State-of-the-art in ligand-based virtual screening

Machine learning-based chemical binding similarity using evolutionary relationships of target genes

Chemical similarity searching is a basic research tool that can be used to find small molecules which are similar in shape to known active molecules. Despite its popularity, the retrieval of local molecular features that are critical to functional activity related to target binding often fails. To overcome this limitation, we developed a novel machine learning-based chemical binding similarity score by using various evolutionary relationships of binding targets. The chemical similarity was defined by the probability of chemical compounds binding to identical targets. Comprehensive and heterogeneous multiple target-binding chemical data were integrated into a paired data format and processed using multiple classification similarity-learning models with various levels of target evolutionary information. Encoding evolutionary information to chemical compounds through their binding targets substantially expanded available chemical-target interaction data and significantly improved model performance. The output probability of our integrated model, referred to as ensemble evolutionary chemical binding similarity (ensECBS), was effective for finding hidden chemical relationships. The developed method can serve as a novel chemical similarity tool that uses evolutionarily conserved target binding information.

Ligand based virtual screening using SVM on GPU

In silico methods play an essential role in modern drug discovery methods. Virtual screening, an in silico method, is used to filter out the chemical space on which actual wet lab experiments are need to be conducted. Ligand based virtual screening is a computational strategy using which one can build a model of the target protein based on the knowledge of the ligands that bind successfully to the target. This model is then used to predict if the new molecule is likely to bind to the target. Support vector machine, a supervised learning algorithm used for classification, can be utilized for virtual screening the ligand data. When used for virtual screening purpose, SVM could produce interesting results. But since we have a huge ligand data, the time taken for training the SVM model is quite high compared to other learning algorithms. By parallelizing these algorithms on multi-core processors, one can easily expedite these discoveries. In this paper, a GPU based ligand based virtual screening tool (GpuSVMScreen) which uses SVM have been proposed and bench-marked. This data parallel virtual screening tool provides high throughput by running in short time. The proposed GpuSVMScreen can successfully screen large number of molecules (billions) also. The source code of this tool is available at http://ccc.nitc.ac.in/project/GPUSVMSCREEN.

Feature vector clustering molecular pairs in computer simulations

A clustering framework is introduced to analyze the microscopic structural organization of molecular pairs in liquids and solutions. A molecular pair is represented by a representative vector (RV). To obtain RV, intermolecular atom distances in the pair are extracted from simulation trajectory as components of the key feature vector (KFV). A specific scheme is then suggested to transform KFV to RV by removing the influence of permutational molecular symmetry on the KFV as the predicted clusters should be independent of possible permutations of identical atoms in the pair. After RVs of pairs are obtained, a clustering analysis technique is finally used to classify all the RVs of molecular pairs into the clusters. The framework is applied to analyze trajectory from molecular dynamics simulations of an ionic liquid (trihexyltetradecylphosphonium bis(oxalato)borate ([P_6,6,6,14 ][BOB])). The molecular pairs are successfully categorized into physically meaningful clusters, and their effectiveness is evaluated by computing the product moment correlation coefficient (PMCC). (Willett, Winterman, and Bawden, J. Chem. Inf. Comput. Sci. 1986, 26, 109-118; Downs, Willett, and Fisanick, J. Chem. Inf. Comput. Sci. 1994, 34, 1094-1102) It is observed that representative configurations of two clusters are related to two energy local minimum structures optimized by density functional theory (DFT) calculation, respectively. Several widely used clustering analysis techniques of both nonhierarchical (k-means) and hierarchical clustering algorithms are also evaluated and compared with each other. The proposed KFV technique efficiently reveals local molecular pair structures in the simulated complex liquid. It is a method, which is highly useful for liquids and solutions in particular with strong intermolecular interactions. © 2019 Wiley Periodicals, Inc.

N-arylpiperazine-containing compound (C2): An enhancer of sunitinib in the treatment of pancreatic cancer, involving D1DR activation

Previous studies showed that dopamine (DA) significantly reduces the frequency of cancer stem-like cells (CSC) and enhances the efficacy of sunitinib (SUN) in the treatment of breast cancer and non-small cell lung cancer (NSCLC). To overcome the shortcomings of DA in clinical practice, the purpose of this study was to investigate the efficacy as well as the underlying mechanism of an orally available, N-arylpiperazine-containing compound C2, in the treatment of pancreatic cancer when used alone or in combination with SUN. Our results showed that C2 and SUN exerted synergistic effects on inhibiting the growth of SW1990 and PANC-1 pancreatic cancer cells. C2 significantly inhibited colony formation and migration of both cells. SW1990 xenograft and patient-derived xenograft (PDX) models were utilized for pharmacodynamic investigation in vivo. C2 alone showed little inhibition effect on tumor growth but increased the anti-tumor efficacy of SUN in both xenografts. Moreover, C2 down-regulated CSC markers (CD133 and ALDH) of both cancer cells and up-regulated the expression of dopamine receptor D1 (D1DR) in tumor. Besides, the SW1990 tumor growth was dose-dependently inhibited when the cells were pretreated with C2 before implantation. C2 increased intratumoral cAMP level, and the combination with D1DR specific antagonist SCH23390 reversed the above-mentioned effects of C2 both in vitro and in vivo, indicating the activation of D1DR may be involved in the underlying mechanism of C2 action. In summary, C2 could reduce the CSC frequency and enhance the anti-cancer effect of SUN in the treatment of pancreatic cancer, demonstrating its potential in cancer therapy.

Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases

The identification of interactions between drugs/compounds and their targets is crucial for the development of new drugs. In vitro screening experiments (i.e. bioassays) are frequently used for this purpose; however, experimental approaches are insufficient to explore novel drug-target interactions, mainly because of feasibility problems, as they are labour intensive, costly and time consuming. A computational field known as 'virtual screening' (VS) has emerged in the past decades to aid experimental drug discovery studies by statistically estimating unknown bio-interactions between compounds and biological targets. These methods use the physico-chemical and structural properties of compounds and/or target proteins along with the experimentally verified bio-interaction information to generate predictive models. Lately, sophisticated machine learning techniques are applied in VS to elevate the predictive performance. The objective of this study is to examine and discuss the recent applications of machine learning techniques in VS, including deep learning, which became highly popular after giving rise to epochal developments in the fields of computer vision and natural language processing. The past 3 years have witnessed an unprecedented amount of research studies considering the application of deep learning in biomedicine, including computational drug discovery. In this review, we first describe the main instruments of VS methods, including compound and protein features (i.e. representations and descriptors), frequently used libraries and toolkits for VS, bioactivity databases and gold-standard data sets for system training and benchmarking. We subsequently review recent VS studies with a strong emphasis on deep learning applications. Finally, we discuss the present state of the field, including the current challenges and suggest future directions. We believe that this survey will provide insight to the researchers working in the field of computational drug discovery in terms of comprehending and developing novel bio-prediction methods.

Large-Scale Comparison of Alternative Similarity Search Strategies with Varying Chemical Information Contents

Similarity searching (SS) is a core approach in computational compound screening and has a long tradition in pharmaceutical research. Over the years, different approaches have been introduced to increase the information content of search calculations and optimize the ability to detect compounds having similar activity. We present a large-scale comparison of distinct search strategies on more than 600 qualifying compound activity classes. Challenging test cases for SS were identified and used to evaluate different ways to further improve search performance, which provided a differentiated view of alternative search strategies and their relative performance. It was found that search results could not only be improved by increasing compound input information but also by focusing similarity calculations on database compounds. In the presence of multiple active reference compounds, asymmetric SS with high weights on chemical features of target compounds emerged as an overall preferred approach across many different activity classes. These findings have implications for practical virtual screening applications.

Comparison of Target Features for Predicting Drug-Target Interactions by Deep Neural Network Based on Large-Scale Drug-Induced Transcriptome Data

Uncovering drug-target interactions (DTIs) is pivotal to understand drug mode-of-action (MoA), avoid adverse drug reaction (ADR), and seek opportunities for drug repositioning (DR). For decades, in silico predictions for DTIs have largely depended on structural information of both targets and compounds, e.g., docking or ligand-based virtual screening. Recently, the application of deep neural network (DNN) is opening a new path to uncover novel DTIs for thousands of targets. One important question is which features for targets are most relevant to DTI prediction. As an early attempt to answer this question, we objectively compared three canonical target features extracted from: (i) the expression profiles by gene knockdown (GEPs); (ii) the protein–protein interaction network (PPI network); and (iii) the pathway membership (PM) of a target gene. For drug features, the large-scale drug-induced transcriptome dataset, or the Library of Integrated Network-based Cellular Signatures (LINCS) L1000 dataset was used. All these features are closely related to protein function or drug MoA, of which utility is only sparsely investigated. In particular, few studies have compared the three types of target features in DNN-based DTI prediction under the same evaluation scheme. Among the three target features, the PM and the PPI network show similar performances superior to GEPs. DNN models based on both features consistently outperformed other machine learning methods such as naïve Bayes, random forest, or logistic regression.

Systematic selection of chemical fingerprint features improves the Gibbs energy prediction of biochemical reactions

MOTIVATION

Accurate and wide-ranging prediction of thermodynamic parameters for biochemical reactions can facilitate deeper insights into the workings and the design of metabolic systems.

RESULTS

Here, we introduce a machine learning method with chemical fingerprint-based features for the prediction of the Gibbs free energy of biochemical reactions. From a large pool of 2D fingerprint-based features, this method systematically selects a small number of relevant ones and uses them to construct a regularized linear model. Since a manual selection of 2D structure-based features can be a tedious and time-consuming task, requiring expert knowledge about the structure-activity relationship of chemical compounds, the systematic feature selection step in our method offers a convenient means to identify relevant 2D fingerprint-based features. By comparing our method with state-of-the-art linear regression-based methods for the standard Gibbs free energy prediction, we demonstrated that its prediction accuracy and prediction coverage are most favorable. Our results show direct evidence that a number of 2D fingerprints collectively provide useful information about the Gibbs free energy of biochemical reactions and that our systematic feature selection procedure provides a convenient way to identify them.

