Virtual Screening of Drug Proteins Based on Imbalance Data Mining

<h3>Abstract</h3> Computational methods for virtual screening can dramatically accelerate early-stage drug discovery by identifying potential hits for a specified target. Docking algorithms traditionally use physics-based simulations to address this challenge...

Virtual screening is a new approach attracting increasing levels of interest in the pharmaceutical industry, as a productive and cost-effective technology in the search for novel lead compounds. The preparation of millions of small molecular compounds is the prerequisite for large-scale virtual screening, and these massive data are usually provided with different format. In addition, scientists often need to select some of them that meet certain conditions. Therefore, an efficient data management approach is playing an important role in virtual screening process for managing large-scale small molecular compounds. In this paper, we represent a comprehensive data management framework for pre-docking in large-scale virtual screening. In this framework, we construct a distributed chemical database and utilize parallel processing approach to search certain molecules from the database on the scale of at least several million. We also develop a proxy schema, which is responsible to perform the basic function (such as, splitting large-scale data, update, insert and so on) a collection of multiple, logically interrelated databases distributed over a computer network, meanwhile, we design and establish a rule of splitting large-scale data with optimization. Finally, we simulate and demonstrate a stress test of constructing and searching database. It turns out that our proposal could make the preparing phase of virtual screening process more simple and efficient.

Virtual screening (VS) is a well-established method in the initial stages of many drug and material design projects. VS is typically performed using structure-based approaches such as molecular docking, or various ligand-based approaches. Most docking tools were designed to be as global as possible, and consequently only require knowledge on the 3D structure of the biotarget. In contrast, many ligand-based approaches (e.g., 3D-QSAR and pharmacophore) require prior development of project-specific predictive models. Depending on the type of model (e.g., classification or regression), predictive ability is typically evaluated using metrics of performance on either the training set () or the test set (e.g., specificity, selectivity or ). However, none of these metrics were developed with VS in mind, and consequently, their ability to reliably assess the performances of a model in the context of VS is at best limited. With this in mind we have recently reported the development of the enrichment optimization algorithm (EOA). EOA derives QSAR models in the form of multiple linear regression (MLR) equations for VS by optimizing an enrichment-based metric in the space of the descriptors. Here we present an improved version of the algorithm which better handles active compounds and which also takes into account information on inactive (either known inactive or decoy) compounds. We compared the improved EOA in small-scale VS experiments with three common docking tools, namely, Glide-SP, GOLD and AutoDock Vina, employing five molecular targets (acetylcholinesterase, human immunodeficiency virus type 1 protease, MAP kinase p38 alpha, urokinase-type plasminogen activator, and trypsin I). We found that EOA consistently outperformed all docking tools in terms of the area under the ROC curve (AUC) and EF1% metrics that measured the overall and initial success of the VS process, respectively. This was the case when the docking metrics were calculated based on a consensus approach and when they were calculated based on two different sets of single crystal structures. Finally, we propose that EOA could be combined with molecular docking to derive target-specific scoring functions.

The increasing resistance to current therapeutic agents for HIV drug regiment remains a major problem for effective acquired immune deficiency syndrome (AIDS) therapy. Many potential inhibitors have today been developed which inhibits key cellular pathways in the HIV cycle. Inhibition of HIV-1 reverse transcriptase associated ribonuclease H (RNase H) function provides a novel target for anti-HIV chemotherapy. Here we report on the applicability of conceptually different in silico approaches as virtual screening (VS) tools in order to efficiently identify RNase H inhibitors from large chemical databases. The methods used here include machine-learning algorithms (e.g. support vector machine, random forest and kappa nearest neighbor), shape similarity (rapid overlay of chemical structures), pharmacophore, molecular interaction fields-based fingerprints for ligands and protein (FLAP) and flexible ligand docking methods. The results show that receptor-based flexible docking experiments provides good enrichment (80–90%) compared to ligand-based approaches such as FLAP (74%), shape similarity (75%) and random forest (72%). Thus, this study suggests that flexible docking experiments is the model of choice in terms of best retrieval of active from inactive compounds and efficiency and efficacy schemes. Moreover, shape similarity, machine learning and FLAP models could also be used for further validation or filtration in virtual screening processes. The best models could potentially be use for identifying structurally diverse and selective RNase H inhibitors from large chemical databases. In addition, pharmacophore models suggest that the inter-distance between hydrogen bond acceptors play a key role in inhibition of the RNase H domain through metal chelation.

