In silico prediction of chemical acute oral toxicity using multi-classification methods

GCLmf: A Novel Molecular Graph Contrastive Learning Framework Based on Hard Negatives and Application in Toxicity Prediction

In silico methods for prediction of chemical toxicity can decrease the cost and increase the efficiency in the early stage of drug discovery. However, due to low accessibility of sufficient and reliable toxicity data, constructing robust and accurate prediction models is challenging. Contrastive learning, a type of self-supervised learning, leverages large unlabeled data to obtain more expressive molecular representations, which can boost the prediction performance on downstream tasks. While molecular graph contrastive learning has gathered growing attentions, current models neglect the quality of negative data set. Here, we proposed a self-supervised pretraining deep learning framework named GCLmf. We first utilized molecular fragments that meet specific conditions as hard negative samples to boost the quality of the negative set and thus increase the difficulty of the proxy tasks during pre-training to learn informative representations. GCLmf has shown excellent predictive power on various molecular property benchmarks and demonstrates high performance in 33 toxicity tasks in comparison with multiple baselines. In addition, we further investigated the necessity of introducing hard negatives in model building and the impact of the proportion of hard negatives on the model.

Palladium catalysed cross coupling reactions on 2,3-isoxazol-17α-ethynyltestosterone, their anti-cancer activity, molecular docking studies and ADMET analysis

In the current study, the Sonogashira coupling reaction of danazol with aryl halides was carried out, yielding new aryl substituted danazol derivatives. The synthetic compounds were examined for anti-cancer potential on the HeLa human cervical cancer cell line, and they showed promising cytotoxic action. Synthesized compounds 2, 4 and 5 inhibited the growth of HeLa cervical cancer cells, potentially making them effective anti-cancer drugs in the future. Furthermore, molecular docking studies were performed to evaluate the inhibitory impact of danazol derivatives on the Human Papillomavirus (HPV) target protein (1F9F). The docking results showed a significant inhibitory action against the cervical cancer protein (1F9F). The binding energy (ΔG) values of 1, 2, 3, 4 and 5 against the protein 1F9F were -8.01, -8.70, -9.43, -9.58 and -9.75 kcal/mol, indicating a high affinity of the synthesized compounds to bind with the HPV target proteins compared to their parent compound danazol (1). ADMET analyses of all derivatives have also been carried out.

Multi-task pretrained language model with novel application domains enables more comprehensive health and ecological toxicity prediction

In silico models for screening substances of healthy and ecological concern are essential for effective chemical management. However, current data-driven toxicity prediction models confront formidable challenges related to expressive capacity, data scarcity, and reliability issues. Thus, this study introduces TOX-BERT, a SMILES-based pretrained model for screening health and ecological toxicity. Results show that masked atom recovery pretraining and multi-task learning offer promising solutions to enhance model capacity and address data scarcity issues. Two novel application domain (AD) parameters, termed PCA-AD and LDS, were proposed to improve prediction reliability of TOX-BERT with accuracy surpassing 90 % and mean absolute error (MAE) below 0.52. TOX-BERT was applied to 18,905 IECSC chemicals, revealing distinct toxicity relationships that align with experimental studies such as those between cardiotoxicity and acute ecotoxicity. In addition to previous PBT screening, 156 potential high-risk chemicals for specific endpoint were identified covering 7 categories. Furthermore, a SMILES-based toxicity site detection approach was developed for structural toxicity analysis. These advancements carry profound implications to address challenges faced by current data-driven toxicity prediction models. TOX-BERT emerges as a valuable tool for more comprehensive, reliable, and applicable predictions of health and ecological toxicity in chemical risk assessment and management.

Interaction mechanism of oseltamivir phosphate with bovine serum albumin: multispectroscopic and molecular docking study

Oseltamivir phosphate (OP) is an antiviral drug with potential risks to human health due to overuse, leading to serious consequences such as gastrointestinal disturbances, abnormal neuropsychiatric symptoms, and sudden death. Therefore, gaining an in-depth understanding of its interaction with proteins is crucial. We investigated the interaction between OP and bovine serum albumin (BSA) utilizing multispectral methods (i.e., fluorescence, ultraviolet absorption, circular dichroism) combined with molecular docking techniques. Fluorescence spectroscopy indicated that OP quenched BSA fluorescence by forming the OP-BSA complex. The Stern-Volmer constants (KSV) between OP and BSA were determined to be 3.06 × 103 L/mol, 2.36 × 103 L/mol, and 1.86 × 103 L/mol at 293 K, 298 K, and 303 K, respectively. OP occupies exclusively one binding site on BSA, and the fluorescent probe displacement measurements revealed that this is BSA site I. Thermodynamic data (∆H, ∆S, and ∆G) obtained by fitting the van't Hoff equation were - 77.49 kJ/mol, -176.54 J/(mol∙K), and - 24.88 kJ/mol, respectively, suggesting that hydrogen bonding and van der Waals forces mainly participate in OP-BSA complex stabilization. Moreover, the reaction occurs spontaneously at room temperature. Synchronous fluorescence spectra indicated that OP interacts with tryptophan residue of BSA. The results of ultraviolet (UV) and 3D fluorescence spectroscopy indicated that the OP-BSA complex formation altered the microenvironment around amino acid residues. Circular dichroism spectra revealed that the addition of OP decreased the α-helix content of BSA by 7.13%. Docking analysis confirmed that OP binds to BSA site I through hydrogen bonding with amino acids VAL342, SER453, and ASP450. Finally, ADMET studies were conducted to explore the pharmacokinetics of OP as an antiviral drug.

Phytochemical Profile, Antioxidant, Enzyme Inhibition, Acute Toxicity, In Silico Molecular Docking and Dynamic Analysis of Apis Mellifera Propolis as Antidiabetic Supplement

This study aims to identify the phytochemical profile of Apis mellifera propolis and explore the potential of its anti-diabetic activity through inhibition of α-amylase (α-AE), α-glucosidase(α-GE), as well as novel antidiabetic compounds of propolis. Apis mellifera propolis extract (AMPE) exhibited elevated polyphenol 33.26±0.17 (mg GAE/g) and flavonoid (15.45±0.13 mg RE/g). It also indicated moderate strong antioxidant activity (IC50 793.09±1.94 μg/ml). This study found that AMPE displayed promising α-AE and α-GE inhibition through in vitro study. Based on LC-MS/MS screening, 18 unique AMPE compounds were identified, with majorly belonging to anthraquinone and flavonoid compounds. Furthermore, in silico study determined that 8 compounds of AMPE exhibited strong binding to α-AE that specifically interacted with its catalytic residue of ASP197. Moreover, 2 compounds exhibit potential inhibition of α-GE, by interacting with crucial amino acids of ARG315, ASP352, and ASP69. Finally, we suggested that 2,7-Dihydroxy-1-(p-hydroxybenzyl)-4-methoxy-9,10-dihydrophenanthrene and 3(3-(3,4-Dihydroxybenzyl)-7-hydroxychroman-4-one as novel inhibitors of α-AE and α-GE. Notably, these compounds were initially discovered from Apis mellifera propolis in this study. The molecular dynamic analysis confirmed their stable binding with both enzymes over 100 ns simulations. The in vivo acute toxicity assay reveals AMPE as a practically non-toxic product with an LD50 value of 16,050 mg/kg. Therefore, this propolis may serve as a promising natural product for diabetes mellitus treatment.