AVAILABILITY AND IMPLEMENTATION

Our software is freely available for download at http://sfb.kaust.edu.sa/Pages/Software.aspx.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Ligity: A Non-Superpositional, Knowledge-Based Approach to Virtual Screening

We present Ligity, a hybrid ligand-structure-based, non-superpositional method for virtual screening of large databases of small molecules. Ligity uses the relative spatial distribution of pharmacophoric interaction points (PIPs) derived from the conformations of small molecules. These are compared with the PIPs derived from key interaction features found in protein-ligand complexes and are used to prioritize likely binders. We investigated the effect of generating PIPs using the single lowest energy conformer versus an ensemble of conformers for each screened ligand, using different bin sizes for the distance between two features, utilizing triangular sets of pharmacophoric features (3-PIPs) versus chiral tetrahedral sets (4-PIPs), fusing data for targets with multiple protein-ligand complex structures, and applying different similarity measures. Ligity was benchmarked using the Directory of Useful Decoys-Enhanced (DUD-E). Optimal results were obtained using the tetrahedral PIPs derived from an ensemble of bound ligand conformers and a bin size of 1.5 Å, which are used as the default settings for Ligity. The high-throughput screening mode of Ligity, using only the lowest-energy conformer of each ligand, was used for benchmarking against the whole of the DUD-E, and a more resource-intensive, "information-rich" mode of Ligity, using a conformational ensemble of each ligand, were used for a representative subset of 10 targets. Against the full DUD-E database, mean area under the receiver operating characteristic curve (AUC) values ranged from 0.44 to 0.99, while for the representative subset they ranged from 0.61 to 0.86. Data fusion further improved Ligity's performance, with mean AUC values ranging from 0.64 to 0.95. Ligity is very efficient compared to a protein-ligand docking method such as AutoDock Vina: if the time taken for the precalculation of Ligity descriptors is included in the comparason, then Ligity is about 20 times faster than docking. A direct comparison of the virtual screening steps shows Ligity to be over 5000 times faster. Ligity highly ranks the lowest-energy conformers of DUD-E actives, in a statistically significant manner, behavior that is not observed for DUD-E decoys. Thus, our results suggest that active compounds tend to bind in relatively low-energy conformations compared to decoys. This may be because actives-and thus their lowest-energy conformations-have been optimized for conformational complementarity with their cognate binding sites.

Computer-based techniques for lead identification and optimization I: Basics

This chapter focuses on computational techniques for identifying and optimizing lead molecules, with a special emphasis on natural compounds. A number of case studies have been specifically discussed, such as the case of the naphthyridine scaffold, discovered through a structure-based virtual screening (SBVS) and proposed as the starting point for further lead optimization process, to enhance its telomeric RNA selectivity. Another example is the case of Liphagal, a tetracyclic meroterpenoid extracted fromAka coralliphaga, known as PI3Kα inhibitor, provide an evidence for the design of new active congeners against PI3Kα using molecular dynamics (MD) simulations. These are only two of the numerous examples of the computational techniques’ powerful in drug design and drug discovery fields. Finally, the design of drugs that can simultaneously interact with multiple targets as a promising approach for treating complicated diseases has been reported. An example of polypharmacological agents are the compounds extracted from mushrooms identified by means of molecular docking experiments. This chapter may be a useful manual of molecular modeling techniques used in the lead-optimization and lead identification processes.

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.

Inhibition of Oncogenic Kinases: An In Vitro Validated Computational Approach Identified Potential Multi-Target Anticancer Compounds

Tumorigenesis in humans is a multistep progression that imitates genetic changes leading to cell transformation and malignancy. Oncogenic kinases play a central role in cancer progression, rendering them putative targets for the design of anti-cancer drugs. The presented work aims to identify the potential multi-target inhibitors of oncogenic receptor tyrosine kinases (RTKs) and serine/threonine kinases (STKs). For this, chemoinformatics and structure-based virtual screening approaches were combined with an in vitro validation of lead hits on both cancerous and non-cancerous cell lines. A total of 16 different kinase structures were screened against ~739,000 prefiltered compounds using diversity selection, after which the top hits were filtered for promising pharmacokinetic properties. This led to the identification of 12 and 9 compounds against RTKs and STKs, respectively. Molecular dynamics (MD) simulations were carried out to better comprehend the stability of the predicted hit kinase-compound complexes. Two top-ranked compounds against each kinase class were tested in vitro for cytotoxicity, with compound F34 showing the most promising inhibitory activity in HeLa, HepG2, and Vero cell lines with IC50 values of 145.46 μM, 175.48 μM, and 130.52 μM, respectively. Additional docking of F34 against various RTKs was carried out to support potential multi-target inhibition. Together with reliable MD simulations, these results suggest the promising potential of identified multi-target STK and RTK scaffolds for further kinase-specific anti-cancer drug development toward combinatorial therapies.

De Novo Molecular Design by Combining Deep Autoencoder Recurrent Neural Networks with Generative Topographic Mapping

Here we show that Generative Topographic Mapping (GTM) can be used to explore the latent space of the SMILES-based autoencoders and generate focused molecular libraries of interest. We have built a sequence-to-sequence neural network with Bidirectional Long Short-Term Memory layers and trained it on the SMILES strings from ChEMBL23. Very high reconstruction rates of the test set molecules were achieved (>98%), which are comparable to the ones reported in related publications. Using GTM, we have visualized the autoencoder latent space on the two-dimensional topographic map. Targeted map zones can be used for generating novel molecular structures by sampling associated latent space points and decoding them to SMILES. The sampling method based on a genetic algorithm was introduced to optimize compound properties "on the fly". The generated focused molecular libraries were shown to contain original and a priori feasible compounds which, pending actual synthesis and testing, showed encouraging behavior in independent structure-based affinity estimation procedures (pharmacophore matching, docking).

