Addressing toxicity risk when designing and selecting compounds in early drug discovery

The STING antagonist SN-011 ameliorates cisplatin induced acute kidney injury via suppression of STING/NF-κB-mediated inflammation

Acute kidney injury (AKI) is a critical clinical syndrome associated with both innate and adaptive immune responses and thus increases mortality. Nevertheless, specific therapeutics for AKI are scarce so far. Recent studies have revealed that knockout of STING alleviate AKI, suggesting that STING could be an attractive target for AKI therapy. SN-011, a promising STING inhibitor, has not been reported in studies of its anti-AKI activity. In this study, we sought to examine the effects of SN-011 on AKI and explore its underlying mechanism. Our findings indicate that SN-011 could modulate the NF-κB and MAPK pathways, suppress the expression of inflammatory factors, and decrease ROS release in the cisplatin-induced cell model. In addition, SN-011 blocked the nuclear translocation of NF-κB p65, further mitigating the inflammatory response. In vivo, SN-011 enhanced survival rates and alleviated renal dysfunction. According to gene set enrichment analysis of sequencing data from mouse kidneys, we further confirm that SN-011 modulates the NF-κB and MAPK pathways. Our study suggests that SN-011 could be an attractive anti-inflammatory agent for further anti-AKI research.

Design, synthesis and structure-activity relationship of novel 1,2,4-triazolopyrimidin-5-one derivatives targeting GABAA1 and Nav1.2 with antiepileptic activity

A novel class of 7-phenyl-[1,2,4]triazol-5(4H)-one derivatives was designed and synthesized, and their in vivo anticonvulsant activities were evaluated using subcutaneous pentylenetetrazole (Sc-PTZ) and maximal electroshock (MES) tests. Compounds 3u, 4f and 4k exhibited significant anticonvulsant activities in the Sc-PTZ model with ED50 values of 23.7, 17.1 and 18.3 mg/kg, respectively. Neurotoxicity was accessed using the rotarod assay and none of the compounds demonstrated neurotoxicity at maximum solubility, with all TD50 values exceeding 267 mg/kg. This resulted in protective indexes (PI = TD50/ED50) values of greater than 11.3, 15.6 and 14.6, respectively. Compared to control drugs such as sodium phenytoin, sodium valproate, and carbamazepine, compounds 3u, 4f and 4k displayed superior anticonvulsant activities and reduced neurotoxicity. Mechanism results indicated that compounds 4k and 4f were sensitive to the subunit configuration of synaptic α1β2γ2 GABAA receptors, while compounds 3u and 4f dose-dependently reduced the peak amplitude of Nav1.2 currents. These structural compounds may provide a foundation for the further design of novel antiepileptic molecules with low neurotoxicity.

Improved higher resolution cryo-EM structures reveal the binding modes of hERG channel inhibitors

During drug discovery, it is crucial to exclude compounds with toxic effects. The human ether-à-go-go-related gene (hERG) channel is essential for maintaining cardiac repolarization and is a critical target in drug safety evaluation due to its role in drug-induced arrhythmias. Inhibition of the hERG channel can lead to severe cardiac issues, including Torsades de Pointes tachycardia. Understanding hERG inhibition mechanisms is essential to avoid these toxicities. Several structural studies have elucidated the interactions between inhibitors and hERG. However, orientation and resolution issues have so far limited detailed insights. Here, we used digitonin to analyze the apo state of hERG, which resolved orientation issues and improved the resolution. We determined the structure of hERG bound to astemizole, showing a clear map in the pore pathway. Using this strategy, we also analyzed the binding modes of E-4031 and pimozide. These insights into inhibitor interactions with hERG may aid safer drug design and enhance cardiac safety.

The Future of Cystic Fibrosis Care: Exploring AI's Impact on Detection and Therapy

:

Cystic Fibrosis (CF) is a fatal hereditary condition marked by thicker mucus production, which can cause problems with the digestive and respiratory systems. The quality of life and survival rates of CF patients can be improved by early identification and individualized therapy measures. With an emphasis on its applications in diagnosis and therapy, this paper investigates how Artificial Intelligence (AI) is transforming the management of Cystic Fibrosis (CF). AI-powered algorithms are revolutionizing CF diagnosis by utilizing huge genetic, clinical, and imaging data databases. In order to identify CF mutations quickly and precisely, machine learning methods evaluate genomic profiles. Furthermore, AI-driven imaging analysis helps to identify lung and gastrointestinal issues linked to cystic fibrosis early and allows for prompt treatment. Additionally, AI aids in individualized CF therapy by anticipating how patients will react to already available medications and enabling customized treatment regimens. Drug repurposing algorithms find prospective candidates from already-approved drugs, advancing treatment choices. Additionally, AI supports the optimization of pharmacological combinations, enhancing therapeutic results while minimizing side effects. AI also helps with patient stratification by connecting people with CF mutations to therapies that are best for their genetic profiles. Improved treatment effectiveness is promised by this tailored strategy. The transformational potential of artificial intelligence (AI) in the field of cystic fibrosis is highlighted in this review, from early identification to individualized medication, bringing hope for better patient outcomes, and eventually prolonging the lives of people with this difficult ailment.

Data-driven toxicity prediction in drug discovery: Current status and future directions

Early toxicity assessment plays a vital role in the drug discovery process on account of its significant influence on the attrition rate of candidates. Recently, constant upgrading of information technology has greatly promoted the continuous development of toxicity prediction. To give an overview of the current state of data-driven toxicity prediction, we reviewed relevant studies and summarized them in three main respects: the features and difficulties of toxicity prediction, the evolution of modeling approaches, and the available tools for toxicity prediction. For each part, we expound the research status, existing challenges, and feasible solutions. Finally, several new directions and suggestions for toxicity prediction are also put forward.

Antitumor properties of griseofulvin and its toxicity

Griseofulvin (GF), which is mainly extracted from Penicillium griseofulvum, is a heat-resistant, chlorine-containing non-polyene antifungal antibiotic. Previous research shows that GF has a variety of pharmacological effects, such as anti-inflammatory, antifungal, antiviral, and antitumor effects. In recent years, GF has received extensive attention for its antitumor effects as a natural compound, offering a low price, a wide range of uses, and other beneficial characteristics. However, no comprehensive review of GF pharmacological activity in tumors has been published so far. In order to fully elucidate the antitumor activities of GF, this review focuses on the antitumor potential and toxicity of GF and its derivatives, based on a literature search using PubMed, Web of Science, and other databases, to lay a good foundation for further research of GF and the development of new drugs for antitumor activities.

1H NMR spectroscopic characterisation of HepG2 cells as a model metabolic system for toxicology studies

The immortalised human hepatocellular HepG2 cell line is commonly used for toxicology studies as an alternative to animal testing due to its characteristic liver-distinctive functions. However, little is known about the baseline metabolic changes within these cells upon toxin exposure. We have applied 1H Nuclear Magnetic Resonance (NMR) spectroscopy to characterise the biochemical composition of HepG2 cells at baseline and post-exposure to hydrogen peroxide (H2O2). Metabolic profiles of live cells, cell extracts, and their spent media supernatants were obtained using 1H high-resolution magic angle spinning (HR-MAS) NMR and 1H NMR spectroscopic techniques. Orthogonal partial least squares discriminant analysis (O-PLS-DA) was used to characterise the metabolites that differed between the baseline and H2O2 treated groups. The results showed that H2O2 caused alterations to 10 metabolites, including acetate, glutamate, lipids, phosphocholine, and creatine in the live cells; 25 metabolites, including acetate, alanine, adenosine diphosphate (ADP), aspartate, citrate, creatine, glucose, glutamine, glutathione, and lactate in the cell extracts, and 22 metabolites, including acetate, alanine, formate, glucose, pyruvate, phenylalanine, threonine, tryptophan, tyrosine, and valine in the cell supernatants. At least 10 biochemical pathways associated with these metabolites were disrupted upon toxin exposure, including those involved in energy, lipid, and amino acid metabolism. Our findings illustrate the ability of NMR-based metabolic profiling of immortalised human cells to detect metabolic effects on central metabolism due to toxin exposure. The established data sets will enable more subtle biochemical changes in the HepG2 model cell system to be identified in future toxicity testing.

