Computer-aided Drug Design Research Articles

Drug–target affinity prediction with extended graph learning-convolutional networks

BackgroundHigh-performance computing plays a pivotal role in computer-aided drug design, a field that holds significant promise in pharmaceutical research. The prediction of drug–target affinity (DTA) is a crucial stage in this process, potentially accelerating drug development through rapid and extensive preliminary compound screening, while also minimizing resource utilization and costs. Recently, the incorporation of deep learning into DTA prediction and the enhancement of its accuracy have emerged as key areas of interest in the research community. Drugs and targets can be characterized through various methods, including structure-based, sequence-based, and graph-based representations. Despite the progress in structure and sequence-based techniques, they tend to provide limited feature information. Conversely, graph-based approaches have risen to prominence, attracting considerable attention for their comprehensive data representation capabilities. Recent studies have focused on constructing protein and drug molecular graphs using sequences and SMILES, subsequently deriving representations through graph neural networks. However, these graph-based approaches are limited by the use of a fixed adjacent matrix of protein and drug molecular graphs for graph convolution. This limitation restricts the learning of comprehensive feature representations from intricate compound and protein structures, consequently impeding the full potential of graph-based feature representation in DTA prediction. This, in turn, significantly impacts the models’ generalization capabilities in the complex realm of drug discovery.ResultsTo tackle these challenges, we introduce GLCN-DTA, a model specifically designed for proficiency in DTA tasks. GLCN-DTA innovatively integrates a graph learning module into the existing graph architecture. This module is designed to learn a soft adjacent matrix, which effectively and efficiently refines the contextual structure of protein and drug molecular graphs. This advancement allows for learning richer structural information from protein and drug molecular graphs via graph convolution, specifically tailored for DTA tasks, compared to the conventional fixed adjacent matrix approach. A series of experiments have been conducted to validate the efficacy of the proposed GLCN-DTA method across diverse scenarios. The results demonstrate that GLCN-DTA possesses advantages in terms of robustness and high accuracy.ConclusionsThe proposed GLCN-DTA model enhances DTA prediction performance by introducing a novel framework that synergizes graph learning operations with graph convolution operations, thereby achieving richer representations. GLCN-DTA does not distinguish between different protein classifications, including structurally ordered and intrinsically disordered proteins, focusing instead on improving feature representation. Therefore, its applicability scope may be more effective in scenarios involving structurally ordered proteins, while potentially being limited in contexts with intrinsically disordered proteins.

SQM2.20: Semiempirical quantum-mechanical scoring function yields DFT-quality protein–ligand binding affinity predictions in minutes

Accurate estimation of protein–ligand binding affinity is the cornerstone of computer-aided drug design. We present a universal physics-based scoring function, named SQM2.20, addressing key terms of binding free energy using semiempirical quantum-mechanical computational methods. SQM2.20 incorporates the latest methodological advances while remaining computationally efficient even for systems with thousands of atoms. To validate it rigorously, we have compiled and made available the PL-REX benchmark dataset consisting of high-resolution crystal structures and reliable experimental affinities for ten diverse protein targets. Comparative assessments demonstrate that SQM2.20 outperforms other scoring methods and reaches a level of accuracy similar to much more expensive DFT calculations. In the PL-REX dataset, it achieves excellent correlation with experimental data (average R2 = 0.69) and exhibits consistent performance across all targets. In contrast to DFT, SQM2.20 provides affinity predictions in minutes, making it suitable for practical applications in hit identification or lead optimization.

Research on the application of computer in drug design

Virtual screening by computer is of great scientific significance for drug research and development. In recent years, a large number of computer simulation methods have been developed and applied to drug development for a variety of diseases. This paper summarized and prospected the application progress of computer aided drug design (CADD) in the research and development of new drugs, focusing on the working principle of CADD, related algorithms, and the advantages and disadvantages of existing methods. Although CADD has been successfully applied to a number of drug development projects, the accuracy of auxiliary drug structure optimization is still not high. Therefore, it is urgent to develop more accurate and efficient CADD models and algorithms to promote the process of new drug discovery.

