In silico prediction of ROCK II inhibitors by different classification approaches

Enhancing property and activity prediction and interpretation using multiple molecular graph representations with MMGX

Graph Neural Networks (GNNs) excel in compound property and activity prediction, but the choice of molecular graph representations significantly influences model learning and interpretation. While atom-level molecular graphs resemble natural topology, they overlook key substructures or functional groups and their interpretation partially aligns with chemical intuition. Recent research suggests alternative representations using reduced molecular graphs to integrate higher-level chemical information and leverages both representations for model. However, there is a lack of studies about applicability and impact of different molecular graphs on model learning and interpretation. Here, we introduce MMGX (Multiple Molecular Graph eXplainable discovery), investigating the effects of multiple molecular graphs, including Atom, Pharmacophore, JunctionTree, and FunctionalGroup, on model learning and interpretation with various perspectives. Our findings indicate that multiple graphs relatively improve model performance, but in varying degrees depending on datasets. Interpretation from multiple graphs in different views provides more comprehensive features and potential substructures consistent with background knowledge. These results help to understand model decisions and offer valuable insights for subsequent tasks. The concept of multiple molecular graph representations and diverse interpretation perspectives has broad applicability across tasks, architectures, and explanation techniques, enhancing model learning and interpretation for relevant applications in drug discovery.

Recent advances in the development of Rho kinase inhibitors (2015-2021)

Rho-associated coiled-coil kinases (ROCKs) are key downstream effectors of small GTPases. ROCK plays a central role in diverse cellular events with accumulating evidence supporting the concept that ROCK is important in tumor development and progression. Numerous ROCK inhibitors have been investigated for their therapeutic potential in the treatment of cancers. In this article, we review recent research progress on ROCK inhibitors, especially those with potential for the treatment of cancers, reported in the literature from 2015 to 2021. Most ROCK inhibitors show potent in vitro and in vivo antitumor activities and have potential in the treatment of cancers.

Identification of Drug Targets and Their Inhibitors in Yersinia pestis Strain 91001 through Subtractive Genomics, Machine Learning, and MD Simulation Approaches

Yersinia pestis, the causative agent of plague, is a Gram-negative bacterium. If the plague is not properly treated it can cause rapid death of the host. Bubonic, pneumonic, and septicemic are the three types of plague described. Bubonic plague can progress to septicemic plague, if not diagnosed and treated on time. The mortality rate of pneumonic and septicemic plague is quite high. The symptom-defining disease is the bubo, which is a painful lymph node swelling. Almost 50% of bubonic plague leads to sepsis and death if not treated immediately with antibiotics. The host immune response is slow as compared to other bacterial infections. Clinical isolates of Yersinia pestis revealed resistance to many antibiotics such as tetracycline, spectinomycin, kanamycin, streptomycin, minocycline, chloramphenicol, and sulfonamides. Drug discovery is a time-consuming process. It always takes ten to fifteen years to bring a single drug to the market. In this regard, in silico subtractive proteomics is an accurate, rapid, and cost-effective approach for the discovery of drug targets. An ideal drug target must be essential to the pathogen's survival and must be absent in the host. Machine learning approaches are more accurate as compared to traditional virtual screening. In this study, k-nearest neighbor (kNN) and support vector machine (SVM) were used to predict the active hits against the beta-ketoacyl-ACP synthase III drug target predicted by the subtractive genomics approach. Among the 1012 compounds of the South African Natural Products database, 11 hits were predicted as active. Further, the active hits were docked against the active site of beta-ketoacyl-ACP synthase III. Out of the total 11 active hits, the 3 lowest docking score hits that showed strong interaction with the drug target were shortlisted along with the standard drug and were simulated for 100 ns. The MD simulation revealed that all the shortlisted compounds display stable behavior and the compounds formed stable complexes with the drug target. These compounds may have the potential to inhibit the beta-ketoacyl-ACP synthase III drug target and can help to combat Yersinia pestis-related infections. The dataset and the source codes are freely available on GitHub.

