A novel interaction fingerprint derived from per atom score contributions: exhaustive evaluation of interaction fingerprint performance in docking based virtual screening

Machine-learning-assisted high-throughput identification of potent and stable neutralizing antibodies against all four dengue virus serotypes

Several computational methods have been developed to identify neutralizing antibodies (NAbs) covering four dengue virus serotypes (DENV-1 to DENV-4); however, limitations of the dataset and the resulting performance remain. Here, we developed a new computational framework to predict potent and stable NAbs against DENV-1 to DENV-4 using only antibody (CDR-H3) and epitope sequences as input. Specifically, our proposed computational framework employed sequence-based ML and molecular dynamic simulation (MD) methods to achieve more accurate identification. First, we built a novel dataset (n = 1108) by compiling the interactions of CDR-H3 and epitope sequences with the half maximum inhibitory concentration (IC50) values, which represent neutralizing activities. Second, we achieved an accurately predictive ML model that showed high AUC values of 0.879 and 0.885 by tenfold cross-validation and independent tests, respectively. Finally, our computational framework could be applied to filter approximately 2.5 million unseen antibodies into two final candidates that showed strong and stable binding to all four serotypes. In addition, the most potent and stable candidate (1B3B9_V21) was evaluated for its development potential as a therapeutic agent by molecular docking and MD simulations. This study provides an antibody computational approach to facilitate the high-throughput identification of NAbs and accelerate the development of therapeutic antibodies.

Systematic analysis, aggregation and visualisation of interaction fingerprints for molecular dynamics simulation data

Computational methods such as molecular docking or molecular dynamics (MD) simulations have been developed to simulate and explore the interactions between biomolecules. However, the interactions obtained using these methods are difficult to analyse and evaluate. Interaction fingerprints (IFPs) have been proposed to derive interactions from static 3D coordinates and transform them into 1D bit vectors. More recently, the concept has been applied to derive IFPs from MD simulations, which adds a layer of complexity by adding the temporal motion and dynamics of a system. As a result, many IFPs are obtained from one MD simulation, resulting in a large number of individual IFPs that are difficult to analyse compared to IFPs derived from static 3D structures. Scientific contribution: We introduce a new method to systematically aggregate IFPs derived from MD simulation data. In addition, we propose visualisations to effectively analyse and compare IFPs derived from MD simulation data to account for the temporal evolution of interactions and to compare IFPs across different MD simulations. This has been implemented as a freely available Python library and can therefore be easily adopted by other researchers and to different MD simulation datasets.

3D-QSAR, docking and molecular dynamics simulations of novel Pyrazolo-pyridazinone derivatives as covalent inhibitors of FGFR1: a scientific approach for possible anticancer agents

Developing highly potent covalent inhibitors of Fibroblast growth factor receptors 1 (FGFR1) has always been a challenging task. In the current study, various computational techniques, such as 3D-QSAR, covalent docking, fingerprinting analysis, MD simulation followed by MMGB/PBSA, and per-residue energy decomposition analysis were used to explore the binding mechanism of pyrazolo[3,4-d]pyridazinone derivatives to FGFR1. The high q2 and r2 values for the CoMFA and CoMSIA models, suggest that the constructed 3D-QSAR models could reliably predict the bioactivities of FGFR1 inhibitors. The structural requirements revealed by the model's contour maps were strategically used to computationally create an in-house library of more than 100 new FGFR1 inhibitors using the R-group exploration technique implemented in the SparkTM software. The compounds from the in-house library were also mapped in the 3D-QSAR model that predicts comparable pIC50 values with the experimental values. A comparison between 3D-QSAR generated contours and molecular docking conformation of ligands was performed to reveal the fundamentals to design potent FGFR1 covalent inhibitors. The estimated binding free energies (MMGB/PBSA) for the selected compounds were in agreement with the experimental value ranking of their binding affinities towards FGFR1. Furthermore, per-residue energy decomposition analysis has identified Arg627 and Glu531 to contribute significantly in improved binding affinity of compound W16. During ADME analysis, the majority of in-house library compounds exhibited pharmacokinetic properties superior to those of experimentally produced compounds. These new compounds may help researchers better understand FGFR1 inhibition and lead to the creation of novel, potent FGFR1 inhibitors.Communicated by Ramaswamy H. Sarma.

