ADMET evaluation in drug discovery. 12. Development of binary classification models for prediction of hERG potassium channel blockage

Molecular designing of potential environmentally friendly PFAS based on deep learning and generative models

Perfluoroalkyl and polyfluoroalkyl substances (PFAS) are widely used across a spectrum of industrial and consumer goods. Nonetheless, their persistent nature and tendency to accumulate in biological systems pose substantial environmental and health threats. Consequently, striking a balance between maximizing product efficiency and minimizing environmental and health risks by tailoring the molecular structure of PFAS has become a pivotal challenge in the fields of environmental chemistry and sustainable development. To address this issue, a computational workflow was proposed for designing an environmentally friendly PFAS by incorporating deep learning (DL) and molecular generative models. The hybrid DL architecture MolHGT+ based on heterogeneous graph neural network with transformer-like attention was applied to predict the surface tension, bioaccumulation, and hepatotoxicity of the molecules. Through virtual screening of the PFAS master database using MolHGT+, the findings indicate that incorporating the siloxane group and betaine fragment can effectively decrease both the bioaccumulation and hepatotoxicity of PFAS while preserving low surface tension. In addition, molecular generative models were employed to create a structurally diverse pool of novel PFASs with the aforementioned hit molecules serving as the initial template structures. Overall, our study presents a promising AI-driven method for advancing the development of environmentally friendly PFAS.

In silico validation of hyaluronic acid - drug conjugates based targeted drug delivery for the treatment of COVID-19

The impact of COVID-19 urges scientists to develop targeted drug delivery to manage Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) viral infections with a fast recovery rate. The aim of the study is to develop Hyaluronic Acid (HA) drug conjugates of viral drugs to target two important enzymes (Mpro and PLpro) of SARS-CoV-2. Three antiviral drugs, namely Dexamethasone (DEX), Favipiravir (FAV), and Remdesivir (REM), were chosen for HA conjugation due to their reactive functional groups. Free forms of drugs (DEX, FAV, REM) and HA drug conjugates (HA-DEX, HA-FAV, HA-REM, HA-RHA, HA-RHE) were validated against Mpro (PDB ID 6LU7) and PLpro (PDB 7LLZ), which play an essential role in the replication and reproduction of the SARS-CoV-2 virus. The results of the present study revealed that HA-drug conjugates possess higher binding affinity and the best docking score towards the Mpro and PLpro target proteins of SARS-CoV-2 than their free forms of drugs. ADMET screening resulted that HA-drug conjugates exhibited better pharmacokinetic profiles than their pure forms of drugs. Further, molecular dynamic simulation studies, essential dynamics and free energy landscape analyses show that HA antiviral drug conjugates possess good trajectories and energy status, with the PLpro target protein (PDB 7LLZ) of SARS-CoV-2 through long-distance (500 ns) simulation screening. The research work recorded the best drug candidate for Cell-Targeted Drug Delivery (CTDD) for SARS-CoV-2-infected cells through hyaluronic acid conjugates of antiviral drugs.Communicated by Ramaswamy H. Sarma.

Modification of ibuprofen to improve the medicinal effect; structural, biological, and toxicological study

Ibuprofen is classified as a non-steroidal anti-inflammatory drug (NSAID) that is employed as an initial treatment option for its non-steroidal anti-inflammatory, pain-relieving, and antipyretic properties. However, Ibuprofen is linked to specific well-known gastrointestinal adverse effects like ulceration and gastrointestinal bleeding. It has been linked to harmful effects on the liver, kidney, and heart. The purpose of the study is to create novel and potential IBU analogue with reduced side effects with the enhancement of their medicinal effects, so as to advance the overall safety profile of the drug. The addition of some novel functional groups including CH3, F, CF3, OCF3, Cl, and OH at various locations in its core structure suggestively boost the chemical as well as biological action. The properties of these newly designed structures were analyzed through chemical, physical, and spectral calculations using Density Functional Theory (DFT) and time-dependent DFT through B3LYP/6-31 g (d,p) basis set for geometry optimization. Molecular docking and non-bonding interaction studies were conducted by means of the human prostaglandin synthase protein (PDB ID: 5F19) to predict binding affinity, interaction patterns, and the stability of the protein-drug complex. Additionally, ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) and PASS (Prediction of Activity Spectra for Substances) predictions were employed to evaluate the pharmacokinetic and toxicological properties of these structures. Importantly, most of the analogues displayed reduced hepatotoxicity, nephrotoxicity, and carcinogenicity in comparison to the original drug. Moreover, molecular docking analyses indicated improved medicinal outcomes, which were further supported by pharmacokinetic calculations. Together, these findings suggest that the modified structures have reduced adverse effects along with improved therapeutic action compared to the parent drug.

Molecular characterization of glutor-GLUT interaction and prediction of glutor's drug-likeness: implications for its utility as an antineoplastic agent

Recent experimental evidence from our and other laboratories has strongly indicated that glutor, a piperazine-2-one derivative, which is a pan-GLUT inhibitor, displays a promising antineoplastic action by hampering glucose uptake owing to its ability to inhibit GLUT1 and GLUT3, which are overexpressed in neoplastic cells. However, the molecular mechanism(s) of the inhibiting action of glutor has remained elusive. Thus, for optimal utilization of the antineoplastic potential of glutor, it is essential to decipher the precise mechanism(s) of its interaction with GLUTs. Therefore, the present investigation was carried out to understand the molecular mechanism(s) of the binding of glutor to GLUT1 and GLUT3 in silico. This study suggests that glutor can effectively bind to GLUTs at the reported binding site. Moreover, the docking of glutor to GLUT was stabilised by several contacts between these two partners as shown by the 200 ns long molecular dynamic simulation carried out using Gromacs, indicating the formation of a stable complex. Moreover, glutor was found to possess all characteristics conducive to its drug-likeness. Hence, these observations suggest that glutor has the potential to be used in antineoplastic therapeutic applications.Communicated by Ramaswamy H. Sarma.

