Structure-Based Virtual Screening: From Classical to Artificial Intelligence

Coronavirus (CoV) diseases are widespread throughout the world and have caused considerable socio-economic disruptions. For this reason, efforts have been made to develop a direct or indirect antiviral drugs against these diseases. However, no specific antiviral drug has yet been approved by the Food and Drug Administration (FDA) for CoV infections. Thus, the challenge in discovering therapeutic molecules against these infections remains pertinent. Computer-aided drug design (CADD) is one of the modern techniques for drug discovery and development. It accelerates the process, minimizes costs, and reduces research time. In this article, we present the three CADD approaches, namely structure-based drug discovery (SBDD), ligand-based drug discovery (LBDD) and high-throughput virtual screening (HTVS). The different methods used in these three approaches CADD, such as molecular modelling, target structure analysis, molecular docking, molecular dynamics simulation, pharmacophore modelling, quantitative structure-activity relationship (QSAR), ligand-based virtual screening (LBVS) and structure-based virtual screening (SBVS) are detailed. In addition, the bioinformatics tools and databases commonly used in these different CADD techniques are also described.

In Silico drug design represents a new approach for drug discovery and industry. Structure based computer aided drug design (CADD) was used in this study to find an antibiofilm agents to suppress Staphylococcus epidermidis biofilm production which is considered the main virulence factor of this bacterium. The sarA protein was chosen as the target for this process as it stimulates icaADBC operon which is responsible for biofilm production. The first step was constructing a 3D structure of the protein which was obtained using the RaptorX homology modeling. Pharmacophore generation was performed using the Hip Hop generator from Discovery Studio package. One hundred seventy seven molecules were chosen by ligand based virtual screening using ZincPharmer. Thirty seven molecules were found suitable as having negative binding free energies with sarA protein in EADock engine from the SwissDock Website. These molecules can be tested for in vitro studies as antibiofilm agents.

A drug takes many years to develop and reach the market using the conventional drug discovery procedure. Computer-aided drug design (CADD) is an emerging technology that accelerates the process of drug discovery and minimizes the total expenditure associated with labour and resources. In the current scenario, the computational aided drug design (CADD) techniques play a significant role in the design and development of lead molecules for the treatment of various lethal pathological conditions. The prediction of the tertiary structure of a protein is a big concern in drug design and discovery. A typical drug discovery procedure starts with the tertiary structure of a protein. At present, a total of 184,407 protein structures are available in the protein data bank, which are determinedusing experimental methods. However, the procedures are difficult and time-consuming. A more advanced technique has been developed for the prediction of the 3D structure of a protein using a computational method. This technique has played a vital role in drug discovery. It has not only facilitated but also hastened the process of drug discovery. The method is named homology modeling since it involves the building of a protein model based on its homology to similar evolutionary proteins. The method is based on the fact that evolutionary related proteins have similar structures. In homology modelling, the 3D structure of a protein is derived from its primary sequence based on its similarity to the existing protein templates. There are many computational tools for homology modelling such as Modeller, Swiss model, Composer, 3D-JIGSAW, etc. The proposed book chapter will cover the introduction to homology modelling, step-by-step guide to building a protein model, various challenges and how to refine and validate the model, different algorithms related to sequence alignment, similarity search, and the applications of homology modelling in drug design and discovery. The chapter would be very fruitful to the readers to get insights into protein modelling, which will facilitate their research activities. It will be of great application in various disciplines,such as bioinformatics, physics, structural biology, and molecular biology. The content of the chapter will cover various research papers, review papers, and corresponding reference books.

Drug design and development are crucial areas of study for chemists and pharmaceutical companies. Nevertheless, the significant expenses, lengthy process, inaccurate delivery, and limited effectiveness present obstacles and barriers that affect the development and exploration of new drugs. Moreover, big and complex datasets from clinical trials, genomics, proteomics, and microarray data also disrupt the drug discovery approach. The integration of Artificial Intelligence (AI) into drug design is both timely and crucial due to several pressing challenges in the pharmaceutical industry, including the escalating costs of drug development, high failure rates in clinical trials, and the increasing complexity of disease biology. AI offers innovative solutions to address these challenges, promising to improve the efficiency, precision, and success rates of drug discovery and development. Artificial intelligence (AI) and machine learning (ML) technology are crucial tools in the field of drug discovery and development. More precisely, the field has been revolutionized by the utilization of deep learning (DL) techniques and artificial neural networks (ANNs). DL algorithms & ML have been employed in drug design using various approaches such as physiochemical activity, polypharmacology, drug repositioning, quantitative structure-activity relationship, pharmacophore modeling, drug monitoring and release, toxicity prediction, ligand-based virtual screening, structure-based virtual screening, and peptide synthesis. The use of DL and AI in this field is supported by historical evidence. Furthermore, management strategies, curation, and unconventional data mining aided assistance in modern modeling algorithms. In summary, the progress made in artificial intelligence and deep learning algorithms offers a promising opportunity for the development and discovery of effective drugs, ultimately leading to significant benefits for humanity. In this review, several tools and algorithmic programs have been discussed which are being used in drug design along with the descriptions of the patents that have been granted for the use of AI in this field, which constitutes the main focus of this review and differentiates it fromalready published materials.