Integrated computational approaches for designing potent pyrimidine-based CDK9 inhibitors: 3D-QSAR, docking, and molecular dynamics simulations

CDK9 is an emerging target for the development of anticancer drugs. The development of CDK9 inhibitors with significant potency had consistently posed a formidable challenge. In the current research, a number of computational methodologies, such as, 3D-QSAR, molecular docking, fingerprint analysis, molecular dynamic (MD) simulations followed by MMGB/PBSA and ADMET studies were used systemically to uncover the binding mechanism of pyrimidine derivatives against CDK9. The CoMFA and CoMSIA models having high q2 (0.53, 0.54) and r2 values (0.96, 0.93) respectively indicating that model could accurately predict the bioactivities of CDK9 inhibitors. Using the R-group exploration technique implemented by the Spark™ by Cresset group, the structural requirements revealed by the contour maps of model were utilized strategically to create an in-house library of 100 new CDK9 inhibitors. Additionally, the compounds from the in-house library were mapped into 3D-QSAR model which predicted pIC50 values comparable to the experimental values. A comparison between 3D-QSAR generated contours and molecular docking conformation of ligands was performed to elucidate the essentials of CDK9 inhibitor design. MD simulations (100 ns) were performed on the selected docked complexes A21, A14 and D98 which contributed in validating the binding interactions. According to the findings of binding free energy analysis (MMGB/PBSA), It was observed that residues CYS106 and GLU107 had a considerable tendency to facilitate ligand-protein interactions via H-bond interactions. The aforementioned findings have the potential to enhance researchers comprehension of the mechanism underlying CDK9 inhibition and may be utilized in the development of innovative and efficacious CDK9 inhibitors.

Improving structure-based protein-ligand affinity prediction by graph representation learning and ensemble learning

Predicting protein-ligand binding affinity presents a viable solution for accelerating the discovery of new lead compounds. The recent widespread application of machine learning approaches, especially graph neural networks, has brought new advancements in this field. However, some existing structure-based methods treat protein macromolecules and ligand small molecules in the same way and ignore the data heterogeneity, potentially leading to incomplete exploration of the biochemical information of ligands. In this work, we propose LGN, a graph neural network-based fusion model with extra ligand feature extraction to effectively capture local features and global features within the protein-ligand complex, and make use of interaction fingerprints. By combining the ligand-based features and interaction fingerprints, LGN achieves Pearson correlation coefficients of up to 0.842 on the PDBbind 2016 core set, compared to 0.807 when using the features of complex graphs alone. Finally, we verify the rationalization and generalization of our model through comprehensive experiments. We also compare our model with state-of-the-art baseline methods, which validates the superiority of our model. To reduce the impact of data similarity, we increase the robustness of the model by incorporating ensemble learning.

MetalProGNet: a structure-based deep graph model for metalloprotein-ligand interaction predictions

