Critical Comparison of Virtual Screening Methods against the MUV Data Set

Maximizing the Performance of Similarity-Based Virtual Screening Methods by Generating Synergy from the Integration of 2D and 3D Approaches

Methods for the pairwise comparison of 2D and 3D molecular structures are established approaches in virtual screening. In this work, we explored three strategies for maximizing the virtual screening performance of these methods: (i) the merging of hit lists obtained from multi-compound screening using a single screening method, (ii) the merging of the hit lists obtained from 2D and 3D screening by parallel selection, and (iii) the combination of both of these strategies in an integrated approach. We found that any of these strategies led to a boost in virtual screening performance, with the clearest advantages observed for the integrated approach. On test sets for virtual screening, covering 50 pharmaceutically relevant proteins, the integrated approach, using sets of five query molecules, yielded, on average, an area under the receiver operating characteristic curve (AUC) of 0.84, an early enrichment among the top 1% of ranked compounds (EF1%) of 53.82 and a scaffold recovery rate among the top 1% of ranked compounds (SRR1%) of 0.50. In comparison, the 2D and 3D methods on their own (when using a single query molecule) yielded AUC values of 0.68 and 0.54, EF1% values of 19.96 and 17.52, and SRR1% values of 0.20 and 0.17, respectively. In conclusion, based on these results, the integration of 2D and 3D methods, via a (balanced) parallel selection strategy, is recommended, and, in particular, when combined with multi-query screening.

Systematic comparison of ligand-based and structure-based virtual screening methods on poly (ADP-ribose) polymerase-1 inhibitors

The poly (ADP-ribose) polymerase-1 (PARP1) has been regarded as a vital target in recent years and PARP1 inhibitors can be used for ovarian and breast cancer therapies. However, it has been realized that most of PARP1 inhibitors have disadvantages of low solubility and permeability. Therefore, by discovering more molecules with novel frameworks, it would have greater opportunities to apply it into broader clinical fields and have a more profound significance. In the present study, multiple virtual screening (VS) methods had been employed to evaluate the screening efficiency of ligand-based, structure-based and data fusion methods on PARP1 target. The VS methods include 2D similarity screening, structure-activity relationship (SAR) models, docking and complex-based pharmacophore screening. Moreover, the sum rank, sum score and reciprocal rank were also adopted for data fusion methods. The evaluation results show that the similarity searching based on Torsion fingerprint, six SAR models, Glide docking and pharmacophore screening using Phase have excellent screening performance. The best data fusion method is the reciprocal rank, but the sum score also performs well in framework enrichment. In general, the ligand-based VS methods show better performance on PARP1 inhibitor screening. These findings confirmed that adding ligand-based methods to the early screening stage will greatly improve the screening efficiency, and be able to enrich more highly active PARP1 inhibitors with diverse structures.

Predicting Accurate Lead Structures for Screening Molecular Libraries: A Quantum Crystallographic Approach

Optimization of lead structures is crucial for drug discovery. However, the accuracy of such a prediction using the traditional molecular docking approach remains a major concern. Our study demonstrates that the employment of quantum crystallographic approach-counterpoise corrected kernel energy method (KEM-CP) can improve the accuracy by and large. We select human aldose reductase at 0.66 Å, cyclin dependent kinase 2 at 2.0 Å and estrogen receptor β at 2.7 Å resolutions with active site environment ranging from highly hydrophilic to moderate to highly hydrophobic and several of their known ligands. Overall, the use of KEM-CP alongside the GoldScore resulted superior prediction than the GoldScore alone. Unlike GoldScore, the KEM-CP approach is neither environment-specific nor structural resolution dependent, which highlights its versatility. Further, the ranking of the ligands based on the KEM-CP results correlated well with that of the experimental IC₅₀ values. This computationally inexpensive yet simple approach is expected to ease the process of virtual screening of potent ligands, and it would advance the drug discovery research.

InterLig: improved ligand-based virtual screening using topologically independent structural alignments

Motivation

In the past few years, drug discovery processes have been relying more and more on computational methods to sift out the most promising molecules before time and resources are spent to test them in experimental settings. Whenever the protein target of a given disease is not known, it becomes fundamental to have accurate methods for ligand-based virtual screening, which compares known active molecules against vast libraries of candidate compounds. Recently, 3D-based similarity methods have been developed that are capable of scaffold hopping and to superimpose matching molecules.

Results

Here, we present InterLig, a new method for the comparison and superposition of small molecules using topologically independent alignments of atoms. We test InterLig on a standard benchmark and show that it compares favorably to the best currently available 3D methods.