Deep-PK: deep learning for small molecule pharmacokinetic and toxicity prediction

Evaluating pharmacokinetic properties of small molecules is considered a key feature in most drug development and high-throughput screening processes. Generally, pharmacokinetics, which represent the fate of drugs in the human body, are described from four perspectives: absorption, distribution, metabolism and excretion-all of which are closely related to a fifth perspective, toxicity (ADMET). Since obtaining ADMET data from in vitro, in vivo or pre-clinical stages is time consuming and expensive, many efforts have been made to predict ADMET properties via computational approaches. However, the majority of available methods are limited in their ability to provide pharmacokinetics and toxicity for diverse targets, ensure good overall accuracy, and offer ease of use, interpretability and extensibility for further optimizations. Here, we introduce Deep-PK, a deep learning-based pharmacokinetic and toxicity prediction, analysis and optimization platform. We applied graph neural networks and graph-based signatures as a graph-level feature to yield the best predictive performance across 73 endpoints, including 64 ADMET and 9 general properties. With these powerful models, Deep-PK supports molecular optimization and interpretation, aiding users in optimizing and understanding pharmacokinetics and toxicity for given input molecules. The Deep-PK is freely available at https://biosig.lab.uq.edu.au/deeppk/.

In silico prediction of ocular toxicity of compounds using explainable machine learning and deep learning approaches

The accurate identification of chemicals with ocular toxicity is of paramount importance in health hazard assessment. In contemporary chemical toxicology, there is a growing emphasis on refining, reducing, and replacing animal testing in safety evaluations. Therefore, the development of robust computational tools is crucial for regulatory applications. The performance of predictive models is heavily reliant on the quality and quantity of data. In this investigation, we amalgamated the most extensive dataset (4901 compounds) sourced from governmental GHS-compliant databases and literature to develop binary classification models of chemical ocular toxicity. We employed 12 molecular representations in conjunction with six machine learning algorithms and two deep learning algorithms to create a series of binary classification models. The findings indicated that the deep learning method GCN outperformed the machine learning models in cross-validation, achieving an impressive AUC of 0.915. However, the top-performing machine learning model (RF-Descriptor) demonstrated excellent performance with an AUC of 0.869 on the test set and was therefore selected as the best model. To enhance model interpretability, we conducted the SHAP method and attention weights analysis. The two approaches offered visual depictions of the relevance of key descriptors and substructures in predicting ocular toxicity of chemicals. Thus, we successfully struck a delicate balance between data quality and model interpretability, rendering our model valuable for predicting and comprehending potential ocular-toxic compounds in the early stages of drug discovery.

Unveiling a Novel Solvatomorphism of Anti-inflammatory Flufenamic Acid: X-ray Structure, Quantum Chemical, and In Silico Studies

This paper delves into the polymorphism of 2-[3-(trifluoromethyl)anilino]benzoic acid, commonly referred to as flufenamic acid (FA), a pharmaceutical agent employed in treating inflammatory conditions. The central focus of the study is on a newly unearthed solvatomorphic structure of FA in methanol (FAM), and a thorough comparison is conducted with the commercially available standard structure. Employing a comprehensive approach, including X-ray crystallography, Hirshfeld surface analysis, density functional theory (DFT), molecular docking, and molecular dynamics (MD) simulations, the research aims to unravel the structural and functional implications of solvatomorphism. The X-ray crystal structure analysis brings to light notable differences between the standard FA and solvatomorphic FAM, showcasing variations in intermolecular interactions and crystal packing. Key features such as hydrogen bonding, π···π stacking, and C-H···π interactions are identified as influential factors shaping the stability and conformation of the compounds. Hirshfeld surface analysis further quantifies the nature and contribution of intermolecular interactions, providing a comprehensive perspective on molecular stability. Density functional theory offers valuable electronic structure insights, highlighting disparities in frontier molecular orbitals between FA and FAM. Molecular docking studies against prostaglandin D2 11-ketoreductase explore potential drug interactions, unveiling distinct binding modes and hydrogen bonding patterns that shed light on how the solvatomorphic structure may impact drug-target interactions. In-depth molecular dynamics simulations over 100 ns investigate the stability of the protein-ligand complex, with root mean square deviation and root mean square fluctuation analyses revealing minimal deviations and affirming the stability of FAM within the active site of the target protein.

Computational investigation of phytochemicals identified from medicinal plant extracts against tuberculosis

Tuberculosis (TB) is still one of the world's most challenging infectious diseases and the emergence of drug-resistant Mycobacterium tuberculosis poses a significant threat to the treatment of TB. Identifying new medications based on local traditional remedies has become more essential. Gas Chromatography-Mass spectrometry (GC-MS) (Perkin-Elmer, MA, USA) was used to identify potential bioactive components in Solanum surattense, Piper longum, and Alpinia galanga plants sections. The fruits and rhizomes' chemical compositions were analyzed using solvents like petroleum ether, chloroform, ethyl acetate, and methanol. A total of 138 phytochemicals were identified, further categorized and finalized with 109 chemicals. The phytochemicals were docked with selected proteins (ethA, gyrB, and rpoB) using AutoDock Vina. The top complexes were selected and preceded with molecular dynamics simulation. It was found that the rpoB-sclareol complex is very stable, which means it could be further explored. The compounds were further studied for ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) properties. Sclareol has obeyed all the rules and it might be a potential chemical to treat TB.Communicated by Ramaswamy H. Sarma.

Antiemetic activity of abietic acid possibly through the 5HT3 and muscarinic receptors interaction pathways

The present study was designed to evaluate the antiemetic activity of abietic acid (AA) using in vivo and in silico studies. To assess the effect, doses of 50 mg/kg b.w. copper sulfate (CuSO4⋅5H2O) were given orally to 2-day-old chicks. The test compound (AA) was given orally at two doses of 20 and 40 mg/kg b.w. On the other hand, aprepitant (16 mg/kg), domperidone (6 mg/kg), diphenhydramine (10 mg/kg), hyoscine (21 mg/kg), and ondansetron (5 mg/kg) were administered orally as positive controls (PCs). The vehicle was used as a control group. Combination therapies with the referral drugs were also given to three separate groups of animals to see the synergistic and antagonizing activity of the test compound. Molecular docking and visualization of ligand-receptor interaction were performed using different computational tools against various emesis-inducing receptors (D2, D3, 5HT3, H1, and M1-M5). Furthermore, the pharmacokinetics and toxicity properties of the selected ligands were predicted by using the SwissADME and Protox-II online servers. Findings indicated that AA dose-dependently enhances the latency of emetic retching and reduces the number of retching compared to the vehicle group. Among the different treatments, animals treated with AA (40 mg/kg) exhibited the highest latency (98 ± 2.44 s) and reduced the number of retching (11.66 ± 2.52 times) compared to the control groups. Additionally, the molecular docking study indicated that AA exhibits the highest binding affinity (- 10.2 kcal/mol) toward the M4 receptors and an elevated binding affinity toward the receptors 5HT3 (- 8.1 kcal/mol), M1 (- 7.7 kcal/mol), M2 (- 8.7 kcal/mol), and H1 (- 8.5 kcal/mol) than the referral ligands. Taken together, our study suggests that AA has potent antiemetic effects by interacting with the 5TH3 and muscarinic receptor interaction pathways. However, additional extensive pre-clinical and clinical studies are required to evaluate the efficacy and toxicity of AA.

