GFscore: a general nonlinear consensus scoring function for high-throughput docking

Deep Learning in Structure-Based Drug Design

Computational methods play an increasingly important role in drug discovery. Structure-based drug design (SBDD), in particular, includes techniques that take into account the structure of the macromolecular target to predict compounds that are likely to establish optimal interactions with the binding site. The current interest in machine learning algorithms based on deep neural networks encouraged the application of deep learning to SBDD related problems. This chapter covers selected works in this active area of research.

Applying Machine Learning to Ultrafast Shape Recognition in Ligand-Based Virtual Screening

Ultrafast Shape Recognition (USR), along with its derivatives, are Ligand-Based Virtual Screening (LBVS) methods that condense 3-dimensional information about molecular shape, as well as other properties, into a small set of numeric descriptors. These can be used to efficiently compute a measure of similarity between pairs of molecules using a simple inverse Manhattan Distance metric. In this study we explore the use of suitable Machine Learning techniques that can be trained using USR descriptors, so as to improve the similarity detection of potential new leads. We use molecules from the Directory for Useful Decoys-Enhanced to construct machine learning models based on three different algorithms: Gaussian Mixture Models (GMMs), Isolation Forests and Artificial Neural Networks (ANNs). We train models based on full molecule conformer models, as well as the Lowest Energy Conformations (LECs) only. We also investigate the performance of our models when trained on smaller datasets so as to model virtual screening scenarios when only a small number of actives are known a priori. Our results indicate significant performance gains over a state of the art USR-derived method, ElectroShape 5D, with GMMs obtaining a mean performance up to 430% better than that of ElectroShape 5D in terms of Enrichment Factor with a maximum improvement of up to 940%. Additionally, we demonstrate that our models are capable of maintaining their performance, in terms of enrichment factor, within 10% of the mean as the size of the training dataset is successively reduced. Furthermore, we also demonstrate that running times for retrospective screening using the machine learning models we selected are faster than standard USR, on average by a factor of 10, including the time required for training. Our results show that machine learning techniques can significantly improve the virtual screening performance and efficiency of the USR family of methods.

Virtual Screening Meets Deep Learning

BACKGROUND

Automated compound testing is currently the de facto standard method for drug screening, but it has not brought the great increase in the number of new drugs that was expected. Computer- aided compounds search, known as Virtual Screening, has shown the benefits to this field as a complement or even alternative to the robotic drug discovery. There are different methods and approaches to address this problem and most of them are often included in one of the main screening strategies. Machine learning, however, has established itself as a virtual screening methodology in its own right and it may grow in popularity with the new trends on artificial intelligence.

OBJECTIVE

This paper will attempt to provide a comprehensive and structured review that collects the most important proposals made so far in this area of research. Particular attention is given to some recent developments carried out in the machine learning field: the deep learning approach, which is pointed out as a future key player in the virtual screening landscape.

An Overview of Scoring Functions Used for Protein-Ligand Interactions in Molecular Docking

Currently, molecular docking is becoming a key tool in drug discovery and molecular modeling applications. The reliability of molecular docking depends on the accuracy of the adopted scoring function, which can guide and determine the ligand poses when thousands of possible poses of ligand are generated. The scoring function can be used to determine the binding mode and site of a ligand, predict binding affinity and identify the potential drug leads for a given protein target. Despite intensive research over the years, accurate and rapid prediction of protein-ligand interactions is still a challenge in molecular docking. For this reason, this study reviews four basic types of scoring functions, physics-based, empirical, knowledge-based, and machine learning-based scoring functions, based on an up-to-date classification scheme. We not only discuss the foundations of the four types scoring functions, suitable application areas and shortcomings, but also discuss challenges and potential future study directions.

Empirical Scoring Functions for Structure-Based Virtual Screening: Applications, Critical Aspects, and Challenges

Structure-based virtual screening (VS) is a widely used approach that employs the knowledge of the three-dimensional structure of the target of interest in the design of new lead compounds from large-scale molecular docking experiments. Through the prediction of the binding mode and affinity of a small molecule within the binding site of the target of interest, it is possible to understand important properties related to the binding process. Empirical scoring functions are widely used for pose and affinity prediction. Although pose prediction is performed with satisfactory accuracy, the correct prediction of binding affinity is still a challenging task and crucial for the success of structure-based VS experiments. There are several efforts in distinct fronts to develop even more sophisticated and accurate models for filtering and ranking large libraries of compounds. This paper will cover some recent successful applications and methodological advances, including strategies to explore the ligand entropy and solvent effects, training with sophisticated machine-learning techniques, and the use of quantum mechanics. Particular emphasis will be given to the discussion of critical aspects and further directions for the development of more accurate empirical scoring functions.