Availability and implementation

The program is available from http://wallnerlab.org/InterLig.

Supplementary information

Supplementary data are available at Bioinformatics online.

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.

Novel natural non-nucleoside inhibitors of HIV-1 reverse transcriptase identified by shape- and structure-based virtual screening techniques

In this work we report a parallel application of both docking- and shape-based virtual screening (VS) methods, followed by Molecular Dynamics simulations (MDs), for discovering new compounds able to inhibit the human immunodeficiency virus type 1 (HIV-1) reverse transcriptase (RT) RNA-dependent DNA polymerase activity. Specifically, we screened more than 143000 natural compounds commercially available in the ZINC database against the best five RT crystallographic models, taking into account the five approved NNRTIs as query compounds. As a result, 20 hit molecules were selected and tested on biochemical assays for the inhibition of the RNA dependent DNA polymerase RT function and, among them, an indoline pyrrolidine (hit1), an indonyl piperazine (hit2) and an indolyl indolinone (hit3) derivatives were identified as novel non-nucleoside RT inhibitors in the low micromolar range.

Prediction of Compound Profiling Matrices Using Machine Learning

Screening of compound libraries against panels of targets yields profiling matrices. Such matrices typically contain structurally diverse screening compounds, large numbers of inactives, and small numbers of hits per assay. As such, they represent interesting and challenging test cases for computational screening and activity predictions. In this work, modeling of large compound profiling matrices was attempted that were extracted from publicly available screening data. Different machine learning methods including deep learning were compared and different prediction strategies explored. Prediction accuracy varied for assays with different numbers of active compounds, and alternative machine learning approaches often produced comparable results. Deep learning did not further increase the prediction accuracy of standard methods such as random forests or support vector machines. Target-based random forest models were prioritized and yielded successful predictions of active compounds for many assays.

Decoys Selection in Benchmarking Datasets: Overview and Perspectives

Virtual Screening (VS) is designed to prospectively help identifying potential hits, i.e., compounds capable of interacting with a given target and potentially modulate its activity, out of large compound collections. Among the variety of methodologies, it is crucial to select the protocol that is the most adapted to the query/target system under study and that yields the most reliable output. To this aim, the performance of VS methods is commonly evaluated and compared by computing their ability to retrieve active compounds in benchmarking datasets. The benchmarking datasets contain a subset of known active compounds together with a subset of decoys, i.e., assumed non-active molecules. The composition of both the active and the decoy compounds subsets is critical to limit the biases in the evaluation of the VS methods. In this review, we focus on the selection of decoy compounds that has considerably changed over the years, from randomly selected compounds to highly customized or experimentally validated negative compounds. We first outline the evolution of decoys selection in benchmarking databases as well as current benchmarking databases that tend to minimize the introduction of biases, and secondly, we propose recommendations for the selection and the design of benchmarking datasets.

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.

Comparative analysis of chemical similarity methods for modular natural products with a hypothetical structure enumeration algorithm

Natural products represent a prominent source of pharmaceutically and industrially important agents. Calculating the chemical similarity of two molecules is a central task in cheminformatics, with applications at multiple stages of the drug discovery pipeline. Quantifying the similarity of natural products is a particularly important problem, as the biological activities of these molecules have been extensively optimized by natural selection. The large and structurally complex scaffolds of natural products distinguish their physical and chemical properties from those of synthetic compounds. However, no analysis of the performance of existing methods for molecular similarity calculation specific to natural products has been reported to date. Here, we present LEMONS, an algorithm for the enumeration of hypothetical modular natural product structures. We leverage this algorithm to conduct a comparative analysis of molecular similarity methods within the unique chemical space occupied by modular natural products using controlled synthetic data, and comprehensively investigate the impact of diverse biosynthetic parameters on similarity search. We additionally investigate a recently described algorithm for natural product retrobiosynthesis and alignment, and find that when rule-based retrobiosynthesis can be applied, this approach outperforms conventional two-dimensional fingerprints, suggesting it may represent a valuable approach for the targeted exploration of natural product chemical space and microbial genome mining. Our open-source algorithm is an extensible method of enumerating hypothetical natural product structures with diverse potential applications in bioinformatics.