Computational drug discovery on human immunodeficiency virus with a customized long short-term memory variational autoencoder deep-learning architecture

Despite attempts to control the spread of human immunodeficiency virus (HIV) through the use of anti-HIV medications, the absence of an effective vaccine continues to present a significant obstacle. In addition, the development of drug resistance by HIV underscores the necessity for computational drug discovery methods to identify novel therapies. This investigation specifically focused on employing a long short-term memory (LSTM) variational autoencoder deep-learning architecture for computational drug discovery in relation to HIV. Our data set comprised simplified molecular input line entry system (SMILES)-encoded compounds, which were used to train the LSTM autoencoder. Remarkably, our model achieved a training accuracy of 91%, with a data set containing 1377 compounds. Leveraging the generative model derived from the training phase, we generated potential new drugs for combating HIV and assessed their interaction with the virus using a previously developed artificial intelligence model. Lastly, we verified the drug likeliness of our computationally generated compounds in accordance with Lipinski's rule of five. Overall, our study presents a promising approach to computational drug discovery in the ongoing battle against HIV.

Computational identification of potential inhibitors targeting cdk1 in colorectal cancer

Introduction: Despite improved treatment options, colorectal cancer (CRC) remains a huge public health concern with a significant impact on affected individuals. Cell cycle dysregulation and overexpression of certain regulators and checkpoint activators are important recurring events in the progression of cancer. Cyclin-dependent kinase 1 (CDK1), a key regulator of the cell cycle component central to the uncontrolled proliferation of malignant cells, has been reportedly implicated in CRC. This study aimed to identify CDK1 inhibitors with potential for clinical drug research in CRC. Methods: Ten thousand (10,000) naturally occurring compounds were evaluated for their inhibitory efficacies against CDK1 through molecular docking studies. The stability of the lead compounds in complex with CDK1 was evaluated using molecular dynamics simulation for one thousand (1,000) nanoseconds. The top-scoring candidates' ADME characteristics and drug-likeness were profiled using SwissADME. Results: Four hit compounds, namely, spiraeoside, robinetin, 6-hydroxyluteolin, and quercetagetin were identified from molecular docking analysis to possess the least binding scores. Molecular dynamics simulation revealed that robinetin and 6-hydroxyluteolin complexes were stable within the binding pocket of the CDK1 protein. Discussion: The findings from this study provide insight into novel candidates with specific inhibitory CDK1 activities that can be further investigated through animal testing, clinical trials, and drug development research for CRC treatment.

Assessing the multitargeted antidiabetic potential of three pomegranate peel-specific metabolites: An in silico and pharmacokinetics study

Diabetes is a chronic metabolic disorder that occurs due to impaired secretion of insulin, insulin resistance, or both. Recent studies show that the antidiabetic drugs used to control hyperglycemic levels are associated with undesirable adverse effects. Therefore, developing a safe and effective medicine with antidiabetic potential is needed. In this context, in silico studies are considered a rapid, effectual, and cost-effective method in drug discovery procedures. It is evident from the literature that plant-based natural components have shown promising outcomes in drug development to alleviate various diseases and hence have diversified the screening of potential antidiabetic agents. Purposely, in the present study, an in silico approach was performed on three Punica granatum peel metabolites (punicalin, punicalagin, and ellagic acid). All these three compounds were docked against nine protein targets involved in glucose metabolism (GFAT, PTP1β, PPAR-ᵞ, TKIR, RBP4, α-amylase, α-glucosidase, GCK, and AQP-2). These three pomegranate-specific compounds demonstrated significant interactions with GFAT, PTP1β, PPAR-ᵞ, TKIR, RBP4, α-amylase, α-glucosidase, GCK, and AQP-2 protein targets. Specifically, punicalin, punicalagin, and ellagic acid revealed significant binding scores (-9.2, -9.3, -8.1, -9.1, -8.5, -11.3, -9.2, -9.5, -10.1 kcal/mol; -10, -9.9, -8.5, -8.9, -10.4, -9.0, -10.2, -9.4, -9.0 kcal/mol; and -8.1, -8.0, -8.0, -6.8, -8.7, -7.8, -8.3, -8.1, -8.1 kcal/mol, respectively), with nine protein targets mentioned above. Hence, punicalin, punicalagin, and ellagic acid can be promising candidates in drug discovery to manage diabetes. Furthermore, in vivo and clinical trials must be conducted to validate the outcomes of the current study.

Review of machine learning and deep learning models for toxicity prediction

The ever-increasing number of chemicals has raised public concerns due to their adverse effects on human health and the environment. To protect public health and the environment, it is critical to assess the toxicity of these chemicals. Traditional in vitro and in vivo toxicity assays are complicated, costly, and time-consuming and may face ethical issues. These constraints raise the need for alternative methods for assessing the toxicity of chemicals. Recently, due to the advancement of machine learning algorithms and the increase in computational power, many toxicity prediction models have been developed using various machine learning and deep learning algorithms such as support vector machine, random forest, k-nearest neighbors, ensemble learning, and deep neural network. This review summarizes the machine learning- and deep learning-based toxicity prediction models developed in recent years. Support vector machine and random forest are the most popular machine learning algorithms, and hepatotoxicity, cardiotoxicity, and carcinogenicity are the frequently modeled toxicity endpoints in predictive toxicology. It is known that datasets impact model performance. The quality of datasets used in the development of toxicity prediction models using machine learning and deep learning is vital to the performance of the developed models. The different toxicity assignments for the same chemicals among different datasets of the same type of toxicity have been observed, indicating benchmarking datasets is needed for developing reliable toxicity prediction models using machine learning and deep learning algorithms. This review provides insights into current machine learning models in predictive toxicology, which are expected to promote the development and application of toxicity prediction models in the future.

Assembly of Cell-Free Synthesized Ion Channel Molecules in Artificial Lipid Bilayer Observed by Atomic Force Microscopy

Artificial lipid bilayer systems, such as vesicles, black membranes, and supported lipid bilayers (SLBs), are valuable platforms for studying ion channels at the molecular level. The reconstitution of the ion channels in an active form is a crucial process in studies using artificial lipid bilayer systems. In this study, we investigated the assembly of the human ether-a-go-go-related gene (hERG) channel prepared in a cell-free synthesis system. AFM topographies revealed the presence of protrusions with a uniform size in the entire SLB that was prepared with the proteoliposomes (PLs) incorporating the cell-free-synthesized hERG channel. We attributed the protrusions to hERG channel monomers, taking into consideration the AFM tip size, and identified assembled structures of the monomer that exhibited dimeric, trimeric, and tetrameric-like arrangements. We observed molecular images of the functional hERG channel reconstituted in a lipid bilayer membrane using AFM and quantitatively evaluated the association state of the cell-free synthesized hERG channel.

A Review on the Recent Applications of Deep Learning in Predictive Drug Toxicological Studies

Drug toxicity prediction is an important step in ensuring patient safety during drug design studies. While traditional preclinical studies have historically relied on animal models to evaluate toxicity, recent advances in deep-learning approaches have shown great promise in advancing drug safety science and reducing animal use in preclinical studies. However, deep-learning-based approaches also face challenges in handling large biological data sets, model interpretability, and regulatory acceptance. In this review, we provide an overview of recent developments in deep-learning-based approaches for predicting drug toxicity, highlighting their potential advantages over traditional methods and the need to address their limitations. Deep-learning models have demonstrated excellent performance in predicting toxicity outcomes from various data sources such as chemical structures, genomic data, and high-throughput screening assays. The potential of deep learning for automated feature engineering is also discussed. This review emphasizes the need to address ethical concerns related to the use of deep learning in drug toxicity studies, including the reduction of animal use and ensuring regulatory acceptance. Furthermore, emerging applications of deep learning in drug toxicity prediction, such as predicting drug-drug interactions and toxicity in rare subpopulations, are highlighted. The integration of deep-learning-based approaches with traditional methods is discussed as a way to develop more reliable and efficient predictive models for drug safety assessment, paving the way for safer and more effective drug discovery and development. Overall, this review highlights the critical role of deep learning in predictive toxicology and drug safety evaluation, emphasizing the need for continued research and development in this rapidly evolving field. By addressing the limitations of traditional methods, leveraging the potential of deep learning for automated feature engineering, and addressing ethical concerns, deep-learning-based approaches have the potential to revolutionize drug toxicity prediction and improve patient safety in drug discovery and development.