In Silico Prediction of Oral Acute Rodent Toxicity Using Consensus Machine Learning

Acute oral toxicity (AOT) is required for the classification and labeling of chemicals according to the global harmonized system (GHS). Acute oral toxicity studies are optimized to minimize the use of animals. However, with the advent of the three Rs principles and machine learning in toxicology, alternative in silico methods became a reasonable alternative approach for addressing the AOT of new chemical matter. Here, we describe the compilation of AOT data from a commercial database and the development of a consensus classification model after evaluating different combinations of molecular representations and machine learning algorithms. The model shows significantly better performance compared to publicly available AOT models. Its performance was evaluated on an external validation data set, which was compiled from the literature, and an applicability domain was deduced.

PTSA-induced synthesis, in silico and nano study of novel ethylquinolin-thiazolo-triazole in cervical cancer

Aim: p-Toluenesulfonic acid-(PTSA) and grinding-induced novel synthesis of ethylquinolin-thiazolo-triazole derivatives was performed using green chemistry. Materials & methods: Development of a nanoconjugate drug-delivery system of ethylquinolin-thiazolo-triazole was carried out with D-α-tocopheryl polyethylene glycol succinate (TPGS) and the formulation was further characterized by transmission electron microscopy, atomic force microscopy, dynamic light scattering and in vitro drug release assay. The effect of 3a nanoparticles was assessed against a cervical cancer cell line (HeLa) through the 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) assay, and the effect on apoptosis was determined. Results & discussion: The 3a nanoparticles triggered the apoptotic mode of cell death after increasing the intracellular reactive oxygen level by enhancing cellular uptake of micelles. Furthermore, in silico studies revealed higher absorption, distribution, metabolism, elimination and toxicity properties and bioavailability of the enzyme tyrosine protein kinase. Conclusion: The 3a nanoparticles enhanced the therapeutic potential and have higher potential for targeted drug delivery against cervical cancer.

Modeling and insights into the structural characteristics of endocrine-disrupting chemicals

Endocrine-disrupting chemicals (EDCs) can cause serious harm to human health and the environment; therefore, it is important to rapidly and correctly identify EDCs. Different computational models have been proposed for the prediction of EDCs over the past few decades, but the reported models are not always easily available, and few studies have investigated the structural characteristics of EDCs. In the present study, we have developed a series of artificial intelligence models targeting EDC receptors: the androgen receptor (AR); estrogen receptor (ER); and pregnane X receptor (PXR). The consensus models achieved good predictive results for validation sets with balanced accuracy values of 87.37%, 90.13%, and 79.21% for AR, ER, and PXR binding assays, respectively. Analysis of the physical-chemical properties suggested that several chemical properties were significantly (p < 0.05) different between EDCs and non-EDCs. We also identified structural alerts that can indicate an EDC, which were integrated into the web server SApredictor. These models and structural characteristics can provide useful tools and information in the discrimination and mechanistic understanding of EDCs in drug discovery and environmental risk assessment.

In Silico Prediction of Human Organ Toxicity via Artificial Intelligence Methods

Unpredicted human organ level toxicity remains one of the major reasons for drug clinical failure. There is a critical need for cost-efficient strategies in the early stages of drug development for human toxicity assessment. At present, artificial intelligence methods are popularly regarded as a promising solution in chemical toxicology. Thus, we provided comprehensive in silico prediction models for eight significant human organ level toxicity end points using machine learning, deep learning, and transfer learning algorithms. In this work, our results showed that the graph-based deep learning approach was generally better than the conventional machine learning models, and good performances were observed for most of the human organ level toxicity end points in this study. In addition, we found that the transfer learning algorithm could improve model performance for skin sensitization end point using source domain of in vivo acute toxicity data and in vitro data of the Tox21 project. It can be concluded that our models can provide useful guidance for the rapid identification of the compounds with human organ level toxicity for drug discovery.

Hi-MGT: A hybrid molecule graph transformer for toxicity identification

Conventional toxicity testing methods that rely on animal experimentation are resource-intensive, time-consuming, and ethically controversial. Therefore, the development of alternative non-animal testing approaches is crucial. This study proposes a novel hybrid graph transformer architecture, termed Hi-MGT, for the toxicity identification. An innovative aggregation strategy, referred to as GNN-GT combination, enables Hi-MGT to simultaneously and comprehensively aggregate local and global structural information of molecules, thus elucidating more informative toxicity information hidden in molecule graphs. The results show that the state-of-the-art model outperforms current baseline CML and DL models on a diverse range of toxicity endpoints and is even comparable to large-scale pretrained GNNs with geometry enhancement. Additionally, the impact of hyperparameters on model performance is investigated, and a systematic ablation study is conducted to demonstrate the effectiveness of the GNN-GT combination. Moreover, this study provides valuable insights into the learning process on molecules and proposes a novel similarity-based method for toxic site detection, which could potentially facilitate toxicity identification and analysis. Overall, the Hi-MGT model represents a significant advancement in the development of alternative non-animal testing approaches for toxicity identification, with promising implications for enhancing human safety in the use of chemical compounds.