Computational virtual screening (VS) plays a vital role in early-stage drug discovery by enabling the efficient selection of candidate compounds and reducing associated costs. However, the absence of experimentally determined three-dimensional protein structures often limits the applicability of structure-based VS. Advances in protein structure prediction, notably AlphaFold2, have begun to address this gap. Yet, studies indicate that direct use of AlphaFold2-predicted structures often leads to suboptimal VS performance-likely because these structures fail to capture ligand-induced conformational changes (apo-to-holo transitions). To overcome this, we propose an approach that explores and modifies the structural space of AlphaFold2 predictions to generate conformations more amenable to VS. Our method deliberately alters the multiple sequence alignment (MSA) by introducing alanine mutations at key residues in the ligand-binding site, thereby inducing significant conformational shifts. The exploration process is guided by iterative ligand docking simulations, with mutation strategies optimized either by a genetic algorithm or via random search. Our evaluation shows that when sufficient active compounds are available, the genetic algorithm significantly enhances VS accuracy. In contrast, with limited active compound data, a random search strategy proves more effective. Moreover, our approach is particularly promising for targets that yield poor screening results when using experimentally determined structures from the PDB. Overall, these findings underscore the practical utility of modified AlphaFold2-derived structures in VS and expand the potential of computationally predicted protein models in drug discovery.

This research has three parts addressing classification, especially the imbalanced data problem, which is one of the most popular and essential issues in the domain of classification. The first part is to study the Adaptive Boosting (AdaBoost) algorithm. AdaBoost is an effective solution for classification, but it still needs improvement in the imbalanced data problem. This part proposes a method to improve the AdaBoost algorithm using the new weighted vote parameters for the weak classifiers. Our proposed weighted vote parameters are determined not only by the global error rate but also by the classification accuracy rate of the positive class, which is our primary interest. The imbalanced index of the data is also a factor in constructing our algorithms. The numeric studies show that our proposed algorithms outperform the traditional ones, especially regarding the evaluation criterion of the F--1 Measure. Theoretic proofs of the advantages of our proposed algorithms are presented. The second part treats the Relevance Vector Machine (RVM), which is a supervised learning algorithm extended from the Support Vector Machine (SVM) based on the Bayesian sparsity model. Compared with the regression problem, RVM classification is challenging to conduct because there is no closed-form solution for the weight parameter posterior. The original RVM classification algorithm uses Newton's method in optimization to obtain the mode of weight parameter posterior, then approximates it by a Gaussian distribution in Laplace's method. This original model would work, but it just applies the frequency methods in a Bayesian framework. This part first proposes a Generic Bayesian RVM classification, which is a pure Bayesian model. We conjecture that our algorithm achieves convergent estimates of the quantities of interest compared with the nonconvergent estimates of the original RVM classification algorithm. Furthermore, a fully Bayesian approach with the hierarchical hyperprior structure for RVM classification is proposed, which improves the classification performance, especially in the imbalanced data problem. The third part is an extended work of the second one. The original RVM classification model uses the logistic link function to build the likelihood, which makes the model hard to conduct since the posterior of the weight parameter has no closed-form solution. This part proposes the probit link function approach instead of the logistic one for the likelihood function in RVM classification, namely PRVM (RVM with the Probit link function). We show that the posterior of the weight parameter in our model follows the multivariate normal distribution and achieves a closed-form solution. A latent variable is needed in our algorithm to simplify the Bayesian computation greatly, and its conditional posterior follows a truncated normal distribution. Compared with the original RVM classification model, our proposed one is another pure Bayesian approach and it has a more efficient computation process. For the prior structure, we first consider the Normal-Gamma independent prior to propose a Generic Bayesian PRVM algorithm. Furthermore, the Fully Bayesian PRVM algorithm with a hierarchical hyperprior structure is proposed, which improves the classification performance, especially in the imbalanced data problem.

In this investigation, we describe the discovery of novel potent Pim-1 inhibitors by employing a proposed hierarchical multistage virtual screening (VS) approach, which is based on support vector machine-based (SVM-based VS or SB-VS), pharmacophore-based VS (PB-VS), and docking-based VS (DB-VS) methods. In this approach, the three VS methods are applied in an increasing order of complexity so that the first filter (SB-VS) is fast and simple, while successive ones (PB-VS and DB-VS) are more time-consuming but are applied only to a small subset of the entire database. Evaluation of this approach indicates that it can be used to screen a large chemical library rapidly with a high hit rate and a high enrichment factor. This approach was then applied to screen several large chemical libraries, including PubChem, Specs, and Enamine as well as an in-house database. From the final hits, 47 compounds were selected for further in vitro Pim-1 inhibitory assay, and 15 compounds show nanomolar level or low micromolar inhibition potency against Pim-1. In particular, four of them were found to have new scaffolds which have potential for the chemical development of Pim-1 inhibitors.