In Silico and In Vitro Identification of P-Glycoprotein Inhibitors from a Library of 375 Phytochemicals

Cancer therapy with clinically established anticancer drugs is frequently hampered by the development of drug resistance of tumors and severe side effects in normal organs and tissues. The demand for powerful, but less toxic, drugs is high. Phytochemicals represent an important reservoir for drug development and frequently exert less toxicity than synthetic drugs. Bioinformatics can accelerate and simplify the highly complex, time-consuming, and expensive drug development process. Here, we analyzed 375 phytochemicals using virtual screenings, molecular docking, and in silico toxicity predictions. Based on these in silico studies, six candidate compounds were further investigated in vitro. Resazurin assays were performed to determine the growth-inhibitory effects towards wild-type CCRF-CEM leukemia cells and their multidrug-resistant, P-glycoprotein (P-gp)-overexpressing subline, CEM/ADR5000. Flow cytometry was used to measure the potential to measure P-gp-mediated doxorubicin transport. Bidwillon A, neobavaisoflavone, coptisine, and z-guggulsterone all showed growth-inhibitory effects and moderate P-gp inhibition, whereas miltirone and chamazulene strongly inhibited tumor cell growth and strongly increased intracellular doxorubicin uptake. Bidwillon A and miltirone were selected for molecular docking to wildtype and mutated P-gp forms in closed and open conformations. The P-gp homology models harbored clinically relevant mutations, i.e., six single missense mutations (F336Y, A718C, Q725A, F728A, M949C, Y953C), three double mutations (Y310A-F728A; F343C-V982C; Y953A-F978A), or one quadruple mutation (Y307C-F728A-Y953A-F978A). The mutants did not show major differences in binding energies compared to wildtypes. Closed P-gp forms generally showed higher binding affinities than open ones. Closed conformations might stabilize the binding, thereby leading to higher binding affinities, while open conformations may favor the release of compounds into the extracellular space. In conclusion, this study described the capability of selected phytochemicals to overcome multidrug resistance.

Identification of medicinal plant-based phytochemicals as a potential inhibitor for SARS-CoV-2 main protease (Mpro) using molecular docking and deep learning methods

Highly transmissive and rapidly evolving Coronavirus disease-2019 (COVID-19), a viral disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), triggered a global pandemic, which is one of the most researched viruses in the academia. Effective drugs to treat people with COVID-19 have yet to be developed to reduce mortality and transmission. Studies on the SARS-CoV-2 virus identified that its main protease (Mpro) might be a potential therapeutic target for drug development, as this enzyme plays a key role in viral replication. In search of potential inhibitors of Mpro, we developed a phytochemical library consisting of 2431 phytochemicals from 104 Korean medicinal plants that exhibited medicinal and antioxidant properties. The library was screened by molecular docking, followed by revalidation by re-screening with a deep learning method. Recurrent Neural Networks (RNN) computing system was used to develop an inhibitory predictive model using SARS coronavirus Mpro dataset. It was deployed to screen the top 12 compounds based on their docked binding affinity that ranged from -8.0 to -8.9 kcal/mol. The top two lead compounds, Catechin gallate and Quercetin 3-O-malonylglucoside, were selected depending on inhibitory potency against Mpro. Interactions with the target protein active sites, including His41, Met49, Cys145, Met165, and Thr190 were also examined. Molecular dynamics simulation was performed to analyze root mean square deviation (RMSD), root mean square fluctuation (RMSF), radius of gyration (RG), solvent accessible surface area (SASA), and number of hydrogen bonds. Results confirmed the inflexible nature of the docked complexes. Absorption, distribution, metabolism, excretion, and toxicity (ADMET), as well as bioactivity prediction confirmed the pharmaceutical activities of the lead compound. Findings of this research might help scientists to optimize compatible drugs for the treatment of COVID-19 patients.

Computational modeling of cyanobacterial phytoconstituents against toll-like receptors of skin cancer

Melanoma is an extremely dangerous disease. The diagnosis and treatment of it may be difficult because of its diversity and complexity. More than 90% of the marine biomass (microflora and microalgae) constitutes the natural biodiversity reserves. TLR-related research developments indicate possible cancer therapeutic possibilities. In addition to its significant function in innate immunity, TLR activation is connected to the start of pyroptosis, apoptosis, or autophagy in malignance cells. For these reasons, TLR agonists are appealing candidates for the production of cancer medications. From the web databases, the ternary structures of the receptors (TLR3 and TLR4) and ligands are extracted. Sixty-nine compounds were subjected to a drug likeness filter, but only twenty-two were screened further for evaluating ADMET criteria, in which only seven compounds satisfied the pharmacological properties. These compounds are further analyzed for docking parameters against TLRs (TLR3 and TLR4) and molecular simulation investigation of the best cluster to evaluate the complex stability. Molecular docking methodology discovered that Scytonmein has a significant binding potential energy of -5.21 and -7.92 kcal/mol against TLR3 and TLR4, respectively, in comparison to the redock co-crystal structure (-3.98 and -4.30 kcal/mol, respectively). The simulation analysis demonstrates the significant stability of the Scytonemin and TLR4 complexes in terms of average RMSD and RMSF compared to the redock complex, while criteria like solvent-accessible surface area (SASA), gyration (Rg) and hydrogen bonding have further supported the significant interaction and stability of the conformations.Communicated by Ramaswamy H. Sarma.

TOXRIC: a comprehensive database of toxicological data and benchmarks

The toxic effects of compounds on environment, humans, and other organisms have been a major focus of many research areas, including drug discovery and ecological research. Identifying the potential toxicity in the early stage of compound/drug discovery is critical. The rapid development of computational methods for evaluating various toxicity categories has increased the need for comprehensive and system-level collection of toxicological data, associated attributes, and benchmarks. To contribute toward this goal, we proposed TOXRIC (https://toxric.bioinforai.tech/), a database with comprehensive toxicological data, standardized attribute data, practical benchmarks, informative visualization of molecular representations, and an intuitive function interface. The data stored in TOXRIC contains 113 372 compounds, 13 toxicity categories, 1474 toxicity endpoints covering in vivo/in vitro endpoints and 39 feature types, covering structural, target, transcriptome, metabolic data, and other descriptors. All the curated datasets of endpoints and features can be retrieved, downloaded and directly used as output or input to Machine Learning (ML)-based prediction models. In addition to serving as a data repository, TOXRIC also provides visualization of benchmarks and molecular representations for all endpoint datasets. Based on these results, researchers can better understand and select optimal feature types, molecular representations, and baseline algorithms for each endpoint prediction task. We believe that the rich information on compound toxicology, ML-ready datasets, benchmarks and molecular representation distribution can greatly facilitate toxicological investigations, interpretation of toxicological mechanisms, compound/drug discovery and the development of computational methods.