Accurate clinical toxicity prediction using multi-task deep neural nets and contrastive molecular explanations

Explainable machine learning for molecular toxicity prediction is a promising approach for efficient drug development and chemical safety. A predictive ML model of toxicity can reduce experimental cost and time while mitigating ethical concerns by significantly reducing animal and clinical testing. Herein, we use a deep learning framework for simultaneously modeling in vitro, in vivo, and clinical toxicity data. Two different molecular input representations are used; Morgan fingerprints and pre-trained SMILES embeddings. A multi-task deep learning model accurately predicts toxicity for all endpoints, including clinical, as indicated by the area under the Receiver Operator Characteristic curve and balanced accuracy. In particular, pre-trained molecular SMILES embeddings as input to the multi-task model improved clinical toxicity predictions compared to existing models in MoleculeNet benchmark. Additionally, our multitask approach is comprehensive in the sense that it is comparable to state-of-the-art approaches for specific endpoints in in vitro, in vivo and clinical platforms. Through both the multi-task model and transfer learning, we were able to indicate the minimal need of in vivo data for clinical toxicity predictions. To provide confidence and explain the model's predictions, we adapt a post-hoc contrastive explanation method that returns pertinent positive and negative features, which correspond well to known mutagenic and reactive toxicophores, such as unsubstituted bonded heteroatoms, aromatic amines, and Michael receptors. Furthermore, toxicophore recovery by pertinent feature analysis captures more of the in vitro (53%) and in vivo (56%), rather than of the clinical (8%), endpoints, and indeed uncovers a preference in known toxicophore data towards in vitro and in vivo experimental data. To our knowledge, this is the first contrastive explanation, using both present and absent substructures, for predictions of clinical and in vivo molecular toxicity.

Computer-based identification of olive oil components as a potential inhibitor of neirisaral adhesion a regulatory protein

In silico methods such as molecular docking and molecular dynamic (MD) simulations have significant interest due to their ability to identify the protein-ligand interactions at the atomic level. In this work, different computational methods were used to elucidate the ability of some olive oil components to act as Neisseria adhesion A Regulatory protein (NadR) inhibitors. The frontier molecular orbitals (FMOs) and the global properties such as global hardness, electronegativity, and global softness of ten olive oil components (α-Tocopherol, Erythrodiol, Hydroxytyrosol, Linoleic acid, Apigenin, Luteolin, Oleic acid, Oleocanthal, Palmitic acid, and Tyrosol) were reported using Density Functional Theory (DFT) methods. Among all investigated compounds, Erythrodiol, Apigenin, and Luteolin demonstrated the highest binding affinities (-8.72, -7.12, and -8.24 kcal/mol, respectively) against NadR, compared to -8.21 kcal/mol of the native ligand based on molecular docking calculations. ADMET properties and physicochemical features showed that Erythrodiol, Apigenin, and Luteolin have good physicochemical features and can act as drugs candidate. Molecular dynamics (MD) simulations demonstrated that Erythrodiol, Apigenin, and Luteolin show stable binding affinity and molecular interaction with NadR. Further Molecular Mechanics Poisson-Boltzmann Surface Area (MM-PBSA) analyses using the MD trajectories also demonstrated the higher binding affinity of Erythrodiol, Apigenin and Luteolin inside NadR protein. The overall study provides a rationale to use Erythrodiol, Apigenin, and Luteolin in the drug development as anti-adhesive drugs lead. Communicated by Ramaswamy H. Sarma.

Ensemble multiclassification model for aquatic toxicity of organic compounds

With environmental pollution becoming increasingly serious, organic compounds have become the main hazard of environmental pollution and exert substantial negative impacts on aquatic organisms. In research pertaining to the acute toxicity of organic compounds, traditional biological experimental methods are time-consuming and expensive. In addition, computer-aided binary classification models cannot accurately classify acute toxicity. Therefore, the multiclassication model is necessary for more accurate classification of acute toxicity. In this study, median lethal concentrations of 373 organic compounds in the environmental toxicology datasets ECOTOX and EAT5 were used. These chemicals were classified into four categories based on the European Economic Community criteria. Then the random forest, support vector machine, extreme gradient boosting, adaptive gradient boosting, and C5.0 decision tree algorithms and eight molecular fingerprints were used to build a multiclassification base model for the acute toxicity of organic compounds. The base models were repeated 100 times with fivefold cross-validation and external validation. The ensemble model was obtained by the voting method. The best base classifier was ExtendFP-C5.0, which had an accuracy, sensitivity and specificity values of 87.30%, 87.32% and 95.76% for external validation, and the voting ensemble model performance of 96.92%, 96.93% and 98.97%, respectively. The ensemble model achieved a higher accuracy than previously reported studies. Our study will help to further classify the acute toxicity of organic compounds to aquatic organisms and predict the hazard classes of organic compounds.

Identification of vital chemical information via visualization of graph neural networks

Qualitative or quantitative prediction models of structure-activity relationships based on graph neural networks (GNNs) are prevalent in drug discovery applications and commonly have excellently predictive power. However, the network information flows of GNNs are highly complex and accompanied by poor interpretability. Unfortunately, there are relatively less studies on GNN attributions, and their developments in drug research are still at the early stages. In this work, we adopted several advanced attribution techniques for different GNN frameworks and applied them to explain multiple drug molecule property prediction tasks, enabling the identification and visualization of vital chemical information in the networks. Additionally, we evaluated them quantitatively with attribution metrics such as accuracy, sparsity, fidelity and infidelity, stability and sensitivity; discussed their applicability and limitations; and provided an open-source benchmark platform for researchers. The results showed that all attribution techniques were effective, while those directly related to the predicted labels, such as integrated gradient, preferred to have better attribution performance. These attribution techniques we have implemented could be directly used for the vast majority of chemical GNN interpretation tasks.

Virtual screening and structure-based 3D pharmacophore approach to identify small-molecule inhibitors of SARS-CoV-2 Mpro

The outbreak caused by a coronavirus 2 has required quick and potential treatment strategies. The main protease enzyme M^pro plays an important role in the viral replication which renders it an important target for discovering SARS-CoV-2 inhibitors. In this study, 3D pharmacophore structure-based virtual screening and molecular docking were conducted using MOE and Bristol University Docking Engine (BUDE). Around 400,000 molecules of ZINC15 database were docked against the crystal structure of main protease, followed by 3D pharmacophore filtration. Six top-ranked hits (ZINC58717986, ZINC60399606, ZINC58662884, ZINC45988635, ZINC54706757 and ZINC17320595) were identified based on their strong spatial affinity and forming H-bonds with key residues H41, E166, Q189 and T190 of the binding pocket of M^pro SARS-CoV-2. The 6 hits subjected to molecular dynamics simulations for 100 ns followed by binding free energy calculations using MM-PBSA technique. Interestingly, three hits showed free binding energy (ΔG_binding) lower than tert-butyl N-[1-[(2S)-1-[[(2S)-4-(benzylamino)-3,4-dioxo-1-[(3S)-2-oxopyrrolidin-3-yl]butan-2-yl]amino]-3-cyclopropyl-1-oxopropan-2-yl]-2-oxopyridin-3-yl]carbamate (α-ketoamide 13 b) (ΔG_binding) -76.67 ± 0.5 kJ/mol which suggested their potential against SARS-CoV-2. The best binding free energy candidates, ZINC58717986 (ΔG_binding) -98.41 ± 0.7 kJ/mol. The second-best hit candidate, ZINC54706757 (ΔG_binding) -83.4 ± 0.6 kJ/mol and the third one ZINC17320595 (ΔG_binding) -78.85 ± 0.5 kJ/mol. Per residue decomposition free energy indicates H41, S46, H164, E166, D187, Q189 and Q192 are hot spot residues while residues M49, M165, L167 and P168 contribute to the hydrophobic interactions. The pharmacokinetic study suggests that the selected 6 hits possess drug-like properties. The 3D pharmacophore virtual screening, molecular dynamics and MM-PBSA approaches facilitated identification 3 promising hits with low free binding energy as SARS-CoV-2 inhibitors.Communicated by Ramaswamy H. Sarma.