Activity Models of Key GPCR Families in the Central Nervous System: A Tool for Many Purposes

G protein-coupled receptors (GPCRs) are targets of many drugs, of which ∼25% are indicated for central nervous system (CNS) disorders. Drug promiscuity affects their efficacy and safety profiles. Predicting the polypharmacology profile of compounds against GPCRs can thus provide a basis for producing more precise therapeutics by considering the targets and the anti-targets in that family of closely related proteins. We provide a tool for predicting the polypharmacology of compounds within prominent GPCR families in the CNS: serotonin, dopamine, histamine, muscarinic, opioid, and cannabinoid receptors. Our in-house algorithm, "iterative stochastic elimination" (ISE), produces high-quality ligand-based models for agonism and antagonism at 31 GPCRs. The ISE models correctly predict 68% of CNS drug-GPCR interactions, while the "similarity ensemble approach" predicts only 33%. The activity models correctly predict 56% of reported activities of DrugBank molecules for these CNS receptors. We conclude that the combination of interactions and activity profiles generated by screening through our models form the basis for subsequent designing and discovering novel therapeutics, either single, multitargeting, or repurposed.

iANP-EC: Identifying Anticancer Natural Products Using Ensemble Learning Incorporated with Evolutionary Computation

Cancer is one of the most deadly diseases that annually kills millions of people worldwide. The investigation on anticancer medicines has never ceased to seek better and more adaptive agents with fewer side effects. Besides chemically synthetic anticancer compounds, natural products are scientifically proved as a highly potential alternative source for anticancer drug discovery. Along with experimental approaches being used to find anticancer drug candidates, computational approaches have been developed to virtually screen for potential anticancer compounds. In this study, we construct an ensemble computational framework, called iANP-EC, using machine learning approaches incorporated with evolutionary computation. Four learning algorithms (k-NN, SVM, RF, and XGB) and four molecular representation schemes are used to build a set of classifiers, among which the top-four best-performing classifiers are selected to form an ensemble classifier. Particle swarm optimization (PSO) is used to optimise the weights used to combined the four top classifiers. The models are developed by a set of curated 997 compounds which are collected from the NPACT and CancerHSP databases. The results show that iANP-EC is a stable, robust, and effective framework that achieves an AUC-ROC value of 0.9193 and an AUC-PR value of 0.8366. The comparative analysis of molecular substructures between natural anticarcinogens and nonanticarcinogens partially unveils several key substructures that drive anticancerous activities. We also deploy the proposed ensemble model as an online web server with a user-friendly interface to support the research community in identifying natural products with anticancer activities.

Chemical Distance Measurement and System Pharmacology Approach Uncover the Novel Protective Effects of Biotransformed Ginsenoside C-Mc against UVB-Irradiated Photoaging

Long-term exposure to ultraviolet light induces photoaging and may eventually increase the risk of skin carcinogenesis. Rare minor ginsenosides isolating from traditional medicine Panax (ginseng) have shown biomedical efficacy as antioxidation and antiphotodamage agents. However, due to the difficulty of component extraction and wide variety of ginsenoside, the identification of active antiphotoaging ginsenoside remains a huge challenge. In this study, we proposed a novel in silico approach to identify potential compound against photoaging from 82 ginsenosides. Specifically, we calculated the shortest distance between unknown and known antiphotoaging ginsenoside set in the chemical space and applied chemical structure similarity assessment, drug-likeness screening, and ADMET evaluation for the candidates. We highlighted three rare minor ginsenosides (C-Mc, Mx, and F2) that possess high potential as antiphotoaging agents. Among them, C-Mc deriving from American ginseng (Panax quinquefolius L.) was validated by wet-lab experimental assays and showed significant antioxidant and cytoprotective activity against UVB-induced photodamage in human dermal fibroblasts. Furthermore, system pharmacology analysis was conducted to explore the therapeutic targets and molecular mechanisms through integrating global drug-target network, high quality photoaging-related gene profile from multiomics data, and skin tissue-specific expression protein network. In combination with in vitro assays, we found that C-Mc suppressed MMP production through regulating the MAPK/AP-1/NF-κB pathway and expedited collagen synthesis via the TGF-β/Smad pathway, as well as enhanced the expression of Nrf2/ARE to hold a balance of endogenous oxidation. Overall, this study offers an effective drug discovery framework combining in silico prediction and in vitro validation, uncovering that ginsenoside C-Mc has potential antiphotoaging properties and might be a novel natural agent for use in oral drug, skincare products, or functional food.

