vNN Web Server for ADMET Predictions

DrugFlow: An AI-Driven One-Stop Platform for Innovative Drug Discovery

Artificial intelligence (AI)-aided drug design has demonstrated unprecedented effects on modern drug discovery, but there is still an urgent need for user-friendly interfaces that bridge the gap between these sophisticated tools and scientists, particularly those who are less computer savvy. Herein, we present DrugFlow, an AI-driven one-stop platform that offers a clean, convenient, and cloud-based interface to streamline early drug discovery workflows. By seamlessly integrating a range of innovative AI algorithms, covering molecular docking, quantitative structure-activity relationship modeling, molecular generation, ADMET (absorption, distribution, metabolism, excretion and toxicity) prediction, and virtual screening, DrugFlow can offer effective AI solutions for almost all crucial stages in early drug discovery, including hit identification and hit/lead optimization. We hope that the platform can provide sufficiently valuable guidance to aid real-word drug design and discovery. The platform is available at https://drugflow.com.

admetSAR3.0: a comprehensive platform for exploration, prediction and optimization of chemical ADMET properties

Absorption, distribution, metabolism, excretion and toxicity (ADMET) properties play a crucial role in drug discovery and chemical safety assessment. Built on the achievements of admetSAR and its successor, admetSAR2.0, this paper introduced the new version of the series, admetSAR3.0, as a comprehensive platform for chemical ADMET assessment, including search, prediction and optimization modules. In the search module, admetSAR3.0 hosted over 370 000 high-quality experimental ADMET data for 104 652 unique compounds, and supplemented chemical structure similarity search function to facilitate read-across. In the prediction module, we introduced comprehensive ADMET endpoints and two new sections for environmental and cosmetic risk assessments, empowering admetSAR3.0 to provide prediction for 119 endpoints, more than double numbers compared to the previous version. Furthermore, the advanced multi-task graph neural network framework offered robust and reliable support for ADMET prediction. In particular, a module named ADMETopt was added to automatically optimize the ADMET properties of query molecules through transformation rules or scaffold hopping. Finally, admetSAR3.0 provides user-friendly interfaces for multiple types of input data, such as SMILES string, chemical structure and batch molecule file, and supports various output types, including digital, chart displays and file downloads. In summary, admetSAR3.0 is anticipated to be a valuable and powerful tool in drug discovery and chemical safety assessment at http://lmmd.ecust.edu.cn/admetsar3/.

ADMET-AI: a machine learning ADMET platform for evaluation of large-scale chemical libraries

MOTIVATION

The emergence of large chemical repositories and combinatorial chemical spaces, coupled with high-throughput docking and generative AI, have greatly expanded the chemical diversity of small molecules for drug discovery. Selecting compounds for experimental validation requires filtering these molecules based on favourable druglike properties, such as Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET).

RESULTS

We developed ADMET-AI, a machine learning platform that provides fast and accurate ADMET predictions both as a website and as a Python package. ADMET-AI has the highest average rank on the TDC ADMET Leaderboard, and it is currently the fastest web-based ADMET predictor, with a 45% reduction in time compared to the next fastest public ADMET web server. ADMET-AI can also be run locally with predictions for one million molecules taking just 3.1 h.

AVAILABILITY AND IMPLEMENTATION

The ADMET-AI platform is freely available both as a web server at admet.ai.greenstonebio.com and as an open-source Python package for local batch prediction at github.com/swansonk14/admet_ai (also archived on Zenodo at doi.org/10.5281/zenodo.10372930). All data and models are archived on Zenodo at doi.org/10.5281/zenodo.10372418.

Elevated N1-Acetylspermidine Levels in Doxorubicin-treated MCF-7 Cancer Cells: Histone Deacetylase 10 Inhibition with an N1-Acetylspermidine Mimetic

Cancer drug resistance is associated with metabolic adaptation. Cancer cells have been shown to implicate acetylated polyamines in adaptations during cell death. However, exploring the mimetic of acetylated polyamines as a potential anticancer drug is lacking. We performed intracellular metabolite profiling of human breast cancer MCF-7 cells treated with doxorubicin (DOX), a well known anticancer drug. A novel and in-house vertical tube gel electrophoresis assisted procedure followed by LC-HRMS analysis was employed to detect acetylated polyamines such as N1-acetylspermidine. We designed a mimetic N1-acetylspermidine (MINAS) which is a known substrate of histone deacetylase 10 (HDAC10). Molecular docking and molecular dynamics (MDs) simulations were used to evaluate the inhibitory potential of MINAS against HDAC10. The inhibitory potential and the ADMET profile of MINAS were compared to a known HDAC10 inhibitor Tubastatin A. N1-acetylspermidine, an acetylated form of polyamine, was detected intracellularly in MCF-7 cells treated with DOX over DMSO-treated MCF-7 cells. We designed and curated MINAS (PubChem CID 162679241). Molecular docking and MD simulations suggested the strong and comparable inhibitory potential of MINAS (-8.2 kcal/mol) to Tubastatin A (-8.4 kcal/mol). MINAS and Tubastatin A share similar binding sites on HDAC10, including Ser138, Ser140, Tyr183, and Cys184. Additionally, MINAS has a better ADMET profile compared to Tubastatin A, with a high MRTD value and lower toxicity. In conclusion, the data show that N1-acetylspermidine levels rise during DOX-induced breast cancer cell death. Additionally, MINAS, an N1-acetylspermidine mimetic compound, could be investigated as a potential anticancer drug when combined with chemotherapy like DOX.

Targeting cyclin-dependent kinase 2 CDK2: Insights from molecular docking and dynamics simulation - A systematic computational approach to discover novel cancer therapeutics

Global public health is confronted with significant challenges due to the prevalence of cancer and the emergence of treatment resistance. This work focuses on the identification of cyclin-dependent kinase 2 (CDK2) through a systematic computational approach to discover novel cancer therapeutics. A ligand-based pharmacophore model was initially developed using a training set of seven potent CDK2 inhibitors. The obtained most robust model was characterized by three features: one donor (|Don|) and two acceptors (|Acc|). Screening this model against the ZINC database resulted in identifying 108 hits, which underwent further molecular docking studies. The docking results indicated binding affinity, with energy values ranging from -6.59 kcal mol⁻¹ to -7.40 kcal mol⁻¹ compared to the standard Roscovitine. The top 10 compounds (Z1-Z10) selected from the docking data were further screened for ADMET profiling, ensuring their compliance with pharmacokinetic and toxicological criteria. The top 3 compounds (Z1-Z3) chosen from the docking were subjected to Density Functional Theory (DFT) studies. They revealed significant variations in electronic properties, providing insights into the reactivity, stability, and polarity of these compounds. Molecular dynamics simulations confirmed the stability of the ligand-protein complexes, with acceptable RMSD and RMSF values. Specifically, compound Z1 demonstrated stability, around 2.4 Å, and maintained throughout the 100 ns simulation period with minimal conformational changes, stable RMSD, and consistent protein-ligand interactions.