Metalloproteins play indispensable roles in various biological processes ranging from reaction catalysis to free radical scavenging, and they are also pertinent to numerous pathologies including cancer, HIV infection, neurodegeneration, and inflammation. Discovery of high-affinity ligands for metalloproteins powers the treatment of these pathologies. Extensive efforts have been made to develop in silico approaches, such as molecular docking and machine learning (ML)-based models, for fast identification of ligands binding to heterogeneous proteins, but few of them have exclusively concentrated on metalloproteins. In this study, we first compiled the largest metalloprotein-ligand complex dataset containing 3079 high-quality structures, and systematically evaluated the scoring and docking powers of three competitive docking tools (i.e., PLANTS, AutoDock Vina and Glide SP) for metalloproteins. Then, a structure-based deep graph model called MetalProGNet was developed to predict metalloprotein-ligand interactions. In the model, the coordination interactions between metal ions and protein atoms and the interactions between metal ions and ligand atoms were explicitly modelled through graph convolution. The binding features were then predicted by the informative molecular binding vector learned from a noncovalent atom-atom interaction network. The evaluation on the internal metalloprotein test set, the independent ChEMBL dataset towards 22 different metalloproteins and the virtual screening dataset indicated that MetalProGNet outperformed various baselines. Finally, a noncovalent atom-atom interaction masking technique was employed to interpret MetalProGNet, and the learned knowledge accords with our understanding of physics.

Concepts and applications of chemical fingerprint for hit and lead screening

Molecular fingerprints are used to represent chemical (structural, physicochemical, etc.) properties of large-scale chemical sets in a low computational cost way. They have a prominent role in transforming chemical data sets into consistent input formats (bit strings or numeric values) suitable for in silico approaches. In this review, we summarize and classify common and state-of-the-art fingerprints into eight different types (dictionary based, circular, topological, pharmacophore, protein-ligand interaction, shape based, reinforced, and multi). We also highlight applications of fingerprints in early drug research and development (R&D). Thus, this review provides a guide for the selection of appropriate fingerprints of compounds (or ligand-protein complexes) for use in drug R&D.

Combined docking and machine learning identify key molecular determinants of ligand pharmacological activity on β2 adrenoceptor

G protein‐coupled receptors (GPCRs) are valuable therapeutic targets for many diseases. A central question of GPCR drug discovery is to understand what determines the agonism or antagonism of ligands that bind them. Ligands exert their action via the interactions in the ligand binding pocket. We hypothesized that there is a common set of receptor interactions made by ligands of diverse structures that mediate their action and that among a large dataset of different ligands, the functionally important interactions will be over‐represented. We computationally docked ~2700 known β2AR ligands to multiple β2AR structures, generating ca 75 000 docking poses and predicted all atomic interactions between the receptor and the ligand. We used machine learning (ML) techniques to identify specific interactions that correlate with the agonist or antagonist activity of these ligands. We demonstrate with the application of ML methods that it is possible to identify the key interactions associated with agonism or antagonism of ligands. The most representative interactions for agonist ligands involve K97^2.68×67, F194^ECL2, S203^5.42×43, S204^5.43×44, S207^5.46×641, H296^6.58×58, and K305^7.32×31. Meanwhile, the antagonist ligands made interactions with W286^6.48×48 and Y316^7.43×42, both residues considered to be important in GPCR activation. The interpretation of ML analysis in human understandable form allowed us to construct an exquisitely detailed structure‐activity relationship that identifies small changes to the ligands that invert their pharmacological activity and thus helps to guide the drug discovery process. This approach can be readily applied to any drug target.

Scoring Functions for Protein-Ligand Binding Affinity Prediction using Structure-Based Deep Learning: A Review

The rapid and accurate in silico prediction of protein-ligand binding free energies or binding affinities has the potential to transform drug discovery. In recent years, there has been a rapid growth of interest in deep learning methods for the prediction of protein-ligand binding affinities based on the structural information of protein-ligand complexes. These structure-based scoring functions often obtain better results than classical scoring functions when applied within their applicability domain. Here we review structure-based scoring functions for binding affinity prediction based on deep learning, focussing on different types of architectures, featurization strategies, data sets, methods for training and evaluation, and the role of explainable artificial intelligence in building useful models for real drug-discovery applications.

fingeRNAt—A novel tool for high-throughput analysis of nucleic acid-ligand interactions