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.

In Vitro and In Silico Studies for the Identification of Potent Metabolites of Some High-Altitude Medicinal Plants from Nepal Inhibiting SARS-CoV-2 Spike Protein

Despite ongoing vaccination programs against COVID-19 around the world, cases of infection are still rising with new variants. This infers that an effective antiviral drug against COVID-19 is crucial along with vaccinations to decrease cases. A potential target of such antivirals could be the membrane components of the causative pathogen, SARS-CoV-2, for instance spike (S) protein. In our research, we have deployed in vitro screening of crude extracts of seven ethnomedicinal plants against the spike receptor-binding domain (S1-RBD) of SARS-CoV-2 using an enzyme-linked immunosorbent assay (ELISA). Following encouraging in vitro results for Tinospora cordifolia, in silico studies were conducted for the 14 reported antiviral secondary metabolites isolated from T. cordifolia-a species widely cultivated and used as an antiviral drug in the Himalayan country of Nepal-using Genetic Optimization for Ligand Docking (GOLD), Molecular Operating Environment (MOE), and BIOVIA Discovery Studio. The molecular docking and binding energy study revealed that cordifolioside-A had a higher binding affinity and was the most effective in binding to the competitive site of the spike protein. Molecular dynamics (MD) simulation studies using GROMACS 5.4.1 further assayed the interaction between the potent compound and binding sites of the spike protein. It revealed that cordifolioside-A demonstrated better binding affinity and stability, and resulted in a conformational change in S1-RBD, hence hindering the activities of the protein. In addition, ADMET analysis of the secondary metabolites from T. cordifolia revealed promising pharmacokinetic properties. Our study thus recommends that certain secondary metabolites of T. cordifolia are possible medicinal candidates against SARS-CoV-2.

Machine Learning Modeling and Insights into the Structural Characteristics of Drug-Induced Neurotoxicity

Neurotoxicity can be resulted from many diverse clinical drugs, which has been a cause of concern to human populations across the world. The detection of drug-induced neurotoxicity (DINeurot) potential with biological experimental methods always required a lot of budget and time. In addition, few studies have addressed the structural characteristics of neurotoxic chemicals. In this study, we focused on the computational modeling for drug-induced neurotoxicity with machine learning methods and the insights into the structural characteristics of neurotoxic chemicals. Based on the clinical drug data with neurotoxicity effects, we developed 35 different classifiers by combining five different machine learning methods and seven fingerprint packages. The best-performing model achieved good results on both 5-fold cross-validation (balanced accuracy of 76.51%, AUC value of 0.83, and MCC value of 0.52) and external validation (balanced accuracy of 83.63%, AUC value of 0.87, and MCC value of 0.67). The model can be freely accessed on the web server DINeuroTpredictor (http://dineurot.sapredictor.cn/). We also analyzed the distribution of several key molecular properties between neurotoxic and non-neurotoxic structures. The results indicated that several physicochemical properties were significantly different between the neurotoxic and non-neurotoxic compounds, including molecular polar surface area (MPSA), AlogP, the number of hydrogen bond acceptors (nHAcc) and donors (nHDon), the number of rotatable bonds (nRotB), and the number of aromatic rings (nAR). In addition, 18 structural alerts responsible for chemical neurotoxicity were identified. The structural alerts have been integrated with our web server SApredictor (http://www.sapredictor.cn). The results of this study could provide useful information for the understanding of the structural characteristics and computational prediction for chemical neurotoxicity.

Isopropyl Gallate, a Gallic Acid Derivative: In Silico and In Vitro Investigation of Its Effects on Leishmania major

Isopropyl gallate (IPG) is a polyphenol obtained from alterations in the gallic acid molecule via acid catalysis with previously reported leishmanicidal and trypanocidal activities. The present study aims to evaluate in silico binding activity towards some targets for antileishmanial chemotherapy against Leishmania major species, and ADMET parameters for IPG, as well as in vitro antileishmanial and cytotoxic effects. Molecular docking was performed using AutoDockVina and BIOVIA Discovery Studio software, whereas in silico analysis used SwissADME, PreADMET and admetSAR software. In vitro antileishmanial activity on promastigotes and amastigotes of Leishmania major, cytotoxicity and macrophages activation were assessed. IPG exhibited affinity for pteridine reductase (PTR1; -8.2 kcal/mol) and oligopeptidase B (OPB; -8.0 kcal/mol) enzymes. ADMET assays demonstrated good lipophilicity, oral bioavailability, and skin permeability, as well as non-mutagenic, non-carcinogenic properties and low risk of cardiac toxicity for IPG. Moreover, IPG inhibited the in vitro growth of promastigotes (IC₅₀ = 90.813 µM), presented significant activity against amastigotes (IC₅₀ = 13.45 μM), promoted low cytotoxicity in macrophages (CC₅₀ = 1260 μM), and increased phagocytic capacity. These results suggest IPG is more selectively toxic to the parasite than to mammalian cells. IPG demonstrated acceptable in silico pharmacokinetics parameters, and reduced infection and infectivity in parasitized macrophages, possibly involving macrophage activation pathways and inhibition of leishmania enzymes.