Predicting ADMET Properties from Molecule SMILE: A Bottom-Up Approach Using Attention-Based Graph Neural Networks

Understanding the pharmacokinetics, safety and efficacy of candidate drugs is crucial for their success. One key aspect is the characterization of absorption, distribution, metabolism, excretion and toxicity (ADMET) properties, which require early assessment in the drug discovery and development process. This study aims to present an innovative approach for predicting ADMET properties using attention-based graph neural networks (GNNs). The model utilizes a graph-based representation of molecules directly derived from Simplified Molecular Input Line Entry System (SMILE) notation. Information is processed sequentially, from substructures to the whole molecule, employing a bottom-up approach. The developed GNN is tested and compared with existing approaches using six benchmark datasets and by encompassing regression (lipophilicity and aqueous solubility) and classification (CYP2C9, CYP2C19, CYP2D6 and CYP3A4 inhibition) tasks. Results show the effectiveness of our model, which bypasses the computationally expensive retrieval and selection of molecular descriptors. This approach provides a valuable tool for high-throughput screening, facilitating early assessment of ADMET properties and enhancing the likelihood of drug success in the development pipeline.

Tinospora cordifolia Extract Enhances Dextromethorphan Bioavailability: Implications for Alzheimer's Disease

Tinospora cordifolia (Willd.) Miers (Menispermaceae) is a traditional rejuvenator and a conventional medicine used to manage oxidative stress-related diseases, including those associated with the central nervous system. Decreased dextromethorphan (DEM) metabolism is necessary for high bioavailability and application against Alzheimer's disease (AD). Since T. cordifolia stem extract (TCE) can potentially inhibit several metabolic enzymes, it can also enhance dextromethorphan bioavailability. This study investigates the potential of TCE to improve DEM's bioavailability and efficacy for the management of AD. In silico analysis was carried out to find the inhibition potential of phytocomponents of T. cordifolia for CYP2D6 and CYP3A4. The LC-MS method was revalidated for the analysis of DEM and metabolite dextrorphan (DEX) in the presence of quinidine (QN). The ratio of DEM to DEX was estimated with varying doses of TCE following pharmacokinetic analysis. Network pharmacology analysis was carried out to understand the complementary potential of phytocomponents. This was further validated in the scopolamine-induced dementia model through behavioral and histopathological analyses. TCE (100 mg/kg) for 14 days increased the DEM to DEX ratio by 2.8-fold compared to QN treatment. While T max was comparable to that of QN treatment at this dose (100 mg/kg) of TCE, it increased significantly at the higher dose (400 mg/kg) of TCE pretreatment. All other pharmacokinetic parameters were also enhanced at this dose with a 4.7-fold increase in DEM/DEX compared with QN. Network pharmacology analysis indicated the ability of TCE to target multiple factors associated with AD. Furthermore, it improved spatial memory and reduced hyperactivity in rodents better than the combination of QN and DEM.

Exploration of morpholine-thiophene hybrid thiosemicarbazones for the treatment of ureolytic bacterial infections via targeting urease enzyme: Synthesis, biochemical screening and computational analysis

An important component of the pathogenicity of potentially pathogenic bacteria in humans is the urease enzyme. In order to avoid the detrimental impact of ureolytic bacterial infections, the inhibition of urease enzyme appears to be an appealing approach. Therefore, in the current study, morpholine-thiophene hybrid thiosemicarbazone derivatives (5a-i) were designed, synthesized and characterized through FTIR, 1H NMR, 13C NMR spectroscopy and mass spectrometry. A range of substituents including electron-rich, electron-deficient and inductively electron-withdrawing groups on the thiophene ring was successfully tolerated. The synthesized derivatives were evaluated in vitro for their potential to inhibit urease enzyme using the indophenol method. The majority of compounds were noticeably more potent than the conventional inhibitor, thiourea. The lead inhibitor, 2-(1-(5-chlorothiophen-2-yl)ethylidene)-N-(2-morpholinoethyl)hydrazinecarbothioamide (5g) inhibited the urease in an uncompetitive manner with an IC50 value of 3.80 ± 1.9 µM. The findings of the docking studies demonstrated that compound 5g has a strong affinity for the urease active site. Significant docking scores and efficient binding free energies were displayed by the lead inhibitor. Finally, the ADME properties of lead inhibitor (5g) suggested the druglikeness behavior with zero violation.

Enhancing Multi-species Liver Microsomal Stability Prediction through Artificial Intelligence

Liver microsomal stability, a crucial aspect of metabolic stability, significantly impacts practical drug discovery. However, current models for predicting liver microsomal stability are based on limited molecular information from a single species. To address this limitation, we constructed the largest public database of compounds from three common species: human, rat, and mouse. Subsequently, we developed a series of classification models using both traditional descriptor-based and classic graph-based machine learning (ML) algorithms. Remarkably, the best-performing models for the three species achieved Matthews correlation coefficients (MCCs) of 0.616, 0.603, and 0.574, respectively, on the test set. Furthermore, through the construction of consensus models based on these individual models, we have demonstrated their superior predictive performance in comparison with the existing models of the same type. To explore the similarities and differences in the properties of liver microsomal stability among multispecies molecules, we conducted preliminary interpretative explorations using the Shapley additive explanations (SHAP) and atom heatmap approaches for the models and misclassified molecules. Additionally, we further investigated representative structural modifications and substructures that decrease the liver microsomal stability in different species using the matched molecule pair analysis (MMPA) method and substructure extraction techniques. The established prediction models, along with insightful interpretation information regarding liver microsomal stability, will significantly contribute to enhancing the efficiency of exploring practical drugs for development.

Azoles display promising anticonvulsant effects through possible PPAR-α activation

Azoles such as nafimidone, denzimol and loreclezole are known for their clinical efficacy against epilepsy, and loreclezole acts by potentiating γ-aminobutyric acid (GABA)-ergic currents. In the current study, we report a series of azole derivatives in alcohol ester and oxime ester structure showing promising anticonvulsant effects in 6 Hz and maximal electro shock (MES) models with minimal toxicity. The most promising of the series, 5f, was active in both 6 Hz and MES tests with a median effective dose (ED50) of 118.92 mg/kg in 6 Hz test and a median toxic dose (TD50) twice as high in mice. The compounds were predicted druglike and blood-brain barrier (BBB) penetrant in silico. Contrary to what was expected, the compounds showed no in vitro affinity to GABAA receptors (GABAARs) in radioligand binding assays; however, they were found structurally similar to peroxisome proliferator-activated receptors alpha (PPAR-α) agonists and predicted to show high affinity and agonist-like binding to PPAR-α in molecular docking studies. As a result, 5f emerged as a safe azole anticonvulsant with a wide therapeutic window and possible action through PPAR-α activation.

ViCEKb: Vitiligo-linked Chemical Exposome Knowledgebase

Vitiligo is a complex disease wherein the environmental factors, in conjunction with the underlying genetic predispositions, trigger the autoimmune destruction of melanocytes, ultimately leading to depigmented patches on the skin. While genetic factors have been extensively studied, the knowledge on environmental triggers remains sparse and less understood. To address this knowledge gap, we present the first comprehensive knowledgebase of vitiligo-triggering chemicals namely, Vitiligo-linked Chemical Exposome Knowledgebase (ViCEKb). ViCEKb involves an extensive and systematic manual effort in curation of published literature and subsequent compilation of 113 unique chemical triggers of vitiligo. ViCEKb standardizes various chemical information, and categorizes the chemicals based on their evidences and sources of exposure. Importantly, ViCEKb contains a wide range of metrics necessary for different toxicological evaluations. Notably, we observed that ViCEKb chemicals are present in a variety of consumer products. For instance, Propyl gallate is present as a fragrance substance in various household products, and Flutamide is used in medication to treat prostate cancer. These two chemicals have the highest level of evidence in ViCEKb, but are not regulated for their skin sensitizing effects. Furthermore, an extensive cheminformatics-based investigation revealed that ViCEKb chemical space is structurally diverse and comprises unique chemical scaffolds in comparison with skin specific regulatory lists. For example, Neomycin and 2,3,5-Triglycidyl-4-aminophenol have unique chemical scaffolds and the highest level of evidence in ViCEKb, but are not regulated for their skin sensitizing effects. Finally, a transcriptomics-based analysis of ViCEKb chemical perturbations in skin cell samples highlighted the commonality in their linked biological processes. Overall, we present the first comprehensive effort in compilation and exploration of various chemical triggers of vitiligo. We believe such a resource will enable in deciphering the complex etiology of vitiligo and aid in the characterization of human chemical exposome. ViCEKb is freely available for academic research at: https://cb.imsc.res.in/vicekb.