Computational methods play a pivotal role in drug discovery and are widely applied in virtual screening, structure optimization, and compound activity profiling. Over the last decades, almost all the attention in medicinal chemistry has been directed to protein-ligand binding, and computational tools have been created with this target in mind. With novel discoveries of functional RNAs and their possible applications, RNAs have gained considerable attention as potential drug targets. However, the availability of bioinformatics tools for nucleic acids is limited. Here, we introduce fingeRNAt—a software tool for detecting non-covalent interactions formed in complexes of nucleic acids with ligands. The program detects nine types of interactions: (i) hydrogen and (ii) halogen bonds, (iii) cation-anion, (iv) pi-cation, (v) pi-anion, (vi) pi-stacking, (vii) inorganic ion-mediated, (viii) water-mediated, and (ix) lipophilic interactions. However, the scope of detected interactions can be easily expanded using a simple plugin system. In addition, detected interactions can be visualized using the associated PyMOL plugin, which facilitates the analysis of medium-throughput molecular complexes. Interactions are also encoded and stored as a bioinformatics-friendly Structural Interaction Fingerprint (SIFt)—a binary string where the respective bit in the fingerprint is set to 1 if a particular interaction is present and to 0 otherwise. This output format, in turn, enables high-throughput analysis of interaction data using data analysis techniques. We present applications of fingeRNAt-generated interaction fingerprints for visual and computational analysis of RNA-ligand complexes, including analysis of interactions formed in experimentally determined RNA-small molecule ligand complexes deposited in the Protein Data Bank. We propose interaction fingerprint-based similarity as an alternative measure to RMSD to recapitulate complexes with similar interactions but different folding. We present an application of interaction fingerprints for the clustering of molecular complexes. This approach can be used to group ligands that form similar binding networks and thus have similar biological properties. The fingeRNAt software is freely available at https://github.com/n-szulc/fingeRNAt.

Discovery of microtubule stabilizers with novel scaffold structures based on virtual screening, biological evaluation, and molecular dynamics simulation

Disrupting the dynamics and structures of microtubules can perturb mitotic spindle formation, cause cell cycle arrest in G2/M phase, and subsequently lead to cellular death via apoptosis. In this investigation, the structure-based virtual screening methods, including molecular docking and rescoring, and similarity analysis of interaction molecular fingerprints, were developed to discover novel tubulin inhibitors from ChemDiv database with 1,601,806 compounds. The screened compounds were further filtered by PAINS, ADME/T, Toxscore, SAscore, and Drug-likeness analysis. Finally, 17 hit compounds were selected, and then submitted to the biologic evaluation. Among these hits, the P2 exhibited the strongest antiproliferative activity against four tumor cells including HeLa, HepG2, MCF-7, and A549. The in vitro tubulin polymerization assay revealed P2 could promote tubulin polymerization in a dose dependent manner. Finally, in order to analyze the interaction modes of complexes, the molecular dynamics simulation was performed to investigate the interactions between P2 and tubulin. The molecular dynamics simulation analysis showed that P2 could stably bind to taxane site, induced H6-H7, B9-B10, and M-loop regions changes. The ΔG_bind energies of tubulin-P2 and tubulin-paclitaxel were -68.25 ± 12.98 and -146.05 ± 16.17 kJ mol^-1, respectively, which were in line with the results of the experimental test. Therefore, P2 has been well characterized as lead compounds for developing new tubulin inhibitors with potential anticancer activity.

Structure-based protein-ligand interaction fingerprints for binding affinity prediction

Binding affinity prediction (BAP) using protein–ligand complex structures is crucial to computer-aided drug design, but remains a challenging problem. To achieve efficient and accurate BAP, machine-learning scoring functions (SFs) based on a wide range of descriptors have been developed. Among those descriptors, protein–ligand interaction fingerprints (IFPs) are competitive due to their simple representations, elaborate profiles of key interactions and easy collaborations with machine-learning algorithms. In this paper, we have adopted a building-block-based taxonomy to review a broad range of IFP models, and compared representative IFP-based SFs in target-specific and generic scoring tasks. Atom-pair-counts-based and substructure-based IFPs show great potential in these tasks.