Characterization of Streptomyces Species and Validation of Antimicrobial Activity of Their Metabolites through Molecular Docking

Finding new antibacterial agents from natural products is urgently necessary to address the growing cases of antibiotic-resistant pathogens. Actinomycetes are regarded as an excellent source of therapeutically important secondary metabolites including antibiotics. However, they have not yet been characterized and explored in great detail for their utility in developing countries such as Nepal. In silico molecular docking in addition to antimicrobial assays have been used to examine the efficacy of chemical scaffolds biosynthesized by actinomycetes. This paper depicts the characterization of actinomycetes based on their morphology, biochemical tests, and partial molecular sequencing. Furthermore, antimicrobial assays and mass spectrometry-based metabolic profiling of isolates were studied. Seventeen actinomycete-like colonies were isolated from ten soil samples, of which three isolates showed significant antimicrobial activities. Those isolates were subsequently identified to be Streptomyces species by partial 16S rRNA gene sequencing. The most potent Streptomyces species_SB10 has exhibited an MIC and MBC of 1.22 μg/mL and 2.44 μg/mL, respectively, against each Staphylococcus aureus and Shigella sonnei. The extract of S. species_SB10 showed the presence of important metabolites such as albumycin. Ten annotated bioactive metabolites (essramycin, maculosin, brevianamide F, cyclo (L-Phe-L-Ala), cyclo (L-Val-L-Phe), cyclo (L-Leu-L-Pro), cyclo (D-Ala-L-Pro), N6, N6-dimethyladenosine, albumycin, and cyclo (L-Tyr-L-Leu)) were molecularly docked against seven antimicrobial target proteins. Studies on binding energy, docking viability, and protein-ligand molecular interactions showed that those metabolites are responsible for conferring antimicrobial properties. These findings indicate that continuous research on the isolation of the Streptomyces species from Nepal could lead to the discovery of novel and therapeutically relevant antimicrobial agents in the future.

Computational identification of bioactive compounds from Cydonia oblonga Mill. against hepatocellular carcinoma by targeting pTEN and HBx-interacting protein

Phytochemicals derived from Cydonia oblonga have been investigated for their anti-oxidant and anti-cancer activities in various cancer cell lines. The reported bioactive compounds are evaluated in silico to develop a novel antagonist against pTEN (phosphatase and tensin homolog) and HBx (hepatitis B X-interacting protein) to target hepatocellular carcinoma. Lower expression of pTEN or higher expression of HBx represents the progression of hepatocellular carcinoma. This research is intended to identify the best candidate who interacts with our target proteins (pTEN and HBx) from the quince seeds by using computational methodologies. The ternary structures of the proteins and phytochemicals are retrieved from the online databases (RCSB and PubChem). The drug likeness analysis of the reported seventeen compounds was done, but only five follow the selection criteria. ADMET profiling of these five compounds was done, followed by docking analysis and molecular dynamics study of the best complexes to determine the stability of the complexes. A docking study revealed that caffeoylquinic acids (CQA) derivatives have the significant inhibitory potential of 3-O-caffeoylquinic acid (3CQA) and 5-O-caffeoylquinic acid (5CQA) with binding affinity of - 7.53 and - 7.49 against pTEN and - 5.94 and - 6.01 against HBx in comparison to the doxorubicin. The average root mean square deviation and root mean square fluctuation values for protein-ligand complexes were found quite stable compared to the standard, while parameters like gyration and SASA (solvent-accessible surface area) supported the complexes significant binding and stability. The results obtained from the evaluation show that 3CQA and 5CQA have the best stability, especially with the pTEN protein target. Hence, these compounds have to be considered for detailed experimental studies to understand their biological function against hepato-carcinoma.

Potential Therapeutic Candidates against Chlamydia pneumonia Discovered and Developed In Silico Using Core Proteomics and Molecular Docking and Simulation-Based Approaches

Chlamydia pneumonia, a species of the family Chlamydiacea, is a leading cause of pneumonia. Failure to eradicate C. pneumoniae can lead to chronic infection, which is why it is also considered responsible for chronic inflammatory disorders such as asthma, arthritis, etc. There is an urgent need to tackle the major concerns arising due to persistent infections caused by C. pneumoniae as no FDA-approved drug is available against this chronic infection. In the present study, an approach named subtractive proteomics was employed to the core proteomes of five strains of C. pneumonia using various bioinformatic tools, servers, and software. However, 958 non-redundant proteins were predicted from the 4754 core proteins of the core proteome. BLASTp was used to analyze the non-redundant genes against the proteome of humans, and the number of potential genes was reduced to 681. Furthermore, based on subcellular localization prediction, 313 proteins with cytoplasmic localization were selected for metabolic pathway analysis. Upon subsequent analysis, only three cytoplasmic proteins, namely 30S ribosomal protein S4, 4-hydroxybenzoate decarboxylase subunit C, and oligopeptide binding protein, were identified, which have the potential to be novel drug target candidates. The Swiss Model server was used to predict the target proteins’ three-dimensional (3D) structure. The molecular docking technique was employed using MOE software for the virtual screening of a library of 15,000 phytochemicals against the interacting residues of the target proteins. Molecular docking experiments were also evaluated using molecular dynamics simulations and the widely used MM-GBSA and MM-PBSA binding free energy techniques. The findings revealed a promising candidate as a novel target against C. pneumonia infections.

cropCSM: designing safe and potent herbicides with graph-based signatures

Herbicides have revolutionised weed management, increased crop yields and improved profitability allowing for an increase in worldwide food security. Their widespread use, however, has also led to a rise in resistance and concerns about their environmental impact. Despite the need for potent and safe herbicidal molecules, no herbicide with a new mode of action has reached the market in 30 years. Although development of computational approaches has proven invaluable to guide rational drug discovery pipelines, leading to higher hit rates and lower attrition due to poor toxicity, little has been done in contrast for herbicide design. To fill this gap, we have developed cropCSM, a computational platform to help identify new, potent, nontoxic and environmentally safe herbicides. By using a knowledge-based approach, we identified physicochemical properties and substructures enriched in safe herbicides. By representing the small molecules as a graph, we leveraged these insights to guide the development of predictive models trained and tested on the largest collected data set of molecules with experimentally characterised herbicidal profiles to date (over 4500 compounds). In addition, we developed six new environmental and human toxicity predictors, spanning five different species to assist in molecule prioritisation. cropCSM was able to correctly identify 97% of herbicides currently available commercially, while predicting toxicity profiles with accuracies of up to 92%. We believe cropCSM will be an essential tool for the enrichment of screening libraries and to guide the development of potent and safe herbicides. We have made the method freely available through a user-friendly webserver at http://biosig.unimelb.edu.au/crop_csm.

A new method for predicting the acute toxicity of carbamate pesticides based on the perspective of binding information with carrier protein

Toxicity is one of the most important factors limiting the success of new drug development. In this paper, we built a fast and convenient new method (Carrier protein binding information-toxicity relationship, CPBITR) for predicting drug acute toxicity based on the perspective of binding information with carrier protein. First, we studied the binding information between carbamate pesticides and human serum albumin (HSA) through various spectroscopic methods and molecular docking. Then a total of 16 models were established to clarify the relationship between binding information with HSA and drug toxicity. The results showed that the binding information was related to toxicity. Finally we obtained the effective toxicity prediction model for carbamate pesticides. And the "Platform for Predicting Drug Toxicity Based on the Information of Binding with Carrier Protein" was established with the Back-propagation neural network model. We proposed and proved that it was feasible to predict drug toxicity from this new perspective: binding with carrier protein. According to this new perspective, toxicity prediction model of other drugs can also be established. This new method has the advantages of convenience and fast, and can be used to screen out low-toxic drugs quickly in the early stage. It is helpful for drug research and development.

Screening cyclooxygenase-2 inhibitors from Allium sativum L. compounds: in silico approach

Inflammation is a natural protective response toward various simulators, including tissue damage or pathogens. The cyclooxygenase-2 (COX-2) is a very important protein in triggering pain and inflammation. Previous studies have claimed that Allium sativum offers a wide range of anti-inflammatory therapeutics for human consumption. Drug discovery is a complicated process, though in silico methods can make this procedure simpler and more cost-effective. At the current study, we performed the virtual screening of eight Allium sativum-derived compounds via molecular docking with COX-2 enzyme and confirmed the binding energy by docking score estimate followed by ADMET and drug-likeness investigation. The resulting highest-docking scored compound was exposed to molecular dynamics simulation (MDS) for evaluating stability of the docked enzyme-ligand complex and to gauge the oscillation and conformational alterations for the time of enzyme-ligand interaction. The factors of RMSD, RMSF, hydrogen bond interactions, and Rg after 100 ns of MDS proved the stability of alliin in the active site of COX-2 in comparison with celecoxib (CEL) as the control. Moreover, we investigated the binding affinity analysis of all compounds via MM/PBSA method. The results from this study suggest that alliin (a sulfuric compound) exhibits a higher binding affinity for the COX-2 enzyme compared to the other compounds and CEL. Alliin showed to be a possible anti-inflammatory therapeutic candidate for managing the inflammatory conditions.