Prediction of N-Methyl-D-Aspartate Receptor GluN1-Ligand Binding Affinity by a Novel SVM-Pose/SVM-Score Combinatorial Ensemble Docking Scheme

The glycine-binding site of the N-methyl-D-aspartate receptor (NMDAR) subunit GluN1 is a potential pharmacological target for neurodegenerative disorders. A novel combinatorial ensemble docking scheme using ligand and protein conformation ensembles and customized support vector machine (SVM)-based models to select the docked pose and to predict the docking score was generated for predicting the NMDAR GluN1-ligand binding affinity. The predicted root mean square deviation (RMSD) values in pose by SVM-Pose models were found to be in good agreement with the observed values (n = 30, r² = 0.928–0.988,  = 0.894–0.954, RMSE = 0.002–0.412, s = 0.001–0.214), and the predicted pK_i values by SVM-Score were found to be in good agreement with the observed values for the training samples (n = 24, r² = 0.967,  = 0.899, RMSE = 0.295, s = 0.170) and test samples (n = 13, q² = 0.894, RMSE = 0.437, s = 0.202). When subjected to various statistical validations, the developed SVM-Pose and SVM-Score models consistently met the most stringent criteria. A mock test asserted the predictivity of this novel docking scheme. Collectively, this accurate novel combinatorial ensemble docking scheme can be used to predict the NMDAR GluN1-ligand binding affinity for facilitating drug discovery.

Scoring Functions of Protein-Ligand Interactions

Scoring function of protein-ligand interactions is used to recognize the “native” binding pose of a ligand on the protein and to predict the binding affinity, so that the active small molecules can be discriminated from the non-active ones. Scoring function is widely used in computationally molecular docking and structure-based drug discovery. The development and improvement of scoring functions have broad implications in pharmaceutical industry and academic research. During the past three decades, much progress have been made in methodology and accuracy for scoring functions, and many successful cases have be witnessed in virtual database screening. In this chapter, the authors introduced the basic types of scoring functions and their derivations, the commonly-used evaluation methods and benchmarks, as well as the underlying challenges and current solutions. Finally, the authors discussed the promising directions to improve and develop scoring functions for future molecular docking-based drug discovery.

Molecular Docking at a Glance

The current chapter introduces different aspects of molecular docking technique in order to give an overview to the readers about the topics which will be dealt with throughout this volume. Like many other fields of science, molecular docking studies has experienced a lagging period of slow and steady increase in terms of acquiring attention of scientific community as well as its frequency of application, followed by a pronounced era of exponential expansion in theory, methodology, areas of application and performance due to developments in related technologies such as computational resources and theoretical as well as experimental biophysical methods. In the following sections the evolution of molecular docking will be reviewed and its different components including methods, search algorithms, scoring functions, validation of the methods, and area of applications plus few case studies will be touched briefly.

Machine-learning scoring functions to improve structure-based binding affinity prediction and virtual screening

Docking tools to predict whether and how a small molecule binds to a target can be applied if a structural model of such target is available. The reliability of docking depends, however, on the accuracy of the adopted scoring function (SF). Despite intense research over the years, improving the accuracy of SFs for structure-based binding affinity prediction or virtual screening has proven to be a challenging task for any class of method. New SFs based on modern machine-learning regression models, which do not impose a predetermined functional form and thus are able to exploit effectively much larger amounts of experimental data, have recently been introduced. These machine-learning SFs have been shown to outperform a wide range of classical SFs at both binding affinity prediction and virtual screening. The emerging picture from these studies is that the classical approach of using linear regression with a small number of expert-selected structural features can be strongly improved by a machine-learning approach based on nonlinear regression allied with comprehensive data-driven feature selection. Furthermore, the performance of classical SFs does not grow with larger training datasets and hence this performance gap is expected to widen as more training data becomes available in the future. Other topics covered in this review include predicting the reliability of a SF on a particular target class, generating synthetic data to improve predictive performance and modeling guidelines for SF development. WIREs Comput Mol Sci 2015, 5:405-424. doi: 10.1002/wcms.1225 For further resources related to this article, please visit the WIREs website.