ImmtorLig_DB: repertoire of virtually screened small molecules against immune receptors to bolster host immunity

Host directed therapies to boost immunity against infection are gaining considerable impetus following the observation that use of antibiotics has become a continuous source for the emergence of drug resistant strains of pathogens. Receptors expressed by the cells of immune system play a cardinal role in initiating sequence of events necessary to ameliorate many morbid conditions. Although, ligands for the immune receptors are available; but their use is limited due to complex structure, synthesis and cost-effectiveness. Virtual screening (VS) is an integral part of chemoinformatics and computer-aided drug design (CADD) and aims to streamline the process of drug discovery. ImmtorLig_DB is a repertoire of 5000 novel small molecules, screened from ZINC database and ranked using structure based virtual screening (SBVS) against 25 immune receptors which play a pivotal role in defending and initiating the activation of immune system. Consequently, in the current study, small molecules were screened by docking on the essential domains present on the receptors expressed by cells of immune system. The screened molecules exhibited efficacious binding to immune receptors, and indicated a possibility of discovering novel small molecules. Other features of ImmtorLig_DB include information about availability, clustering analysis, and estimation of absorption, distribution, metabolism, and excretion (ADME) properties of the screened small molecules. Structural comparisons indicate that predicted small molecules may be considered novel. Further, this repertoire is available via a searchable graphical user interface (GUI) through http://bioinfo.imtech.res.in/bvs/immtor/ .

Ligand biological activity predicted by cleaning positive and negative chemical correlations

Predicting ligand biological activity is a key challenge in drug discovery. Ligand-based statistical approaches are often hampered by noise due to undersampling: The number of molecules known to be active or inactive is vastly less than the number of possible chemical features that might determine binding. We derive a statistical framework inspired by random matrix theory and combine the framework with high-quality negative data to discover important chemical differences between active and inactive molecules by disentangling undersampling noise. Our model outperforms standard benchmarks when tested against a set of challenging retrospective tests. We prospectively apply our model to the human muscarinic acetylcholine receptor M1, finding four experimentally confirmed agonists that are chemically dissimilar to all known ligands. The hit rate of our model is significantly higher than the state of the art. Our model can be interpreted and visualized to offer chemical insights about the molecular motifs that are synergistic or antagonistic to M1 agonism, which we have prospectively experimentally verified.

All in One: Cavity Detection, Druggability Estimate, Cavity-Based Pharmacophore Perception, and Virtual Screening

Discovering the very first ligands of pharmacologically important targets in a fast and cost-efficient manner is an important issue in drug discovery. In the absence of structural information on either endogenous or synthetic ligands, computational chemists classically identify the very first hits by docking compound libraries to a binding site of interest, with well-known biases arising from the usage of scoring functions. We herewith propose a novel computational method tailored to ligand-free protein structures and consisting in the generation of simple cavity-based pharmacophores to which potential ligands could be aligned by the use of a smooth Gaussian function. The method, embedded in the IChem toolkit, automatically detects ligand-binding cavities, then predicts their structural druggability, and last creates a structure-based pharmacophore for predicted druggable binding sites. A companion tool (Shaper2) was designed to align ligands to cavity-derived pharmacophoric features. The proposed method is as efficient as state-of-the-art virtual screening methods (ROCS, Surflex-Dock) in both posing and virtual screening challenges. Interestingly, IChem-Shaper2 is clearly orthogonal to these latter methods in retrieving unique chemotypes from high-throughput virtual screening data.

Energy windows for computed compound conformers: covering artefacts or truly large reorganization energies?

The generation of 3D conformers of small molecules underpins most computational drug discovery. Thus, the conformer quality is critical and depends on their energetics. A key parameter is the empirical conformational energy window (ΔEw), since only conformers within ΔEw are retained. However, ΔEw values in use appear unrealistically large. We analyze the factors pertaining to the conformer energetics and ΔEw. We argue that more attention must be focused on the problem of collapsed low-energy conformers. That is due to artificial intramolecular stabilization and occurs even with continuum solvation. Consequently, the conformational energy of extended bioactive structures is artefactually increased, which inflates ΔEw. Thus, this Perspective highlights the issues arising from low-energy conformers and suggests improvements via empirical or physics-based strategies.

In silico identification of inhibitors targeting N-Terminal domain of human Replication Protein A

Replication Protein A (RPA) mediates DNA Damage Response (DDR) pathways through protein-protein interactions (PPIs). Targeting the PPIs formed between RPA and other DNA Damage Response (DDR) mediators has become an intriguing area of research for cancer drug discovery. A number of studies applied different methods ranging from high throughput screening approaches to fragment-based drug design tools to discover RPA inhibitors. Although these methods are robust, virtual screening approaches may be allocated as an alternative to such experimental methods, especially for screening of large libraries. Here we report the comprehensive screening of the large database, ZINC15 composed of ∼750 M compounds and the comparison of the identified ligands with the previously known inhibitors by means of binding affinity and drug-likeness. Initially, a ligand library sharing similarity with a promising inhibitor of the N-terminal domain of the RPA70 subunit (RPA70N) was generated by screening of the ZINC15 library. 46,999 ligands were collected and screened by LeDock which produced a satisfactory correlation with the experimental values (R² = 0.77). 10 of the top-scoring ligands in LeDock were directly progressed to molecular dynamics (MD) simulations, while 10 additional ligands were also selected based on their LeDock scores and the presence of a functional group that could interact with the key amino acids in the RPA70N cleft. MD simulations were used to predict the binding free energy of the ligands by the MM-PBSA method which produced a high level of agreement with the experiments (R² = 0.85). Binding free energy predictions pointed out 2 ligands with higher binding affinity than any of the reference inhibitors. Particularly the ligand ZINC000753854163 exhibited superior drug-likeness features than any of the known inhibitors. Overall, this study reports ZINC000753854163 as a possible inhibitor of RPA70N, reflecting its possible use in RPA70N targeted cancer therapy.