Molecular modeling, dynamic simulation, and metabolic reactivity studies of quinazoline derivatives to investigate their anti-angiogenic potential by targeting wild EGFRwt and mutant EGFRT790M receptor tyrosine kinases

Non-small cell lung cancer, head and neck cancer, glioblastoma, and various other cancer types often demonstrate persistent elevation in EGFR tyrosine kinase activity due to acquired mutations in its kinase domain. Any alteration in the EGFR is responsible for triggering the upregulation of tumor angiogenic pathways, such as the PI3k-AKT-mTOR pathway, MAPK-ERK pathway and PLC-Ƴ pathway, which are critically involved in promoting tumor angiogenesis in cancer cells. The emergence of frequently occurring EGFR kinase domain mutations (L858R/T790M/C797S) that confer resistance to approved therapeutic agents has presented a significant challenge for researchers aiming to develop effective and well-tolerated treatments against tumor angiogenesis. In this study, we directed our efforts towards the rational design and development of novel quinazoline derivatives with the potential to act as antagonists against both wild-type and mutant EGFR. Our approach encompasing the application of advanced drug design strategies, including structure-based virtual screening, molecular docking, molecular dynamics, metabolic reactivity and cardiotoxicity prediction studies led to the identification of two prominent lead compounds: QU648, for EGFRwt inhibition and QU351, for EGFRmt antagonism. The computed binding energies of selected leads and their molecular dynamics simulations exhibited enhanced conformational stability of QU648 and QU351 when compared to standard drugs Erlotinib and Afatinib. Notably, the lead compounds also demonstrated promising pharmacokinetic properties, metabolic reactivity, and cardiotoxicity profiles. Collectively, the outcomes of our study provide compelling evidence supporting the potential of QU648 and QU351 as prominent anti-angiogenic agents, effectively inhibiting EGFR activity across various cancer types harboring diverse EGFR mutations.Communicated by Ramaswamy H. Sarma.

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.

In silico prediction of hERG blockers using machine learning and deep learning approaches

The human ether-à-go-go-related gene (hERG) is associated with drug cardiotoxicity. If the hERG channel is blocked, it will lead to prolonged QT interval and cause sudden death in severe cases. Therefore, it is important to evaluate the hERG-blocking property of compounds in early drug discovery. In this study, a dataset containing 4556 compounds with IC50 values determined by patch clamp techniques on mammalian lineage cells was collected, and hERG blockers and non-blockers were distinguished according to three single thresholds and two binary thresholds. Four machine learning (ML) algorithms combining four molecular fingerprints and molecular descriptors as well as graph convolutional neural networks (GCNs) were used to construct a series of binary classification models. The results showed that the best models varied for different thresholds. The ML models implemented by support vector machine and random forest performed well based on Morgan fingerprints and molecular descriptors, with AUCs ranging from 0.884 to 0.950. GCN showed superior prediction performance with AUCs above 0.952, which might be related to its direct extraction of molecular features from the original input. Meanwhile, the classification of binary threshold was better than that of single threshold, which could provide us with a more accurate prediction of hERG blockers. At last, the applicability domain for the model was defined, and seven structural alerts that might generate hERG blockage were identified by information gain and substructure frequency analysis. Our work would be beneficial for identifying hERG blockers in chemicals.

Discovery of dual-target natural antimalarial agents against DHODH and PMT of Plasmodium falciparum: pharmacophore modelling, molecular docking, quantum mechanics, and molecular dynamics simulations

Malaria is a lethal disease that claims thousands of lives worldwide annually. The objective of this study was to identify new natural compounds that can target two P. falciparum enzymes; P. falciparum Dihydroorotate dehydrogenase (PfDHODH) and P. falciparum phosphoethanolamine methyltransferase (PfPMT). To accomplish this, e-pharmacophore modelling and molecular docking were employed against PfDHODH. Following this, 1201 natural compounds with docking scores of ≤ -7 kcal/mol were docked into the active site of the second enzyme PMT. The top nine compounds were subjected to further investigation using MM-GBSA free binding energy calculations and ADME analysis. The results revealed favourable free binding energy values better than the references, as well as acceptable pharmacokinetic properties. Compounds ZINC000013377887, ZINC000015113777, and ZINC000085595753 were scrutinized to assess their interaction stability with the PfDHODH enzyme, and chemical stability reactivity using molecular dynamics (MD) simulation and density functional theory (DFT) calculations. These findings indicate that the three natural compounds are potential candidates for dual PfDHODH and PfPMT inhibitors for malaria treatment.

TargIDe: a machine-learning workflow for target identification of molecules with antibiofilm activity against Pseudomonas aeruginosa

Bacterial biofilms are a source of infectious human diseases and are heavily linked to antibiotic resistance. Pseudomonas aeruginosa is a multidrug-resistant bacterium widely present and implicated in several hospital-acquired infections. Over the last years, the development of new drugs able to inhibit Pseudomonas aeruginosa by interfering with its ability to form biofilms has become a promising strategy in drug discovery. Identifying molecules able to interfere with biofilm formation is difficult, but further developing these molecules by rationally improving their activity is particularly challenging, as it requires knowledge of the specific protein target that is inhibited. This work describes the development of a machine learning multitechnique consensus workflow to predict the protein targets of molecules with confirmed inhibitory activity against biofilm formation by Pseudomonas aeruginosa. It uses a specialized database containing all the known targets implicated in biofilm formation by Pseudomonas aeruginosa. The experimentally confirmed inhibitors available on ChEMBL, together with chemical descriptors, were used as the input features for a combination of nine different classification models, yielding a consensus method to predict the most likely target of a ligand. The implemented algorithm is freely available at https://github.com/BioSIM-Research-Group/TargIDe under licence GNU General Public Licence (GPL) version 3 and can easily be improved as more data become available.

Investigating cardiotoxicity related with hERG channel blockers using molecular fingerprints and graph attention mechanism

Human ether-a-go-go-related gene (hERG) channel blockade by small molecules is a big concern during drug development in the pharmaceutical industry. Failure or inhibition of hERG channel activity caused by drug molecules can lead to prolonging QT interval, which will result in serious cardiotoxicity. Thus, evaluating the hERG blocking activity of all these small molecular compounds is technically challenging, and the relevant procedures are expensive and time-consuming. In this study, we develop a novel deep learning predictive model named DMFGAM for predicting hERG blockers. In order to characterize the molecule more comprehensively, we first consider the fusion of multiple molecular fingerprint features to characterize its final molecular fingerprint features. Then, we use the multi-head attention mechanism to extract the molecular graph features. Both molecular fingerprint features and molecular graph features are fused as the final features of the compounds to make the feature expression of compounds more comprehensive. Finally, the molecules are classified into hERG blockers or hERG non-blockers through the fully connected neural network. We conduct 5-fold cross-validation experiment to evaluate the performance of DMFGAM, and verify the robustness of DMFGAM on external validation datasets. We believe DMFGAM can serve as a powerful tool to predict hERG channel blockers in the early stages of drug discovery and development.