Targeting with Structural Analogs of Natural Products the Purine Salvage Pathway in Leishmania (Leishmania) infantum by Computer-Aided Drug-Design Approaches.

Visceral Leishmaniasis (VL) has a high death rate, with 500,000 new cases and 50,000 deaths occurring annually. Despite the development of novel strategies and technologies, there is no adequate treatment for the disease. Therefore, the purpose of this study is to find structural analogs of natural products as potential novel drugs to treat VL. We selected structural analogs from natural products that have shown antileishmanial activities, and that may impede the purine salvage pathway using computer-aided drug-design (CADD) approaches. For these, we started with the vastly studied target in the pathway, the adenine phosphoribosyl transferase (APRT) protein, which alone is non-essential for the survival of the parasite. Keeping this in mind, we search for a substance that can bind to multiple targets throughout the pathway. Computational techniques were used to study the purine salvage pathway from Leishmania infantum, and molecular dynamic simulations were used to gather information on the interactions between ligands and proteins. Because of its low homology to human proteins and its essential role in the purine salvage pathway proteins network interaction, the findings further highlight the significance of adenylosuccinate lyase protein (ADL) as a therapeutic target. An analog of the alkaloid Skimmianine, N,N-diethyl-4-methoxy-1-benzofuran-6-carboxamide, demonstrated a good binding affinity to APRT and ADL targets, no expected toxicity, and potential for oral route administration. This study indicates that the compound may have antileishmanial activity, which was granted in vitro and in vivo experiments to settle this finding in the future.

Caffeic acid 3,4-dihydroxyphenethyl ester prevents colorectal cancer through inhibition of multiple cancer-promoting signal pathways in 1,2-Dimethylhydrazine/dextran sodium sulphate mouse model.

To elucidate the potential feature and mechanism of the caffeic acid 3,4-dihydroxyphenethyl ester (CADPE) molecule, which can prevent colorectal cancer (CRC) in the 1,2-Dimethylhydrazine (DMH)/dextran sodium sulphate (DSS)-induced mouse model. Institute of cancer research (ICR) male mice were injected with 20 mg/kg DMH for a week. After that, 2% DSS was administered in the drinking water for another 7 d. The CADPE treatment was given to the DMH/DSS induced male mice at three different periods until their sacrifice. Histopathological examination was used for observing the CRC development at colonic mucosa. Immunohistochemistry (IHC), blood cells smearing and crypt damage scoring methods were used for investigating the anti-inflammation feature of CADPE related to CRC. The reversing targets searching method was applied with artificial intelligence (AI), computer-aided drug designing (CADD) and Ingenuity Pathway Analysis (IPA) techniques for predicting the potential targets and mechanism of CADPE highly related to CRC. The data indicated that CADPE inhibited CRC tumor development in the colitis-associated DMH/DSS induced mouse model after giving the early treatment. CADPE also impeded the acute inflammation by decreasing the infiltration of neutrophils significantly during the initial stage of CRC development. Finally, our data showed that CADPE prevented CRC by blocking active sites of three pivotal protein targets including epidermal growth factor receptor (EGFR), extracellular signal-regulated kinase (ERK) and mammalian target of rapamycin (mTOR) in two major cancer development pathways. CADPE effectively prevented CRC at early stage of tumor germination in the DMH/DSS mouse model highly likely due to its anti-acute inflammation characteristic and the ability of blocking EGFR, ERK and mTOR activities in two highly related CRC developing pathways.

LSTM-SAGDTA: Predicting Drug-target Binding Affinity with an Attention Graph Neural Network and LSTM Approach.

Drug development is a challenging and costly process, yet it plays a crucial role in improving healthcare outcomes. Drug development requires extensive research and testing to meet the demands for economic efficiency, cures, and pain relief. Drug development is a vital research area that necessitates innovation and collaboration to achieve significant breakthroughs. Computer-aided drug design provides a promising avenue for drug discovery and development by reducing costs and improving the efficiency of drug design and testing. In this study, a novel model, namely LSTM-SAGDTA, capable of accurately predicting drug-target binding affinity, was developed. We employed SeqVec for characterizing the protein and utilized the graph neural networks to capture information on drug molecules. By introducing self-attentive graph pooling, the model achieved greater accuracy and efficiency in predicting drug-target binding affinity. Moreover, LSTM-SAGDTA obtained superior accuracy over current state-of-the-art methods only by using less training time. The results of experiments suggest that this method represents a highprecision solution for the DTA predictor.