Protein-Ligand Scoring with Convolutional Neural Networks

Computational approaches to drug discovery can reduce the time and cost associated with experimental assays and enable the screening of novel chemotypes. Structure-based drug design methods rely on scoring functions to rank and predict binding affinities and poses. The ever-expanding amount of protein-ligand binding and structural data enables the use of deep machine learning techniques for protein-ligand scoring. We describe convolutional neural network (CNN) scoring functions that take as input a comprehensive three-dimensional (3D) representation of a protein-ligand interaction. A CNN scoring function automatically learns the key features of protein-ligand interactions that correlate with binding. We train and optimize our CNN scoring functions to discriminate between correct and incorrect binding poses and known binders and nonbinders. We find that our CNN scoring function outperforms the AutoDock Vina scoring function when ranking poses both for pose prediction and virtual screening.

Comparing structural fingerprints using a literature-based similarity benchmark

Background

The concept of molecular similarity is one of the central ideas in cheminformatics, despite the fact that it is ill-defined and rather difficult to assess objectively. Here we propose a practical definition of molecular similarity in the context of drug discovery: molecules A and B are similar if a medicinal chemist would be likely to synthesise and test them around the same time as part of the same medicinal chemistry program. The attraction of such a definition is that it matches one of the key uses of similarity measures in early-stage drug discovery. If we make the assumption that molecules in the same compound activity table in a medicinal chemistry paper were considered similar by the authors of the paper, we can create a dataset of similar molecules from the medicinal chemistry literature. Furthermore, molecules with decreasing levels of similarity to a reference can be found by either ordering molecules in an activity table by their activity, or by considering activity tables in different papers which have at least one molecule in common.

Results

Using this procedure with activity data from ChEMBL, we have created two benchmark datasets for structural similarity that can be used to guide the development of improved measures. Compared to similar results from a virtual screen, these benchmarks are an order of magnitude more sensitive to differences between fingerprints both because of their size and because they avoid loss of statistical power due to the use of mean scores or ranks. We measure the performance of 28 different fingerprints on the benchmark sets and compare the results to those from the Riniker and Landrum (J Cheminf 5:26, 2013. doi:10.1186/1758-2946-5-26) ligand-based virtual screening benchmark.

Conclusions

Extended-connectivity fingerprints of diameter 4 and 6 are among the best performing fingerprints when ranking diverse structures by similarity, as is the topological torsion fingerprint. However, when ranking very close analogues, the atom pair fingerprint outperforms the others tested. When ranking diverse structures or carrying out a virtual screen, we find that the performance of the ECFP fingerprints significantly improves if the bit-vector length is increased from 1024 to 16,384.Graphical abstract

Fragment oriented molecular shapes

Molecular shape is an important concept in drug design and virtual screening. Shape similarity typically uses either alignment methods, which dynamically optimize molecular poses with respect to the query molecular shape, or feature vector methods, which are computationally less demanding but less accurate. The computational cost of alignment can be reduced by pre-aligning shapes, as is done with the Volumetric-Aligned Molecular Shapes (VAMS) method. Here, we introduce and evaluate fragment oriented molecular shapes (FOMS), where shapes are aligned based on molecular fragments. FOMS enables the use of shape constraints, a novel method for precisely specifying molecular shape queries that provides the ability to perform partial shape matching and supports search algorithms that function on an interactive time scale. When evaluated using the challenging Maximum Unbiased Validation dataset, shape constraints were able to extract significantly enriched subsets of compounds for the majority of targets, and FOMS matched or exceeded the performance of both VAMS and an optimizing alignment method of shape similarity search.

Relational Agreement Measures for Similarity Searching of Cheminformatic Data Sets

Research on similarity searching of cheminformatic data sets has been focused on similarity measures using fingerprints. However, nominal scales are the least informative of all metric scales, increasing the tied similarity scores, and decreasing the effectivity of the retrieval engines. Tanimoto's coefficient has been claimed to be the most prominent measure for this task. Nevertheless, this field is far from being exhausted since the computer science no free lunch theorem predicts that "no similarity measure has overall superiority over the population of data sets". We introduce 12 relational agreement (RA) coefficients for seven metric scales, which are integrated within a group fusion-based similarity searching algorithm. These similarity measures are compared to a reference panel of 21 proximity quantifiers over 17 benchmark data sets (MUV), by using informative descriptors, a feature selection stage, a suitable performance metric, and powerful comparison tests. In this stage, RA coefficients perform favourably with repect to the state-of-the-art proximity measures. Afterward, the RA-based method outperform another four nearest neighbor searching algorithms over the same data domains. In a third validation stage, RA measures are successfully applied to the virtual screening of the NCI data set. Finally, we discuss a possible molecular interpretation for these similarity variants.