Virtual screening of DrugBank database for hERG blockers using topological Laplacian-assisted AI models

The human ether-a-go-go (hERG) potassium channel (Kv11.1) plays a critical role in mediating cardiac action potential. The blockade of this ion channel can potentially lead fatal disorder and/or long QT syndrome. Many drugs have been withdrawn because of their serious hERG-cardiotoxicity. It is crucial to assess the hERG blockade activity in the early stage of drug discovery. We are particularly interested in the hERG-cardiotoxicity of compounds collected in the DrugBank database considering that many DrugBank compounds have been approved for therapeutic treatments or have high potential to become drugs. Machine learning-based in silico tools offer a rapid and economical platform to virtually screen DrugBank compounds. We design accurate and robust classifiers for blockers/non-blockers and then build regressors to quantitatively analyze the binding potency of the DrugBank compounds on the hERG channel. Molecular sequences are embedded with two natural language processing (NLP) methods, namely, autoencoder and transformer. Complementary three-dimensional (3D) molecular structures are embedded with two advanced mathematical approaches, i.e., topological Laplacians and algebraic graphs. With our state-of-the-art tools, we reveal that 227 out of the 8641 DrugBank compounds are potential hERG blockers, suggesting serious drug safety problems. Our predictions provide guidance for the further experimental interrogation of DrugBank compounds' hERG-cardiotoxicity.

Machine Learning Toxicity Prediction: Latest Advances by Toxicity End Point

Machine learning (ML) models to predict the toxicity of small molecules have garnered great attention and have become widely used in recent years. Computational toxicity prediction is particularly advantageous in the early stages of drug discovery in order to filter out molecules with high probability of failing in clinical trials. This has been helped by the increase in the number of large toxicology databases available. However, being an area of recent application, a greater understanding of the scope and applicability of ML methods is still necessary. There are various kinds of toxic end points that have been predicted in silico. Acute oral toxicity, hepatotoxicity, cardiotoxicity, mutagenicity, and the 12 Tox21 data end points are among the most commonly investigated. Machine learning methods exhibit different performances on different data sets due to dissimilar complexity, class distributions, or chemical space covered, which makes it hard to compare the performance of algorithms over different toxic end points. The general pipeline to predict toxicity using ML has already been analyzed in various reviews. In this contribution, we focus on the recent progress in the area and the outstanding challenges, making a detailed description of the state-of-the-art models implemented for each toxic end point. The type of molecular representation, the algorithm, and the evaluation metric used in each research work are explained and analyzed. A detailed description of end points that are usually predicted, their clinical relevance, the available databases, and the challenges they bring to the field are also highlighted.

Exploring Low-Toxicity Chemical Space with Deep Learning for Molecular Generation

Creating a wide range of new compounds that not only have ideal pharmacological properties but also easily pass long-term toxicity evaluation is still a challenging task in current drug discovery. In this study, we developed a conditional generative model by combining a semisupervised variational autoencoder (SSVAE) with an MGA toxicity predictor. Our aim is to generate molecules with low toxicity, good drug-like properties, and structural diversity. For multiobjective optimization, we have developed a method with hierarchical constraints on the toxicity space of small molecules to generate drug-like small molecules, which can also minimize the effect on the diversity of generated results. The evaluation results of the metrics indicate that the developed model has good effectiveness, novelty, and diversity. The generated molecules by this model are mainly distributed in low-toxicity regions, which suggests that our model can efficiently constrain the generation of toxic structures. In contrast to simply filtering toxic ones after generation, the low-toxicity molecular generative model can generate molecules with structural diversity. Our strategy can be used in target-based drug discovery to improve the quality of generated molecules with low-toxicity, drug-like, and highly active properties.

Interpretable-ADMET: a web service for ADMET prediction and optimization based on deep neural representation

MOTIVATION

In the process of discovery and optimization of lead compounds, it is difficult for non-expert pharmacologists to intuitively determine the contribution of substructure to a particular property of a molecule.

RESULTS

In this work, we develop a user-friendly web service, named interpretable-absorption, distribution, metabolism, excretion and toxicity (ADMET), which predict 59 ADMET-associated properties using 90 qualitative classification models and 28 quantitative regression models based on graph convolutional neural network and graph attention network algorithms. In interpretable-ADMET, there are 250 729 entries associated with 59 kinds of ADMET-associated properties for 80 167 chemical compounds. In addition to making predictions, interpretable-ADMET provides interpretation models based on gradient-weighted class activation map for identifying the substructure, which is important to the particular property. Interpretable-ADMET also provides an optimize module to automatically generate a set of novel virtual candidates based on matched molecular pair rules. We believe that interpretable-ADMET could serve as a useful tool for lead optimization in drug discovery.

AVAILABILITY AND IMPLEMENTATION

Interpretable-ADMET is available at http://cadd.pharmacy.nankai.edu.cn/interpretableadmet/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Knowledge-based BERT: a method to extract molecular features such as computational chemists

Molecular property prediction models based on machine learning algorithms have become important tools to triage unpromising lead molecules in the early stages of drug discovery. Compared with the mainstream descriptor- and graph-based methods for molecular property predictions, SMILES-based methods can directly extract molecular features from SMILES without human expert knowledge, but they require more powerful algorithms for feature extraction and a larger amount of data for training, which makes SMILES-based methods less popular. Here, we show the great potential of pre-training in promoting the predictions of important pharmaceutical properties. By utilizing three pre-training tasks based on atom feature prediction, molecular feature prediction and contrastive learning, a new pre-training method K-BERT, which can extract chemical information from SMILES like chemists, was developed. The calculation results on 15 pharmaceutical datasets show that K-BERT outperforms well-established descriptor-based (XGBoost) and graph-based (Attentive FP and HRGCN+) models. In addition, we found that the contrastive learning pre-training task enables K-BERT to 'understand' SMILES not limited to canonical SMILES. Moreover, the general fingerprints K-BERT-FP generated by K-BERT exhibit comparative predictive power to MACCS on 15 pharmaceutical datasets and can also capture molecular size and chirality information that traditional binary fingerprints cannot capture. Our results illustrate the great potential of K-BERT in the practical applications of molecular property predictions in drug discovery.