Machine Learning Empowering Drug Discovery: Applications, Opportunities and Challenges

Drug discovery plays a critical role in advancing human health by developing new medications and treatments to combat diseases. How to accelerate the pace and reduce the costs of new drug discovery has long been a key concern for the pharmaceutical industry. Fortunately, by leveraging advanced algorithms, computational power and biological big data, artificial intelligence (AI) technology, especially machine learning (ML), holds the promise of making the hunt for new drugs more efficient. Recently, the Transformer-based models that have achieved revolutionary breakthroughs in natural language processing have sparked a new era of their applications in drug discovery. Herein, we introduce the latest applications of ML in drug discovery, highlight the potential of advanced Transformer-based ML models, and discuss the future prospects and challenges in the field.

Secretion of Sphinganine by Drug-Induced Cancer Cells and Modified Mimetic Sphinganine (MMS) as c-Src Kinase Inhibitor

BACKGROUND

Cancer cells exhibit selective metabolic reprogramming to promote proliferation, invasiveness, and metastasis. Sphingolipids such as sphingosine and sphinganine have been reported to modulate cell death processes in cancer cells. However, the potential of extracellular sphinganine and its mimetic compounds as inducers of cancer cell death has not been thoroughly investigated.

METHODS

We obtained extracellular conditioned medium from HCT-116 cells treated with the previously reported anticancer composition, goat urine DMSO fraction (GUDF). The extracellular metabolites were purified using a novel and in-house developed vertical tube gel electrophoresis (VTGE) technique and identified through LC-HRMS. Extracellular metabolites such as sphinganine, sphingosine, C16 sphinganine, and phytosphingosine were screened for their inhibitory role against intracellular kinases using molecular docking. Molecular dynamics (MD) simulations were performed to study the inhibitory potential of a novel designed modified mimetic sphinganine (MMS) (Pubchem CID: 162625115) upon c-Src kinase. Furthermore, inhibitory potential and ADME profile of MMS was compared with luteolin, a known c-Src kinase inhibitor.

RESULTS

Data showed accumulation of sphinganine and other sphingolipids such as C16 sphinganine, phytosphingosine, and ceramide (d18:1/14:0) in the extracellular compartment of GUDF-treated HCT-116 cells. Molecular docking projected c-Src kinase as an inhibitory target of sphinganine. MD simulations projected MMS with strong (-7.1 kcal/mol) and specific (MET341, ASP404) binding to the inhibitory pocket of c-Src kinase. The projected MMS showed comparable inhibitory role and acceptable ADME profile over known inhibitors.

CONCLUSION

In summary, our findings highlight the significance of extracellular sphinganine and other sphingolipids, including C16 sphinganine, phytosphingosine, and ceramide (d18:1/14:0), in the context of drug-induced cell death in HCT-116 cancer cells. Furthermore, we demonstrated the importance of extracellular sphinganine and its modified mimetic sphinganine (MMS) as a potential inhibitor of c-Src kinase. These findings suggest that MMS holds promise for future applications in targeted and combinatorial anticancer therapy.

Unlocking The Mysteries of DNA Adducts with Artificial Intelligence

Cellular genome is considered a dynamic blueprint of a cell since it encodes genetic information that gets temporally altered due to various endogenous and exogenous insults. Largely, the extent of genomic dynamicity is controlled by the trade-off between DNA repair processes and the genotoxic potential of the causative agent (genotoxins or potential carcinogens). A subset of genotoxins form DNA adducts by covalently binding to the cellular DNA, triggering structural or functional changes that lead to significant alterations in cellular processes via genetic (e. g., mutations) or non-genetic (e. g., epigenome) routes. Identification, quantification, and characterization of DNA adducts are indispensable for their comprehensive understanding and could expedite the ongoing efforts in predicting carcinogenicity and their mode of action. In this review, we elaborate on using Artificial Intelligence (AI)-based modeling in adducts biology and present multiple computational strategies to gain advancements in decoding DNA adducts. The proposed AI-based strategies encompass predictive modeling for adduct formation via metabolic activation, novel adducts' identification, prediction of biochemical routes for adduct formation, adducts' half-life predictions within biological ecosystems, and, establishing methods to predict the link between adducts chemistry and its location within the genomic DNA. In summary, we discuss some futuristic AI-based approaches in DNA adduct biology.

Intracellular Ellagic Acid Derived from Goat Urine DMSO Fraction (GUDF) Predicted as an Inhibitor of c-Raf Kinase

BACKGROUND

Dietary chemicals and their gut-metabolized products are explored for their anti-proliferative and pro-cell death effects. Dietary and metabolized chemicals are different from ruminants such as goats over humans.

METHODS

Loss of cell viability and induction of death due to goat urine DMSO fraction (GUDF) derived chemicals were assessed by routine in vitro assays upon MCF-7 breast cancer cells. Intracellular metabolite profiling of MCF-7 cells treated with goat urine DMSO fraction (GUDF) was performed using an in-house designed vertical tube gel electrophoresis (VTGE) assisted methodology, followed by LC-HRMS. Next, identified intracellular dietary chemicals such as ellagic acid were evaluated for their inhibitory effects against transducers of the c-Raf signaling pathway employing molecular docking and molecular dynamics (MD) simulation.

RESULTS

GUDF treatment upon MCF-7 cells displayed significant loss of cell viability and induction of cell death. A set of dietary and metabolized chemicals in the intracellular compartment of MCF-7 cells, such as ellagic acid, 2-hydroxymyristic acid, artelinic acid, 10-amino-decanoic acid, nervonic acid, 2,4-dimethyl-2-eicosenoic acid, 2,3,4'- Trihydroxy,4-Methoxybenzophenone and 9-amino-nonanoic acid were identified. Among intracellular dietary chemicals, ellagic acid displayed a strong inhibitory affinity (-8.7 kcal/mol) against c-Raf kinase. The inhibitory potential of ellagic acid was found to be significantly comparable with a known c-Raf kinase inhibitor sorafenib with overlapping inhibitory site residues (ARG450, GLU425, TRP423, VA403).

CONCLUSION

Intracellular dietary-derived chemicals such as ellagic acid are suggested for the induction of cell death in MCF-7 cells. Ellagic acid is predicted as an inhibitor of c-Raf kinase and could be explored as an anti-cancer drug.

Optimizing the Extraction of Polyphenols from the Bark of Terminalia arjuna and an In-silico Investigation on its Activity in Colorectal Cancer

BACKGROUND

The interconnection between different fields of research has gained interest due to its cutting-edge perspectives in solving scientific problems. Terminalia arjuna is indigenously used in India for curing several diseases, and its pharmacological activities are being revisited in recent drug-repurposing research.

OBJECTIVES

Efficient ultrasound-assisted extraction of phytochemicals from the bark of Terminalia arjuna is highlighted in this study. Following the optimization of the extraction process, the crude hydroethanolic extract is subjected to phytochemical profiling and an in-silico investigation of its anti-cancer properties.