Molecular docking and structure-based drug design strategies

Pharmaceutical research has successfully incorporated a wealth of molecular modeling methods, within a variety of drug discovery programs, to study complex biological and chemical systems. The integration of computational and experimental strategies has been of great value in the identification and development of novel promising compounds. Broadly used in modern drug design, molecular docking methods explore the ligand conformations adopted within the binding sites of macromolecular targets. This approach also estimates the ligand-receptor binding free energy by evaluating critical phenomena involved in the intermolecular recognition process. Today, as a variety of docking algorithms are available, an understanding of the advantages and limitations of each method is of fundamental importance in the development of effective strategies and the generation of relevant results. The purpose of this review is to examine current molecular docking strategies used in drug discovery and medicinal chemistry, exploring the advances in the field and the role played by the integration of structure- and ligand-based methods.

Reranking docking poses using molecular simulations and approximate free energy methods

Fast and accurate identification of active compounds is essential for effective use of virtual screening workflows. Here, we have compared the ligand-ranking efficiency of the linear interaction energy (LIE) method against standard docking approaches. Using a trypsin set of 1549 compounds, we performed 12,250 molecular dynamics simulations. The LIE method proved effective but did not yield results significantly better than those obtained with docking codes. The entire database of simulations is released.

Virtual interactomics of proteins from biochemical standpoint

Virtual interactomics represents a rapidly developing scientific area on the boundary line of bioinformatics and interactomics. Protein-related virtual interactomics then comprises instrumental tools for prediction, simulation, and networking of the majority of interactions important for structural and individual reproduction, differentiation, recognition, signaling, regulation, and metabolic pathways of cells and organisms. Here, we describe the main areas of virtual protein interactomics, that is, structurally based comparative analysis and prediction of functionally important interacting sites, mimotope-assisted and combined epitope prediction, molecular (protein) docking studies, and investigation of protein interaction networks. Detailed information about some interesting methodological approaches and online accessible programs or databases is displayed in our tables. Considerable part of the text deals with the searches for common conserved or functionally convergent protein regions and subgraphs of conserved interaction networks, new outstanding trends and clinically interesting results. In agreement with the presented data and relationships, virtual interactomic tools improve our scientific knowledge, help us to formulate working hypotheses, and they frequently also mediate variously important in silico simulations.

Inhibition of bacterial virulence: drug-like molecules targeting the Salmonella enterica PhoP response regulator

Two-component signal transduction (TCST) is the predominant signaling scheme used in bacteria to sense and respond to environmental changes in order to survive and thrive. A typical TCST system consists of a sensor histidine kinase to detect external signals and an effector response regulator to respond to external changes. In the signaling scheme, the histidine kinase phosphorylates and activates the response regulator, which functions as a transcription factor to modulate gene expression. One promising strategy toward antibacterial development is to target TCST regulatory systems, specifically the response regulators to disrupt the expression of genes important for virulence. In Salmonella enterica, the PhoQ/PhoP signal transduction system is used to sense and respond to low magnesium levels and regulates the expression for over 40 genes necessary for growth under these conditions, and more interestingly, genes that are important for virulence. In this study, a hybrid approach coupling computational and experimental methods was applied to identify drug-like compounds to target the PhoP response regulator. A computational approach of structure-based virtual screening combined with a series of biochemical and biophysical assays was used to test the predictability of the computational strategy and to characterize the mode of action of the compounds. Eight compounds from virtual screening inhibit the formation of the PhoP-DNA complex necessary for virulence gene regulation. This investigation served as an initial case study for targeting TCST response regulators to modulate the gene expression of a signal transduction pathway important for bacterial virulence. With the increasing resistance of pathogenic bacteria to current antibiotics, targeting TCST response regulators that control virulence is a viable strategy for the development of antimicrobial therapeutics with novel modes of action.