In Silico Prediction and Bioactivity Evaluation of Chemical Ingredients Against Influenza A Virus From Isatis tinctoria L

Influenza A virus (IAV) is one of the major causes of seasonal endemic diseases and unpredictable periodic pandemics. Due to the high mutation rate and drug resistance, it poses a persistent threat and challenge to public health. Isatis tinctoria L. (Banlangen, BLG), a traditional herbal medicine widely used in Asian countries, has been reported to possess strong efficacy on respiratory viruses, including IAV. However, its effective anti-IAV components and the mechanism of actions (MOAs) are not yet fully elucidated. In this study, we first summarized the chemical components and corresponding contents in BLG according to current available chemical analysis literature. We then presented a network-based in silico framework for identifying potential drug candidates against IAV from BLG. A total of 269 components in BLG were initially screened by drug-likeness and ADME (absorption, distribution, metabolism, and excretion) evaluation. Thereafter, network predictive models were built via the integration of compound–target networks and influenza virus–host proteins. We highlighted 23 compounds that possessed high potential as anti-influenza virus agents. Through experimental evaluation, six compounds, namely, eupatorin, dinatin, linarin, tryptanthrin, indirubin, and acacetin, exhibited good inhibitory activity against wild-type H1N1 and H3N2. Particularly, they also exerted significant effects on drug-resistant strains. Finally, we explored the anti-IAV MOAs of BLG and showcased the potential biological pathways by systems pharmacology analysis. In conclusion, this work provides important information on BLG regarding its use in the development of anti-IAV drugs, and the network-based prediction framework proposed here also offers a powerfulful strategy for the in silico identification of novel drug candidates from complex components of herbal medicine.

CardioTox net: a robust predictor for hERG channel blockade based on deep learning meta-feature ensembles

MOTIVATION

Ether-a-go-go-related gene (hERG) channel blockade by small molecules is a big concern during drug development in the pharmaceutical industry. Blockade of hERG channels may cause prolonged QT intervals that potentially could lead to cardiotoxicity. Various in-silico techniques including deep learning models are widely used to screen out small molecules with potential hERG related toxicity. Most of the published deep learning methods utilize a single type of features which might restrict their performance. Methods based on more than one type of features such as DeepHIT struggle with the aggregation of extracted information. DeepHIT shows better performance when evaluated against one or two accuracy metrics such as negative predictive value (NPV) and sensitivity (SEN) but struggle when evaluated against others such as Matthew correlation coefficient (MCC), accuracy (ACC), positive predictive value (PPV) and specificity (SPE). Therefore, there is a need for a method that can efficiently aggregate information gathered from models based on different chemical representations and boost hERG toxicity prediction over a range of performance metrics.

RESULTS

In this paper, we propose a deep learning framework based on step-wise training to predict hERG channel blocking activity of small molecules. Our approach utilizes five individual deep learning base models with their respective base features and a separate neural network to combine the outputs of the five base models. By using three external independent test sets with potency activity of IC50 at a threshold of 10 [Formula: see text]m, our method achieves better performance for a combination of classification metrics. We also investigate the effective aggregation of chemical information extracted for robust hERG activity prediction. In summary, CardioTox net can serve as a robust tool for screening small molecules for hERG channel blockade in drug discovery pipelines and performs better than previously reported methods on a range of classification metrics.

A review on machine learning approaches and trends in drug discovery

Drug discovery aims at finding new compounds with specific chemical properties for the treatment of diseases. In the last years, the approach used in this search presents an important component in computer science with the skyrocketing of machine learning techniques due to its democratization. With the objectives set by the Precision Medicine initiative and the new challenges generated, it is necessary to establish robust, standard and reproducible computational methodologies to achieve the objectives set. Currently, predictive models based on Machine Learning have gained great importance in the step prior to preclinical studies. This stage manages to drastically reduce costs and research times in the discovery of new drugs. This review article focuses on how these new methodologies are being used in recent years of research. Analyzing the state of the art in this field will give us an idea of where cheminformatics will be developed in the short term, the limitations it presents and the positive results it has achieved. This review will focus mainly on the methods used to model the molecular data, as well as the biological problems addressed and the Machine Learning algorithms used for drug discovery in recent years.

Recent trends in artificial intelligence-driven identification and development of anti-neurodegenerative therapeutic agents

Neurological disorders affect various aspects of life. Finding drugs for the central nervous system is a very challenging and complex task due to the involvement of the blood-brain barrier, P-glycoprotein, and the drug's high attrition rates. The availability of big data present in online databases and resources has enabled the emergence of artificial intelligence techniques including machine learning to analyze, process the data, and predict the unknown data with high efficiency. The use of these modern techniques has revolutionized the whole drug development paradigm, with an unprecedented acceleration in the central nervous system drug discovery programs. Also, the new deep learning architectures proposed in many recent works have given a better understanding of how artificial intelligence can tackle big complex problems that arose due to central nervous system disorders. Therefore, the present review provides comprehensive and up-to-date information on machine learning/artificial intelligence-triggered effort in the brain care domain. In addition, a brief overview is presented on machine learning algorithms and their uses in structure-based drug design, ligand-based drug design, ADMET prediction, de novo drug design, and drug repurposing. Lastly, we conclude by discussing the major challenges and limitations posed and how they can be tackled in the future by using these modern machine learning/artificial intelligence approaches.