Predicting Dose-Range Chemical Toxicity using Novel Hybrid Deep Machine-Learning Method

Humans are exposed to thousands of chemicals, including environmental chemicals. Unfortunately, little is known about their potential toxicity, as determining the toxicity remains challenging due to the substantial resources required to assess a chemical in vivo. Here, we present a novel hybrid neural network (HNN) deep learning method, called HNN-Tox, to predict chemical toxicity at different doses. To develop a hybrid HNN-Tox method, we combined two neural network frameworks, the Convolutional Neural Network (CNN) and the multilayer perceptron (MLP)-type feed-forward neural network (FFNN). Combining the CNN and FCNN in the field of environmental chemical toxicity prediction is a novel approach. We developed several binary and multiclass classification models to assess dose-range chemical toxicity that is trained based on thousands of chemicals with known toxicity. The performance of the HNN-Tox was compared with other machine-learning methods, including Random Forest (RF), Bootstrap Aggregation (Bagging), and Adaptive Boosting (AdaBoost). We also analyzed the model performance dependency on varying features, descriptors, dataset size, route of exposure, and toxic dose. The HNN-Tox model, trained on 59,373 chemicals annotated with known LD50 and routes of exposure, maintained its predictive ability with an accuracy of 84.9% and 84.1%, even after reducing the descriptor size from 318 to 51, and the area under the ROC curve (AUC) was 0.89 and 0.88, respectively. Further, we validated the HNN-Tox with several external toxic chemical datasets on a large scale. The HNN-Tox performed optimally or better than the other machine-learning methods for diverse chemicals. This study is the first to report a large-scale prediction of dose-range chemical toxicity with varying features. The HNN-Tox has broad applicability in predicting toxicity for diverse chemicals and could serve as an alternative methodology approach to animal-based toxicity assessment.

Synthesis and Anticancer Activity of Indole-Functionalized Derivatives of Betulin

Pentacyclic triterpenes, including betulin, are widespread natural products with various pharmacological effects. These compounds are the starting material for the synthesis of substances with promising anticancer activity. The chemical modification of the betulin scaffold that was carried out as part of the research consisted of introducing the indole moiety at the C-28 position. The synthesized new 28-indole-betulin derivatives were evaluated for anticancer activity against seven human cancer lines (A549, MDA-MB-231, MCF-7, DLD-1, HT-29, A375, and C32). It was observed that MCF-7 breast cancer cells were most sensitive to the action of the 28-indole-betulin derivatives. The study shows that the lup-20(29)-ene-3-ol-28-yl 2-(1H-indol-3-yl)acetate caused the MCF-7 cells to arrest in the G1 phase, preventing the cells from entering the S phase. The performed cytometric analysis of DNA fragmentation indicates that the mechanism of EB355A action on the MCF-7 cell line is related to the induction of apoptosis. An in silico ADMET profile analysis of EB355A and EB365 showed that both compounds are bioactive molecules characterized by good intestinal absorption. In addition, the in silico studies indicate that the 28-indole-betulin derivatives are substances of relatively low toxicity.

In Silico Prediction of Human and Rat Liver Microsomal Stability via Machine Learning Methods

Liver microsomal stability is an important property considered for the screening of drug candidates in the early stage of drug development. Determination of hepatic metabolic stability can be performed by an in vitro assay, but it requires quite a few resources and time. In recent years, machine learning methods have made much progress. Therefore, development of computational models to predict liver microsomal stability is highly desirable in the drug discovery process. In this study, the in silico classification models for the prediction of the metabolic stability of compounds in rat and human liver microsomes were constructed by the conventional machine learning and deep learning methods. The performance of the models was evaluated using the test and external sets. For the rat liver microsomes (RLM) stability, the best model yielded the AUC values of 0.84 and 0.71 on the test and external validation sets, respectively. For the human liver microsome (HLM) stability, the best model exhibited the AUC values of 0.86 and 0.77 on the test and external validation sets, respectively. In addition, several important substructure fragments were detected using information gain and frequency substructure analysis methods. The applicability domain of the models was defined using the Euclidean distance-based method. We anticipate that our results would be helpful for the prediction of liver microsomal stability of compounds in the early stage of drug discovery.

Classifying the toxicity of pesticides to honey bees via support vector machines with random walk graph kernels

Pesticides benefit agriculture by increasing crop yield, quality, and security. However, pesticides may inadvertently harm bees, which are valuable as pollinators. Thus, candidate pesticides in development pipelines must be assessed for toxicity to bees. Leveraging a dataset of 382 molecules with toxicity labels from honey bee exposure experiments, we train a support vector machine (SVM) to predict the toxicity of pesticides to honey bees. We compare two representations of the pesticide molecules: (i) a random walk feature vector listing counts of length- L walks on the molecular graph with each vertex- and edge-label sequence and (ii) the Molecular ACCess System (MACCS) structural key fingerprint (FP), a bit vector indicating the presence/absence of a list of pre-defined subgraph patterns in the molecular graph. We explicitly construct the MACCS FPs but rely on the fixed-length- L random walk graph kernel (RWGK) in place of the dot product for the random walk representation. The L-RWGK-SVM achieves an accuracy, precision, recall, and F1 score (mean over 2000 runs) of 0.81, 0.68, 0.71, and 0.69, respectively, on the test data set—with L = 4 being the mode optimal walk length. The MACCS-FP-SVM performs on par/marginally better than the L-RWGK-SVM, lends more interpretability, but varies more in performance. We interpret the MACCS-FP-SVM by illuminating which subgraph patterns in the molecules tend to strongly push them toward the toxic/non-toxic side of the separating hyperplane.

SApredictor: An Expert System for Screening Chemicals Against Structural Alerts

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

Artificial Intelligence-Based Toxicity Prediction of Environmental Chemicals: Future Directions for Chemical Management Applications

Recently, research on the development of artificial intelligence (AI)-based computational toxicology models that predict toxicity without the use of animal testing has emerged because of the rapid development of computer technology. Various computational toxicology techniques that predict toxicity based on the structure of chemical substances are gaining attention, including the quantitative structure-activity relationship. To understand the recent development of these models, we analyzed the databases, molecular descriptors, fingerprints, and algorithms considered in recent studies. Based on a selection of 96 papers published since 2014, we found that AI models have been developed to predict approximately 30 different toxicity end points using more than 20 toxicity databases. For model development, molecular access system and extended-connectivity fingerprints are the most commonly used molecular descriptors. The most used algorithm among the machine learning techniques is the random forest, while the most used algorithm among the deep learning techniques is a deep neural network. The use of AI technology in the development of toxicity prediction models is a new concept that will aid in achieving a scientific accord and meet regulatory applications. The comprehensive overview provided in this study will provide a useful guide for the further development and application of toxicity prediction models.