ProLIF: a library to encode molecular interactions as fingerprints

Interaction fingerprints are vector representations that summarize the three-dimensional nature of interactions in molecular complexes, typically formed between a protein and a ligand. This kind of encoding has found many applications in drug-discovery projects, from structure-based virtual-screening to machine-learning. Here, we present ProLIF, a Python library designed to generate interaction fingerprints for molecular complexes extracted from molecular dynamics trajectories, experimental structures, and docking simulations. It can handle complexes formed of any combination of ligand, protein, DNA, or RNA molecules. The available interaction types can be fully reparametrized or extended by user-defined ones. Several tutorials that cover typical use-case scenarios are available, and the documentation is accompanied with code snippets showcasing the integration with other data-analysis libraries for a more seamless user-experience. The library can be freely installed from our GitHub repository (https://github.com/chemosim-lab/ProLIF).

Computational representations of protein-ligand interfaces for structure-based virtual screening

Introduction: Structure-based virtual screening (SBVS) is an essential strategy for hit identification. SBVS primarily uses molecular docking, which exploits the protein-ligand binding mode and associated affinity score for compound ranking. Previous studies have shown that computational representation of protein-ligand interfaces and the later establishment of machine learning models are efficacious in improving the accuracy of SBVS.Areas covered: The authors review the computational methods for representing protein-ligand interfaces, which include the traditional ones that use deliberately designed fingerprints and descriptors and the more recent methods that automatically extract features with deep learning. The effects of these methods on the performance of machine learning models are briefly discussed. Additionally, case studies that applied various computational representations to machine learning are cited with remarks.Expert opinion: It has become a trend to extract binding features automatically by deep learning, which uses a completely end-to-end representation. However, there is still plenty of scope for improvement . The interpretability of deep-learning models, the organization of data management, the quantity and quality of available data, and the optimization of hyperparameters could impact the accuracy of feature extraction. In addition, other important structural factors such as water molecules and protein flexibility should be considered.

Deep Learning in Virtual Screening: Recent Applications and Developments

Drug discovery is a cost and time-intensive process that is often assisted by computational methods, such as virtual screening, to speed up and guide the design of new compounds. For many years, machine learning methods have been successfully applied in the context of computer-aided drug discovery. Recently, thanks to the rise of novel technologies as well as the increasing amount of available chemical and bioactivity data, deep learning has gained a tremendous impact in rational active compound discovery. Herein, recent applications and developments of machine learning, with a focus on deep learning, in virtual screening for active compound design are reviewed. This includes introducing different compound and protein encodings, deep learning techniques as well as frequently used bioactivity and benchmark data sets for model training and testing. Finally, the present state-of-the-art, including the current challenges and emerging problems, are examined and discussed.

Structure-based virtual screening for novel potential selective inhibitors of class IIa histone deacetylases for cancer treatment

The fundamental cause of human cancer is strongly influenced by down- or up-regulations of epigenetic factors. Upregulated histone deacetylases (HDAC) have been shown to be effectively neutralized by the action of HDACs inhibitors (HDACi). However, cytotoxicity has been reported in normal cells because of non-specificity of several available HDACis that are in clinical use or at different phases of clinical trials. Because of the high amino acid sequence and structural similarity among HDAC enzymes, it is believed to be a challenging task to obtain isoform-selectivity. The essential aim of the present research work was to identify isoform-selective inhibitors against class IIa HDACs via structure-based drug design. Based on the highest binding affinity and isoform-selectivity, the top-ranked inhibitors were in silico tested for their absorption, distribution, metabolism, elimination, and toxicity (ADMET) properties, which were classified as drug-like compounds. Later, molecular dynamics simulation (MD) was carried out for all compound-protein complexes to evaluate the structural stability and the biding mode of the inhibitors, which showed high stability throughout the 100 ns simulation. Free binding energy predictions by MM-PBSA method showed the high binding affinity of the identified compounds toward their respective targets. Hence, these inhibitors could be used as drug candidates or as lead compounds for more in silico or in vitro optimization to design safe isoform-selective HDACs inhibitors.