Virtual Chemical Libraries

Advances in computer processing speed and storage capacity have enabled researchers to generate virtual chemical libraries containing billions of molecules. While these numbers appear large, they are only a small fraction of the number of organic molecules that could potentially be synthesized. This review provides an overview of recent advances in the generation and use of virtual chemical libraries in medicinal chemistry. We also consider the practical implications of these libraries in drug discovery programs and highlight a number of current and future challenges.

Spresso: an ultrafast compound pre-screening method based on compound decomposition

Motivation

Recently, the number of available protein tertiary structures and compounds has increased. However, structure-based virtual screening is computationally expensive owing to docking simulations. Thus, methods that filter out obviously unnecessary compounds prior to computationally expensive docking simulations have been proposed. However, the calculation speed of these methods is not fast enough to evaluate ≥ 10 million compounds.

Results

In this article, we propose a novel, docking-based pre-screening protocol named Spresso (Speedy PRE-Screening method with Segmented cOmpounds). Partial structures (fragments) are common among many compounds; therefore, the number of fragment variations needed for evaluation is smaller than that of compounds. Our method increases calculation speeds by ∼200-fold compared to conventional methods.

Availability and Implementation

Spresso is written in C ++ and Python, and is available as an open-source code (http://www.bi.cs.titech.ac.jp/spresso/) under the GPLv3 license.

Supplementary information

Supplementary data are available at Bioinformatics online.

Selection of protein conformations for structure-based polypharmacology studies

Several drugs exert their therapeutic effect through the modulation of multiple targets. Structure-based approaches hold great promise for identifying compounds with the desired polypharmacological profiles. These methods use knowledge of the protein binding sites to identify stereoelectronically complementary ligands. The selection of the most suitable protein conformations to be used in the design process is vital, especially for multitarget drug design in which the same ligand has to be accommodated in multiple binding pockets. Herein, we focus on currently available techniques for the selection of the most suitable protein conformations for multitarget drug design, compare the potential advantages and limitations of each method, and comment on how their combination could help in polypharmacology drug design.

Structure⁻Activity Relationship and Molecular Docking of Natural Product Library Reveal Chrysin as a Novel Dipeptidyl Peptidase-4 (DPP-4) Inhibitor: An Integrated In Silico and In Vitro Study

Numerous studies indicate that diets with a variety of fruits and vegetables decrease the incidence of severe diseases, like diabetes, obesity, and cancer. Diets contain a variety of bioactive compounds, and their features, like diverge scaffolds, and structural complexity make them the most successful source of potential leads or hits in the process of drug discovery and drug development. Recently, novel serine protease dipeptidyl peptidase-4 (DPP-4) inhibitors played a role in the management of diabetes, obesity, and cancer. This study describes the development of field template, field-based qualitative structure⁻activity relationship (SAR) model demonstrating DPP-4 inhibitors of natural origin, and the same model is used to screen virtually focused food database composed of polyphenols as potential DPP-4 inhibitors. Compounds’ similarity to field template, and novelty score “high and very high”, were used as primary criteria to identify novel DPP-4 inhibitors. Molecular docking simulations were performed on the resulting natural compounds using FlexX algorithm. Finally, one natural compound, chrysin, was chosen to be evaluated experimentally to demonstrate the applicability of constructed SAR model. This study provides the molecular insights necessary in the discovery of new leads as DPP-4 inhibitors, to improve the potency of existing DPP-4 natural inhibitors.

Cheminformatics in Drug Discovery, an Industrial Perspective

Cheminformatics has established itself as a core discipline within large scale drug discovery operations. It would be impossible to handle the amount of data generated today in a small molecule drug discovery project without persons skilled in cheminformatics. In addition, due to increased emphasis on "Big Data", machine learning and artificial intelligence, not only in the society in general, but also in drug discovery, it is expected that the cheminformatics field will be even more important in the future. Traditional areas like virtual screening, library design and high-throughput screening analysis are highlighted in this review. Applying machine learning in drug discovery is an area that has become very important. Applications of machine learning in early drug discovery has been extended from predicting ADME properties and target activity to tasks like de novo molecular design and prediction of chemical reactions.