MATERIALS AND METHODS

A three-level four-factor Box-Behnken design is exploited to optimize four operational parameters, namely extraction time, ultrasonic power, ethanol concentration (as the extracting solvent) and solute (in g): solvent (in mL) ratio. At the optimum parametric condition, the crude extract is obtained, and its GC-MS analysis is carried out. An analysis of network pharmacology (by constructing and visualizing biological networks using Cytoscape) combined with molecular docking reveals the potential antineoplastic targets of the crude extract.

RESULTS

The ANOVA table exhibits the significance, adequacy and reliability of the proposed second-order polynomial model with the R² value of 0.917 and adjusted R² of 0.865. Experimental results portray the significant antioxidant potential of the prepared extract in its crude form. The GC-MS analysis of the crude extract predicts the extracted phytochemicals, while the constructed biological networks highlight its multi-targeted activity in colorectal cancer.

CONCLUSION

The study identifies three phytochemicals viz. luteolin, β-sitosterol and arjunic acid as potent anti-cancer agents and can be extended with in-vitro and in-vivo experiments to validate the in-silico results, thus establishing lead phytochemicals in multi-targeted colorectal cancer therapies.

Automation of Drug Discovery through Cutting-edge In-silico Research in Pharmaceuticals: Challenges and Future Scope

The rapidity and high-throughput nature of in silico technologies make them advantageous for predicting the properties of a large array of substances. In silico approaches can be used for compounds intended for synthesis at the beginning of drug development when there is either no or very little compound available. In silico approaches can be used for impurities or degradation products. Quantifying drugs and related substances (RS) with pharmaceutical drug analysis (PDA) can also improve drug discovery (DD) by providing additional avenues to pursue. Potential future applications of PDA include combining it with other methods to make insilico predictions about drugs and RS. One possible outcome of this is a determination of the drug potential of nontoxic RS. ADME estimation, QSAR research, molecular docking, bioactivity prediction, and toxicity testing all involve impurity profiling. Before committing to DD, RS with minimal toxicity can be utilised in silico. The efficacy of molecular docking in getting a medication to market is still debated despite its refinement and improvement. Biomedical labs and pharmaceutical companies were hesitant to adopt molecular docking algorithms for drug screening despite their decades of development and improvement. Despite the widespread use of "force fields" to represent the energy exerted within and between molecules, it has been impossible to reliably predict or compute the binding affinities between proteins and potential binding medications.

Combined in silico and in vitro approaches to identify P-glycoprotein-inhibiting pesticides

The P-glycoprotein (P-gp) efflux pump plays a major role in xenobiotic detoxification. The inhibition of its activity by environmental contaminants remains however rather little characterised. The present study was designed to develop a combination of different approaches to identify P-gp inhibitors among a large number of pesticides using in silico and in vitro models. First, the prediction performance of four web tools was evaluated alone or in combination using a set of recently marketed drugs. The best combination of web tools-AdmetSAR2.0/PgpRules/pkCSM-was next used to predict P-gp activity inhibition by 762 pesticides. Among the 187 pesticides predicted to be P-gp inhibitors, 11 were tested in vitro for their ability to inhibit the efflux of reference substrates (rhodamine 123 and Hoechst 33342) in P-gp overexpressing MCF7R cells and to inhibit the efflux of the reference substrate rhodamine 123 in the Caco-2 cell monolayer. In MCF7R cell assays, ivermectin B1a, emamectin B1 benzoate, spinosad, dimethomorph and tralkoxydim inhibited P-gp activity; ivermectin B1a, emamectin B1 benzoate and spinosad were determined to be stronger inhibitors (half-maximal inhibitory concentration [IC50 ] of 3 ± 1, 5 ± 1 and 7 ± 1 µM, respectively) than dimethomorph and tralkoxydim (IC50 of 102 ± 7 and 88 ± 7 µM, respectively). Ivermectin B1a, emamectin B1 benzoate, spinosad and dimethomorph also inhibited P-gp activity in Caco-2 cell monolayer assays, with dimethomorph being a weaker P-gp inhibitor. These combined approaches could be used to identify P-gp inhibitors among food contaminants, but need to be optimised and adapted for high-throughput screening.

ADMET-AI: A machine learning ADMET platform for evaluation of large-scale chemical libraries

Summary

The emergence of large chemical repositories and combinatorial chemical spaces, coupled with high-throughput docking and generative AI, have greatly expanded the chemical diversity of small molecules for drug discovery. Selecting compounds for experimental validation requires filtering these molecules based on favourable druglike properties, such as Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET). We developed ADMET-AI, a machine learning platform that provides fast and accurate ADMET predictions both as a website and as a Python package. ADMET-AI has the highest average rank on the TDC ADMET Benchmark Group leaderboard, and it is currently the fastest web-based ADMET predictor, with a 45% reduction in time compared to the next fastest ADMET web server. ADMET-AI can also be run locally with predictions for one million molecules taking just 3.1 hours.

Availability and Implementation

The ADMET-AI platform is freely available both as a web server at admet.ai.greenstonebio.com and as an open-source Python package for local batch prediction at github.com/swansonk14/admet_ai (also archived on Zenodo at doi.org/10.5281/zenodo.10372930 ). All data and models are archived on Zenodo at doi.org/10.5281/zenodo.10372418 .

Designing Cell Delivery Peptides and SARS-CoV-2-Targeting Small Interfering RNAs: A Comprehensive Bioinformatics Study with Generative Adversarial Network-Based Peptide Design and In Vitro Assays

Nucleic acid technologies with designed intracellular delivery systems are some of the most promising therapies of the future. Small interfering (si)RNAs inhibit gene expression and protein synthesis and may complement current vaccines with faster design and production. Although successful delivery remains an issue, delivery peptides may help to fill this gap. Here, we address this issue by applying bioinformatic approaches to design new putative cell delivery peptides and siRNAs for COVID-19 variants and other related viral diseases. Of the 29,880 RNA sequences analyzed, 62 were identified in silico as able to target the virus mRNA sequence, and from the 9,984 peptide sequences analyzed, 10 were selected as delivery peptides. From the latter, we further performed in vitro studies of the two best-ranked peptides and compared them with the broadly used TAT delivery peptide. One of them, seq5, displayed better internalization results with about double intensity signal compared to TAT after a 1 h incubation time in GFP-HeLa cells. This peptide has, thus, the features of a delivery peptide and could be used for cargo intracellular delivery.

Design of new chemical entities targeting both native and H275Y mutant influenza a virus by deep reinforcement learning

Influenza virus remains a major public health challenge due to its high morbidity and mortality and seasonal surge. Although antiviral drugs against the influenza virus are widely used as a first-line defense, the virus undergoes rapid genetic changes, resulting in the emergence of drug-resistant strains. Thus, new antiviral drugs that can outwit resistant strains are of significant importance. Herein, we used deep reinforcement learning (RL) algorithm to design new chemical entities (NCEs) that are able to bind to the native and H275Y mutant (oseltamivir-resistant) neuraminidases (NAs) of influenza A virus with better binding energy than oseltamivir. We generated more than 66211 NCEs, which were prioritized based on the filtering rules, structural alerts, and synthetic accessibility. Then, 18 NCEs with better MM/PBSA scores than oseltamivir were further analyzed in molecular dynamics (MD) simulations conducted for 100 ns. The MD experiments showed that 8 NCEs formed very stable complexes with the binding pocket of both native and H275Y mutant NAs of H1N1. Furthermore, most NCEs demonstrated much better binding affinity to group 2 (N2, N3, and N9) and influenza B virus NAs than oseltamivir. Although all 8 NCEs have non-sialic acid-like structures, they showed a similar binding mode as oseltamivir, indicating that it is possible to find new scaffolds with better binding and antiviral properties than sialic acid-like inhibitors. In conclusion, we have designed potential compounds as antiviral candidates for further synthesis and testing against wild and mutant influenza virus.Communicated by Ramaswamy H. Sarma.