Merging Ligand-Based and Structure-Based Methods in Drug Discovery: An Overview of Combined Virtual Screening Approaches

Virtual screening (VS) is an outstanding cornerstone in the drug discovery pipeline. A variety of computational approaches, which are generally classified as ligand-based (LB) and structure-based (SB) techniques, exploit key structural and physicochemical properties of ligands and targets to enable the screening of virtual libraries in the search of active compounds. Though LB and SB methods have found widespread application in the discovery of novel drug-like candidates, their complementary natures have stimulated continued efforts toward the development of hybrid strategies that combine LB and SB techniques, integrating them in a holistic computational framework that exploits the available information of both ligand and target to enhance the success of drug discovery projects. In this review, we analyze the main strategies and concepts that have emerged in the last years for defining hybrid LB + SB computational schemes in VS studies. Particularly, attention is focused on the combination of molecular similarity and docking, illustrating them with selected applications taken from the literature.

Structure-guided screening of chemical database to identify NS3-NS2B inhibitors for effective therapeutic application in dengue infection

Dengue infection is the most common arthropod-borne disease caused by dengue viruses, predominantly affecting millions of human beings annually. To find out promising chemical entities for therapeutic application in Dengue, in the current research, a multi-step virtual screening effort was conceived to screen out the entire "screening library" of the Asinex database. Initially, through "Lipinski rule of five" filtration criterion almost 0.6 million compounds were collected and docked with NS3-NS2B protein. Thereby, the chemical space was reduced to about 3500 compounds through the analysis of binding affinity obtained from molecular docking study in AutoDock Vina. Further, the "Virtual Screening Workflow" (VSW) utility of Schrödinger suite was used, which follows a stepwise multiple docking programs such as - high-throughput virtual screening (HTVS), standard precision (SP), and extra precision (XP) docking, and in postprocessing analysis the MM-GBSA based free binding energy calculation. Finally, five potent molecules were proposed as potential inhibitors for the dengue NS3-NS2B protein based on the investigation of molecular interactions map and protein-ligand fingerprint analyses. Different pharmacokinetics and drug-likeness parameters were also checked, which favour the potentiality of selected molecules for being drug-like candidates. The molecular dynamics (MD) simulation analyses of protein-ligand complexes were explained that NS3-NS2B bound with proposed molecules quite stable in dynamic states as observed from the root means square deviation (RMSD) and root means square fluctuation (RMSF) parameters. The binding free energy was calculated using MM-GBSA method from the MD simulation trajectories revealed that all proposed molecules possess such a strong binding affinity towards the dengue NS3-NS2B protein. Therefore, proposed molecules may be potential chemical components for effective inhibition of dengue NS3-NS2B protein subjected to experimental validation.

Investigation of Crystal Structures in Structure-Based Virtual Screening for Protein Kinase Inhibitors

Protein kinases are important drug targets in several therapeutic areas ,and structure-based virtual screening (SBVS) is an important strategy in discovering lead compounds for kinase targets. However, there are multiple crystal structures available for each target, and determining which one is the most favorable is a key step in molecular docking for SBVS due to the ligand induce-fit effect. This work aimed to find the most desirable crystal structures for molecular docking by a comprehensive analysis of the protein kinase database which covers 190 different kinases from all eight main kinase families. Through an integrated self-docking and cross-docking evaluation, 86 targets were eventually evaluated on a total of 2608 crystal structures. Results showed that molecular docking has great capability in reproducing conformation of crystallized ligands and for each target, the most favorable crystal structure was selected, and the AGC family outperformed the other family targets based on RMSD comparison. In addition, RMSD values, GlideScore, and corresponding bioactivity data were compared and demonstrated certain relationships. This work provides great convenience for researchers to directly select the optimal crystal structure in SBVS-based kinase drug design and further validates the effectiveness of molecular docking in drug discovery.