GC-MS analysis of phytoconstituents from Ruellia prostrata and Senna tora and identification of potential anti-viral activity against SARS-CoV-2

SARS-CoV-2 is an etiologic agent responsible for the coronavirus disease 2019 (COVID-19) pandemic. The virus has rapidly extended globally and taken millions of lives due to the unavailability of therapeutics candidates against the virus. Till now, no specific drug candidates have been developed that can prevent or treat infections caused by the pathogen. The main protease (M^pro) of the SARS-CoV-2 plays a pivotal role in mediating viral replication and mechanistically inhibition of the protein can hinder the replication and infection process of the virus. Therefore, the study aimed to identify the natural bioactive compounds against the virus that can block the activity of the M^pro and subsequently block viral infections. Initially, a total of 96 phytochemicals from Ruellia prostrata Poir. and Senna tora (L.) Roxb. plants were identified through the gas chromatography-mass spectrometry (GC-MS) analytical method. Subsequently, the compounds were screened through molecular docking, absorption, distribution, metabolism, excretion (ADME), toxicity (T), and molecular dynamics (MD) simulation approach. The molecular docking method initially identified four molecules having a PubChem CID: 70825, CID: 25247358, CID: 54685836 and, CID: 1983 with a binding affinity ranging between −6.067 to −6.53 kcal mol⁻¹ to the active site of the target protein. All the selected compounds exhibit good pharmacokinetics and toxicity properties. Finally, the four compounds were further evaluated based on the MD simulation methods that confirmed the binding stability of the compounds to the targeted protein. The computational approaches identified the best four compounds CID: 70825, CID: 25247358, CID: 54685836 and, CID: 1983 that can be developed as a treatment option of SARS-CoV-2 disease-related complications. Although, experimental validation is suggested for further evaluation of the work.

Protease (M^pro) of SARS-CoV-2 has been identified as being able to hinder the replication process of the virus. Using GC-MS analytical methods, phytochemicals were identified from different medicinal plants that resulted in inhibitory activity of the molecules against M^pro.

Spike protein recognizer receptor ACE2 targeted identification of potential natural antiviral drug candidates against SARS-CoV-2

Angiotensin-converting enzyme 2 (ACE2), also known as peptidyl-dipeptidase A, belongs to the dipeptidyl carboxydipeptidases family has emerged as a potential antiviral drug target against SARS-CoV-2. Most of the ACE2 inhibitors discovered till now are chemical synthesis; suffer from many limitations related to stability and adverse side effects. However, natural, and selective ACE2 inhibitors that possess strong stability and low side effects can be replaced instead of those chemicals' inhibitors. To envisage structurally diverse natural entities as an ACE2 inhibitor with better efficacy, a 3D structure-based-pharmacophore model (SBPM) has been developed and validated by 20 known selective inhibitors with their correspondence 1166 decoy compounds. The validated SBPM has excellent goodness of hit score and good predictive ability, which has been appointed as a query model for further screening of 11,295 natural compounds. The resultant 23 hits compounds with pharmacophore fit score 75.31 to 78.81 were optimized using in-silico ADMET and molecular docking analysis. Four potential natural inhibitory molecules namely D-DOPA (Amb17613565), L-Saccharopine (Amb6600091), D-Phenylalanine (Amb3940754), and L-Mimosine (Amb21855906) have been selected based on their binding affinity (−7.5, −7.1, −7.1, and −7.0 kcal/mol), respectively. Moreover, 250 ns molecular dynamics (MD) simulations confirmed the structural stability of the ligands within the protein. Additionally, MM/GBSA approach also used to support the stability of molecules to the binding site of the protein that also confirm the stability of the selected four natural compounds. The virtual screening strategy used in this study demonstrated four natural compounds that can be utilized for designing a future class of potential natural ACE2 inhibitor that will block the spike (S) protein dependent entry of SARS-CoV-2 into the host cell.

Reversion of antibiotic resistance in multidrug-resistant pathogens using non-antibiotic pharmaceutical benzydamine

Antimicrobial resistance has been a growing concern that gradually undermines our tradition treatment regimens. The fact that few antibacterial drugs with new scaffolds or targets have been approved in the past two decades aggravates this crisis. Repurposing drugs as potent antibiotic adjuvants offers a cost-effective strategy to mitigate the development of resistance and tackle the increasing infections by multidrug-resistant (MDR) bacteria. Herein, we found that benzydamine, a widely used non-steroidal anti-inflammatory drug in clinic, remarkably potentiated broad-spectrum antibiotic-tetracyclines activity against a panel of clinically important pathogens, including MRSA, VRE, MCRPEC and tet(X)-positive Gram-negative bacteria. Mechanistic studies showed that benzydamine dissipated membrane potential (▵Ψ) in both Gram-positive and Gram-negative bacteria, which in turn upregulated the transmembrane proton gradient (▵pH) and promoted the uptake of tetracyclines. Additionally, benzydamine exacerbated the oxidative stress by triggering the production of ROS and suppressing GAD system-mediated oxidative defensive. This mode of action explains the great bactericidal activity of the doxycycline-benzydamine combination against different metabolic states of bacteria involve persister cells. As a proof-of-concept, the in vivo efficacy of this drug combination was evidenced in multiple animal infection models. These findings indicate that benzydamine is a potential tetracyclines adjuvant to address life-threatening infections by MDR bacteria.

Application of artificial intelligence in liver diseases: From diagnosis to treatment

Infectious or noninfectious liver disease has inexorably risen as one of the leading causes of global death and disease burden. There were an estimated 2.14 million liver-related deaths in 2017, representing an 11.4% increase since 2012. Traditional diagnosis and treatment methods have various dilemmas in different causes of liver disease. As a hot research topic in recent years, the application of artificial intelligence (AI) in different fields has attracted extensive attention, and new technologies have brought more ideas for the diagnosis and treatment of some liver diseases. Machine learning (ML) is the core of AI and the basic way to make a computer intelligent. ML technology has many potential uses in hepatology, ranging from exploring new noninvasive means to predict or diagnose different liver diseases to automated image analysis. The application of ML in liver diseases can help clinical staff to diagnose and treat different liver diseases quickly, accurately and scientifically, which is of importance for reducing the incidence and mortality of liver diseases, reducing medical errors, and promoting the development of medicine. This paper reviews the application and prospects of AI in liver diseases, and aims to improve clinicians’ awareness of the importance of AI in the diagnosis and treatment of liver diseases.

Multitask CapsNet: An Imbalanced Data Deep Learning Method for Predicting Toxicants

Drug development has a high failure rate, with safety properties constituting a considerable challenge. To reduce risk, in silico tools, including various machine learning methods, have been applied for toxicity prediction. However, these approaches often confront a serious problem: the training data sets are usually biased (imbalanced positive and negative samples), which would result in model training difficulty and unsatisfactory prediction accuracy. Multitask networks obtained significantly better predictive accuracies than single-task methods, and capsule neural networks showed excellent performance in sparse data sets in previous studies. In this study, we developed a new multitask framework based on a capsule neural network (multitask CapsNet) to measure 12 different toxic effects simultaneously. We found that multitask CapsNet excelled in toxicity prediction and outperformed many other computational approaches using the multitask strategy. Only after training on biased data sets did multitask CapsNet achieve significantly improved prediction accuracy on the Tox21 Data Challenge, which gave the largest ratio of highest accuracy (8/12) among compared models. Our model gave a prediction accuracy of 96.6% for the target NR.PPAR.gamma, whose ratio of negative to positive samples was up to 36:1. These results suggested that multitask CapsNet could overcome the bias problems and would provide a novel, accurate, and efficient approach for predicting the toxicities of compounds.