Drug-drug interaction prediction: databases, web servers and computational models

In clinical treatment, two or more drugs (i.e. drug combination) are simultaneously or successively used for therapy with the purpose of primarily enhancing the therapeutic efficacy or reducing drug side effects. However, inappropriate drug combination may not only fail to improve efficacy, but even lead to adverse reactions. Therefore, according to the basic principle of improving the efficacy and/or reducing adverse reactions, we should study drug-drug interactions (DDIs) comprehensively and thoroughly so as to reasonably use drug combination. In this review, we first introduced the basic conception and classification of DDIs. Further, some important publicly available databases and web servers about experimentally verified or predicted DDIs were briefly described. As an effective auxiliary tool, computational models for predicting DDIs can not only save the cost of biological experiments, but also provide relevant guidance for combination therapy to some extent. Therefore, we summarized three types of prediction models (including traditional machine learning-based models, deep learning-based models and score function-based models) proposed during recent years and discussed the advantages as well as limitations of them. Besides, we pointed out the problems that need to be solved in the future research of DDIs prediction and provided corresponding suggestions.

Exploring cyclin-dependent kinase inhibitors: a comprehensive study in search of CDK-6 inhibitors using a pharmacophore modelling and dynamics approach

Cancer prevalence and resistance issues in cancer treatment are a significant public health concern globally. Among the existing strategies in cancer therapy, targeting cyclin-dependent kinases (CDKs), especially CDK-6 is found to be one of the most promising targets, as this enzyme plays a pivotal role in cell cycle stages and cell proliferation. Cell proliferation is the characteristic feature of cancer giving rise to solid tumours. Our research focuses on creating novel compounds, specifically, pyrazolopyrimidine fused azetidinones, using a groundbreaking molecular hybridization approach to target CDK-6. Through computational investigations, ligand-based pharmacophore modelling, pharmacokinetic studies (ADMET), molecular docking, and dynamics simulations, we identified 18 promising compounds. The pharmacophore model featured one aromatic hydrophobic centre (F1: Aro/Hyd) and two H-bond acceptors (F2 and F3: Acc). Molecular docking results showed favourable binding energies (-6.5 to -8.0 kcal mol-1) and effective hydrogen bonds and hydrophobic interactions. The designed compounds demonstrated good ADMET profiles. Specifically, B6 and B18 showed low energy conformation (-7.8 kcal and -7.6 kcal), providing insights into target inhibition compared to the standard drug Palbociclib. Extensive molecular dynamics simulations confirmed the stability of these derivatives. Throughout the 100 ns simulation, the ligand-protein complexes maintained structural stability, with acceptable RMSD values. These compounds hold promise as potential leads in cancer therapy.

Structure-based drug design of potential inhibitors of FBXW8, the substrate recognition component of Cullin-RING ligase 7

FBXW8 plays an irreplaceable role in the substrate recognition of ubiquitin-dependent proteolysis, which further regulates cell cycle progression and signal transduction. However, the abnormal expression of FBXW8 triggers malignancy, inflammation, and autophagy irregulation. FBXW8 is considered as an effective therapeutic target for Cullin-RING ligase 7 (CRL7)-related cancers. Still, the lack of selective inhibitors hinders further therapeutic development and limits the exploration of its biological mechanism. This study constructed an integrated protocol that combines pharmacophore modeling, structure-based virtual screening, and Molecular Dynamic Simulation. It was then used as a screening query to identify hit compounds targeted at the substrate recognition site of FBXW8 from a large-scale compound database including 120 million compounds. Then, ten lead compounds were retrieved by using molecular docking analysis and ADMET prediction. Finally, MD simulations were performed to validate the binding stability of selected drug candidates. The result indicated that three newly obtained compounds, namely ZINC96179876, ZINC72174069, and ZINC97730272, might be potent FBXW8 inhibitors against CRL7-related cancers such as endometrial cancer.

A promising natural anthraquinones mediated by photodynamic therapy for anti-cancer therapy

BACKGROUND

Experimental studies emphasize the therapeutic potential of plant-derived photosensitizers used in photodynamic therapy. Moreover, several in vitro and in vivo research present the promising roles of less-known anthraquinones that can selectively target cancer cells and eliminate them after light irradiation. This literature review summarizes the current knowledge of chosen plant-based-photosensitizers in PDT to show the results of emodin, aloe-emodin, parietin, rubiadin, hypericin, and soranjidiol in photodynamic therapy of cancer treatment and describe the comprehensive perspective of their role as natural photosensitizers.

METHODS

Literature searches of chosen anthraquinones were conducted on PubMed.gov with keywords: "emodin", "aloe-emodin", "hypericin", "parietin", "rubiadin", "soranjidiol" with "cancer" and "photodynamic therapy".

RESULTS

According to literature data, this review concentrated on all existing in vitro and in vivo studies of emodin, aloe-emodin, parietin, rubiadin, soranjidiol used as natural photosensitizers emphasizing their effectiveness and detailed mechanism of action in anticancer therapy. Moreover, comprehensive preclinical and clinical studies on hypericin reveal that the above-described substances may be included in the phototoxic treatment of different cancers.

CONCLUSIONS

Overall, this review presented less-known anthraquinones with their promising molecular mechanisms of action. It is expected that in the future they may be used as natural PSs in cancer treatment as well as hypericin.

Discovery of Hybrid Thiouracil-Coumarin Conjugates as Potential Novel Anti-SARS-CoV-2 Agents Targeting the Virus's Polymerase "RdRp" as a Confirmed Interacting Biomolecule

The coronavirus (COVID-19) pandemic, along with its various strains, has emerged as a global health crisis that has severely affected humankind and posed a great challenge to the public health system of affected countries. The replication of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) mainly depends on RNA-dependent RNA polymerase (RdRp), a key enzyme that is involved in RNA synthesis. In this regard, we designed, synthesized, and characterized hybrid thiouracil and coumarin conjugates (HTCAs) by ether linkage, which were found to have anti-SARS-CoV-2 properties. Our in vitro real-time quantitative reverse transcription PCR (RT-qPCR) results confirmed that compounds such as 5d, 5e, 5f, and 5i inhibited the replication of SARS-CoV-2 with EC50 values of 14.3 ± 0.14, 6.59 ± 0.28, 86.3 ± 1.45, and 124 ± 2.38 μM, respectively. Also, compound 5d displayed significant antiviral activity against human coronavirus 229E (HCoV-229E). In addition, some of the HTCAs reduced the replication of SARS-CoV-2 variants such as D614G and B.617.2. In parallel, HTCAs in uninfected Vero CCL-81 cells indicated that no cytotoxicity was noticed. Furthermore, we compared the in silico interaction of lead compounds 5d and 5e toward the cocrystal structure of Suramin and RdRp polymerase with Remdesvir triphosphate, which showed that compounds 5d, 5e, and Remdesvir triphosphate (RTP) share a common catalytical site of RdRp but not Suramin. Additionally, the in silico ADMET properties predicted for the lead HTCAs and RTP showed that the maximum therapeutic doses recommended for compounds 5d and 5e were comparable to those of RTP. Concurrently, the pharmacokinetics of 5d was characterized in male Wistar Albino rats by administering a single oral gavage at a dose of 10 mg/kg, which gave a Cmax value of 0.22 μg/mL and a terminal elimination half-life period of 73.30 h. In conclusion, we established a new chemical entity that acts as a SARS-CoV-2 viral inhibitor with minimal or no toxicity to host cells in the rodent model, encouraging us to proceed with preclinical studies.