Combinatorial Consensus Scoring for Ligand-Based Virtual Fragment Screening: A Comparative Case Study for Serotonin 5-HT(3)A, Histamine H(1), and Histamine H(4) Receptors

In the current study we have evaluated the applicability of ligand-based virtual screening (LBVS) methods for the identification of small fragment-like biologically active molecules using different similarity descriptors and different consensus scoring approaches. For this purpose, we have evaluated the performance of 14 chemical similarity descriptors in retrospective virtual screening studies to discriminate fragment-like ligands of three membrane-bound receptors from fragments that are experimentally determined to have no affinity for these proteins (true inactives). We used a complete fragment affinity data set of experimentally determined ligands and inactives for two G protein-coupled receptors (GPCRs), the histamine H1 receptor (H1R) and the histamine H4 receptor (H4R), and one ligand-gated ion channel (LGIC), the serotonin receptor (5-HT3AR), to validate our retrospective virtual screening studies. We have exhaustively tested consensus scoring strategies that combine the results of multiple actives (group fusion) or combine different similarity descriptors (similarity fusion), and for the first time systematically evaluated different combinations of group fusion and similarity fusion approaches. Our studies show that for these three case study protein targets both consensus scoring approaches can increase virtual screening enrichments compared to single chemical similarity search methods. Our cheminformatics analyses recommend to use a combination of both group fusion and similarity fusion for prospective ligand-based virtual fragment screening.

Benchmarking methods and data sets for ligand enrichment assessment in virtual screening

Retrospective small-scale virtual screening (VS) based on benchmarking data sets has been widely used to estimate ligand enrichments of VS approaches in the prospective (i.e. real-world) efforts. However, the intrinsic differences of benchmarking sets to the real screening chemical libraries can cause biased assessment. Herein, we summarize the history of benchmarking methods as well as data sets and highlight three main types of biases found in benchmarking sets, i.e. "analogue bias", "artificial enrichment" and "false negative". In addition, we introduce our recent algorithm to build maximum-unbiased benchmarking sets applicable to both ligand-based and structure-based VS approaches, and its implementations to three important human histone deacetylases (HDACs) isoforms, i.e. HDAC1, HDAC6 and HDAC8. The leave-one-out cross-validation (LOO CV) demonstrates that the benchmarking sets built by our algorithm are maximum-unbiased as measured by property matching, ROC curves and AUCs.

Open-source platform to benchmark fingerprints for ligand-based virtual screening

Similarity-search methods using molecular fingerprints are an important tool for ligand-based virtual screening. A huge variety of fingerprints exist and their performance, usually assessed in retrospective benchmarking studies using data sets with known actives and known or assumed inactives, depends largely on the validation data sets used and the similarity measure used. Comparing new methods to existing ones in any systematic way is rather difficult due to the lack of standard data sets and evaluation procedures. Here, we present a standard platform for the benchmarking of 2D fingerprints. The open-source platform contains all source code, structural data for the actives and inactives used (drawn from three publicly available collections of data sets), and lists of randomly selected query molecules to be used for statistically valid comparisons of methods. This allows the exact reproduction and comparison of results for future studies. The results for 12 standard fingerprints together with two simple baseline fingerprints assessed by seven evaluation methods are shown together with the correlations between methods. High correlations were found between the 12 fingerprints and a careful statistical analysis showed that only the two baseline fingerprints were different from the others in a statistically significant way. High correlations were also found between six of the seven evaluation methods, indicating that despite their seeming differences, many of these methods are similar to each other.

Fusing similarity rankings in ligand-based virtual screening

Data fusion is the name given to a range of methods for combining multiple sources of evidence. This mini-review summarizes the use of one such class of methods for combining the rankings obtained when similarity searching is used for ligand-based virtual screening. Two main approaches are described: similarity fusion involves combining rankings from single searches based on multiple similarity measures; and group fusion involves combining rankings from multiple searches based on a single similarity measure. The review then focuses on the rules that are available for combining similarity rankings, and on the evidence that exists for the superiority of fusion-based methods over conventional similarity searching.

Identification and characterization of new DNA G-quadruplex binders selected by a combination of ligand and structure-based virtual screening approaches

Nowadays, it has been demonstrated that DNA G-quadruplex arrangements are involved in cellular aging and cancer, thus boosting the discovery of selective binders for these DNA secondary structures. By taking advantage of available structural and biological information on these structures, we performed a high throughput in silico screening of commercially available molecules databases by merging ligand- and structure-based approaches by means of docking experiments. Compounds selected by the virtual screening procedure were then tested for their ability to interact with the human telomeric G-quadruplex folding by circular dichroism, fluorescence spectroscopy, and photodynamic techniques. Interestingly, our screening succeeded in retrieving a new promising scaffold for G-quadruplex binders characterized by a psoralen moiety.