Molecular Docking: Shifting Paradigms in Drug Discovery

Molecular docking is an established in silico structure-based method widely used in drug discovery. Docking enables the identification of novel compounds of therapeutic interest, predicting ligand-target interactions at a molecular level, or delineating structure-activity relationships (SAR), without knowing a priori the chemical structure of other target modulators. Although it was originally developed to help understanding the mechanisms of molecular recognition between small and large molecules, uses and applications of docking in drug discovery have heavily changed over the last years. In this review, we describe how molecular docking was firstly applied to assist in drug discovery tasks. Then, we illustrate newer and emergent uses and applications of docking, including prediction of adverse effects, polypharmacology, drug repurposing, and target fishing and profiling, discussing also future applications and further potential of this technique when combined with emergent techniques, such as artificial intelligence.

Profiling the interaction of 1-phenylbenzimidazoles to cyclooxygenases

In the design of 1-phenylbenzimidazoles as model cyclooxygenase (COX) inhibitors, docking to a series of crystallographic COX structures was performed to evaluate their potential for high-affinity binding and to reproduce the interaction profile of well-known COX inhibitors. The effect of ligand-specific induced fit on the calculations was also studied. To quantitatively compare the pattern of interactions of model compounds to the profile of several cocrystallized COX inhibitors, a geometric parameter, denominated ligand-receptor contact distance (LRCD), was developed. The interaction profile of several model complexes showed similarity to the profile of COX complexes with inhibitors such as iodosuprofen, iodoindomethacin, diclofenac, and flurbiprofen. Shaping of high-affinity binding sites upon ligand-specific induced fit mostly determined both the affinity and the binding mode of the ligands in the docking calculations. The results suggest potential of 1-phenylbenzimidazole derivatives as COX inhibitors on the basis of their predicted affinity and interaction profile to COX enzymes. The analyses also provided insights into the role of induced fit in COX enzymes. While inhibitors produce different local structural changes at the COX ligand binding site, induced fit allows inhibitors in diverse chemical classes to share characteristic interaction patterns that ensure key contacts to be achieved. Different interaction patterns may also be associated with different inhibitory mechanisms.

Rescoring and Linearly Combining: A Highly Effective Consensus Strategy for Virtual Screening Campaigns

The study proposes a novel consensus strategy based on linear combinations of different docking scores to be used in the evaluation of virtual screening campaigns. The consensus models are generated by applying the recently proposed Enrichment Factor Optimization (EFO) method, which develops the linear equations by exhaustively combining the available docking scores and by optimizing the resulting enrichment factors. The performances of such a consensus strategy were evaluated by simulating the entire Directory of Useful Decoys (DUD datasets). In detail, the poses were initially generated by the PLANTS docking program and then rescored by ReScore+ with and without the minimization of the complexes. The so calculated scores were then used to generate the mentioned consensus models including two or three different scoring functions. The reliability of the generated models was assessed by a per target validation as performed by default by the EFO approach. The encouraging performances of the here proposed consensus strategy are emphasized by the average increase of the 17% in the Top 1% enrichment factor (EF) values when comparing the single best score with the linear combination of three scores. Specifically, kinases offer a truly convincing demonstration of the efficacy of the here proposed consensus strategy since their Top 1% EF average ranges from 6.4 when using the single best performing primary score to 23.5 when linearly combining scoring functions. The beneficial effects of this consensus approach are clearly noticeable even when considering the entire DUD datasets as evidenced by the area under the curve (AUC) averages revealing a 14% increase when combining three scores. The reached AUC values compare very well with those reported in literature by an extended set of recent benchmarking studies and the three-variable models afford the highest AUC average.