DruMAP: A Novel Drug Metabolism and Pharmacokinetics Analysis Platform

We developed a novel drug metabolism and pharmacokinetics (DMPK) analysis platform named DruMAP. This platform consists of a database for DMPK parameters and programs that can predict many DMPK parameters based on the chemical structure of a compound. The DruMAP database includes curated DMPK parameters from public sources and in-house experimental data obtained under standardized conditions; it also stores predicted DMPK parameters produced by our prediction programs. Users can predict several DMPK parameters simultaneously for novel compounds not found in the database. Furthermore, the highly flexible search system enables users to search for compounds as they desire. The current version of DruMAP comprises more than 30,000 chemical compounds, about 40,000 activity values (collected from public databases and in-house data), and about 600,000 predicted values. Our platform provides a simple tool for searching and predicting DMPK parameters and is expected to contribute to the acceleration of new drug development. DruMAP can be freely accessed at: https://drumap.nibiohn.go.jp/.

Linkers in fragment-based drug design: an overview of the literature

INTRODUCTION

In fragment-based drug design, fragment linking is a popular strategy where two fragments binding to different sub-pockets of a target are linked together. This attractive method remains challenging especially due to the design of ideal linkers.

AREAS COVERED

The authors review the types of linkers and chemical reactions commonly used to the synthesis of linkers, including those utilized in protein-templated fragment self-assembly, where fragments are directly linked in the presence of the protein. Finally, they detail computational workflows and software including generative models that have been developed for fragment linking.

EXPERT OPINION

The authors believe that fragment linking offers key advantages for compound design, particularly for the design of bivalent inhibitors linking two distinct pockets of the same or different subunits. On the other hand, more studies are needed to increase the potential of protein-templated approaches in FBDD. Important computational tools such as structure-based de novo software are emerging to select suitable linkers. Fragment linking will undoubtedly benefit from developments in computational approaches and machine learning models.

Using a Graph Convolutional Neural Network Model to Identify Bile Salt Export Pump Inhibitors

The bile salt export pump (BSEP) is a key transporter involved in the efflux of bile salts from hepatocytes to bile canaliculi. Inhibition of BSEP leads to the accumulation of bile salts within the hepatocytes, leading to possible cholestasis and drug-induced liver injury. Screening for and identification of chemicals that inhibit this transporter aid in understanding the safety liabilities of these chemicals. Moreover, computational approaches to identify BSEP inhibitors provide an alternative to the more resource-intensive, gold standard experimental approaches. Here, we used publicly available data to develop predictive machine learning models for the identification of potential BSEP inhibitors. Specifically, we analyzed the utility of a graph convolutional neural network (GCNN)-based approach in combination with multitask learning to identify BSEP inhibitors. Our analyses showed that the developed GCNN model performed better than the variable-nearest neighbor and Bayesian machine learning approaches, with a cross-validation receiver operating characteristic area under the curve of 0.86. In addition, we compared GCNN-based single-task and multitask models and evaluated their utility in addressing data limitation challenges commonly observed in bioactivity modeling. We found that multitask models performed better than single-task models and can be utilized to identify active molecules for targets with limited data availability. Overall, our developed multitask GCNN-based BSEP model provides a useful tool for prioritizing hits during early drug discovery and in risk assessment of chemicals.

Recent Advances in Computer-Aided Structure-Based Drug Design on Ion Channels

Ion channels play important roles in fundamental biological processes, such as electric signaling in cells, muscle contraction, hormone secretion, and regulation of the immune response. Targeting ion channels with drugs represents a treatment option for neurological and cardiovascular diseases, muscular degradation disorders, and pathologies related to disturbed pain sensation. While there are more than 300 different ion channels in the human organism, drugs have been developed only for some of them and currently available drugs lack selectivity. Computational approaches are an indispensable tool for drug discovery and can speed up, especially, the early development stages of lead identification and optimization. The number of molecular structures of ion channels has considerably increased over the last ten years, providing new opportunities for structure-based drug development. This review summarizes important knowledge about ion channel classification, structure, mechanisms, and pathology with the main focus on recent developments in the field of computer-aided, structure-based drug design on ion channels. We highlight studies that link structural data with modeling and chemoinformatic approaches for the identification and characterization of new molecules targeting ion channels. These approaches hold great potential to advance research on ion channel drugs in the future.

Transporter proteins knowledge graph construction and its application in drug development

Transporters are the main determinant for pharmacokinetics characteristics of drugs, such as absorption, distribution, and excretion of drugs in humans. However, it is difficult to perform drug transporter validation and structure analysis of membrane transporter proteins by experimental methods. Many studies have demonstrated that knowledge graphs (KG) could effectively excavate potential association information between different entities. To improve the effectiveness of drug discovery, a transporter-related KG was constructed in this study. Meanwhile, a predictive frame (AutoInt_KG) and a generative frame (MolGPT_KG) were established based on the heterogeneity information obtained from the transporter-related KG by the RESCAL model. Natural product Luteolin with known transporters was selected to verify the reliability of the AutoInt_KG frame, its ROC-AUC (1:1), ROC-AUC (1:10), PR-AUC (1:1), PR-AUC (1:10) are 0.91, 0.94, 0.91 and 0.78, respectively. Subsequently, the MolGPT_KG frame was constructed to implement efficient drug design based on transporter structure. The evaluation results showed that the MolGPT_KG could generate novel and valid molecules and that these molecules were further confirmed by molecular docking analysis. The docking results showed that they could bind to important amino acids at the active site of the target transporter. Our findings will provide rich information resources and guidance for the further development of the transporter-related drugs.

Prioritization of mycotoxins based on mutagenicity and carcinogenicity evaluation using combined in silico QSAR methods

Mycotoxins and their metabolites are a family of compounds that contains a great diversity of both structure and biological properties. Information on their toxicity is spread within several databases and in scientific literature. Due to the number of molecules and their structure diversity, the cost and time required for hazard evaluation of each compound is unrealistic. In that purpose, new approach methodologies (NAMs) can be applied to evaluate such large set of molecules. Among them, quantitative structure-activity relationship (QSAR) in silico models could be useful to predict the mutagenic and carcinogenic properties of mycotoxins. First, a complete list of 904 mycotoxins and metabolites was built. Then, some known mycotoxins were used to determine the best QSAR tools for mutagenicity and carcinogenicity predictions. The best tool was further applied to the whole list of 904 mycotoxins. At the end, 95 mycotoxins were identified as both mutagen and carcinogen and should be prioritized for further evaluation.