Bromodomain-containing protein 4 (BRD4) is implicated in the pathogenesis of a number of different cancers, inflammatory diseases and heart failure. Much effort has been dedicated toward discovering novel scaffold BRD4 inhibitors (BRD4is) with different selectivity profiles and potential antiresistance properties. Structure-based drug design (SBDD) and virtual screening (VS) are the most frequently used approaches. Here, we demonstrate a novel, structure-based VS approach that uses machine-learning algorithms trained on the priori structure and activity knowledge to predict the likelihood that a compound is a BRD4i based on its binding pattern with BRD4. In addition to positive experimental data, such as X-ray structures of BRD4-ligand complexes and BRD4 inhibitory potencies, negative data such as false positives (FPs) identified from our earlier ligand screening results were incorporated into our knowledge base. We used the resulting data to train a machine-learning model named BRD4LGR to predict the BRD4i-likeness of a compound. BRD4LGR achieved a 20-30% higher AUC-ROC than that of Glide using the same test set. When conducting in vitro experiments against a library of previously untested, commercially available organic compounds, the second round of VS using BRD4LGR generated 15 new BRD4is. Moreover, inverting the machine-learning model provided easy access to structure-activity relationship (SAR) interpretation for hit-to-lead optimization.

RNAs are a vast reservoir of untapped drug targets. Structure-based virtual screening (VS) identifies candidate molecules by leveraging binding site information, traditionally using molecular docking simulations. However, docking struggles to scale with large compound libraries and RNA targets. Machine learning offers a solution but remains underdeveloped for RNA due to limited data and practical evaluations. We introduce a data-driven VS pipeline tailored for RNA, utilizing coarse-grained 3D modeling, synthetic data augmentation, and RNA-specific self-supervision. Our model achieves a 10,000x speedup over docking while ranking active compounds in the top 2.8% on structurally distinct test sets. It is robust to binding site variations and successfully screens unseen RNA riboswitches in a 20,000-compound in-vitro microarray, with a mean enrichment factor of 2.93 at 1%. This marks the first experimentally validated success of structure-based deep learning for RNA VS.

Integrated in silico-in vitro strategy for screening of some traditional Egyptian plants for human aromatase inhibitors

Advances in Artificial Intelligence (AI)-assisted approaches in drug screening

Neuropathic pain is due to an injury or disease of the somatosensory nervous system, which accounts for a significant economical and health burden to society. Due to poor understanding of their underlying mechanisms, the available treatments merely provide symptomatic relief and precipitates a variety of adverse effects. This suggests that there is an unmet medical need that must be addressed with effective strategies for the development of novel therapeutics. Sphingosine kinase 2 (SphK2) is an oncogenic lipid kinase that has emerged as a promising target for chronic pain and other diseases. In the present study, we have explored the structure-based virtual high-throughput screening of the Nuclei of Bioassays, Ecophysiology, and Biosynthesis of Natural Products Database (NuBBE) to identify potent natural products as inhibitors of SphK2. A molecular docking study was performed to calculate binding affinities and specificity to identify potential leads against SphK2. Initially, hits were selected by the implementation of absorption, distribution, metabolism, excretion and toxicity properties, Lipinski rule, and PAINS filters. The top-scoring hits also exhibiting an optimal ADMET profile were subjected to MM/GBSA free binding free energy calculation and molecular dynamics simulation. The results from molecular dynamics simulation revealed a stable ligand -SphK2 complex with protein and ligand RMSD within reasonable limits. Overall, we identified compounds, NuBBE_972 and NuBBE_1107 as potential inhibitors of SphK2 with optimal pharmacokinetic properties which have the potential to be developed as novel therapeutics for the management of chronic pain. Communicated by Ramaswamy H. Sarma