Application status and challenges of molecular docking in development of traditional Chinese medicine

Traditional Chinese medicine is precious treasure of ancient Chinese science and a key to unlocking the treasure trove of Chinese civilization. To elucidate the efficacy and mechanism of traditional Chinese medicines, scientists have been engaged in the research on the molecular basis and regulatory targets. Molecular docking is a computer-aided drug design method capable of visualizing the interaction between components and target proteins. With the progress in the modernization of traditional Chinese medicine and the advancement of algorithms and computing power, molecular docking has become an essential approach in the development of new traditional Chinese medicines. This article summarizes the recent research progress in molecular docking in the development of traditional Chinese medicine, aiming to provide valuable references for further screening of active components and offering insights for improving the development of new traditional Chinese medicines.

In silico docking of anti-Alzheimer’s molecules from plant derivatives

Alzheimer’s disease is a progressive neurodegenerative disease and most often associated with memory deficits and cognitive decline. This study pertains to the development of plant based molecules that can help treating the Alzheimer’s conditions. Plant based molecules usually render no side effects, compared to the Allopathic drugs. Also, this study is based on the novel approach of Computer aided drug design. The molecules selected for study are screened for drug likeness property using DruLiTo software. The molecules are also screened for presence of carcinogenicity and mutagenicity using T.E.S.T software. The molecule is then docked with the receptor using the Molegro software. The best pose is selected and results are tabulated and concluded. Any molecule can be considered as ‘well-bound’ or ‘well-docked’ if it expresses a fairly negative docking score. The H-bond energy is also a parameter to be considered. Negative H-bond energy is correlated with strong H-bond interaction between the amino acid residues and the molecule. Out of the 3 compounds, Compound 1 [Punicic acid] docked with Acetylcholine Esterase Receptor[1ACJ] displayed the highest negative moldock score [-156.709] and is very well bound to the receptor, followed by compound 2 [Ferrulic acid] and compound 3[Caeffic acd]. These plant based molecules can be further tested to evaluate the extent of their anti-Alzheimer’s activity through pre-clinical and clinical testing and may also be incorporated in Ayurvedic medicine for treating Alzheimer’s disease.

A Hands-On Collaboration-Ready Single- or Interdisciplinary Computational Exercise in Molecular Recognition and Drug Design

Molecular docking plays an increasingly necessary role in interdisciplinary research, particularly in modern drug design. Pharmaceutical companies compose a trillion dollar per year industry and the public is generally unaware of how beneficial pharmaceutics come to be. Despite this increasing relevance in contemporary research, docking and, by extension, computational science, have been under-represented in undergraduate education in the chemical, biochemical, and biophysical sciences. We describe herein how a multidisciplinary approach is used to design novel inhibitors of the butyrylcholinesterase enzyme (BChE), an upregulated protein in patients suffering from Alzheimer’s disease. Students will then be able to compare their designed inhibitors to known BChE inhibitors via molecular docking using this easily adapted hands-on computational laboratory exercise or at-home activity that provides users with a module in which to learn the fundamentals of computer-aided drug design. While being well suited for upper-division courses in biology/biochemistry and physics/physical chemistry, the accessibility of this module allows for its incorporation into college curricula as early as second-term organic chemistry. Highly portable freeware makes this an ideal learning tool by which to infuse single- or multidisciplinary drug design reasoning into college level curricula at no cost to the student or instructor.