Quantitative Toxicity Prediction via Meta Ensembling of Multitask Deep Learning Models

Toxicity prediction using quantitative structure-activity relationship has achieved significant progress in recent years. However, most existing machine learning methods in toxicity prediction utilize only one type of feature representation and one type of neural network, which essentially restricts their performance. Moreover, methods that use more than one type of feature representation struggle with the aggregation of information captured within the features since they use predetermined aggregation formulas. In this paper, we propose a deep learning framework for quantitative toxicity prediction using five individual base deep learning models and their own base feature representations. We then propose to adopt a meta ensemble approach using another separate deep learning model to perform aggregation of the outputs of the individual base deep learning models. We train our deep learning models in a weighted multitask fashion combining four quantitative toxicity data sets of LD50, IGC50, LC50, and LC50-DM and minimizing the root-mean-square errors. Compared to the current state-of-the-art toxicity prediction method TopTox on LD50, IGC50, and LC50-DM, that is, three out of four data sets, our method, respectively, obtains 5.46, 16.67, and 6.34% better root-mean-square errors, 6.41, 11.80, and 12.16% better mean absolute errors, and 5.21, 7.36, and 2.54% better coefficients of determination. We named our method QuantitativeTox, and our implementation is available from the GitHub repository https://github.com/Abdulk084/QuantitativeTox.

Identification of novel Src, Bcl-2 dual inhibitors by the pharmacophore model, molecular docking, and molecular dynamics simulations

Src is a tyrosine kinase that plays a key role in cell proliferation, migration, invasion, and angiogenesis.

Design and screening of FAK, CDK 4/6 dual inhibitors by pharmacophore model, molecular docking, and molecular dynamics simulation

Focal adhesion kinase (FAK) is one kind of tyrosine kinases that modulates integrin and growth factor signaling pathways, which is a promising therapeutic target because of involving in the migration, proliferation and survival of cancer cell. Overexpression and amplification of cyclin-dependent kinase 4/6 (CDK4/6) occur in many cancers and may be the cause of resistance to CDK4/6 inhibitors in preclinical models. The latest research shows that the combination of FAK and CDK4/6 can be dually targeted to enhance the antitumor effects. In this study, FAK and CDK4/6 dual target inhibitors were designed by computer-aided drug design. Seven million molecules were screened by the pharmacophore model and molecular docking. Finally, 6 compounds were obtained. Molecular dynamics simulation of compound 1, 2 and 3 showed that it has good binding stability to both receptors. According to the binding modes of compound 1 with two receptors, corresponding modifications were made, and 7 novel designed compounds were obtained. The docking energy of these novel designed compounds were lower than that of compound 1, and they can be tested in future.Communicated by Ramaswamy H. Sarma.

Study on the interactions of pyrimidine derivatives with FAK by 3D-QSAR, molecular docking and molecular dynamics simulation

Focal adhesion kinase (FAK) is a kind of tyrosine kinase that modulates integrin and growth factor signaling pathways.

Design and screening of SGK1, Src dual inhibitors using pharmacophore models, molecular docking, and molecular dynamics simulation

Serum and glucocorticoid-regulated protein kinase 1 that can promote the growth of tumor cells is highly expressed in many tumors. Sarcoma gene plays an important role in the pathogenesis of cancer and is an important kinase in tumor cell expression pathways.

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery

Artificial intelligence (AI), and, in particular, deep learning as a subcategory of AI, provides opportunities for the discovery and development of innovative drugs. Various machine learning approaches have recently (re)emerged, some of which may be considered instances of domain-specific AI which have been successfully employed for drug discovery and design. This review provides a comprehensive portrayal of these machine learning techniques and of their applications in medicinal chemistry. After introducing the basic principles, alongside some application notes, of the various machine learning algorithms, the current state-of-the art of AI-assisted pharmaceutical discovery is discussed, including applications in structure- and ligand-based virtual screening, de novo drug design, physicochemical and pharmacokinetic property prediction, drug repurposing, and related aspects. Finally, several challenges and limitations of the current methods are summarized, with a view to potential future directions for AI-assisted drug discovery and design.