Molecular insights of hyaluronic acid - ethambutol and hyaluronic acid - isoniazid drug conjugates act as promising novel drugs for the treatment of tuberculosis

The present study examines cellular targeted drug delivery (CTDD) pattern of two novel Hyaluronic acid (HA) Tuberculosis Drug (TB) conjugates and its efficacy and strong binding affinity towards TB molecular protein targets. Two TB drugs ethambutol (EB) and isoniazid (IN) and their Hyaluronic acid conjugates (HA-EB & HA-IN) were tested for its metabolism, toxicity and excretion prediction through In silico tools they revealed hyaluronic acid conjugate of two TB drugs exhibited good drug profile over their free form of TB drugs. Further these four molecules subjected to In silico molecular docking study with four potential Mycobacterium tuberculosis target proteins (3PD8, 4Y0L, 5DZK and 6GAU). Molecular docking study revealed that hyaluronic conjugates (HA-EB & HA-IN) exhibit significant binding affinity and excellent docking scores with all screened molecular protein targets of TB over their free form of drug. Further molecular dynamic simulation was calculated for the four drug molecules (EB, IN, HA- EB & HA-IN) with DNA gyrase enzyme (PDB ID 6GAU) of Mycobacterium tuberculosis and the MDS results revealed that both the conjugates with the TB target protein possessed good number of interaction with binding pocket residues and good simulation scores than the free form of drugs.Communicated by Ramaswamy H. Sarma.

Predicting hERG channel blockers with directed message passing neural networks

Compounds with human ether-à-go-go related gene (hERG) blockade activity may cause severe cardiotoxicity. Assessing the hERG liability in the early stages of the drug discovery process is important, and the in silico methods for predicting hERG channel blockers are actively pursued. In the present study, the directed message passing neural network (D-MPNN) was applied to construct classification models for identifying hERG blockers based on diverse datasets. Several descriptors and fingerprints were tested along with the D-MPNN model. Among all these combinations, D-MPNN with the moe206 descriptors generated from MOE (D-MPNN + moe206) showed significantly improved performances. The AUC-ROC values of the D-MPNN + moe206 model reached 0.956 ± 0.005 under random split and 0.922 ± 0.015 under scaffold split on Cai's hERG dataset, respectively. Moreover, the comparisons between our models and several recently reported machine learning models were made based on various datasets. Our results indicated that the D-MPNN + moe206 model is among the best classification models. Overall, the excellent performance of the DMPNN + moe206 model achieved in this study highlights its potential application in the discovery of novel and effective hERG blockers.

Compounds with human ether-à-go-go related gene (hERG) blockade activity may cause severe cardiotoxicity.

Machine learning - Predicting Ames mutagenicity of small molecules

In modern drug discovery, detection of a compound's potential mutagenicity is crucial. However, the traditional method of mutagenicity detection using the Ames test is costly and time consuming as the compounds need to be synthesised and then tested and the results are not always accurate and reproducible. Therefore, it would be advantageous to develop robust in silico models which can accurately predict the mutagenicity of a compound prior to synthesis to overcome the inadequacies of the Ames test. After curation of a previously defined compound mutagenicity library, over 5000 molecules had their chemical fingerprints and molecular properties calculated. Using 8 classification modelling algorithms, including support vector machine (SVM), random forest (RF) and extreme gradient boosting (XGB), a total of 112 predictive models have been constructed. Their performance has been assessed using 10-fold cross validation and a hold-out test set and some of the top performing models have been assessed using the y-randomisation approach. As a result, we have found SVM and XGB models to have good performance during the 10-fold cross validation (AUROC >0.90, sensitivity >0.85, specificity >0.75, balanced accuracy >0.80, Kappa >0.65) and on the test set (AUROC >0.65, sensitivity >0.65, specificity >0.60, balanced accuracy >0.65, Kappa >0.30). We have also identified molecular properties that are the most influential for mutagenicity prediction when combined with chemical molecular fingerprints. Using the Class A mutagenic compounds from the Ames/QSAR International Challenge Project, we were able to verify our models perform better, predicting more mutagens correctly then the StarDrop Ames mutagenicity prediction and TEST mutagenicity prediction.

The rise of deep learning and transformations in bioactivity prediction power of molecular modeling tools

The search and design for the better use of bioactive compounds are used in many experiments to best mimic compounds' functions in the human body. However, finding a cost-effective and timesaving approach is a top priority in different disciplines. Nowadays, artificial intelligence (AI) and particularly deep learning (DL) methods are widely applied to improve the precision and accuracy of models used in the drug discovery process. DL approaches have been used to provide more opportunities for a faster, efficient, cost-effective, and reliable computer-aided drug discovery. Moreover, the increasing biomedical data volume in areas, like genome sequences, medical images, protein structures, etc., has made data mining algorithms very important in finding novel compounds that could be drugs, uncovering or repurposing drugs and improving the area of genetic markers-based personalized medicine. Furthermore, deep neural networks (DNNs) have been demonstrated to outperform other techniques such as random forests and SVMs for QSAR studies and ligand-based virtual screening. Despite this, in QSAR studies, the quality of different data sources and potential experimental errors has greatly affected the accuracy of QSAR predictions. Therefore, further researches are still needed to improve the accuracy, selectivity, and sensitivity of the DL approach in building the best models of drug discovery.

Hyperbolic relational graph convolution networks plus: a simple but highly efficient QSAR-modeling method

Accurate predictions of druggability and bioactivities of compounds are desirable to reduce the high cost and time of drug discovery. After more than five decades of continuing developments, quantitative structure-activity relationship (QSAR) methods have been established as indispensable tools that facilitate fast, reliable and affordable assessments of physicochemical and biological properties of compounds in drug-discovery programs. Currently, there are mainly two types of QSAR methods, descriptor-based methods and graph-based methods. The former is developed based on predefined molecular descriptors, whereas the latter is developed based on simple atomic and bond information. In this study, we presented a simple but highly efficient modeling method by combining molecular graphs and molecular descriptors as the input of a modified graph neural network, called hyperbolic relational graph convolution network plus (HRGCN+). The evaluation results show that HRGCN+ achieves state-of-the-art performance on 11 drug-discovery-related datasets. We also explored the impact of the addition of traditional molecular descriptors on the predictions of graph-based methods, and found that the addition of molecular descriptors can indeed boost the predictive power of graph-based methods. The results also highlight the strong anti-noise capability of our method. In addition, our method provides a way to interpret models at both the atom and descriptor levels, which can help medicinal chemists extract hidden information from complex datasets. We also offer an HRGCN+'s online prediction service at https://quantum.tencent.com/hrgcn/.