Binding mode information improves fragment docking

Docking is commonly used in drug discovery to predict how ligand binds to protein target. Best programs are generally able to generate a correct solution, yet often fail to identify it. In the case of drug-like molecules, the correct and incorrect poses can be sorted by similarity to the crystallographic structure of the protein in complex with reference ligands. Fragments are particularly sensitive to scoring problems because they are weak ligands which form few interactions with protein. In the present study, we assessed the utility of binding mode information in fragment pose prediction. We compared three approaches: interaction fingerprints, 3D-matching of interaction patterns and 3D-matching of shapes. We prepared a test set composed of high-quality structures of the Protein Data Bank. We generated and evaluated the docking poses of 586 fragment/protein complexes. We observed that the best approach is twice as accurate as the native scoring function, and that post-processing is less effective for smaller fragments. Interestingly, fragments and drug-like molecules both proved to be useful references. In the discussion, we suggest the best conditions for a successful pose prediction with the three approaches.

Life beyond the Tanimoto coefficient: similarity measures for interaction fingerprints

Background

Interaction fingerprints (IFP) have been repeatedly shown to be valuable tools in virtual screening to identify novel hit compounds that can subsequently be optimized to drug candidates. As a complementary method to ligand docking, IFPs can be applied to quantify the similarity of predicted binding poses to a reference binding pose. For this purpose, a large number of similarity metrics can be applied, and various parameters of the IFPs themselves can be customized. In a large-scale comparison, we have assessed the effect of similarity metrics and IFP configurations to a number of virtual screening scenarios with ten different protein targets and thousands of molecules. Particularly, the effect of considering general interaction definitions (such as Any Contact, Backbone Interaction and Sidechain Interaction), the effect of filtering methods and the different groups of similarity metrics were studied.

Results

The performances were primarily compared based on AUC values, but we have also used the original similarity data for the comparison of similarity metrics with several statistical tests and the novel, robust sum of ranking differences (SRD) algorithm. With SRD, we can evaluate the consistency (or concordance) of the various similarity metrics to an ideal reference metric, which is provided by data fusion from the existing metrics. Different aspects of IFP configurations and similarity metrics were examined based on SRD values with analysis of variance (ANOVA) tests.

Conclusion

A general approach is provided that can be applied for the reliable interpretation and usage of similarity measures with interaction fingerprints. Metrics that are viable alternatives to the commonly used Tanimoto coefficient were identified based on a comparison with an ideal reference metric (consensus). A careful selection of the applied bits (interaction definitions) and IFP filtering rules can improve the results of virtual screening (in terms of their agreement with the consensus metric). The open-source Python package FPKit was introduced for the similarity calculations and IFP filtering; it is available at: https://github.com/davidbajusz/fpkit.

Electronic supplementary material

The online version of this article (10.1186/s13321-018-0302-y) contains supplementary material, which is available to authorized users.

Polypharmacology by Design: A Medicinal Chemist's Perspective on Multitargeting Compounds

Multitargeting compounds comprising activity on more than a single biological target have gained remarkable relevance in drug discovery owing to the complexity of multifactorial diseases such as cancer, inflammation, or the metabolic syndrome. Polypharmacological drug profiles can produce additive or synergistic effects while reducing side effects and significantly contribute to the high therapeutic success of indispensable drugs such as aspirin. While their identification has long been the result of serendipity, medicinal chemistry now tends to design polypharmacology. Modern in vitro pharmacological methods and chemical probes allow a systematic search for rational target combinations and recent innovations in computational technologies, crystallography, or fragment-based design equip multitarget compound development with valuable tools. In this Perspective, we analyze the relevance of multiple ligands in drug discovery and the versatile toolbox to design polypharmacology. We conclude that despite some characteristic challenges remaining unresolved, designed polypharmacology holds enormous potential to secure future therapeutic innovation.