Construction of microgravity biological knowledge graph and its applications in anti-osteoporosis drug prediction

Microgravity in the space environment can potentially have various negative effects on the human body, one of which is bone loss. Given the increasing frequency of human space activities, there is an urgent need to identify effective anti-osteoporosis drugs for the microgravity environment. Traditional microgravity experiments conducted in space suffer from limitations such as time-consuming procedures, high costs, and small sample sizes. In recent years, the in-silico drug discovery method has emerged as a promising strategy due to the advancements in bioinformatics and computer technology. In this study, we first collected a total of 184,915 literature articles related to microgravity and bone loss. We employed a combination of dependency path extraction and clustering techniques to extract data from the text. Afterwards, we conducted data cleaning and standardization to integrate data from several sources, including The Global Network of Biomedical Relationships (GNBR), Curated Drug–Drug Interactions Database (DDInter), Search Tool for Interacting Chemicals (STITCH), DrugBank, and Traditional Chinese Medicines Integrated Database (TCMID). Through this integration process, we constructed the Microgravity Biology Knowledge Graph (MBKG) consisting of 134,796 biological entities and 3,395,273 triplets. Subsequently, the TransE model was utilized to perform knowledge graph embedding. By calculating the distances between entities in the model space, the model successfully predicted potential drugs for treating osteoporosis and microgravity-induced bone loss. The results indicate that out of the top 10 ranked western medicines, 7 have been approved for the treatment of osteoporosis. Additionally, among the top 10 ranked traditional Chinese medicines, 5 have scientific literature supporting their effectiveness in treating bone loss. Among the top 20 predicted medicines for microgravity-induced bone loss, 15 have been studied in microgravity or simulated microgravity environments, while the remaining 5 are also applicable for treating osteoporosis. This research highlights the potential application of MBKG in the field of space drug discovery.

Herbicide Safeners: From Molecular Structure Design to Safener Activity.

Herbicide safeners, highly effective antidotes, find widespread application in fields for alleviating the phytotoxicity of herbicides to crops. Designing new herbicide safeners remains a notable issue in pesticide research. This review focuses on discussing and summarizing the structure-activity relationships, molecular structures, physicochemical properties, and molecular docking of herbicide safeners in order to explore how different structures affect the safener activities of target compounds. It also provides insights into the application prospects of computer-aided drug design for designing and synthesizing new safeners in the future.

Design of new molecules against cervical cancer using DFT, theoretical spectroscopy, 2D/3D-QSAR, molecular docking, pharmacophore and ADMET investigations

Cervical cancer is a major health problem of women. Hormone therapy, via aromatase inhibition, has been proposed as a promising way of blocking estrogen production as well as treating the progression of estrogen-dependent cancer. To overcome the challenging complexities of costly drug design, in-silico strategy, integrating Structure-Based Drug Design (SBDD) and Ligand-Based Drug Design (LBDD), was applied to large representative databases of 39 quinazoline and thioquinazolinone compound derivatives. Quantum chemical and physicochemical descriptors have been investigated using density functional theory (DFT) and MM2 force fields, respectively, to develop 2D-QSAR models, while CoMSIA and CoMFA descriptors were used to build 3D-QSAR models. The robustness and predictive power of the reliable models were verified, via several validation methods, leading to the design of 6 new drug-candidates. Afterwards, 2 ligands were carefully selected using virtual screening methods, taking into account the applicability domain, synthetic accessibility, and Lipinski's criteria. Molecular docking and pharmacophore modelling studies were performed to examine potential interactions with aromatase (PDB ID: 3EQM). Finally, the ADMET properties were investigated in order to select potential drug-candidates against cervical cancer for experimental in vitro and in vivo testing.

PlayMolecule Viewer: A Toolkit for the Visualization of Molecules and Other Data.

PlayMolecule Viewer is a web-based data visualization toolkit designed to streamline the exploration of data resulting from structural bioinformatics or computer-aided drug design efforts. By harnessing state-of-the-art web technologies such as WebAssembly, PlayMolecule Viewer integrates powerful Python libraries directly within the browser environment, which enhances its capabilities to manage multiple types of molecular data. With its intuitive interface, it allows users to easily upload, visualize, select, and manipulate molecular structures and associated data. The toolkit supports a wide range of common structural file formats and offers a variety of molecular representations to cater to different visualization needs. PlayMolecule Viewer is freely accessible at open.playmolecule.org, ensuring accessibility and availability to the scientific community and beyond.