In Silico Prediction of Chemical Aquatic Toxicity by Multiple Machine Learning and Deep Learning Approaches

Fish is one of the model animals used to evaluate the adverse effects of a chemical exposed to the ecosystem. However, its low throughput and relevantly high expense make it impossible to test all new chemicals in manufacture. Hence using in silico models to prioritize compounds to be tested has been widely applied in environmental risk assessment and drug discovery. In this study, we constructed the local predictive models for four fish species, including bluegill sunfish, rainbow trout, fathead minnow, and sheepshead minnow, and the global models with all four fish data. A total of 1874 unique compounds with their labels, i.e. toxic (LC₅₀ < 10 ppm) or nontoxic were collected from ECOTOX and literature. Both conventional machine learning methods and the deep learning architecture, graph convolutional network (GCN), were used to build predictive models. The classification accuracy of the best local model for each fish species was higher than 0.83. For the global models, two strategies including consistency prediction and probability threshold were adopted to improve the predictive capability at the cost of limiting applicability domain. For 63% of compounds in domain, the accuracy was around 0.97. By comparison of the deep learning and machine learning methods, we found that the single-task GCN showed specific advantages in performance and multi-task GCN showed no advantages over the conventional machine learning methods. The data and models are available on GitHub (https://github.com/ChemPredict/ChemicalAquaticToxicity).

Identification of bioactive molecules from Triphala (Ayurvedic herbal formulation) as potential inhibitors of SARS-CoV-2 main protease (Mpro) through computational investigations

Severe acute respiratory syndrome coronavirus disease (SARS-CoV-2) induced coronavirus disease 2019 (COVID-19) pandemic is the present worldwide health emergency. The global scientific community faces a significant challenge in developing targeted therapies to combat the SARS-CoV-2 infection. Computational approaches have been critical for identifying potential SARS-CoV-2 inhibitors in the face of limited resources and in this time of crisis. Main protease (M^pro) is an intriguing drug target because it processes the polyproteins required for SARS-CoV-2 replication. The application of Ayurvedic knowledge from traditional Indian systems of medicine may be a promising strategy to develop potential inhibitor for different target proteins of SARS-CoV-2. With this endeavor, we docked bioactive molecules from Triphala, an Ayurvedic formulation, against M^pro followed by molecular dynamics (MD) simulation (100 ns) to investigate their inhibitory potential against SARS-CoV-2. The top four best docked molecules (terflavin A, chebulagic acid, chebulinic acid, and corilagin) were selected for MD simulation study and the results obtained were compared to native ligand X77. From docking and MD simulation studies, the selected molecules showed promising binding affinity with the formation of stable complexes at the active binding pocket of M^pro and exhibited negative binding energy during MM-PBSA calculations, indication their strong binding affinity with the target protein. The identified bioactive molecules were further analyzed for drug-likeness by Lipinski's filter, ADMET and toxicity studies. Computational (in silico) investigations identified terflavin A, chebulagic acid, chebulinic acid, and corilagin from Triphala formulation as promising inhibitors of SARS-CoV-2 M^pro, suggesting experimental (in vitro/in vivo) studies to further explore their inhibitory mechanisms.

In Silico Screening of Cinnamon (Cinnamomum burmannii) Bioactive Compounds as Acetylcholinesterase Inhibitors

Alzheimer’s is a progressive and neurodegenerative disease that mainly affects people aged 65 years and older. The pathophysiology of Alzheimer’s is possibly related to the depletion of the neurotransmitter acetylcholine (ACh) due to beta-amyloid plaques and neurofibrillary tangles. Secondary metabolites found in cinnamon bark (Cinnamomum burmannii) have the potential as anticholinesterases to treat Alzheimer’s symptoms. This study aimed to identify the potency of bioactive compounds from cinnamon bark as AChE inhibitors in silico through analysis of binding energy, inhibition constants, and types of interactions. The research was conducted by screening virtually 60 test ligands using the PyRx program and molecular docking using the Autodock Tools program. The results of the ligand-receptor interaction analysis showed that 12 of the 15 tested ligands had potential as AChE inhibitors. Epicatechin and medioresinol are the ligands with the best potential for AChE inhibition with affinity close to the natural ligand or donepezil. Epicatechin has a binding energy of −10.0 kcal/mol and inhibition constant of 0.0459 M, with four hydrogen bonds and seven hydrophobic bonds. Meanwhile, medioresinol has −9.9 kcal/mol binding energy and inhibition constant of 0.0543 M, with one hydrogen bond and thirteen hydrophobic bonds.

In silico prediction models for thyroid peroxidase inhibitors and their application to synthetic flavors

Systematic toxicity tests are often waived for the synthetic flavors as they are added in a very small amount in foods. However, their safety for some endpoints such as endocrine disruption should be concerned as they are likely to be active in low levels. In this case, structure–activity-relationship (SAR) models are good alternatives. In this study, therefore, binary, ternary, and quaternary prediction models were designed using simple or complex machine-learning methods. Overall, hard-voting classifiers outperformed other methods. The test scores for the best binary, ternary, and quaternary models were 0.6635, 0.5083, and 0.5217, respectively. Along with model development, some substructures including primary aromatic amine, (enol)ether, phenol, heterocyclic sulfur, and heterocyclic nitrogen, dominantly occurred in the most highly active compounds. The best predicting models were applied to synthetic flavors, and 22 agents appeared to have a strong inhibitory potential towards TPO activities.

Optimizing peptide inhibitors of SARS-Cov-2 nsp10/nsp16 methyltransferase predicted through molecular simulation and machine learning

Coronaviruses, including the recent pandemic strain SARS-Cov-2, use a multifunctional 2'-O-methyltransferase (2'-O-MTase) to restrict the host defense mechanism and to methylate RNA. The nonstructural protein 16 2'-O-MTase (nsp16) becomes active when nonstructural protein 10 (nsp10) and nsp16 interact. Novel peptide drugs have shown promise in the treatment of numerous diseases and new research has established that nsp10 derived peptides can disrupt viral methyltransferase activity via interaction of nsp16. This study had the goal of optimizing new analogous nsp10 peptides that have the ability to bind nsp16 with equal to or higher affinity than those naturally occurring. The following research demonstrates that in silico molecular simulations can shed light on peptide structures and predict the potential of new peptides to interrupt methyltransferase activity via the nsp10/nsp16 interface. The simulations suggest that misalignments at residues F68, H80, I81, D94, and Y96 or rotation at H80 abrogate MTase function. We develop a new set of peptides based on conserved regions of the nsp10 protein in the Coronaviridae species and test these to known MTase variant values. This results in the prediction that the H80R variant is a solid new candidate for potential new testing. We envision that this new lead is the beginning of a reputable foundation of a new computational method that combats coronaviruses and that is beneficial for new peptide drug development.