In silico methods and tools for drug discovery

In the past, conventional drug discovery strategies have been successfully employed to develop new drugs, but the process from lead identification to clinical trials takes more than 12 years and costs approximately $1.8 billion USD on average. Recently, in silico approaches have been attracting considerable interest because of their potential to accelerate drug discovery in terms of time, labor, and costs. Many new drug compounds have been successfully developed using computational methods. In this review, we briefly introduce computational drug discovery strategies and outline up-to-date tools to perform the strategies as well as available knowledge bases for those who develop their own computational models. Finally, we introduce successful examples of anti-bacterial, anti-viral, and anti-cancer drug discoveries that were made using computational methods.

Prediction of Drug-Induced Liver Toxicity Using SVM and Optimal Descriptor Sets

Drug-induced liver toxicity is one of the significant safety challenges for the patient's health and the pharmaceutical industry. It causes termination of drug candidates in clinical trials and also the retractions of approved drugs from the market. Thus, it is essential to identify hepatotoxic compounds in the initial stages of drug development process. The purpose of this study is to construct quantitative structure activity relationship models using machine learning algorithms and systematical feature selection methods for molecular descriptor sets. The models were built from a large and diverse set of 1253 drug compounds and were validated internally with 10-fold cross-validation. In this study, we applied a variety of feature selection techniques to extract the optimal subset of descriptors as modeling features to improve the prediction performance. Experimental results suggested that the support vector machine-based classifier had achieved a better classification accuracy with reduced molecular descriptors. The final optimal model provides an accuracy of 0.811, a sensitivity of 0.840, a specificity of 0.783 and Mathew's correlation coefficient of 0.623 with an internal validation set. Furthermore, this model outperformed the prior studies while evaluated in both the internal and external test sets. The utilization of distinct optimal molecular descriptors as modeling features produce an in silico model with a superior performance.

Assessing the impact of expert knowledge on ICH M7 (Q)SAR predictions. Is expert review still needed?

The ICH M7 (R1) guideline recommends the use of complementary (Q)SAR models to assess the mutagenic potential of drug impurities as a state-of-the-art, high-throughput alternative to empirical testing. Additionally, it includes a provision for the application of expert knowledge to increase prediction confidence and resolve conflicting calls. Expert knowledge, which considers structural analogs and mechanisms of activity, has been valuable when models return an indeterminate (equivocal) result or no prediction (out-of-domain). A retrospective analysis of 1002 impurities evaluated in drug regulatory applications between April 2017 and March 2019 assessed the impact of expert review on (Q)SAR predictions. Expert knowledge overturned the default predictions for 26% of the impurities and resolved 91% of equivocal predictions and 75% of out-of-domain calls. Of the 261 overturned default predictions, 15% were upgraded to equivocal or positive and 79% were downgraded to equivocal or negative. Chemical classes with the most overturns were primary aromatic amines (46%), aldehydes (45%), Michael-reactive acceptors (37%), and non-primary alkyl halides (33%). Additionally, low confidence predictions were the most often overturned. Collectively, the results suggest that expert knowledge continues to play an important role in an ICH M7 (Q)SAR prediction workflow and triaging predictions based on chemical class and probability can improve (Q)SAR review efficiency.

Artificial Intelligence in Pharmaceutical Field - A Critical Review

Artificial intelligence is an emerging sector in almost all fields. It is not confined only to a particular category and can be used in various fields like research, technology, and health. AI mainly concentrates on how computers analyze data and mimic the human thought process. As drug development involves high R & D costs and uncertainty in time consumption, artificial intelligence can serve as one of the promising solutions to overcome all these demerits. Due to the availability of enormous data, there are chances of missing out on some crucial details. For solving these issues, algorithms like machine learning, deep learning, and other expert systems are being used. On successful implementation of AI in the pharmaceutical field, the delays in drug development, and failure at the clinical and marketing level can be reduced. This review comprises information regarding the development of AI, its subfields, its overall implementation, and its application in the pharmaceutical sector and provides insights on challenges and limitations concerning AI.

Machine learning-integrated omics for the risk and safety assessment of nanomaterials

With the advancement in nanotechnology, we are experiencing transformation in world order with deep insemination of nanoproducts from basic necessities to advanced electronics, health care products and medicines. Therefore, nanoproducts, however, can have negative side effects and must be strictly monitored to avoid negative outcomes. Future toxicity and safety challenges regarding nanomaterial incorporation into consumer products, including rapid addition of nanomaterials with diverse functionalities and attributes, highlight the limitations of traditional safety evaluation tools. Currently, artificial intelligence and machine learning algorithms are envisioned for enhancing and improving the nano-bio-interaction simulation and modeling, and they extend to the post-marketing surveillance of nanomaterials in the real world. Thus, hyphenation of machine learning with biology and nanomaterials could provide exclusive insights into the perturbations of delicate biological functions after integration with nanomaterials. In this review, we discuss the potential of combining integrative omics with machine learning in profiling nanomaterial safety and risk assessment and provide guidance for regulatory authorities as well.

Mining Toxicity Information from Large Amounts of Toxicity Data

Safety is a main reason for drug failures, and therefore, the detection of compound toxicity and potential adverse effects in the early stage of drug development is highly desirable. However, accurate prediction of many toxicity endpoints is extremely challenging due to low accessibility of sufficient and reliable toxicity data, as well as complicated and diversified mechanisms related to toxicity. In this study, we proposed the novel multitask graph attention (MGA) framework to learn the regression and classification tasks simultaneously. MGA has shown excellent predictive power on 33 toxicity data sets and has the capability to extract general toxicity features and generate customized toxicity fingerprints. In addition, MGA provides a new way to detect structural alerts and discover the relationship between different toxicity tasks, which will be quite helpful to mine toxicity information from large amounts of toxicity data.

PySmash: Python package and individual executable program for representative substructure generation and application

BACKGROUND

Substructure screening is widely applied to evaluate the molecular potency and ADMET properties of compounds in drug discovery pipelines, and it can also be used to interpret QSAR models for the design of new compounds with desirable physicochemical and biological properties. With the continuous accumulation of more experimental data, data-driven computational systems which can derive representative substructures from large chemical libraries attract more attention. Therefore, the development of an integrated and convenient tool to generate and implement representative substructures is urgently needed.

RESULTS

In this study, PySmash, a user-friendly and powerful tool to generate different types of representative substructures, was developed. The current version of PySmash provides both a Python package and an individual executable program, which achieves ease of operation and pipeline integration. Three types of substructure generation algorithms, including circular, path-based and functional group-based algorithms, are provided. Users can conveniently customize their own requirements for substructure size, accuracy and coverage, statistical significance and parallel computation during execution. Besides, PySmash provides the function for external data screening.

CONCLUSION

PySmash, a user-friendly and integrated tool for the automatic generation and implementation of representative substructures, is presented. Three screening examples, including toxicophore derivation, privileged motif detection and the integration of substructures with machine learning (ML) models, are provided to illustrate the utility of PySmash in safety profile evaluation, therapeutic activity exploration and molecular optimization, respectively. Its executable program and Python package are available at https://github.com/kotori-y/pySmash.

Root causes of adverse drug events in hospitals and artificial intelligence capabilities for prevention

AIMS

To identify and prioritize the root causes of adverse drug events (ADEs) in hospitals and to assess the ability of artificial intelligence (AI) capabilities to prevent ADEs.

DESIGN

A mixed method design was used.

METHODS

A cross-sectional study for hospitals in Spain was carried out between February and April 2019 to identify and prioritize the root causes of ADEs. A nominal group technique was also used to assess the ability of AI capabilities to prevent ADEs.