Identification of HIV-1 reverse transcriptase dual inhibitors by a combined shape-, 2D-fingerprint- and pharmacophore-based virtual screening approach

We report the first application of ligand-based virtual screening (VS) methods for discovering new compounds able to inhibit both human immunodeficiency virus type 1 (HIV-1) reverse transcriptase (RT)-associated functions, DNA polymerase and ribonuclease H (RNase H) activities. The overall VS campaign consisted of two consecutive screening processes. In the first, the VS platform Rapid Overlay of Chemical Structures (ROCS) was used to perform in silico shape-based similarity screening on the NCI compounds database in which a hydrazone derivative, previously shown to inhibit the HIV-1 RT, was chosen. As a result, 34 hit molecules were selected and assayed on both RT-associated functions. In the second, the 4 most potent RT inhibitors identified were selected as queries for parallel VS performed by combining shape-based, 2D-fingerprint and 3D-pharmacophore VS methods. Overall, a set of molecules characterized by new different scaffolds were identified as novel inhibitors of both HIV-1 RT-associated activities in the low micromolar range.

Large-scale similarity search profiling of ChEMBL compound data sets

A large-scale similarity search investigation has been carried out on 266 well-defined compound activity classes extracted from the ChEMBL database. The analysis was performed using two widely applied two-dimensional (2D) fingerprints that mark opposite ends of the current performance spectrum of these types of fingerprints, i.e., MACCS structural keys and the extended connectivity fingerprint with bond diameter four (ECFP4). For each fingerprint, three nearest neighbor search strategies were applied. On the basis of these search calculations, a similarity search profile of the ChEMBL database was generated. Overall, the fingerprint search campaign was surprisingly successful. In 203 of 266 test cases (∼76%), a compound recovery rate of at least 50% was observed with at least the better performing fingerprint and one search strategy. The similarity search profile also revealed several general trends. For example, fingerprint searching was often characterized by an early enrichment of active compounds in database selection sets. In addition, compound activity classes have been categorized according to different similarity search performance levels, which helps to put the results of benchmark calculations into perspective. Therefore, a compendium of activity classes falling into different search performance categories is provided. On the basis of our large-scale investigation, the performance range of state-of-the-art 2D fingerprinting has been delineated for compound data sets directed against a wide spectrum of pharmaceutical targets.

From in silico target prediction to multi-target drug design: current databases, methods and applications

Given the tremendous growth of bioactivity databases, the use of computational tools to predict protein targets of small molecules has been gaining importance in recent years. Applications span a wide range, from the 'designed polypharmacology' of compounds to mode-of-action analysis. In this review, we firstly survey databases that can be used for ligand-based target prediction and which have grown tremendously in size in the past. We furthermore outline methods for target prediction that exist, both based on the knowledge of bioactivities from the ligand side and methods that can be applied in situations when a protein structure is known. Applications of successful in silico target identification attempts are discussed in detail, which were based partly or in whole on computational target predictions in the first instance. This includes the authors' own experience using target prediction tools, in this case considering phenotypic antibacterial screens and the analysis of high-throughput screening data. Finally, we will conclude with the prospective application of databases to not only predict, retrospectively, the protein targets of a small molecule, but also how to design ligands with desired polypharmacology in a prospective manner.

HPPD: ligand- and target-based virtual screening on a herbicide target

Hydroxyphenylpyruvate dioxygenase (HPPD) has proven to be a very successful target for the development of herbicides with bleaching properties, and today HPPD inhibitors are well established in the agrochemical market. Syngenta has a long history of HPPD-inhibitor research, and HPPD was chosen as a case study for the validation of diverse ligand- and target-based virtual screening approaches to identify compounds with inhibitory properties. Two-dimensional extended connectivity fingerprints, three-dimensional shape-based tools (ROCS, EON, and Phase-shape) and a pharmacophore approach (Phase) were used as ligand-based methods; Glide and Gold were used as target-based. Both the virtual screening utility and the scaffold-hopping ability of the screening tools were assessed. Particular emphasis was put on the specific pitfalls to take into account for the design of a virtual screening campaign in an agrochemical context, as compared to a pharmaceutical environment.