Brazilian essential oils as source for the discovery of new anti-COVID-19 drug: a review guided by in silico study

The emergence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in China and its spread worldwide has become one of the biggest health problem due to the lack of knowledge about an effective chemotherapy. Based on the current reality of the SARS-CoV-2 pandemic, this study aimed to make a review literature about potential anti-coronavirus natural compounds guided by an in silico study. In the first step, essential oils from native species found in the Brazilian herbal medicine market and Brazilian species that have already shown antiviral potential were used as source for the literature search and compounds selection. Among these compounds, 184 showed high antiviral potential against rhinovirus or picornavirus by quantitative structure-activity relationship analysis. (E)-α-atlantone; 14-hydroxy-α-muurolene; allo-aromadendrene epoxide; amorpha-4,9-dien-2-ol; aristochene; azulenol; germacrene A; guaia-6,9-diene; hedycaryol; humulene epoxide II; α-amorphene; α-cadinene; α-calacorene and α-muurolene showed by a molecular docking study the best result for four target proteins that are essential for SARS-CoV-2 lifecycle. In addition, other parameters obtained for the selected compounds indicated low toxicity and showed good probability to achieve cell permeability and be used as a drug. These results guided the second literature search which included other species in addition to native Brazilian plants. The majority presence of any of these compounds was reported for essential oils from 45 species. In view of the few studies relating essential oils and antiviral activity, this review is important for future assays against the new coronavirus.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s11101-021-09754-4.

Small Molecules Selectively Targeting Sigma-1 Receptor for the Treatment of Neurological Diseases

The sigma-1 (σ1) receptor, an enigmatic protein originally classified as an opioid receptor subtype, is now understood to possess unique structural and functional features of its own and play critical roles to widely impact signaling transduction by interacting with receptors, ion channels, lipids, and kinases. The σ1 receptor is implicated in modulating learning, memory, emotion, sensory systems, neuronal development, and cognition and accordingly is now an actively pursued drug target for various neurological and neuropsychiatric disorders. Evaluation of the five selective σ1 receptor drug candidates (pridopidine, ANAVEX2-73, SA4503, S1RA, and T-817MA) that have entered clinical trials has shown that reaching clinical approval remains an evasive and important goal. This review provides up-to-date information on the selective targeting of σ1 receptors, including their history, function, reported crystal structures, and roles in neurological diseases, as well as a useful collation of new chemical entities as σ1 selective orthosteric ligands or allosteric modulators.

Artificial intelligence in the early stages of drug discovery

Although the use of computational methods within the pharmaceutical industry is well established, there is an urgent need for new approaches that can improve and optimize the pipeline of drug discovery and development. In spite of the fact that there is no unique solution for this need for innovation, there has recently been a strong interest in the use of Artificial Intelligence for this purpose. As a matter of fact, not only there have been major contributions from the scientific community in this respect, but there has also been a growing partnership between the pharmaceutical industry and Artificial Intelligence companies. Beyond these contributions and efforts there is an underlying question, which we intend to discuss in this review: can the intrinsic difficulties within the drug discovery process be overcome with the implementation of Artificial Intelligence? While this is an open question, in this work we will focus on the advantages that these algorithms provide over the traditional methods in the context of early drug discovery.

Activity Prediction of Small Molecule Inhibitors for Antirheumatoid Arthritis Targets Based on Artificial Intelligence

Rheumatoid arthritis (RA) is a chronic autoimmune disease, which is compared to "immortal cancer" in industry. Currently, SYK, BTK, and JAK are the three major targets of protein tyrosine kinase for this disease. According to existing research, marketed and research drugs for RA are mostly based on single target, which limits their efficacy. Therefore, designing multitarget or dual-target inhibitors provide new insights for the treatment of RA regarding of the specific association between SYK, BTK, and JAK from two signal transduction pathways. In this study, machine learning (XGBoost, SVM) and deep learning (DNN) models were combined for the first time to build a powerful integrated model for SYK, BTK, and JAK. The predictive power of the integrated model was proved to be superior to that of a single classifier. In order to accurately assess the generalization ability of the integrated model, comprehensive similarity analysis was performed on the training and the test set, and the prediction accuracy of the integrated model was specifically analyzed under different similarity thresholds. External validation was conducted using single-target and dual-target inhibitors, respectively. Results showed that our model not only obtained a high recall rate (97%) in single-target prediction, but also achieved a favorable yield (54.4%) in dual-target prediction. Furthermore, by clustering dual-target inhibitors, the prediction performance of model in various classes were proved, evaluating the applicability domain of the model in the dual-target drug screening. In summary, the integrated model proposed is promising to screen dual-target inhibitors of SYK/JAK or BTK/JAK as RA drugs, which is beneficial for the clinical treatment of rheumatoid arthritis.

Sunitinib-Containing Carborane Pharmacophore with the Ability to Inhibit Tyrosine Kinases Receptors FLT3, KIT and PDGFR-β, Exhibits Powerful In Vivo Anti-Glioblastoma Activity

Simple Summary

Glioblastoma is one of the most aggressive central nervous system tumors. Combinations of therapies, such as tyrosine kinase receptor inhibition and boron neutron capture therapy (BNCT), could offer greater patients benefits over single-therapies. The aim of our study was to assess the potential of sunitinib-carborane hybrid compound 1 as an anti-glioblastoma agent. We confirmed for 1 the ability to inhibit tyrosine kinase receptors, which could promote canonical and non-canonical effects, absence of mutagenicity, ability to cross the blood–brain barrier, and powerful in vivo anti-glioblastoma activity. The overall attractive profile of 1 makes it an interesting compound for a bimodal therapeutic strategy against high grade gliomas.

