both structure-based (e.g. docking) and ligand-based methods (e.g. QSAR) in the affinity prediction portion of the competition. We found that our structure-based methods based on docking with Smina (Spearman ρ = 0.614), performed slightly better than our ligand-based methods (ρ = 0.543), and had equivalent performance with the other top methods in the competition. Despite the overall good performance of our methods in comparison to other participants in the challenge, there exists significant room for improvement especially in cases such as these where protein flexibility plays such a large role.

Optimal affinity ranking for automated virtual screening validated in prospective D3R grand challenges

The goal of virtual screening is to generate a substantially reduced and enriched subset of compounds from a large virtual chemistry space. Critical in these efforts are methods to properly rank the binding affinity of compounds. Prospective evaluations of ranking strategies in the D3R grand challenges show that for targets with deep pockets the best correlations (Spearman ρ ~ 0.5) were obtained by our submissions that docked compounds to the holo-receptors with the most chemically similar ligand. On the other hand, for targets with open pockets using multiple receptor structures is not a good strategy. Instead, docking to a single optimal receptor led to the best correlations (Spearman ρ ~ 0.5), and overall performs better than any other method. Yet, choosing a suboptimal receptor for crossdocking can significantly undermine the affinity rankings. Our submissions that evaluated the free energy of congeneric compounds were also among the best in the community experiment. Error bars of around 1 kcal/mol are still too large to significantly improve the overall rankings. Collectively, our top of the line predictions show that automated virtual screening with rigid receptors perform better than flexible docking and other more complex methods.

A cross docking pipeline for improving pose prediction and virtual screening performance

Pose prediction and virtual screening performance of a molecular docking method depend on the choice of protein structures used for docking. Multiple structures for a target protein are often used to take into account the receptor flexibility and problems associated with a single receptor structure. However, the use of multiple receptor structures is computationally expensive when docking a large library of small molecules. Here, we propose a new cross-docking pipeline suitable to dock a large library of molecules while taking advantage of multiple target protein structures. Our method involves the selection of a suitable receptor for each ligand in a screening library utilizing ligand 3D shape similarity with crystallographic ligands. We have prospectively evaluated our method in D3R Grand Challenge 2 and demonstrated that our cross-docking pipeline can achieve similar or better performance than using either single or multiple-receptor structures. Moreover, our method displayed not only decent pose prediction performance but also better virtual screening performance over several other methods.