Application of Deep Learning Neural Networks in Computer-aided Drug Discovery: A Review

Abstract: Computer-aided drug design has an important role in drug development and design. It has become a thriving area of research in the pharmaceutical industry to accelerate the drug discovery process. Deep learning, a subdivision of artificial intelligence, is widely applied to advance new drug development and design opportunities. This article reviews the recent technology that uses deep learning techniques to ameliorate the understanding of drug-target interactions in computer-aided drug discovery based on the prior knowledge acquired from various literature. In general, deep learning models can be trained to predict the binding affinity between the protein-ligand complexes and protein structures or generate protein-ligand complexes in structure-based drug discovery. In other words, artificial neural networks and deep learning algorithms, especially graph convolutional neural networks and generative adversarial networks, can be applied to drug discovery. Graph convolutional neural network effectively captures the interactions and structural information between atoms and molecules, which can be enforced to predict the binding affinity between protein and ligand. Also, the ligand molecules with the desired properties can be generated using generative adversarial networks.

Optimization of CHARMM force field parameters for ryanodine receptor inhibitory drug dantrolene using FFTK and FFParam.

Ryanodine receptors (RyRs) are large intracellular ligand-gated calcium release ion channels. Mutations in human RyR1 in combination with a volatile anesthetic or muscle relaxant are known to cause leaky RyRs resulting in malignant hyperthermia (MH). This has long been primarily treated with the RyR inhibitory drug dantrolene. Alternatives to dantrolene as a RyR inhibitor may be found through computer-aided drug design. Additionally, molecular dynamics (MD) studies of dantrolene interacting with RyRs may reveal its full mechanism of action. The availability of accurate force field parameters is important for the success of both. In this study, force field parameters for dantrolene were obtained from the CHARMM General Force Field (CGenFF) program and optimized using the force field toolkit (FFTK) and FFParam programs. The obtained parameters were then validated by a comparison between calculated and experimental IR spectra and normal mode analysis, among other techniques.

New Drug Design to Suppress Nonalcoholic Steatohepatitis

A de novo designed biomolecule called INASHD was utilized through computer-aided drug design techniques to specifically target β2-spectrin, effectively suppressing and preventing NASH disease. Advanced computational software tools concerning the technologies of molecular docking and molecular dynamics (MD), were employed to showcase the drug's remarkable ability to efficiently suppress and control the α-helical topology of β2-spectrin. This protein is a vital component within the disease pathway. We successfully devised an effective design suppressing β2-spectrin, exhibiting an inhibition score surpassing any other molecule documented in scientific literature. With robust support from validated computational software, this bioorganic structure holds significant value and can be applied for a patent due to its innovative design. It shows promising potential for delivering positive outcomes in various stages, including in vitro, in vivo, ex vivo, and human phase studies.

In silico construction of a focused fragment library facilitating exploration of chemical space.

Fragment-based drug design (FBDD) has emerged as a captivating subject in the realm of computer-aided drug design, enabling the generation of novel molecules through the rearrangement of ring systems within known compounds. The construction of focused fragment library plays a pivotal role in FBDD, necessitating the compilation of all potential bioactive ring systems capable of interacting with a specific target. In our study, we propose a workflow for the development of a focused fragment library and combinatorial compound library. The fragment library comprises seed fragments and collected fragments. The extraction of seed fragments is guided by receptor information, serving as a prerequisite for establishing a focused libraries. Conversely, collected fragments are obtained using the feature graph method, which offers a simplified representation of fragments and strikes a balance between diversity and similarity when categorizing different fragments. The utilization of feature graph facilitates the rational partitioning of chemical space at fragment level, enabling the exploration of desired chemical space and enhancing the efficiency of screening compound library. Analysis demonstrates that our workflow enables the enumeration of a greater number of entirely new potential compounds, thereby aiding in the rational design of drugs.

Lysine-Specific Demethylase 1 Inhibitors: A Comprehensive Review Utilizing Computer-Aided Drug Design Technologies.