RESULTS

The main root cause of ADEs was a lack of adherence to safety protocols (64.8%), followed by identification errors (57.4%), and fragile and polymedicated patients (44.4%). An analysis of the AI capabilities to prevent the root causes of ADEs showed that identification and reading are two potentially useful capabilities.

CONCLUSION

Identification error is one of the main root causes of drug adverse events and AI capabilities could potentially prevent drug adverse events.

IMPACT

This study highlights the role of AI capabilities in safely identifying both patients and drugs, which is a crucial part of the medication administration process, and how this can prevent ADEs in hospitals.

MutagenPred-GCNNs: A Graph Convolutional Neural Network-Based Classification Model for Mutagenicity Prediction with Data-Driven Molecular Fingerprints

An important task in the early stage of drug discovery is the identification of mutagenic compounds. Mutagenicity prediction models that can interpret relationships between toxicological endpoints and compound structures are especially favorable. In this research, we used an advanced graph convolutional neural network (GCNN) architecture to identify the molecular representation and develop predictive models based on these representations. The predictive model based on features extracted by GCNNs can not only predict the mutagenicity of compounds but also identify the structure alerts in compounds. In fivefold cross-validation and external validation, the highest area under the curve was 0.8782 and 0.8382, respectively; the highest accuracy (Q) was 80.98% and 76.63%, respectively; the highest sensitivity was 83.27% and 78.92%, respectively; and the highest specificity was 78.83% and 76.32%, respectively. Additionally, our model also identified some toxicophores, such as aromatic nitro, three-membered heterocycles, quinones, and nitrogen and sulfur mustard. These results indicate that GCNNs could learn the features of mutagens effectively. In summary, we developed a mutagenicity classification model with high predictive performance and interpretability based on a data-driven molecular representation trained through GCNNs.

Cryo-EM Structure of K+-Bound hERG Channel Complexed with the Blocker Astemizole

The hERG channel is a voltage-gated potassium channel involved in cardiac repolarization. Off-target hERG inhibition by drugs has become a critical issue in the pharmaceutical industry. The three-dimensional structure of the hERG channel was recently reported at 3.8-Å resolution using cryogenic electron microscopy (cryo-EM). However, the drug inhibition mechanism remains unclear because of the scarce structural information regarding the drug- and potassium-bound hERG channels. In this study, we obtained the cryo-EM density map of potassium-bound hERG channel complexed with astemizole, a well-known hERG inhibitor that increases risk of potentially fatal arrhythmia, at 3.5-Å resolution. The structure suggested that astemizole inhibits potassium conduction by binding directly below the selectivity filter. Furthermore, we propose a possible binding model of astemizole to the hERG channel and provide insights into the unusual sensitivity of hERG to several drugs.

Integrated QSAR and Adverse Outcome Pathway Analysis of Chemicals Released on 3D Printing Using Acrylonitrile Butadiene Styrene

Additive manufacturing commonly known as 3D printing has numerous applications in several domains including material and biomedical technologies and has emerged as a tool of capabilities by providing fast, highly customized, and cost-effective solutions. However, the impact of the printing materials and chemicals present in the printing fumes has raised concerns about their adverse potential affecting humans and the environment. Thus, it is necessary to understand the properties of the chemicals emitted during additive manufacturing for developing safe and biocompatible fibers having controlled emission of fumes including its sustainable usage. Therefore, in this study, we have developed a computational predictive risk-assessment framework on the comprehensive list of chemicals released during 3D printing using the acrylonitrile butadiene styrene (ABS) filament. Our results showed that the chemicals present in the fumes of the ABS-based fiber used in additive manufacturing have the potential to lead to various toxicity end points such as inhalation toxicity, oral toxicity, carcinogenicity, hepatotoxicity, and teratogenicity. Moreover, because of their absorption, distribution in the body, metabolism, and excretion properties, most of the chemicals exhibited a high absorption level in the intestine and the potential to cross the blood-brain barrier. Furthermore, pathway analysis revealed that signaling like alpha-adrenergic receptor signaling, heterotrimeric G-protein signaling, and Alzheimer's disease-amyloid secretase pathway are significantly overrepresented given the identified target proteins of these chemicals. These findings signify the adversities associated with 3D printing fumes and the necessity for the development of biodegradable and considerably safer fibers for 3D printing technology.

Machine Learning in Predictive Toxicology: Recent Applications and Future Directions for Classification Models

In recent times, machine learning has become increasingly prominent in predictive toxicology as it has shifted from in vivo studies toward in silico studies. Currently, in vitro methods together with other computational methods such as quantitative structure-activity relationship modeling and absorption, distribution, metabolism, and excretion calculations are being used. An overview of machine learning and its applications in predictive toxicology is presented here, including support vector machines (SVMs), random forest (RF) and decision trees (DTs), neural networks, regression models, naïve Bayes, k-nearest neighbors, and ensemble learning. The recent successes of these machine learning methods in predictive toxicology are summarized, and a comparison of some models used in predictive toxicology is presented. In predictive toxicology, SVMs, RF, and DTs are the dominant machine learning methods due to the characteristics of the data available. Lastly, this review describes the current challenges facing the use of machine learning in predictive toxicology and offers insights into the possible areas of improvement in the field.

Scopy: an integrated negative design python library for desirable HTS/VS database design

BACKGROUND

High-throughput screening (HTS) and virtual screening (VS) have been widely used to identify potential hits from large chemical libraries. However, the frequent occurrence of 'noisy compounds' in the screened libraries, such as compounds with poor drug-likeness, poor selectivity or potential toxicity, has greatly weakened the enrichment capability of HTS and VS campaigns. Therefore, the development of comprehensive and credible tools to detect noisy compounds from chemical libraries is urgently needed in early stages of drug discovery.

RESULTS

In this study, we developed a freely available integrated python library for negative design, called Scopy, which supports the functions of data preparation, calculation of descriptors, scaffolds and screening filters, and data visualization. The current version of Scopy can calculate 39 basic molecular properties, 3 comprehensive molecular evaluation scores, 2 types of molecular scaffolds, 6 types of substructure descriptors and 2 types of fingerprints. A number of important screening rules are also provided by Scopy, including 15 drug-likeness rules (13 drug-likeness rules and 2 building block rules), 8 frequent hitter rules (four assay interference substructure filters and four promiscuous compound substructure filters), and 11 toxicophore filters (five human-related toxicity substructure filters, three environment-related toxicity substructure filters and three comprehensive toxicity substructure filters). Moreover, this library supports four different visualization functions to help users to gain a better understanding of the screened data, including basic feature radar chart, feature-feature-related scatter diagram, functional group marker gram and cloud gram.

CONCLUSION

Scopy provides a comprehensive Python package to filter out compounds with undesirable properties or substructures, which will benefit the design of high-quality chemical libraries for drug design and discovery. It is freely available at https://github.com/kotori-y/Scopy.

Neurotropic activity and safety of methylene-cycloalkylacetate (MCA) derivative 3-(3-allyl-2-methylenecyclohexyl) propanoic acid

Polyneuropathy is a disease involving multiple peripheral nerves injuries. Axon regrowth remains the major prerequisite for plasticity, regeneration, circuit formation, and eventually functional recovery and therefore, regulation of neurite outgrowth might be a candidate for treating polyneuropathies. In a recent study, we synthesized and established the methylene-cycloalkylacetate (MCAs) pharmacophore as a lead for the development of a neurotropic drug (inducing neurite/axonal outgrowth) using the PC12 neuronal model. In the present study we extended the characterizations of the in vitro neurotropic effect of the derivative 3-(3-allyl-2-methylenecyclohexyl) propanoic acid (MCA-13) on dorsal root ganglia and spinal cord neuronal cultures and analyzed its safety properties using blood biochemistry and cell counting, acute toxicity evaluation in mice and different in vitro "off-target" pharmacological evaluations. This MCA derivative deserves further preclinical mechanistic pharmacological characterizations including therapeutic efficacy in in vivo animal models of polyneuropathies, toward development of a clinically relevant neurotropic drug.