VSDMIP: virtual screening data management on an integrated platform

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.

To address the imbalanced data problem in molecular docking-based virtual screening methods, this paper proposes a virtual screening method for drug proteins based on imbalanced data mining, which introduces machine learning technology into the virtual screening technology for drug proteins to deal with the imbalanced data problem in the virtual screening process and improve the accuracy of the virtual screening. First, to address the data imbalance problem caused by the large difference between the number of active compounds and the number of inactive compounds in the docking conformation generated by the actual virtual screening process, this paper proposes a way to improve the data imbalance problem using SMOTE combined with genetic algorithm to synthesize new active compounds artificially by upsampling active compounds. Then, in order to improve the accuracy in the virtual screening process of drug proteins, the idea of integrated learning is introduced, and the random forest (RF) extended from Bagging integrated learning technique is combined with the support vector machine (SVM) technique, and the virtual screening of molecular docking conformations using RF-SVM technique is proposed to improve the prediction accuracy of active compounds in docking conformations. To verify the effectiveness of the proposed technique, first, HIV-1 protease and SRC kinase were used as test data for the experiments, and then, CA II was used to validate the model of the test data. The virtual screening of drug proteins using the proposed method in this paper showed an improvement in both enrichment factor (EF) and AUC compared with the use of the traditional virtual screening, for the test dataset. Therefore, it can be shown that the proposed method can effectively improve the accuracy of drug virtual screening.

This review provides a detailed analysis of the use of virtual library screening (VLS) in the drug discovery process. The first part is intended as a larger overview of the integrated VLS process. Small molecule and target macromolecule considerations will be described separately and will be subsequently integrated in a discussion of docking, scoring and evaluation. The second half of the review will focus on recent case studies that use VLS as part of an integrated drug discovery program. The case studies will illustrate the range of possible targets in VLS, provide an account of inclusive methodology and reveal the expectations for realistic goals. Recent efforts provide compelling evidence that VLS is successful when practiced in an integrated fashion involving synthetic, structural and computational expertise. Keywords: virtual screening, structure-based drug design, library design, drug discovery, diversity, filtering, ligand binding, docking

The inconsistencies in the performance of the virtual screening (VS) process, depending on the used software and structural conformation of the protein, is a challenging issue in the drug design and discovery field. Varying performance, especially in terms of early recognition of the potential hit compounds, negatively affects the whole process and leads to unnecessary waste of the time and resources. Appropriate application of the ensemble docking and consensus-scoring approaches can significantly increase reliability of the VS results. Dihydroorotate dehydrogenase (DHODH) is a key enzyme in the pyrimidine biosynthesis pathway. It is considered as a valuable therapeutic target in cancer, autoimmune and viral diseases. Based on the conducted benchmark study and analysis of the effect of different combinations of the applied methods and approaches, here we suggested a structure-based virtual screening (SBVS) workflow that can be used to increase the reliability of VS.

BackgroundThe virtual screening (VS) of lead compounds using molecular docking and pharmacophore detection is now an important tool in drug discovery. VS tasks typically require a combination of several software tools and a molecular graphics system. Thus, the integration of all the requisite tools in a single operating environment could reduce the complexity of running VS experiments. However, only a few freely available integrated software platforms have been developed.ResultsA free open-source platform, IVSPlat 1.0, was developed in this study for the management and automation of VS tasks. We integrated several VS-related programs into a molecular graphics system to provide a comprehensive platform for the solution of VS tasks based on molecular docking, pharmacophore detection, and a combination of both methods. This tool can be used to visualize intermediate and final results of the VS execution, while also providing a clustering tool for the analysis of VS results. A case study was conducted to demonstrate the applicability of this platform.ConclusionsIVSPlat 1.0 provides a plug-in-based solution for the management, automation, and visualization of VS tasks. IVSPlat 1.0 is an open framework that allows the integration of extra software to extend its functionality and modified versions can be freely distributed. The open source code and documentation are available at http://kyc.nenu.edu.cn/IVSPlat/.

Introduction: Ligand-based shape matching approaches have become established as important and popular virtual screening (VS) techniques. However, despite their relative success, the question of how to best choose the initial query compounds and their conformations remains largely unsolved. This issue gains importance when dealing with promiscuous targets, that is, proteins that bind multiple ligand scaffold families in one or more binding site. Conventional shape matching VS approaches assume that there is only one binding mode for a given protein target. This may be true for some targets, but it is certainly not true in all cases. Several recent studies have shown that some protein targets bind to different ligands in different ways.Areas covered: The authors discuss the concept of promiscuity in the context of virtual drug screening, and present and analyze several examples of promiscuous targets. The article also reports on the impact of the query conformation on the performance of shape-based VS and the potential to improve VS performance by using consensus shape clustering techniques.Expert opinion: The notion of polypharmacology is becoming highly relevant in drug discovery. Understanding and exploiting promiscuity present challenges and opportunities for drug discovery endeavors. The examples of promiscuity presented here suggest that promiscuous targets and ligands are much more common than previously assumed, and this should be taken into account in practical VS protocols. Although some progress has been made, there is a need to develop more sophisticated computational techniques and protocols that can identify and characterize promiscuous targets on a genomic scale.