PLS-DA - Docking Optimized Combined Energetic Terms (PLSDA-DOCET) protocol: a brief evaluation

Docking studies have become popular approaches in drug design, where the binding energy of the ligand in the active site of the protein is estimated by a scoring function. Many promising techniques were developed to enhance the performance of scoring functions including the fusion of multiple scoring functions outcomes into a so-called consensus scoring function. Hereby, we evaluated the target oriented consensus technique using the energetic terms of several scoring functions. The approach was denoted PLSDA-DOCET. Optimization strategies for consensus energetic terms and scoring functions based on ROC metric were compared to classical rigid docking and to ligand-based similarity search methods comprising 2D fingerprints and ROCS. The ROCS results indicate large performance variations depending on the biological target. The AUC-based strategy of PLSDA-DOCET outperformed the other docking approaches regarding simple retrieval and scaffold-hopping. The superior performance of PLSDA-DOCET protocol relative to single and combined scoring functions was validated on an external test set. We found a relative low mean correlation of the ranks of the chemotypes retrieved by the PLSDA-DOCET protocol and all the other methods employed here.

CSAR benchmark exercise of 2010: combined evaluation across all submitted scoring functions

As part of the Community Structure-Activity Resource (CSAR) center, a set of 343 high-quality, protein–ligand crystal structures were assembled with experimentally determined K_d or K_i information from the literature. We encouraged the community to score the crystallographic poses of the complexes by any method of their choice. The goal of the exercise was to (1) evaluate the current ability of the field to predict activity from structure and (2) investigate the properties of the complexes and methods that appear to hinder scoring. A total of 19 different methods were submitted with numerous parameter variations for a total of 64 sets of scores from 16 participating groups. Linear regression and nonparametric tests were used to correlate scores to the experimental values. Correlation to experiment for the various methods ranged R² = 0.58–0.12, Spearman ρ = 0.74–0.37, Kendall τ = 0.55–0.25, and median unsigned error = 1.00–1.68 pK_d units. All types of scoring functions—force field based, knowledge based, and empirical—had examples with high and low correlation, showing no bias/advantage for any particular approach. The data across all the participants were combined to identify 63 complexes that were poorly scored across the majority of the scoring methods and 123 complexes that were scored well across the majority. The two sets were compared using a Wilcoxon rank-sum test to assess any significant difference in the distributions of >400 physicochemical properties of the ligands and the proteins. Poorly scored complexes were found to have ligands that were the same size as those in well-scored complexes, but hydrogen bonding and torsional strain were significantly different. These comparisons point to a need for CSAR to develop data sets of congeneric series with a range of hydrogen-bonding and hydrophobic characteristics and a range of rotatable bonds.

Allosteric inhibition of the hepatitis C virus NS5B polymerase: in silico strategies for drug discovery and development

Chronic infection by hepatitis C virus (HCV) often leads to severe liver disease including cirrhosis, hepatocellular carcinoma and liver failure. Despite it being more than 20 years since the identification of HCV, the current standard of care for treating the infection is based on aspecific therapy often associated with severe side effects and low-sustained virological response. Research is ongoing to develop new and better medications, including a broad range of allosteric NS5B polymerase inhibitors. This article reviews traditional computational methodologies and more recently developed in silico strategies aimed at identifying and optimizing non-nucleoside inhibitors targeting allosteric sites of HCV NS5B polymerase. The drug-discovery approaches reviewed could provide take-home lessons for general computer-aided research projects.

Scoring functions and their evaluation methods for protein-ligand docking: recent advances and future directions

The scoring function is one of the most important components in structure-based drug design. Despite considerable success, accurate and rapid prediction of protein-ligand interactions is still a challenge in molecular docking. In this perspective, we have reviewed three basic types of scoring functions (force-field, empirical, and knowledge-based) and the consensus scoring technique that are used for protein-ligand docking. The commonly-used assessment criteria and publicly available protein-ligand databases for performance evaluation of the scoring functions have also been presented and discussed. We end with a discussion of the challenges faced by existing scoring functions and possible future directions for developing improved scoring functions.