Abstract

Malignant gliomas are the most common malignant and aggressive primary brain tumors in adults, the prognosis being—especially for glioblastomas—extremely poor. There are no effective treatments yet. However, tyrosine kinase receptor (TKR) inhibitors and boron neutron capture therapy (BNCT), together, have been proposed as future therapeutic strategies. In this sense in our ongoing project of developing new anti-glioblastoma drugs, we identified a sunitinib-carborane hybrid agent, 1, with both in vitro selective cytotoxicity and excellent BNCT-behavior. Consequently, we studied the ability of compound 1 to inhibit TKRs, its promotion of cellular death processes, and its effects on the cell cycle. Moreover, we analyzed some relevant drug-like properties of 1, i.e., mutagenicity and ability to cross the blood–brain barrier. These results encouraged us to perform an in vivo anti-glioblastoma proof of concept assay. It turned out to be a selective FLT3, KIT, and PDGFR-β inhibitor and increased the apoptotic glioma-cell numbers and arrested sub-G1-phase cell cycle. Its in vivo activity in immunosuppressed mice bearing U87 MG human glioblastoma evidenced excellent anti-tumor behavior.

Prediction of hERG potassium channel blockage using ensemble learning methods and molecular fingerprints

The human ether-a-go-go-related gene (hERG) encodes a tetrameric potassium channel called Kv11.1. This channel can be blocked by certain drugs, which leads to long QT syndrome, causing cardiotoxicity. This is a significant problem during drug development. Using computer models to predict compound cardiotoxicity during the early stages of drug design will help to solve this problem. In this study, we used a dataset of 1865 compounds exhibiting known hERG inhibitory activities as a training set. Thirty cardiotoxicity classification models were established using three machine learning algorithms based on molecular fingerprints and molecular descriptors. Through using these models as the base classifier, a new cardiotoxicity classification model with better predictive performance was developed using ensemble learning method. The accuracy of the best base classifier, which was generated using the XGBoost method with molecular descriptors, was 84.8 %, and the area under the receiver-operating characteristic curve (AUC) was 0.876 in the five fold cross-validation. However, all of the ensemble models that we developed had higher predictive performance than the base classifiers in the five fold cross-validation. The best predictive performance was achieved by the Ensemble-Top7 model, with accuracy of 84.9 % and AUC of 0.887. We also tested the ensemble model using external validation data and achieved accuracy of 85.0 % and AUC of 0.786. Furthermore, we identified several hERG-related substructures, which provide valuable information for designing drug candidates.

Benchmarking Data Sets from PubChem BioAssay Data: Current Scenario and Room for Improvement

Developing realistic data sets for evaluating virtual screening methods is a task that has been tackled by the cheminformatics community for many years. Numerous artificially constructed data collections were developed, such as DUD, DUD-E, or DEKOIS. However, they all suffer from multiple drawbacks, one of which is the absence of experimental results confirming the impotence of presumably inactive molecules, leading to possible false negatives in the ligand sets. In light of this problem, the PubChem BioAssay database, an open-access repository providing the bioactivity information of compounds that were already tested on a biological target, is now a recommended source for data set construction. Nevertheless, there exist several issues with the use of such data that need to be properly addressed. In this article, an overview of benchmarking data collections built upon experimental PubChem BioAssay input is provided, along with a thorough discussion of noteworthy issues that one must consider during the design of new ligand sets from this database. The points raised in this review are expected to guide future developments in this regard, in hopes of offering better evaluation tools for novel in silico screening procedures.

Repurposing of chloroquine and some clinically approved antiviral drugs as effective therapeutics to prevent cellular entry and replication of coronavirus

The reemergence of coronavirus prompts the need for the development of effective therapeutics to prevent the cellular entry and replication of coronavirus. This study demonstrated the putative inhibitory potential of lopinavir, remdesivir, oseltamir, azithromycin, ribavirin, and chloroquine towards V-ATPase, protein kinase A, SARS-CoV spike glycoprotein/ACE-2 complex and viral proteases. The pharmacodynamic and pharmacokinetic properties were predicted through the pkCSM server while the corresponding binding affinity of the selected drugs towards the proteins was computed using AutodockVina Screening tool. The ADMET properties revealed all the drugs possess drug-like properties. Lopinavir has the highest binding affinities to the pocket site of SARS-CoV spike glycoprotein/ACE-2 complex, cyclic AMP-dependent protein kinase A and 3-Chymotrypsin like protease while redemsivir has the highest binding affinities for vacuolar proton-translocating ATPase (V-ATPase) and papain-like proteins. The amino acids Asp269, Leu370, His374, and His345 were predicted as the key residues for lopinavir binding to human SARS-CoV spike glycoprotein/ACE-2 complex while His378, Tyr515, Leu73, Leu100, Phe32 and Phe40 for remdesivir and Tyr510, Phe504, Met62, Tyr50, and His378 were predicted for azithromycin as the key residues for binding to SARS-CoV spike glycoprotein/ACE-2 complex. Moreover, it was also observed that chloroquine has appreciable binding affinities for 3-Chymotrpsin- like protease and cyclic AMP-dependent protein kinase A when compared to Oseltamivir and ribavirin. The study provided evidence suggesting putative repurposing of the selected drugs for the development of valuable drugs for the prevention of cellular entry and replication of coronavirus.

Communicated by Ramaswamy H. Sarma

The Antioxidant Peptide Salamandrin-I: First Bioactive Peptide Identified from Skin Secretion of Salamandra Genus (Salamandra salamandra)

Amphibian skin is a multifunctional organ that plays key roles in defense, breathing, and water balance. In this study, skin secretion samples of the fire salamander (Salamandra salamandra) were separated using RP-HPLC and de novo sequenced using MALDI-TOF MS/MS. Next, we used an in silico platform to screen antioxidant molecules in the framework of density functional theory. One of the identified peptides, salamandrin-I, [M + H]⁺ = 1406.6 Da, was selected for solid-phase synthesis; it showed free radical scavenging activity against DPPH and ABTS radicals. Salamandrin-I did not show antimicrobial activity against Gram-positive and -negative bacteria. In vitro assays using human microglia and red blood cells showed that salamandrin-I has no cytotoxicity up to the concentration of 100 µM. In addition, in vivo toxicity tests on Galleria mellonella larvae resulted in no mortality at 20 and 40 mg/kg. Antioxidant peptides derived from natural sources are increasingly attracting interest. Among several applications, these peptides, such as salamandrin-I, can be used as templates in the design of novel antioxidant molecules that may contribute to devising strategies for more effective control of neurological disease.