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

A novel software (VSDMIP) for the virtual screening (VS) of chemical libraries integrated within a MySQL relational database is presented. Two main features make VSDMIP clearly distinguishable from other existing computational tools: (i) its database, which stores not only ligand information but also the results from every step in the VS process, and (ii) its modular and pluggable architecture, which allows customization of the VS stages (such as the programs used for conformer generation or docking), through the definition of a detailed workflow employing user-configurable XML files. VSDMIP, therefore, facilitates the storage and retrieval of VS results, easily adapts to the specific requirements of each method and tool used in the experiments, and allows the comparison of different VS methodologies. To validate the usefulness of VSDMIP as an automated tool for carrying out VS several experiments were run on six protein targets (acetylcholinesterase, cyclin-dependent kinase 2, coagulation factor Xa, estrogen receptor alpha, p38 MAP kinase, and neuraminidase) using nine binary (actives/inactive) test sets. The performance of several VS configurations was evaluated by means of enrichment factors and receiver operating characteristic plots.

The interplay between life sciences and advancing technology drives a continuous cycle of chemical data growth; these data are most often stored in open or partially open databases. In parallel, many different types of algorithms are being developed to manipulate these chemical objects and associated bioactivity data. Virtual screening methods are among the most popular computational approaches in pharmaceutical research. Today, user-friendly web-based tools are available to help scientists perform virtual screening experiments. This article provides an overview of internet resources enabling and supporting chemical biology and early drug discovery with a main emphasis on web servers dedicated to virtual ligand screening and small-molecule docking. This survey first introduces some key concepts and then presents recent and easily accessible virtual screening and related target-fishing tools as well as briefly discusses case studies enabled by some of these web services. Notwithstanding further improvements, already available web-based tools not only contribute to the design of bioactive molecules and assist drug repositioning but also help to generate new ideas and explore different hypotheses in a timely fashion while contributing to teaching in the field of drug development.

Molecular docking programs are widely used modeling tools for predicting ligand binding modes and structure based virtual screening. In this study, six molecular docking programs (DOCK, FlexX, GLIDE, ICM, PhDOCK, and Surflex) were evaluated using metrics intended to assess docking pose and virtual screening accuracy. Cognate ligand docking to 68 diverse, high-resolution X-ray complexes revealed that ICM, GLIDE, and Surflex generated ligand poses close to the X-ray conformation more often than the other docking programs. GLIDE and Surflex also outperformed the other docking programs when used for virtual screening, based on mean ROC AUC and ROC enrichment values obtained for the 40 protein targets in the Directory of Useful Decoys (DUD). Further analysis uncovered general trends in accuracy that are specific for particular protein families. Modifying basic parameters in the software was shown to have a significant effect on docking and virtual screening results, suggesting that expert knowledge is critical for optimizing the accuracy of these methods.

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.

Given activity training data from high-throughput screening (HTS) experiments, virtual high-throughput screening (vHTS) methods aim to predict in silico the activity of untested chemicals. We present a novel method, the Influence Relevance Voter (IRV), specifically tailored for the vHTS task. The IRV is a low-parameter neural network which refines a k-nearest neighbor classifier by nonlinearly combining the influences of a chemical's neighbors in the training set. Influences are decomposed, also nonlinearly, into a relevance component and a vote component. The IRV is benchmarked using the data and rules of two large, open, competitions, and its performance compared to the performance of other participating methods, as well as of an in-house support vector machine (SVM) method. On these benchmark data sets, IRV achieves state-of-the-art results, comparable to the SVM in one case, and significantly better than the SVM in the other, retrieving three times as many actives in the top 1% of its prediction-sorted list. The IRV presents several other important advantages over SVMs and other methods: (1) the output predictions have a probabilistic semantic; (2) the underlying inferences are interpretable; (3) the training time is very short, on the order of minutes even for very large data sets; (4) the risk of overfitting is minimal, due to the small number of free parameters; and (5) additional information can easily be incorporated into the IRV architecture. Combined with its performance, these qualities make the IRV particularly well suited for vHTS.

Due to its capacity to drastically cut the cost and time necessary for experimental screening of compounds, virtual screening (VS) has grown to be a crucial component of drug discovery and development. VS is a computational method used in drug design to identify potential drugs from enormous libraries of chemicals. This approach makes use of molecular modeling and docking simulations to assess the small molecule's ability to bind to the desired protein. Virtual screening has a bright future, as high computational power and modern techniques are likely to further enhance the accuracy and speed of the process.

Introduction: Virtual screening (VS) has emerged as an important tool in identifying bioactive compounds through computational means, by employing knowledge about the protein target or known bioactive ligands. VS has appeared as an adaptive response to the massive throughput synthesis and screening paradigm as necessity has forced the computational chemistry community to develop tools that screen against any given target and/or property millions or perhaps billions of molecules in short period of time.Areas covered: This editorial review attempts to catalog most commonly exercised VS methods, available databases for screening, advantages of VS methods along with pitfalls and technical traps with the aim to make VS as one of the most effective tools in drug discovery process. Finally, several case studies are cited where the VS technology has been applied successfully.Expert opinion: In recent times, many successful examples have been demonstrated in the field of computer-aided VS with the objective of increasing the probability of finding novel hit and lead compounds in terms of cost-effectiveness and commitment in time and material. Despite the inherent limitations, VS is still the best option now available to explore a large chemical space.