Trader as a new optimization algorithm predicts drug-target interactions efficiently

Several machine learning approaches have been proposed for predicting new benefits of the existing drugs. Although these methods have introduced new usage(s) of some medications, efficient methods can lead to more accurate predictions. To this end, we proposed a novel machine learning method which is based on a new optimization algorithm, named Trader. To show the capabilities of the proposed algorithm which can be applied to the different scope of science, it was compared with ten other state-of-the-art optimization algorithms based on the standard and advanced benchmark functions. Next, a multi-layer artificial neural network was designed and trained by Trader to predict drug-target interactions (DTIs). Finally, the functionality of the proposed method was investigated on some DTIs datasets and compared with other methods. The data obtained by Trader showed that it eliminates the disadvantages of different optimization algorithms, resulting in a better outcome. Further, the proposed machine learning method was found to achieve a significant level of performance compared to the other popular and efficient approaches in predicting unknown DTIs. All the implemented source codes are freely available at https://github.com/LBBSoft/Trader .

Deep Learning-Based Prediction of Drug-Induced Cardiotoxicity

Blockade of the human ether-à-go-go-related gene (hERG) channel by small molecules induces the prolongation of the QT interval which leads to fatal cardiotoxicity and accounts for the withdrawal or severe restrictions on the use of many approved drugs. In this study, we develop a deep learning approach, termed deephERG, for prediction of hERG blockers of small molecules in drug discovery and postmarketing surveillance. In total, we assemble 7,889 compounds with well-defined experimental data on the hERG and with diverse chemical structures. We find that deephERG models built by a multitask deep neural network (DNN) algorithm outperform those built by single-task DNN, naı̈ve Bayes (NB), support vector machine (SVM), random forest (RF), and graph convolutional neural network (GCNN). Specifically, the area under the receiver operating characteristic curve (AUC) value for the best model of deephERG is 0.967 on the validation set. Furthermore, based on 1,824 U.S. Food and Drug Administration (FDA) approved drugs, 29.6% drugs are computationally identified to have potential hERG inhibitory activities by deephERG, highlighting the importance of hERG risk assessment in early drug discovery. Finally, we showcase several novel predicted hERG blockers on approved antineoplastic agents, which are validated by clinical case reports, experimental evidence, and the literature. In summary, this study presents a powerful deep learning-based tool for risk assessment of hERG-mediated cardiotoxicities in drug discovery and postmarketing surveillance.

Fasudil in Combination With Bone Marrow Stromal Cells (BMSCs) Attenuates Alzheimer's Disease-Related Changes Through the Regulation of the Peripheral Immune System

Alzheimer’s disease (AD) is a chronic progressive neurodegenerative disease. Its mechanism is still not clear. Majority of research focused on the central nervous system (CNS) changes, while few studies emphasize on peripheral immune system modulation. Our study aimed to investigate the regulation of the peripheral immune system and its relationship to the severity of the disease after treatment in an AD model of APPswe/PSEN1dE9 transgenic (APP/PS1 Tg) mice. APP/PS1 Tg mice (8 months old) were treated with the ROCK-II inhibitor 1-(5-isoquinolinesulfonyl)-homo-piperazine (Fasudil) (intraperitoneal (i.p.) injections, 25 mg/kg/day), bone marrow stromal cells (BMSCs; caudal vein injections, 1 × 10⁶ BMSCs /time/mouse), Fasudil combined with BMSCs, or saline (i.p., control) for 2 months. Morris water maze (MWM) test was used to evaluate learning and memory. The mononuclear cells (MNCs) of spleens of APP/PS1 Tg mice were analyzed using flow cytometry for CD4+ T-cells, macrophages, and the pro-inflammatory and anti-inflammatory molecules of the macrophages. Immunohistochemical staining was used to examine the expression of ROCK-II in the spleens of APP/PS1 Tg mice. The MWM test showed improved spatial learning ability in APP/PS1 Tg mice treated with Fasudil or BMSCs alone or in combination, compared to untreated APP/PS1 Tg mice. Fasudil combined with BMSCs intervention significantly promoted the proliferation of CD4+/CD25+ and CD4+/ IL-10 lymphocytes, induced the release of cytokine factors, and regulated the balance of the immune system to work functionally. It also shifted M1 (MHC-II, CD86) to M2 (IL-10, CD206) phenotype of macrophages of CD11b and significantly enhanced the anti-inflammatory and phagocytic abilities (CD16/32) of macrophages of CD11b. Immunohistochemical staining showed significantly decreased expression of ROCK-II in mice treated with combination of Fasudil with BMSCs as compared to saline control. Fasudil in combination of BMSCs improved cognition of APP/PS1 Tg mice through the regulation of the peripheral immune system, including reduction of ROCK-II expression and increased proportion of anti-inflammatory M2 mononuclear phenotype and phagocytic macrophages in the spleen of the peripheral immune system. The latter was achieved through the communication between brain and spleen to improve the immunoregulation of CNS and AD disease conditions.