Virtual Screening (VS) of large compound libraries using Artificial Intelligence (AI) models is a highly effective approach for early drug discovery. Data splitting is crucial for benchmarking the performance of such AI models. Traditional random data splits often result in structurally similar molecules in both training and test sets, which conflict with the reality of VS libraries that typically contain structurally diverse compounds. To tackle this challenge, scaffold split, which groups molecules by shared core structure, and Butina clustering, which clusters molecules by chemotypes, have long been used. However, we show that these methods still introduce high similarities between training and test sets, leading to overestimated model performance. Our study examined four representative AI models across 60 NCI-60 datasets, each comprising approximately 33,000–54,000 molecules tested on different cancer cell lines. Each dataset was split in four ways: random, scaffold, Butina clustering and the more realistic Uniform Manifold Approximation and Projection (UMAP) clustering. Using Linear Regression, Random Forest, Transformer-CNN, and GEM, we trained a total of 8400 models and evaluated under four splitting methods. These comprehensive results show that UMAP split provides more challenging and realistic benchmarks for model evaluation, followed by Butina splits, then scaffold splits and closely after random splits. Consequently, we recommend using UMAP splits instead of overly optimistic Butina splits and especially scaffold splits for molecular property prediction, including VS. Lastly, we illustrate how misaligned ROC AUC is with VS goals, despite its common use. The code and datasets for reproducibility are available at https://github.com/Rong830/UMAP_split_for_VS and archived in https://zenodo.org/records/14736486. Scientific contribution This work advances the field by introducing UMAP clustering as a robust splitting method for molecular datasets, improving over traditional methods like Butina clustering and especially scaffold splits. It offers a new evaluation framework to benchmark AI models under more realistic conditions, fostering progress in molecular property prediction. The findings also show how inappropriate the use of ROC AUC for virtual screening (VS) continues to be, despite its popularity, emphasizing the need for context-specific evaluation metrics.

BackgroundDespite continued efforts using chemical similarity methods in virtual screening, currently developed approaches suffer from time-consuming multistep procedures and low success rates. We recently developed a machine learning-based chemical binding similarity model considering common structural features from molecules binding to the same, or evolutionarily related targets. The chemical binding similarity measures the resemblance of chemical compounds in terms of binding site similarity to better describe functional similarities that arise from target binding. In this study, we have shown how the chemical binding similarity could be used in virtual screening together with the conventional structure-based methods.ResultsThe chemical binding similarity, receptor-based pharmacophore, chemical structure similarity, and molecular docking methods were evaluated to identify an effective virtual screening procedure for desired target proteins. When we tested the chemical binding similarity method with test sets of 51 kinases, it outperformed the traditional structural similarity-based methods as well as structure-based methods, such as molecular docking and receptor-based pharmacophore modeling, in terms of finding active compounds. We further validated the results by performing virtual screening (using the chemical binding similarity and receptor-based pharmacophore methods) against a completely blind dataset for mitogen-activated protein kinase kinase 1 (MEK1), ephrin type-B receptor 4 (EPHB4) and wee1-like protein kinase (WEE1). The in vitro kinase binding assay confirmed that 6 out of 13 (46.2%) for MEK1 and 2 out of 12 (16.7%) for EPHB4 were newly identified only by the chemical binding similarity model.ConclusionsWe report that the virtual screening results could further be improved by combining the chemical binding similarity model with 3D-QSAR pharmacophore and molecular docking models. Not only the new inhibitors are identified in this study, but also many of the identified molecules have low structural similarity scores against already reported inhibitors and that show the revelation of novel scaffolds.