Functionalized 1,2,3-triazolium salts as potential agents against visceral leishmaniasis

Visceral leishmaniasis (VL) is the most severe clinical form of leishmaniasis, being fatal if untreated. In search of a more effective treatment for VL, one of the main strategies is the development and screening of new antileishmanial compounds. Here, we reported the synthesis of seven new acetyl functionalized 1,2,3-triazolium salts, together with four 1,2,3-triazole precursors, and investigated their effect against different strains of L. infantum from dogs and humans. The 1,2,3-triazolium salts exhibited better activity than the 1,2,3-triazole derivatives with IC₅₀ range from 0.12 to 8.66 μM and, among them, compound 5 showed significant activity against promastigotes (IC₅₀ from 4.55 to 5.28 μM) and intracellular amastigotes (IC₅₀ from 5.36 to 7.92 μM), with the best selective index (SI ~ 6-9) and reduced toxicity. Our findings, using biochemical and ultrastructural approaches, demonstrated that compound 5 targets the mitochondrion of L. infantum promastigotes, leading to the formation of reactive oxygen species (ROS), increase of the mitochondrial membrane potential, and mitochondrial alteration. Moreover, quantitative transmission electron microscopy (TEM) revealed that compound 5 induces the reduction of promastigote size and cytoplasmic vacuolization. Interestingly, the effect of compound 5 was not associated with apoptosis or necrosis of the parasites but, instead, seems to be mediated through a pathway involving autophagy, with a clear detection of autophagic vacuoles in the cytoplasm by using both a fluorescent marker and TEM. As for the in vivo studies, compound 5 showed activity in a mouse model of VL at 20 mg/kg, reducing the parasite load in both spleen and liver (59.80% and 26.88%, respectively). Finally, this compound did not induce hepatoxicity or nephrotoxicity and was able to normalize the altered biochemical parameters in the infected mice. Thus, our findings support the use of 1,2,3-triazolium salts as potential agents against visceral leishmaniasis.

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.

Acetylenic Synthetic Betulin Derivatives Inhibit Akt and Erk Kinases Activity, Trigger Apoptosis and Suppress Proliferation of Neuroblastoma and Rhabdomyosarcoma Cell Lines

Neuroblastoma (NB) and rhabdomyosarcoma (RMS), the most common pediatric extracranial solid tumors, still represent an important clinical challenge since no effective treatment is available for metastatic and recurrent disease. Hence, there is an urgent need for the development of new chemotherapeutics to improve the outcome of patients. Betulin (Bet), a triterpenoid from the bark of birches, demonstrated interesting anti-cancer potential. The modification of natural phytochemicals with evidenced anti-tumor activity, including Bet, is one of the methods of receiving new compounds for potential implementation in oncological treatment. Here, we showed that two acetylenic synthetic Bet derivatives (ASBDs), EB5 and EB25/1, reduced the viability and proliferation of SK-N-AS and TE671 cells, as measured by MTT and BrdU tests, respectively. Moreover, ASBDs were also more cytotoxic than temozolomide (TMZ) and cisplatin (cis-diaminedichloroplatinum [II], CDDP) in vitro, and the combination of EB5 with CDDP enhanced anti-cancer effects. We also showed the slowdown of cell cycle progression at S/G2 phases mediated by EB5 using FACS flow cytometry. The decreased viability and proliferation of pediatric cancers cells after treatment with ASBDs was linked to the reduced activity of kinases Akt, Erk1/2 and p38 and the induction of apoptosis, as investigated using Western blotting and FACS. In addition, in silico analyses of the ADMET profile found EB5 to be a promising anti-cancer drug candidate that would benefit from further investigation.

Synthesis, In Silico Study, and Anti-Cancer Activity of Thiosemicarbazone Derivatives

Thiosemicarbazones are known for their biological and pharmacological activities. In this study, we have synthesized and characterized 3-Methoxybenzaldehyde thiosemicarbazone (3-MBTSc) and 4-Nitrobenzaldehyde thiosemicarbazone (4-NBTSc) using IR, ¹HNMR and ¹³C NMR. The compound’s in vitro anticancer activities against different cell lines were evaluated. Molecular docking, Insilco ADMET, and drug-likeness prediction were also done. The test compounds showed a comparative IC₅₀ and growth inhibition with the standard drug Doxorubicin. The IC₅₀ ranges from 2.82 µg/mL to 14.25 µg/mL in 3-MBTSc and 2.80 µg/mL to 7.59 µg/mL in 4-NBTSc treated cells. The MTT assay result revealed, 3-MBTSc inhibits 50.42 and 50.31 percent of cell growth in B16-F0 and EAC cell lines, respectively. The gene expression showed that tumor suppressor genes such as PTEN and BRCA1 are significantly upregulated in 7.42 and 5.33 folds, and oncogenes, PKC, and RAS are downregulated −7.96 and −7.64 folds, respectively in treated cells. The molecular docking performed on the four targeted proteins (PARP, VEGFR-1, TGF-β1, and BRAF^V600E) indicated that both 4-NBTSc and 3-MBTSc potentially bind to TGF-β1 with the best binding energy of −42.34 Kcal/mol and −32.13 Kcal/mol, respectively. In addition, the test compound possesses desirable ADMET and drug-likeness properties. Overall, both 3-MBTSc and 4-NBTSc have the potential to be multitargeting drug candidates for further study. Moreover, 3-MBTSc showed better activity than 4-NBTSc.

Molecular docking of secondary metabolites from Indonesian marine and terrestrial organisms targeting SARS-CoV-2 ACE-2, M pro, and PL pro receptors

With the uncontrolled spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), development and distribution of antiviral drugs and vaccines have gained tremendous importance. This study focused on two viral proteases namely main protease (Mpro) and papain-like protease (PLpro) and human angiotensin-converting enzyme (ACE-2) to identify which of these are essential for viral replication. We screened 102 secondary metabolites against SARS-CoV-2 isolated from 36 terrestrial plants and 36 marine organisms from Indonesian biodiversity. These organisms are typically presumed to have antiviral effects, and some of them have been used as an immunomodulatory activity in traditional medicine. For the molecular docking procedure to obtain Gibbs free energy value (∆G), toxicity, ADME and Lipinski, AutoDock Vina was used. In this study, five secondary metabolites, namely corilagin, dieckol, phlorofucofuroeckol A, proanthocyanidins, and isovitexin, were found to inhibit ACE-2, Mpro, and PLpro receptors in SARS-CoV-2, with a high affinity to the same sites of ptilidepsin, remdesivir, and chloroquine as the control molecules. This study was delimited to molecular docking without any validation by simulations concerned with molecular dynamics. The interactions with two viral proteases and human ACE-2 may play a key role in developing antiviral drugs for five active compounds. In future, we intend to investigate antiviral drugs and the mechanisms of action by in vitro study.