ADMET evaluation in drug discovery. 20. Prediction of breast cancer resistance protein inhibition through machine learning

Breast cancer resistance protein (BCRP/ABCG2), an ATP-binding cassette (ABC) efflux transporter, plays a critical role in multi-drug resistance (MDR) to anti-cancer drugs and drug–drug interactions. The prediction of BCRP inhibition can facilitate evaluating potential drug resistance and drug–drug interactions in early stage of drug discovery. Here we reported a structurally diverse dataset consisting of 1098 BCRP inhibitors and 1701 non-inhibitors. Analysis of various physicochemical properties illustrates that BCRP inhibitors are more hydrophobic and aromatic than non-inhibitors. We then developed a series of quantitative structure–activity relationship (QSAR) models to discriminate between BCRP inhibitors and non-inhibitors. The optimal feature subset was determined by a wrapper feature selection method named rfSA (simulated annealing algorithm coupled with random forest), and the classification models were established by using seven machine learning approaches based on the optimal feature subset, including a deep learning method, two ensemble learning methods, and four classical machine learning methods. The statistical results demonstrated that three methods, including support vector machine (SVM), deep neural networks (DNN) and extreme gradient boosting (XGBoost), outperformed the others, and the SVM classifier yielded the best predictions (MCC = 0.812 and AUC = 0.958 for the test set). Then, a perturbation-based model-agnostic method was used to interpret our models and analyze the representative features for different models. The application domain analysis demonstrated the prediction reliability of our models. Moreover, the important structural fragments related to BCRP inhibition were identified by the information gain (IG) method along with the frequency analysis. In conclusion, we believe that the classification models developed in this study can be regarded as simple and accurate tools to distinguish BCRP inhibitors from non-inhibitors in drug design and discovery pipelines.

Capsule Networks Showed Excellent Performance in the Classification of hERG Blockers/Nonblockers

Capsule networks (CapsNets), a new class of deep neural network architectures proposed recently by Hinton et al., have shown a great performance in many fields, particularly in image recognition and natural language processing. However, CapsNets have not yet been applied to drug discovery-related studies. As the first attempt, we in this investigation adopted CapsNets to develop classification models of hERG blockers/nonblockers; drugs with hERG blockade activity are thought to have a potential risk of cardiotoxicity. Two capsule network architectures were established: convolution-capsule network (Conv-CapsNet) and restricted Boltzmann machine-capsule networks (RBM-CapsNet), in which convolution and a restricted Boltzmann machine (RBM) were used as feature extractors, respectively. Two prediction models of hERG blockers/nonblockers were then developed by Conv-CapsNet and RBM-CapsNet with the Doddareddy's training set composed of 2,389 compounds. The established models showed excellent performance in an independent test set comprising 255 compounds, with prediction accuracies of 91.8 and 92.2% for Conv-CapsNet and RBM-CapsNet models, respectively. Various comparisons were also made between our models and those developed by other machine learning methods including deep belief network (DBN), convolutional neural network (CNN), multilayer perceptron (MLP), support vector machine (SVM), k-nearest neighbors (kNN), logistic regression (LR), and LightGBM, and with different training sets. All the results showed that the models by Conv-CapsNet and RBM-CapsNet are among the best classification models. Overall, the excellent performance of capsule networks achieved in this investigation highlights their potential in drug discovery-related studies.

Bayesian machine learning to discover Bruton's tyrosine kinase inhibitors

Bruton's tyrosine kinase (BTK) has a crucial role in multiple cell signaling pathways including B-cell antigen receptor (BCR) and Fc receptor (FcR) signaling cascades, which has attracted much attention to find BTK inhibitors to treat autoimmune diseases. In this work, we constructed a Bayesian classification model for virtually seeking novel BTK inhibitors, which showed good performance in terms of screening efficiency and accuracy. Through searching for several chemical libraries including Chembl_17 (1,317,484 compounds), Chembridge (103,473 compounds), and Chemdiv (700,000 compounds) using this model followed by molecular docking and activity prediction, 52 compounds with novel scaffolds were acknowledged as potential BTK inhibitors, which could be promising starting points for further exploration. This study also provided a guide to construct an efficient and effective protocol for virtual screening by integrating machine learning methods.

Recent Advances in Developing K-Ras Plasma Membrane Localization Inhibitors

The Ras proteins play an important role in cell growth, differentiation, proliferation and survival by regulating diverse signaling pathways. Oncogenic mutant K-Ras is the most frequently mutated class of Ras superfamily that is highly prevalent in many human cancers. Despite intensive efforts to combat various K-Ras-mutant-driven cancers, no effective K-Ras-specific inhibitors have yet been approved for clinical use to date. Since K-Ras proteins must be associated to the plasma membrane for their function, targeting K-Ras plasma membrane localization represents a logical and potentially tractable therapeutic approach. Here, we summarize the recent advances in the development of K-Ras plasma membrane localization inhibitors including natural product-based inhibitors achieved from high throughput screening, fragment-based drug design, virtual screening, and drug repurposing as well as hit-to-lead optimizations.

Prediction of hERG K+ channel blockage using deep neural networks

Human ether-a-go-go-related gene (hERG) K+ channel blockage may cause severe cardiac side-effects and has become a serious issue in safety evaluation of drug candidates. Therefore, improving the ability to avoid undesirable hERG activity in the early stage of drug discovery is of significant importance. The purpose of this study was to build predictive models of hERG activity by deep neural networks. For each combination of sampling methods and descriptors, deep neural networks with different architectures were implemented to build classification models. The optimal model M15 with three hidden layers, undersampling method, and 2D descriptors yielded the prediction accuracy of 0.78 and F1 score of 0.75 on the test set as well as accuracy of 0.77 and F1 score of 0.34 on the external validation set, outperforming the other 35 models including 9 random forest models. Particularly, the optimal model M15 achieved the highest F1 score and the second highest accuracy when compared with other five methods from four groups using different machine learning algorithms with the same external validation set. It can be believed that this model has powerful capability on prediction of hERG toxicity, which is of great benefit for developing novel drug candidates.