Maximal Unbiased Benchmarking Data Sets for Human Chemokine Receptors and Comparative Analysis

Chemokine receptors (CRs) have long been druggable targets for the treatment of inflammatory diseases and HIV-1 infection. As a powerful technique, virtual screening (VS) has been widely applied to identifying small molecule leads for modern drug targets including CRs. For rational selection of a wide variety of VS approaches, ligand enrichment assessment based on a benchmarking data set has become an indispensable practice. However, the lack of versatile benchmarking sets for the whole CRs family that are able to unbiasedly evaluate every single approach including both structure- and ligand-based VS somewhat hinders modern drug discovery efforts. To address this issue, we constructed Maximal Unbiased Benchmarking Data sets for human Chemokine Receptors (MUBD-hCRs) using our recently developed tools of MUBD-DecoyMaker. The MUBD-hCRs encompasses 13 subtypes out of 20 chemokine receptors, composed of 404 ligands and 15756 decoys so far and is readily expandable in the future. It had been thoroughly validated that MUBD-hCRs ligands are chemically diverse while its decoys are maximal unbiased in terms of "artificial enrichment", "analogue bias". In addition, we studied the performance of MUBD-hCRs, in particular CXCR4 and CCR5 data sets, in ligand enrichment assessments of both structure- and ligand-based VS approaches in comparison with other benchmarking data sets available in the public domain and demonstrated that MUBD-hCRs is very capable of designating the optimal VS approach. MUBD-hCRs is a unique and maximal unbiased benchmarking set that covers major CRs subtypes so far.

Classifiers and their Metrics Quantified

Molecular modeling frequently constructs classification models for the prediction of two‐class entities, such as compound bio(in)activity, chemical property (non)existence, protein (non)interaction, and so forth. The models are evaluated using well known metrics such as accuracy or true positive rates. However, these frequently used metrics applied to retrospective and/or artificially generated prediction datasets can potentially overestimate true performance in actual prospective experiments. Here, we systematically consider metric value surface generation as a consequence of data balance, and propose the computation of an inverse cumulative distribution function taken over a metric surface. The proposed distribution analysis can aid in the selection of metrics when formulating study design. In addition to theoretical analyses, a practical example in chemogenomic virtual screening highlights the care required in metric selection and interpretation.

A Hybrid Virtual Screening Protocol Based on Binding Mode Similarity

In structure-based virtual screening (SBVS), a scoring function is usually applied to rank a database of docked compounds. Docking programs are often successful in reproducing experimental binding modes; however, the estimation of binding affinity still is the Achilles' heel of docking. The integration of SB and ligand-based (LB) methods is considered a promising strategy to increase hit rates in VS. Herein, we describe a hybrid protocol that is based on the assessment of binding mode similarity between docked compounds and a bound reference ligand. In this context, both experimental and computationally modeled poses have been successfully used as references for three-dimensional (3D) similarity calculations. In this chapter, the methods applied in recent validation studies are described.

Strategies of Virtual Screening in Medicinal Chemistry

Virtual screening represents an effective computational strategy to rise-up the chances of finding new bioactive compounds by accelerating the time needed to move from an initial intuition to market. Classically, the most pursued approaches rely on ligand- and structure-based studies, the former employed when structural data information about the target is missing while the latter employed when X-ray/NMR solved or homology models are instead available for the target. The authors will focus on the most advanced techniques applied in this area. In particular, they will survey the key concepts of virtual screening by discussing how to properly select chemical libraries, how to make database curation, how to applying and- and structure-based techniques, how to wisely use post-processing methods. Emphasis will be also given to the most meaningful databases used in VS protocols. For the ease of discussion several examples will be presented.

Automated Inference of Chemical Discriminants of Biological Activity

Ligand-based virtual screening has become a standard technique for the efficient discovery of bioactive small molecules. Following assays to determine the activity of compounds selected by virtual screening, or other approaches in which dozens to thousands of molecules have been tested, machine learning techniques make it straightforward to discover the patterns of chemical groups that correlate with the desired biological activity. Defining the chemical features that generate activity can be used to guide the selection of molecules for subsequent rounds of screening and assaying, as well as help design new, more active molecules for organic synthesis.The quantitative structure-activity relationship machine learning protocols we describe here, using decision trees, random forests, and sequential feature selection, take as input the chemical structure of a single, known active small molecule (e.g., an inhibitor, agonist, or substrate) for comparison with the structure of each tested molecule. Knowledge of the atomic structure of the protein target and its interactions with the active compound are not required. These protocols can be modified and applied to any data set that consists of a series of measured structural, chemical, or other features for each tested molecule, along with the experimentally measured value of the response variable you would like to predict or optimize for your project, for instance, inhibitory activity in a biological assay or ΔG_binding. To illustrate the use of different machine learning algorithms, we step through the analysis of a dataset of inhibitor candidates from virtual screening that were tested recently for their ability to inhibit GPCR-mediated signaling in a vertebrate.

Methods for Virtual Screening of GPCR Targets: Approaches and Challenges

Virtual screening (VS) has become an integral part of the drug discovery process and is a valuable tool for finding novel chemical starting points for GPCR targets. Ligand-based VS makes use of biochemical data for known, active compounds and has been applied successfully to many diverse GPCRs. Recent progress in GPCR X-ray crystallography has made it possible to incorporate detailed structural information into the VS process. This chapter outlines the latest VS techniques along with examples that highlight successful applications of these methods. Best practices for increasing the likelihood of VS success, as well as ongoing challenges, are also discussed.