Molecular modeling of pyrrolo-pyrimidine based analogs as potential FGFR1 inhibitors: a scientific approach for therapeutic drugs

Fibroblast growth factor receptors 1 (FGFR1) is an emerging target for the development of anticancer drugs. Uncontrolled expression of FGFR1 is strongly associated with a number of different types of cancers. Apart from a few FGFR inhibitors, the FGFR family members have not been thoroughly studied to produce clinically effective anticancer drugs. The application of proper computational techniques may aid in understanding the mechanism of protein-ligand complex formation, which may provide a better notion for developing potent FGFR1 inhibitors. In this study, a variety of computational techniques, including 3D-QSAR, flexible docking and MD simulation followed by MMGB/PBSA, H-bonds and distance analysis, have been performed to systematically explore the binding mechanism of pyrrolo-pyrimidine derivatives against FGFR1. The 3D-QSAR model was generated to deduce the structural determinants of FGFR1 inhibition. The high q2 and r2 values for the CoMFA and CoMSIA models indicated that the created 3D-QSAR models could reliably predict the bioactivities of FGFR1 inhibitors. The computed binding free energies (MMGB/PBSA) for the selected compounds were consistent with the ranking of their experimental binding affinities against FGFR1. Furthermore, per-residue energy decomposition analysis revealed that the residues Lys514 in catalytic region, Asn568, Glu571 in solvent accessible portion and Asp641 in DFG motif exhibited a strong tendency to mediate ligand-protein interactions through the hydrogen bonding and Van Der Waals interactions. These findings may benefit researchers in gaining better knowledge of FGFR1 inhibition and may serve as a guideline for the development of novel and highly effective FGFR1 inhibitors.Communicated by Ramaswamy H. Sarma.

Recent Studies of Artificial Intelligence on In Silico Drug Distribution Prediction

Drug distribution is an important process in pharmacokinetics because it has the potential to influence both the amount of medicine reaching the active sites and the effectiveness as well as safety of the drug. The main causes of 90% of drug failures in clinical development are lack of efficacy and uncontrolled toxicity. In recent years, several advances and promising developments in drug distribution property prediction have been achieved, especially in silico, which helped to drastically reduce the time and expense of screening undesired drug candidates. In this study, we provide comprehensive knowledge of drug distribution background, influencing factors, and artificial intelligence-based distribution property prediction models from 2019 to the present. Additionally, we gathered and analyzed public databases and datasets commonly utilized by the scientific community for distribution prediction. The distribution property prediction performance of five large ADMET prediction tools is mentioned as a benchmark for future research. On this basis, we also offer future challenges in drug distribution prediction and research directions. We hope that this review will provide researchers with helpful insight into distribution prediction, thus facilitating the development of innovative approaches for drug discovery.

Evaluation of Free Online ADMET Tools for Academic or Small Biotech Environments

For a new molecular entity (NME) to become a drug, it is not only essential to have the right biological activity also be safe and efficient, but it is also required to have a favorable pharmacokinetic profile including toxicity (ADMET). Consequently, there is a need to predict, during the early stages of development, the ADMET properties to increase the success rate of compounds reaching the lead optimization process. Since Lipinski's rule of five, the prediction of pharmacokinetic parameters has evolved towards the current in silico tools based on empirical approaches or molecular modeling. The commercial specialized software for performing such predictions, which is usually costly, is, in many cases, not among the possibilities for research laboratories in academia or at small biotech companies. Nevertheless, in recent years, many free online tools have become available, allowing, more or less accurately, for the prediction of the most relevant pharmacokinetic parameters. This paper studies 18 free web servers capable of predicting ADMET properties and analyzed their advantages and disadvantages, their model-based calculations, and their degree of accuracy by considering the experimental data reported for a set of 24 FDA-approved tyrosine kinase inhibitors (TKIs) as a model of a research project.

AMPA GluA2 subunit competitive inhibitors for PICK1 PDZ domain: Pharmacophore-based virtual screening, molecular docking, molecular dynamics simulation, and ADME studies

PICK1 (Protein interacting with C kinase-1) plays a key role in the regulation of intracellular trafficking of AMPA GluA2 subunit that is linked with synaptic plasticity. PICK1 is a scaffolding protein and binds numerous proteins through its PDZ domain. Research showed that synaptic plasticity is altered upon disrupting the GluA2-PDZ interactions. Inhibiting PDZ and GluA2 binding lead to beneficial effects in the cure of neurological diseases thus, targeting PDZ domain is proposed as a novel therapeutic target in such diseases. For this, various classes of synthetic peptides were tested. Though small organic molecules have been utilized to prevent these interactions, the number of such molecules is inadequate. Hence, in this study, ten molecular libraries containing large number of molecules were screened against the PDZ domain using pharmacophore-based virtual screening to find the best hits for the PDZ domain. Molecular docking and molecular dynamics simulation studies revealed that Hit_II is a potent inhibitor for the PDZ domain and confirm the allosteric nature of Hit_III. Additionally, ADME analysis suggests the drug-likeness of both Hit_II and Hit_III. This study suggests that tested hits may have potency against the PDZ domain and can be considered effective to treat neurological disorders.Communicated by Ramaswamy H. Sarma.

In silico study on spice-derived antiviral phytochemicals against SARS-CoV-2 TMPRSS2 target

Corona Virus Disease (COVID-19) caused by Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) is a pandemic that has claimed so far over half a million human life across the globe. Researchers all over the world are exploring various molecules including phytochemicals to get a potential anti-COVID-19 drug. Certain phytochemicals present in some spices are claimed to possess antiviral, anti-bacterial, and anti-fungal properties. Hence, an in-silico study was done by selecting eighteen well reported antiviral phytochemicals from some spices commonly used in Indian kitchen viz. Curcuma longa (Turmeric), Nigella sativa (Black cumin), Piper nigrum (Black pepper), Trachyspermum ammi (Carom) and Zingiber officinale (Ginger) to find out whether they can prevent SARS-CoV-2 infection. Firstly, we predicted the structure of TMPRSS2 (transmembrane protease serine 2), a host protein that truncates spike protein of SARS-CoV-2 thereby facilitating its endocytosis, and then docked against its catalytic domain the selected phytochemicals and camostat (a well-known synthetic inhibitor of TMPRSS2). Thereafter, stability of seven best docked phytochemicals and camostat were scrutinized by Molecular Dynamic Simulation (MDS). MDS analysis indicated bisdemethoxycurcumin (BDMC), carvacrol and thymol as better inhibitors than the camostat due to their stable binding with TMPRSS2 in its oxyanion hole and inducing subtle modification in the spatial arrangement of the catalytic triad residues. Among these three phytochemicals, carvacrol appeared to be the best inhibitor, followed by BDMC, whereas thymol was least effective.

ADMETboost: a web server for accurate ADMET prediction

The absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties are important in drug discovery as they define efficacy and safety. In this work, we applied an ensemble of features, including fingerprints and descriptors, and a tree-based machine learning model, extreme gradient boosting, for accurate ADMET prediction. Our model performs well in the Therapeutics Data Commons ADMET benchmark group. For 22 tasks, our model is ranked first in 18 tasks and top 3 in 21 tasks. The trained machine learning models are integrated in ADMETboost, a web server that is publicly available at https://ai-druglab.smu.edu/admet .

Inhibition of nonstructural protein 15 of SARS-CoV-2 by golden spice: A computational insight

The quick widespread of the coronavirus and speedy upsurge in the tally of cases demand the fast development of effective drugs. The uridine-directed endoribonuclease activity of nonstructural protein 15 (Nsp15) of the coronavirus is responsible for the invasion of the host immune system. Therefore, developing potential inhibitors against Nsp15 is a promising strategy. In this concern, the in silico approach can play a significant role, as it is fast and cost-effective in comparison to the trial and error approaches of experimental investigations. In this study, six turmeric derivatives (curcuminoids) were chosen for in silico analysis. The molecular interactions, pharmacokinetics, and drug-likeness of all the curcuminoids were measured. Further, the stability of Nsp15-curcuminoids complexes was appraised by employing molecular dynamics (MD) simulations and MM-PBSA approaches. All the molecules were affirmed to have strong interactions and pharmacokinetic profile. The MD simulations data stated that the Nsp15-curcuminoids complexes were stable during simulations. All the curcuminoids showed stable and high binding affinity, and these curcuminoids could be admitted as potential modulators for Nsp15 inhibition.