Carboranylanilinoquinazoline EGFR-inhibitors: toward ‘lead-to-candidate’ stage in the drug-development pipeline

Background: Carboranylanilinoquinazoline-hybrids, developed for boron neutron capture therapy, have demonstrated cytotoxicity against murine-glioma cells with EGFR-inhibition ability. In addition, their adequate aqueous/metabolic stabilities and ability to cross blood–brain barrier make them good leads as to become antiglioma drugs. Aim: Analyze drug-like properties of representative carboranylanilinoquinazolines. Materials & methods: To expand carboranylanilinoquinazolines therapeutic spectrum, we studied their ability to act against glioma-mammal cells, U-87 MG and other tyrosine kinase-overexpress cells, HT-29. Additionally, we predicted theoretically and studied experimentally drug-like properties, in other words, organization for economic cooperation and development-recommended toxicity-studies and, due to some aqueous-solubility problems, and vehicularization for oral and intravenous administrations. Conclusion: We have identified a promising drug-candidate with broad activity spectrum, appropriate drug-like properties, adequate toxicological behavior and able ability to be loaded in suitable vehicles.

Support Vector Machine model for hERG inhibitory activities based on the integrated hERG database using descriptor selection by NSGA-II

Assessing the hERG liability in the early stages of drug discovery programs is important. The recent increase of hERG-related information in public databases enabled various successful applications of machine learning techniques to predict hERG inhibition. However, most of these researches constructed the datasets from only one database, limiting the predictability and scope of the models. In this study, a hERG classification model was constructed using the largest dataset for hERG inhibition built by integrating multiple databases. The integrated dataset consisted of more than 291,000 structurally diverse compounds derived from ChEMBL, GOSTAR, PubChem, and hERGCentral. The prediction model was built by support vector machine (SVM) with descriptor selection based on Non-dominated Sorting Genetic Algorithm-II (NSGA-II) to optimize the descriptor set for maximum prediction performance with the minimal number of descriptors. The SVM classification model using 72 selected descriptors and ECFP_4 structural fingerprints recorded kappa statistics of 0.733 and accuracy of 0.984 for the test set, substantially outperforming the prediction performance of the current commercial applications for hERG prediction. Finally, the applicability domain of the prediction model was assessed based on the molecular similarity between the training set and test set compounds.

Novel tetrahydroacridine derivatives with iodobenzoic moieties induce G0/G1 cell cycle arrest and apoptosis in A549 non-small lung cancer and HT-29 colorectal cancer cells

A series of nine tetrahydroacridine derivatives with iodobenzoic moiety were synthesized and evaluated for their cytotoxic activity against cancer cell lines—A549 (human lung adenocarcinoma), HT-29 (human colorectal adenocarcinoma) and somatic cell line—EA.hy926 (human umbilical vein cell line). All compounds displayed high cytotoxicity activity against A549 (IC₅₀ 59.12–14.87 µM) and HT-29 (IC₅₀ 17.32–5.90 µM) cell lines, higher than control agents—etoposide and 5-fluorouracil. Structure–activity relationship showed that the position of iodine in the substituent in the para position and longer linker most strongly enhanced the cytotoxic effect. Among derivatives, 1i turned out to be the most cytotoxic and displayed IC₅₀ values of 14.87 µM against A549 and 5.90 µM against HT-29 cell lines. In hyaluronidase inhibition assay, all compounds presented anti-inflammatory activity, however, slightly lower than reference compound. ADMET prediction showed that almost all compounds had good pharmacokinetic profiles. 1b, 1c and 1f compounds turned out to act against chemoresistance in cisplatin-resistant 253J B-V cells. Compounds intercalated into DNA and inhibited cell cycle in G0/G1 phase—the strongest inhibition was observed for 1i in A549 and 1c in HT-29. Among compounds, the highest apoptotic effect in both cell lines was observed after treatment with 1i. Compounds caused DNA damage and H2AX phosphorylation, which was detected in A549 and HT-29 cells. All research confirmed anticancer properties of novel tetrahydroacridine derivatives and explained a few pathways of their mechanism of cytotoxic action.

Computational determination of hERG-related cardiotoxicity of drug candidates

Background

Drug candidates often cause an unwanted blockage of the potassium ion channel of the human ether-a-go-go-related gene (hERG). The blockage leads to long QT syndrome (LQTS), which is a severe life-threatening cardiac side effect. Therefore, a virtual screening method to predict drug-induced hERG-related cardiotoxicity could facilitate drug discovery by filtering out toxic drug candidates.

Result

In this study, we generated a reliable hERG-related cardiotoxicity dataset composed of 2130 compounds, which were carried out under constant conditions. Based on our dataset, we developed a computational hERG-related cardiotoxicity prediction model. The neural network model achieved an area under the receiver operating characteristic curve (AUC) of 0.764, with an accuracy of 90.1%, a Matthews correlation coefficient (MCC) of 0.368, a sensitivity of 0.321, and a specificity of 0.967, when ten-fold cross-validation was performed. The model was further evaluated using ten drug compounds tested on guinea pigs and showed an accuracy of 80.0%, an MCC of 0.655, a sensitivity of 0.600, and a specificity of 1.000, which were better than the performances of existing hERG-toxicity prediction models.

Conclusion

The neural network model can predict hERG-related cardiotoxicity of chemical compounds with a high accuracy. Therefore, the model can be applied to virtual high-throughput screening for drug candidates that do not cause cardiotoxicity. The prediction tool is available as a web-tool at http://ssbio.cau.ac.kr/CardPred.

Deep Learning-Based Prediction of Drug-Induced Cardiotoxicity

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

Network Pharmacology and Reverse Molecular Docking-Based Prediction of the Molecular Targets and Pathways for Avicularin Against Cancer

AIM AND OBJECTIVE

Avicularin has been found to inhibit the proliferation of HepG-2 cells in vitro in the screening of our laboratory. We intended to explain the molecular mechanism of this effect. Therefore, the combined methods of reverse molecular docking and network pharmacology were used in order to illuminate the molecular mechanisms for Avicularin against cancer.

MATERIALS AND METHODS

Potential targets associated with anti-tumor effects of Avicularin were screened by reverse molecular docking, then a protein database was established through constructing the drugprotein network from literature mining data, and the protein-protein network was built through an in-depth exploration of the relationships between the proteins, and then the network topology analysis was performed. Additionally, gene function and signaling pathways were analyzed by Go bio-enrichment and KEGG Pathway.

RESULTS

The result showed that Avicularin was closely related to 16 targets associated with cancer, and it may significantly influence the pro-survival signals in MAPK signaling pathway that can activate and regulate a series of cellular activities and participate in the regulation of cell proliferation, differentiation, transformation and apoptosis.

CONCLUSION

The network pharmacology strategy used herein provided a powerful means for the mechanisms of action for bioactive ingredients.