Researchers have adopted model-centric artificial intelligence (AI) approaches in cheminformatics by using newer, more sophisticated AI methods to take advantage of growing chemical libraries. It has been shown that complex deep learning methods outperform conventional machine learning (ML) methods in QSAR and ligand-based virtual screening– but such approaches generally lack explanability. Hence, instead of developing more sophisticated AI methods (i.e., pursuing a model-centric approach), we wanted to explore the potential of a data-centric AI paradigm for virtual screening. A data-centric AI is an intelligent system that would automatically identify the right type of data to collect, clean and curate for later use by a predictive AI and this is required given the large volumes of chemical data that exist in chemical databases – PubChem alone has over 100 million unique compounds. However, a systematic assessment of the attributes and properties of suitable data is needed. We show here that it is not the result of deficiencies in current AI algorithms but rather, poor understanding and erroneous use of chemical data that ultimately leads to poor predictive performance. Using a new benchmark dataset of BRAF ligands that we developed, we show that our best performing predictive model can achieve an unprecedented accuracy of 99% with a conventional ML algorithm (SVM) using a merged molecular representation (Extended+ ECFP6 fingerprints), far surpassing past performances of virtual screening platforms using sophisticated deep learning methods. Thus, we demonstrate that it is not necessary to resort to the use of sophisticated deep learning algorithms for virtual screening because conventional ML can perform exceptionally well if given the right data and representation. We also show that the common use of decoys for training leads to high false positive rates and its use for testing will result in an over-optimistic estimation of a model’s predictive performance. Another common practice in virtual screening is defining compounds that are above a certain pharmacological threshold as inactives. Here, we show that the use of these so-called inactive compounds lowers a model’s sensitivity/recall. Considering that some target proteins have a limited number of known ligands, we wanted to also observe how the size and composition of the training data impact predictive performance. We found that an imbalance training dataset where inactives outnumber actives led to a decrease in recall but an increase in precision, regardless of the model or molecular representation used; and overall, we observed a decrease in the model’s accuracy. We highlight in this study some of the considerations that one needs to take into account in future development of data-centric AI for CADD.

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.

<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.

Breast cancer is the highest mortality cause in women with cancer. Protein-protein docking for target-based screening is an effective approach in breast cancer drug discovery via estrogen receptor (ER) signaling. TRIM56, an E3 ubiquitin protein ligase, can bind to and stabilize ER alpha. Thus, drug screening that can inhibit or weaken the interaction between ER alpha and TRIM56 is promising to obtain novel yet specific breast cancer drugs. In this study, we performed protein-protein docking studies for ER alpha and TRIM56 interaction and virtual screening for FDA-approved drugs from the ZINC database against ER alpha and TRIM56 complex protein model structure. We utilized Cluspro 2.0, PyRx 0.8, and Pymol 2.4.1 to conduct protein-protein docking, virtual screening, and model structure visualization. PIP and PLIP software were also applied to analyze the amino acid residue between proteins or protein-ligands. Based on the protein-protein docking, ER alpha and TRIM56 established interaction. Utilizing this complex protein as a macromolecule in the virtual screen of 1071 molecules of FDA-approved drugs, we obtain the top five lowest binding energy molecules i.e., dutasteride, dihydroergotamine, nilotinib, ergotamine, and bromocriptine. In addition, the energy binding affinity between ER alpha-dutasteride complex with TRIM56 was weakened in the presence of dutasteride. In conclusion, protein-protein docking between ER alpha-TRIM56 was able to select FDA-approved drugs that could bind to the complex, and dutasteride binding to ER alpha-TRIM56 complex weakened the interaction.Keywords: protein-protein docking, estrogen receptor alpha, TRIM56, breast cancer, ubiquitin.

Alzheimer's disease (AD) remains a significant challenge in diagnosis and treatment, with current methods insufficient for early detection. A major obstacle is the lack of effective imaging agents targeting the Tau protein, which plays a key role in AD pathology. To address this, we developed a computational methodology for selecting F-18 labeled drug candidates from a library of CNS-penetrant compounds curated from literature and databases. The library, consisting of 977 compounds, was evaluated based on clinical data, target proteins, pathways, toxicity, and other relevant factors. We implemented Python-based algorithms to select the top 39 compounds from virtual screening results, prioritizing those with optimal Tau binding affinity and BBB permeability. Additionally, we developed an algorithm to identify F-18 labeling candidates that maintain their biological activity post-labeling. We then performed virtual screening of an F-18 labeled drug library and selected the top 3 compounds based on stability and imaging potential. The selected compounds exhibited molecular weights of 350-520 Da, favorable logP values (2.05-2.72), and high BBB permeability. Our findings indicate that Drug 388 (BI-D1870), binds to Tau with a binding free energy of ΔG = -8.79 kcal/mol. Drug 416 (reported BRAF inhibitor, RG6344) shows a binding free energy of ΔG = -7.91 kcal/mol, while Drug 610 (Iloperidone/HP 873), a D2/5-HT2 receptor antagonist, exhibits a predicted binding free energy of ΔG = -6.88 kcal/mol with the target Tau protein respectively. Molecular dynamics simulations confirmed stable Tau-drugs interactions, with minimal RMSD fluctuations, indicating strong binding. The F-18 label enabled real-time PET imaging, allowing non-invasive tracking of the drug's binding to Tau in the brain. Our approach provides a comprehensive solution to the current limitations in Alzheimer's diagnosis by offering F-18 labeled drugs that effectively target Tau protein without compromising their biological activity, advancing both diagnostic and therapeutic strategies for AD.

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.