Computational approach to attenuate virulence of Pseudomonas aeruginosa through bioinspired silver nanoparticles

In this study we aim to investigate the computational docking approach of biofabricated silver nanoparticles against P. aeruginosa virulent exoenzymes, such as ExoS and ExoY. Therefore, the synthesis and characterization of biofabricated silver nanoparticles using Piper betle leaves (Pb-AgNPs) were carried out. The surface topology and functional group attachment on the surface of Pb-AgNPs were analyzed using UV-visible spectroscopy, Scanning Electron Microscopy, Fourier Transformed Infrared Spectroscopy (FTIR), and X-Ray Diffraction. The FTIR analysis revealed that the synthesized silver nanoparticles were capped with P. betle phytochemicals importantly Eugenol and Hydroxychavicol. These are the major bioactive compounds present in P. betle leaves; therefore, computational docking of Eugenol-conjugated AgNPs (PbEu-AgNPs) and Hydroxychavicol-conjugated AgNPs (PbHy-AgNPs) against ExoS and ExoY was performed. The active residues of PbEu-AgNPs and PbHy-AgNPs interacted with the active site of ExoS and ExoY exoenzymes. Biofabricated AgNP-mediated inhibition of these virulent exoenzymes blocked the adverse effect of P. aeruginosa on the host cell. The computational analysis provides new approach into the design of biofabricated AgNPs as promising anti-infective nanomedicine agents.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13205-022-03367-0.

cardioToxCSM: A Web Server for Predicting Cardiotoxicity of Small Molecules

The design of novel, safe, and effective drugs to treat human diseases is a challenging venture, with toxicity being one of the main sources of attrition at later stages of development. Failure due to toxicity incurs a significant increase in costs and time to market, with multiple drugs being withdrawn from the market due to their adverse effects. Cardiotoxicity, for instance, was responsible for the failure of drugs such as fenspiride, propoxyphene, and valdecoxib. While significant effort has been dedicated to mitigate this issue by developing computational approaches that aim to identify molecules likely to be toxic, including quantitative structure-activity relationship models and machine learning methods, current approaches present limited performance and interpretability. To overcome these, we propose a new web-based computational method, cardioToxCSM, which can predict six types of cardiac toxicity outcomes, including arrhythmia, cardiac failure, heart block, hERG toxicity, hypertension, and myocardial infarction, efficiently and accurately. cardioToxCSM was developed using the concept of graph-based signatures, molecular descriptors, toxicophore matchings, and molecular fingerprints, leveraging explainable machine learning, and was validated internally via different cross validation schemes and externally via low-redundancy blind sets. The models presented robust performances with areas under ROC curves of up to 0.898 on 5-fold cross-validation, consistent with metrics on blind tests. Additionally, our models provide interpretation of the predictions by identifying whether substructures that are commonly enriched in toxic compounds were present. We believe cardioToxCSM will provide valuable insight into the potential cardiotoxicity of small molecules early on drug screening efforts. The method is made freely available as a web server at https://biosig.lab.uq.edu.au/cardiotoxcsm.

Computational Prediction of Inhibitors and Inducers of the Major Isoforms of Cytochrome P450

Human cytochrome P450 enzymes (CYPs) are heme-containing monooxygenases. This superfamily of drug-metabolizing enzymes is responsible for the metabolism of most drugs and other xenobiotics. The inhibition of CYPs may lead to drug–drug interactions and impair the biotransformation of drugs. CYP inducers may decrease the bioavailability and increase the clearance of drugs. Based on the freely available databases ChEMBL and PubChem, we have collected over 70,000 records containing the structures of inhibitors and inducers together with the IC50 values for the inhibitors of the five major human CYPs: 1A2, 3A4, 2D6, 2C9, and 2C19. Based on the collected data, we developed (Q)SAR models for predicting inhibitors and inducers of these CYPs using GUSAR and PASS software. The developed (Q)SAR models could be applied for assessment of the interaction of novel drug-like substances with the major human CYPs. The created (Q)SAR models demonstrated reasonable accuracy of prediction. They have been implemented in the web application P450-Analyzer that is freely available via the Internet.

Artificial intelligence uncovers carcinogenic human metabolites

The genome of a eukaryotic cell is often vulnerable to both intrinsic and extrinsic threats owing to its constant exposure to a myriad of heterogeneous compounds. Despite the availability of innate DNA damage responses, some genomic lesions trigger malignant transformation of cells. Accurate prediction of carcinogens is an ever-challenging task owing to the limited information about bona fide (non-)carcinogens. We developed Metabokiller, an ensemble classifier that accurately recognizes carcinogens by quantitatively assessing their electrophilicity, their potential to induce proliferation, oxidative stress, genomic instability, epigenome alterations, and anti-apoptotic response. Concomitant with the carcinogenicity prediction, Metabokiller is fully interpretable and outperforms existing best-practice methods for carcinogenicity prediction. Metabokiller unraveled potential carcinogenic human metabolites. To cross-validate Metabokiller predictions, we performed multiple functional assays using Saccharomyces cerevisiae and human cells with two Metabokiller-flagged human metabolites, namely 4-nitrocatechol and 3,4-dihydroxyphenylacetic acid, and observed high synergy between Metabokiller predictions and experimental validations.

SApredictor: An Expert System for Screening Chemicals Against Structural Alerts

The rapid and accurate evaluation of chemical toxicity is of great significance for estimation of chemical safety. In the past decades, a great number of excellent computational models have been developed for chemical toxicity prediction. But most machine learning models tend to be “black box”, which bring about poor interpretability. In the present study, we focused on the identification and collection of structural alerts (SAs) responsible for a series of important toxicity endpoints. Then, we carried out effective storage of these structural alerts and developed a web-server named SApredictor (www.sapredictor.cn) for screening chemicals against structural alerts. People can quickly estimate the toxicity of chemicals with SApredictor, and the specific key substructures which cause the chemical toxicity will be intuitively displayed to provide valuable information for the structural optimization by medicinal chemists.

Blood-brain barrier penetration prediction enhanced by uncertainty estimation

Blood–brain barrier is a pivotal factor to be considered in the process of central nervous system (CNS) drug development, and it is of great significance to rapidly explore the blood–brain barrier permeability (BBBp) of compounds in silico in early drug discovery process. Here, we focus on whether and how uncertainty estimation methods improve in silico BBBp models. We briefly surveyed the current state of in silico BBBp prediction and uncertainty estimation methods of deep learning models, and curated an independent dataset to determine the reliability of the state-of-the-art algorithms. The results exhibit that, despite the comparable performance on BBBp prediction between graph neural networks-based deep learning models and conventional physicochemical-based machine learning models, the GROVER-BBBp model shows greatly improvement when using uncertainty estimations. In particular, the strategy combined Entropy and MC-dropout can increase the accuracy of distinguishing BBB + from BBB − to above 99% by extracting predictions with high confidence level (uncertainty score < 0.1). Case studies on preclinical/clinical drugs for Alzheimer’ s disease and marketed antitumor drugs that verified by literature proved the application value of uncertainty estimation enhanced BBBp prediction model, that may facilitate the drug discovery in the field of CNS diseases and metastatic brain tumors.