The conventional drug discovery approach is an expensive and time-consuming process, but its limitations have been overcome with the help of mathematical modeling and computational drug design approaches. Previously, finding a small molecular candidate as a drug against a disease was very costly and required a long time to screen a compound against a specific target. The development of novel targets and small molecular candidates against different diseases including emerging and reemerging diseases remains a major concern and necessitates the development of novel therapeutic targets as well as drug candidates as early as possible. In this regard, computational and mathematical modeling approaches for drug development are advantageous due to their fastest predictive ability and cost-effectiveness features. Computer-aided drug design (CADD) techniques utilize different computer programs as well as mathematics formulas to comprehend the interaction of a target and drugs. Traditional methods to determine small-molecule candidates as a drug have several limitations, but CADD utilizes novel methods that require little time and accurately predict a compound against a specific disease with minimal cost. Therefore, this review aims to provide a brief insight into the mathematical modeling and computational approaches for identifying a novel target and small molecular candidates for curing a specific disease. The comprehensive review mainly focuses on biological target prediction, structure-based and ligand-based drug design methods, molecular docking, virtual screening, pharmacophore modeling, quantitative structure–activity relationship (QSAR) models, molecular dynamics simulation, and MM-GBSA/MM-PBSA approaches along with valuable database resources and tools for identifying novel targets and therapeutics against a disease. This review will help researchers in a way that may open the road for the development of effective drugs and preventative measures against a disease in the future as early as possible.

Structure-based drug discovery (SBDD) is becoming an essential tool in assisting fast and cost-efficient leaddiscovery and optimization. The application of rational, structure-based drug design is proven to be more efficient than thetraditional way of drug discovery since it aims to understand the molecular basis of a disease and utilizes the knowledgeof the three-dimensional structure of the biological target in the process. In this review, we focus on the principles and applicationsof Virtual Screening (VS) within the context of SBDD and examine different procedures ranging from the initialstages of the process that include receptor and library pre-processing, to docking, scoring and post-processing of topscoringhits. Recent improvements in structure-based virtual screening (SBVS) efficiency through ensemble docking, inducedfit and consensus docking are also discussed. The review highlights advances in the field within the framework ofseveral success studies that have led to nM inhibition directly from VS and provides recent trends in library design as wellas discusses limitations of the method. Applications of SBVS in the design of substrates for engineered proteins that enablethe discovery of new metabolic and signal transduction pathways and the design of inhibitors of multifunctional proteinsare also reviewed. Finally, we contribute two promising VS protocols recently developed by us that aim to increaseinhibitor selectivity. In the first protocol, we describe the discovery of micromolar inhibitors through SBVS designed toinhibit the mutant H1047R PI3Kα kinase. Second, we discuss a strategy for the identification of selective binders for theRXRα nuclear receptor. In this protocol, a set of target structures is constructed for ensemble docking based on bindingsite shape characterization and clustering, aiming to enhance the hit rate of selective inhibitors for the desired protein targetthrough the SBVS process.

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.

In the last decade, cancer has been a leading cause of death worldwide. Despite the impressive progress in cancer therapy, firsthand treatments are not selective to cancer cells and cause serious toxicity. Thus, the design and development of selective and innovative small molecule drugs is of great interest, particularly through in silico tools. The aim of this review is to analyze different subsections of computer-aided drug design (CADD) in the process of discovering anticancer drugs. Articles from the 2008-2021 timeframe were analyzed and based on the relevance of the information and the JCR of its journal of precedence, were selected to be included in this review. The information collected in this study highlights the main traditional and novel CADD approaches used in anticancer drug discovery, its sub-segments, and some applied examples. Throughout this review, the potential use of CADD in drug research and discovery, particularly in the field of oncology, is evident due to the many advantages it presents. CADD approaches play a significant role in the drug development process since they allow a better administration of resources with successful results and a promising future market and clinical wise.

Chapter 5 - Homology modeling: Developing 3D structures of target proteins missing in databases

Introduction The number of diabetic patients is increasing, posing a heavy social and economic burden worldwide. Traditional drug development technology is time-consuming and costly, and the emergence of computer-aided drug design (CADD) has changed this situation. This study reviews the applications of CADD in diabetic drug designing. Areas covered In this article, the authors focus on the advance in CADD in diabetic drug design by elaborating the discovery, including peroxisome proliferator-activated receptor (PPAR), G protein-coupled receptor 40 (GPR40), dipeptidyl peptidase-IV (DDP-IV), protein tyrosine phosphatase 1B (PTP1B), sodium-dependent glucose transporter 2 (SGLT-2), and glucokinase (GK). Some drug discovery of these targets is related to CADD strategies. Expert opinion There is no doubt that CADD has contributed to the discovery of novel anti-diabetic agents. However, there are still many limitations and challenges, such as lack of co-crystal complex, dynamic simulations, water, and metal ion treatment. In the near future, artificial intelligence (AI) may be a promising strategy to accelerate drug discovery and reduce costs by identifying candidates. Moreover, AlphaFold, a deep learning model that predicts the 3D structure of proteins, represents a considerable advancement in the structural prediction of proteins, especially in the absence of homologous templates for protein structures.