Chalcone Derivatives: Promising Starting Points for Drug Design

Medicinal chemists continue to be fascinated by chalcone derivatives because of their simple chemistry, ease of hydrogen atom manipulation, straightforward synthesis, and a variety of promising biological activities. However, chalcones have still not garnered deserved attention, especially considering their high potential as chemical sources for designing and developing new effective drugs. In this review, we summarize current methodological developments towards the design and synthesis of new chalcone derivatives and state-of-the-art medicinal chemistry strategies (bioisosterism, molecular hybridization, and pro-drug design). We also highlight the applicability of computer-assisted drug design approaches to chalcones and address how this may contribute to optimizing research outputs and lead to more successful and cost-effective drug discovery endeavors. Lastly, we present successful examples of the use of chalcones and suggest possible solutions to existing limitations.

Small molecules inhibiting Keap1-Nrf2 protein-protein interactions: a novel approach to activate Nrf2 function

Oxidative stress is well recognized to contribute to the cause of a wide range of diseases, such as cancer, diabetes, Alzheimer's disease, arteriosclerosis, and inflammation. The Keap1-Nrf2-ARE pathway plays a critical regulatory role and can protect cells from oxidative stress through activating Nrf2 to induce its downstream phase II enzymes. Nrf2 activation through the covalent inactivation of Keap1 may cause unpredictable side effects. Non-covalent disruption of the Keap1-Nrf2 protein-protein interactions is an alternative strategy for Nrf2 activation, potentially with reduced risk of toxicity. Efforts have been made in recent years to develop peptide- and small molecule-based Keap1-Nrf2 PPI inhibitors via different approaches, including high-throughput screening, target-based virtual screening, structure-based optimization, and fragment-based drug design. This review aims to highlight the recently discovered small-molecule inhibitors as well as their therapeutic potential.

Octopus: a platform for the virtual high-throughput screening of a pool of compounds against a set of molecular targets

Octopus is an automated workflow management tool that is scalable for virtual high-throughput screening (vHTS). It integrates MOPAC2016, MGLTools, PyMOL, and AutoDock Vina. In contrast to other platforms, Octopus can perform docking simulations of an unlimited number of compounds into a set of molecular targets. After generating the ligands in a drawing package in the Protein Data Bank (PDB) format, Octopus can carry out geometry refinement using the semi-empirical method PM7 implemented in MOPAC2016. Docking simulations can be performed using AutoDock Vina and can utilize the Our Own Molecular Targets (OOMT) databank. Finally, the proposed software compiles the best binding energies into a standard table. Here, we describe two successful case studies that were verified by biological assay. In the first case study, the vHTS process was carried out for 22 (phenylamino)urea derivatives. The vHTS process identified a metalloprotease with the PDB code 1GKC as a molecular target for derivative LE&007. In a biological assay, compound LE&007 was found to inhibit 80% of the activity of this enzyme. In the second case study, compound Tx001 was submitted to the Octopus routine, and the results suggested that Plasmodium falciparum ATP6 (PfATP6) as a molecular target for this compound. Following an antimalarial assay, Tx001 was found to have an inhibitory concentration (IC₅₀) of 8.2 μM against PfATP6. These successful examples illustrate the utility of this software for finding appropriate molecular targets for compounds. Hits can then be identified and optimized as new antineoplastic and antimalarial drugs. Finally, Octopus has a friendly Linux-based user interface, and is available at www.drugdiscovery.com.br . Graphical Abstract Octopus: A platform for inverse virtual screening (IVS) to search new molecular targets for drugs.

Human Aquaporin-4 and Molecular Modeling: Historical Perspective and View to the Future

Among the different aquaporins (AQPs), human aquaporin-4 (hAQP4) has attracted the greatest interest in recent years as a new promising therapeutic target. Such a membrane protein is, in fact, involved in a multiple sclerosis-like immunopathology called Neuromyelitis Optica (NMO) and in several disorders resulting from imbalanced water homeostasis such as deafness and cerebral edema. The gap of knowledge in its functioning and dynamics at the atomistic level of detail has hindered the development of rational strategies for designing hAQP4 modulators. The application, lately, of molecular modeling has proved able to fill this gap providing a breeding ground to rationally address compounds targeting hAQP4. In this review, we give an overview of the important advances obtained in this field through the application of Molecular Dynamics (MD) and other complementary modeling techniques. The case studies presented herein are discussed with the aim of providing important clues for computational chemists and biophysicists interested in this field and looking for new challenges.

Modern approaches to accelerate discovery of new antischistosomal drugs

INTRODUCTION

The almost exclusive use of only praziquantel for the treatment of schistosomiasis has raised concerns about the possible emergence of drug-resistant schistosomes. Consequently, there is an urgent need for new antischistosomal drugs. The identification of leads and the generation of high quality data are crucial steps in the early stages of schistosome drug discovery projects.

AREAS COVERED

Herein, the authors focus on the current developments in antischistosomal lead discovery, specifically referring to the use of automated in vitro target-based and whole-organism screens and virtual screening of chemical databases. They highlight the strengths and pitfalls of each of the above-mentioned approaches, and suggest possible roadmaps towards the integration of several strategies, which may contribute for optimizing research outputs and led to more successful and cost-effective drug discovery endeavors.

EXPERT OPINION

Increasing partnerships and access to funding for drug discovery have strengthened the battle against schistosomiasis in recent years. However, the authors believe this battle also includes innovative strategies to overcome scientific challenges. In this context, significant advances of in vitro screening as well as computer-aided drug discovery have contributed to increase the success rate and reduce the costs of drug discovery campaigns. Although some of these approaches were already used in current antischistosomal lead discovery pipelines, the integration of these strategies in a solid workflow should allow the production of new treatments for schistosomiasis in the near future.