Modified cap group suberoylanilide hydroxamic acid histone deacetylase inhibitor derivatives reveal improved selective antileukemic activity

A series of SAHA cap derivatives was designed and prepared in good-to-excellent yields that varied from 49% to 95%. These derivatives were evaluated for their antiproliferative activity in several human cancer cell lines. Antiproliferative activity was observed for concentrations varying from 0.12 to >100 microM, and a molecular modeling approach of selected SAHA derivatives, based on available structural information of human HDAC8 in complex with SAHA, was performed. Strikingly, two compounds displayed up to 10-fold improved antileukemic activity with respect to SAHA; however, these compounds displayed antiproliferative activity similar to SAHA when assayed against solid tumor-derived cell lines. A 10-fold improvement in the leukemic vs peripheral blood mononuclear cell therapeutic ratio, with no evident in vivo toxicity toward blood cells, was also observed. The herein-described compounds and method of synthesis will provide invaluable tools to investigate the molecular mechanism responsible for the reported selectively improved antileukemic activity.

Lead Discovery Using Virtual Screening

The practice of virtual screening (VS) to identify chemical leads to known or novel targets is becoming a core function of the computational chemist within industry. By employing a range of techniques, when attempting to identify compounds with activity against a biological target, a small focused subset of a larger collection of compounds can be identified and tested, often with results much better than selecting a similar number of compounds at random. We will review the key methods available, their relative success, and provide practical insights into best practices and key gaps. We will also argue that the capability of VS methods has grown to a point where fuller integration with experimental methods, including HTS, could increase the effectiveness of both.

Towards improving compound selection in structure-based virtual screening

Structure-based virtual screening is now an established technology for supporting hit finding and lead optimisation in drug discovery. Recent validation studies have highlighted the poor performance of currently used scoring functions in estimating binding affinity and hence in ranking large datasets of docked ligands. Progress in the analysis of large datasets can be made through the use of appropriate data mining techniques and the derivation of a broader range of descriptors relevant to receptor-ligand binding. In addition, simple scoring functions can be supplemented by simulation-based scoring protocols. Developments in workflow design allow the automation of repetitive tasks, and also encourage the routine use of simulation-based methods and the rapid prototyping of novel modelling and analysis procedures.

Protein protein interaction inhibition (2P2I) combining high throughput and virtual screening: Application to the HIV-1 Nef protein

Protein-protein recognition is the cornerstone of multiple cellular and pathological functions. Therefore, protein-protein interaction inhibition (2P2I) is endowed with great therapeutic potential despite the initial belief that 2P2I was refractory to small-molecule intervention. Improved knowledge of complex molecular binding surfaces has recently stimulated renewed interest for 2P2I, especially after identification of "hot spots" and first inhibitory compounds. However, the combination of target complexity and lack of starting compound has thwarted experimental results and created intellectual barriers. Here we combined virtual and experimental screening when no previously known inhibitors can be used as starting point in a structure-based research program that targets an SH3 binding surface of the HIV type I Nef protein. High-throughput docking and application of a pharmacophoric filter on one hand and search for analogy on the other hand identified drug-like compounds that were further confirmed to bind Nef in the micromolar range (isothermal titration calorimetry), to target the Nef SH3 binding surface (NMR experiments), and to efficiently compete for Nef-SH3 interactions (cell-based assay, GST pull-down). Initial identification of these compounds by virtual screening was validated by screening of the very same library of compounds in the cell-based assay, demonstrating that a significant enrichment factor was attained by the in silico screening. To our knowledge, our results identify the first set of drug-like compounds that functionally target the HIV-1 Nef SH3 binding surface and provide the basis for a powerful discovery process that should help to speed up 2P2I strategies and open avenues for new class of antiviral molecules.

Calculation of Protein-Ligand Binding Affinities

Accurate methods of computing the affinity of a small molecule with a protein are needed to speed the discovery of new medications and biological probes. This paper reviews physics-based models of binding, beginning with a summary of the changes in potential energy, solvation energy, and configurational entropy that influence affinity, and a theoretical overview to frame the discussion of specific computational approaches. Important advances are reported in modeling protein-ligand energetics, such as the incorporation of electronic polarization and the use of quantum mechanical methods. Recent calculations suggest that changes in configurational entropy strongly oppose binding and must be included if accurate affinities are to be obtained. The linear interaction energy (LIE) and molecular mechanics Poisson-Boltzmann surface area (MM-PBSA) methods are analyzed, as are free energy pathway methods, which show promise and may be ready for more extensive testing. Ultimately, major improvements in modeling accuracy will likely require advances on multiple fronts, as well as continued validation against experiment.