In silico investigations on curcuminoids from Curcuma longa as positive regulators of the Wnt/β-catenin signaling pathway in wound healing

Background

Curcuma longa (Turmeric) is a traditionally used herb in wound healing. The efficacy of fresh turmeric paste to heal wounds has already been investigated in multiple ethnobotanical studies. Wnt/β-catenin signaling pathway plays a significant role in wound healing and injury repair processes which has been evident in different in vitro studies. This study aims to analyze the potentiality of curcuminoids (curcumin I, curcumin II and curcumin III) from Curcuma longa to bind and enhance the activity of two intracellular signaling proteins- casein kinase-1 (CK1) and glycogen synthase kinase-3β (GSK3B) involved in Wnt/β-catenin signaling pathway. This study is largely based on a computer-based molecular docking program which mimics the in vivo condition and works on a specific algorithm to interpret the binding affinity and poses of a ligand molecule to a receptor. Subsequently, drug likeness property, ADME/Toxicity profile, pharmacological activity, and site of metabolism of the curcuminoids were also analyzed.

Results

Curcumin I showed better affinity of binding with CK1 (− 10.31 Kcal/mol binding energy) and curcumin II showed better binding affinity (− 7.55 Kcal/mol binding energy) for GSK3B. All of the ligand molecules showed quite similar pharmacological properties.

Conclusion

Curcumin has anti-oxidant, anti-carcinogenic, anti-mutagenic, anti-coagulant, and anti-infective properties. Curcumin has also anti-inflammatory and wound healing properties. It hastens wound healing by acting on different stages of the natural wound healing process. In this study, three curcumins from Curcuma longa were utilized in this experiment in a search for a drug to be used in wound healing and injury repair processes. Hopefully, this study will raise research interest among researchers.

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.

Discovery of Natural Products Targeting NQO1 via an Approach Combining Network-Based Inference and Identification of Privileged Substructures

NAD(P)H:quinone oxidoreductase 1 (NQO1) has been shown to be a potential therapeutic target for various human diseases, such as cancer and neurodegenerative disorders. Recent advances in computational methods, especially network-based methods, have made it possible to identify novel compounds for a target with high efficiency and low cost. In this study, we designed a workflow combining network-based methods and identification of privileged substructures to discover new compounds targeting NQO1 from a natural product library. According to the prediction results, we purchased 56 compounds for experimental validation. Without the assistance of privileged substructures, 31 compounds (31/56 = 55.4%) showed IC₅₀ < 100 μM, and 11 compounds (11/56 = 19.6%) showed IC₅₀ < 10 μM. With the assistance of privileged substructures, the two success rates were increased to 61.8 and 26.5%, respectively. Seven natural products further showed inhibitory activity on NQO1 at the cellular level, which may serve as lead compounds for further development. Moreover, network analysis revealed that osthole may exert anticancer effects against multiple cancer types by inhibiting not only carbonic anhydrases IX and XII but also NQO1. Our workflow and computational methods can be easily applied in other targets and become useful tools in drug discovery and development.

GGL-Tox: Geometric Graph Learning for Toxicity Prediction

Toxicity analysis is a major challenge in drug design and discovery. Recently significant progress has been made through machine learning due to its accuracy, efficiency, and lower cost. US Toxicology in the 21st Century (Tox21) screened a large library of compounds, including approximately 12 000 environmental chemicals and drugs, for different mechanisms responsible for eliciting toxic effects. The Tox21 Data Challenge offered a platform to evaluate different computational methods for toxicity predictions. Inspired by the success of multiscale weighted colored graph (MWCG) theory in protein-ligand binding affinity predictions, we consider MWCG theory for toxicity analysis. In the present work, we develop a geometric graph learning toxicity (GGL-Tox) model by integrating MWCG features and the gradient boosting decision tree (GBDT) algorithm. The benchmark tests of the Tox21 Data Challenge are employed to demonstrate the utility and usefulness of the proposed GGL-Tox model. An extensive comparison with other state-of-the-art models indicates that GGL-Tox is an accurate and efficient model for toxicity analysis and prediction.

Molecular Docking of Red Betel (Piper crocatum Ruiz & Pav) Bioactive Compounds as HMG-CoA Reductase Inhibitor

Cholesterol plaque buildup in artery walls occurs due to oxidation of Low-Density Lipoprotein (LDL) molecules by free radicals, which are a risk factor for coronary heart disease. Piper crocatum contains active compounds that can act as HMG-CoA reductase inhibitors, such as flavonoids, alkaloids, polyphenols, tannins, and essential oils. This study aimed to predict the potential of Piper crocatum extract and fraction compounds as HMG-CoA reductase inhibitors by investigating the ligand affinity to the HMG-CoA reductase enzyme. Ligand and receptor preparation was conducted using BIOVIA Discovery Studio Visualizer v16.1.0.15350 and AutoDock Tools v.1.5.6. Molecular docking used AutoDock Vina, while ligand visualization and receptor binding used PyMOL(TM) 1.7.4.5.Edu. The receptor used was HMG-CoA reductase (PDB code: 1HWK) with atorvastatin as a control ligand. Catechin, schisandrin B, and CHEMBL216163 had the highest inhibition with affinity energies of -7.9 kcal/mol, -8.2 kcal/mol, -8.3 kcal/mol, respectively. Amino acid residues that played a role in ligand and receptor interactions were Ser684, Asp690, Lys691, Lys692.

Molecular Design of Novel Chemicals for Iron Sulfide Scale Removal

Scale deposition is a pertinent challenge in the oil and gas industry. Scales formed from iron sulfide are one of the troublous scales, particularly pyrite. Moreover, the use of biodegradable environmentally friendly chemicals reduces the cost compared to the conventional removal process. In this work, the chelating abilities of four novel chemicals, designed using the in silico technique of density functional theory (DFT), are studied as potential iron sulfide scale removers. Only one of the chemicals containing a hydroxamate functional group had a good chelating ability with Fe2+. The chelating strength and ecotoxicological properties of this chemical were compared to diethylenetriaminepentaacetic acid (DTPA), an already established iron sulfide scale remover. The new promising chemical surpassed DTPA in being a safer chemical and having a greater binding affinity to Fe2+ upon optimization, hence, a better choice. The presence of oxime (-NHOH) and carbonyl (C=O) moieties in the new chemical showed that the bidentate form of chelation is favored. Moreover, the presence of an intramolecular hydrogen bond enhanced its chelating ability.