Adapting Document Similarity Measures for Ligand-Based Virtual Screening

Quantifying the similarity of molecules is considered one of the major tasks in virtual screening. There are many similarity measures that have been proposed for this purpose, some of which have been derived from document and text retrieving areas as most often these similarity methods give good results in document retrieval and can achieve good results in virtual screening. In this work, we propose a similarity measure for ligand-based virtual screening, which has been derived from a text processing similarity measure. It has been adopted to be suitable for virtual screening; we called this proposed measure the Adapted Similarity Measure of Text Processing (ASMTP). For evaluating and testing the proposed ASMTP we conducted several experiments on two different benchmark datasets: the Maximum Unbiased Validation (MUV) and the MDL Drug Data Report (MDDR). The experiments have been conducted by choosing 10 reference structures from each class randomly as queries and evaluate them in the recall of cut-offs at 1% and 5%. The overall obtained results are compared with some similarity methods including the Tanimoto coefficient, which are considered to be the conventional and standard similarity coefficients for fingerprint-based similarity calculations. The achieved results show that the performance of ligand-based virtual screening is better and outperforms the Tanimoto coefficients and other methods.

Accurate and efficient target prediction using a potency-sensitive influence-relevance voter

BACKGROUND

A number of algorithms have been proposed to predict the biological targets of diverse molecules. Some are structure-based, but the most common are ligand-based and use chemical fingerprints and the notion of chemical similarity. These methods tend to be computationally faster than others, making them particularly attractive tools as the amount of available data grows.

RESULTS

Using a ChEMBL-derived database covering 490,760 molecule-protein interactions and 3236 protein targets, we conduct a large-scale assessment of the performance of several target-prediction algorithms at predicting drug-target activity. We assess algorithm performance using three validation procedures: standard tenfold cross-validation, tenfold cross-validation in a simulated screen that includes random inactive molecules, and validation on an external test set composed of molecules not present in our database.

CONCLUSIONS

We present two improvements over current practice. First, using a modified version of the influence-relevance voter (IRV), we show that using molecule potency data can improve target prediction. Second, we demonstrate that random inactive molecules added during training can boost the accuracy of several algorithms in realistic target-prediction experiments. Our potency-sensitive version of the IRV (PS-IRV) obtains the best results on large test sets in most of the experiments. Models and software are publicly accessible through the chemoinformatics portal at http://chemdb.ics.uci.edu/.

Integrating sampling techniques and inverse virtual screening: toward the discovery of artificial peptide-based receptors for ligands

A novel heuristic using an iterative select-and-purge strategy is proposed. It combines statistical techniques for sampling and classification by rigid molecular docking through an inverse virtual screening scheme. This approach aims to the de novo discovery of short peptides that may act as docking receptors for small target molecules when there are no data available about known association complexes between them. The algorithm performs an unbiased stochastic exploration of the sample space, acting as a binary classifier when analyzing the entire peptides population. It uses a novel and effective criterion for weighting the likelihood of a given peptide to form an association complex with a particular ligand molecule based on amino acid sequences. The exploratory analysis relies on chemical information of peptides composition, sequence patterns, and association free energies (docking scores) in order to converge to those peptides forming the association complexes with higher affinities. Statistical estimations support these results providing an association probability by improving predictions accuracy even in cases where only a fraction of all possible combinations are sampled. False positives/false negatives ratio was also improved with this method. A simple rigid-body docking approach together with the proper information about amino acid sequences was used. The methodology was applied in a retrospective docking study to all 8000 possible tripeptide combinations using the 20 natural amino acids, screened against a training set of 77 different ligands with diverse functional groups. Afterward, all tripeptides were screened against a test set of 82 ligands, also containing different functional groups. Results show that our integrated methodology is capable of finding a representative group of the top-scoring tripeptides. The associated probability of identifying the best receptor or a group of the top-ranked receptors is more than double and about 10 times higher, respectively, when compared to classical random sampling methods.

Virtual Screening for UDP-Galactopyranose Mutase Ligands Identifies a New Class of Antimycobacterial Agents

Galactofuranose (Galf) is present in glycans critical for the virulence and viability of several pathogenic microbes, including Mycobacterium tuberculosis, yet the monosaccharide is absent from mammalian glycans. Uridine 5'-diphosphate-galactopyranose mutase (UGM) catalyzes the formation of UDP-Galf, which is required to produce Galf-containing glycoconjugates. Inhibitors of UGM have therefore been sought, both as antimicrobial leads and as tools to delineate the roles of Galf in cells. Obtaining cell permeable UGM probes by either design or high throughput screens has been difficult, as has elucidating how UGM binds small molecule, noncarbohydrate inhibitors. To address these issues, we employed structure-based virtual screening to uncover new inhibitor chemotypes, including a triazolothiadiazine series. These compounds are among the most potent antimycobacterial UGM inhibitors described. They also facilitated determination of a UGM-small molecule inhibitor structure, which can guide optimization. A comparison of results from the computational screen and a high-throughput fluorescence polarization (FP) screen indicated that the scaffold hits from the former had been evaluated in the FP screen but missed. By focusing on promising compounds, the virtual screen rescued false negatives, providing a blueprint for generating new UGM probes and therapeutic leads.