Lysine-specific demethylase 1 (LSD1/KDM1A) has emerged as a promising therapeutic target for treating various cancers (such as breast cancer, liver cancer, etc.) and other diseases (blood diseases, cardiovascular diseases, etc.), owing to its observed overexpression, thereby presenting significant opportunities in drug development. Since its discovery in 2004, extensive research has been conducted on LSD1 inhibitors, with notable contributions from computational approaches. This review systematically summarizes LSD1 inhibitors investigated through computer-aided drug design (CADD) technologies since 2010, showcasing a diverse range of chemical scaffolds, including phenelzine derivatives, tranylcypromine (abbreviated as TCP or 2-PCPA) derivatives, nitrogen-containing heterocyclic (pyridine, pyrimidine, azole, thieno[3,2-b]pyrrole, indole, quinoline and benzoxazole) derivatives, natural products (including sanguinarine, phenolic compounds and resveratrol derivatives, flavonoids and other natural products) and others (including thiourea compounds, Fenoldopam and Raloxifene, (4-cyanophenyl)glycine derivatives, propargylamine and benzohydrazide derivatives and inhibitors discovered through AI techniques). Computational techniques, such as virtual screening, molecular docking and 3D-QSAR models, have played a pivotal role in elucidating the interactions between these inhibitors and LSD1. Moreover, the integration of cutting-edge technologies such as artificial intelligence holds promise in facilitating the discovery of novel LSD1 inhibitors. The comprehensive insights presented in this review aim to provide valuable information for advancing further research on LSD1 inhibitors.

Computational fragment-based drug design of potential Glo-I inhibitors

In this study, a fragment-based drug design approach, particularly de novo drug design, was implemented utilising three different crystal structures in order to discover new privileged scaffolds against glyoxalase-I enzyme as anticancer agents. The fragments were evoluted to indicate potential inhibitors with high receptor affinities. The resulting compounds were served as a benchmark for choosing similar compounds from the ASINEX® database by applying different computational ligand-based drug design techniques. Afterwards, the selection of potential hits was further aided by various structure-based approaches. Then, 14 compounds were purchased, and tested in vitro against Glo-I enzyme. Of the tested 14 hits, the biological screening results showed humble activities where the percentage of Glo-I inhibition ranged from 0–18.70 %. Compound 19 and compound 28, whose percentage of inhibitions are 18.70 and 15.80%, respectively, can be considered as hits that need further optimisation in order to be converted into lead-like compounds.

QSAR of Oxazinanone Derivatives As 11-Β Hydroxysteroid Dehydrogenase Type 1 Inhibitor A Potent Anti Diabetic Agent

11-β hydroxysteroid dehydrogenase type 1 is a key enzyme accountable for the interconversion of physiologically inert cortisone to active cortisol thus presents an effective target for the development of pharmacologically active anti diabetic agents focused on manage blood glucose levels, improve insulin sensitivity. The 11β-HSD1 facilitates intracellular cortisol construction that have a disease-causing role in type 2 diabetes and the co-morbidities that it causes. Drugs in habiting the enzyme 11 β-HSD1 offers a potential therapy to lessen the type 2 diabetes. Oxazinanone ring has shown activities as antitumor, antihypertensive, antibacterial, anti-inflammatory, antioxidant and many more. Oxazinanone ring have emerged as potent inhibitors of 11β-HSD1 enzyme. QSAR of Oxazinanone derivatives is performed with a goal of elucidating the key characteristics that cause their anti-diabetic action. QSAR is the most widespread method to ligand-based drug design. It is supposed that structures of the molecules are directly proportional with biological activities, and thus, the biological activities can be altered with any structural changes. The process involves computational or mathematical models to find important correlations between a series of structures and functions. Step wise partial least square, multiple linear regressions, and feed forward neural network were used in a QSAR investigation on enzyme (IC50 nM). The developed models were cross confirmed by the ‘‘leave one out’’ method. The model reveals the significance of steric parameter Verloop B1 (Substitution 1) and Total lipole molecular descriptor.Total lipole bear a resemblance to lipophilicity which is a ratio of the capability of molecules to transfer between oily partition and aqueous partition. These descriptors will have an impact on the design and expansion of novel anti-diabetic 11-hydroxysteroid dehydrogenase type 1 inhibitors.