A review on machine learning methods for in silico toxicity prediction

Advancing toxicity studies of per- and poly-fluoroalkyl substances (pfass) through machine learning: Models, mechanisms, and future directions

Perfluorinated and perfluoroalkyl substances (PFASs), encompassing a vast array of isomeric chemicals, are recognized as typical emerging contaminants with direct or potential impacts on human health and the ecological environment. With the complex and elusive toxicological profiles of PFASs, machine learning (ML) has been increasingly employed in their toxicity studies due to its proficiency in prediction and data analytics. This integration is poised to become a predominant trend in environmental toxicology, propelled by the swift advancements in computational technology. This review diligently examines the literature to encapsulate the varied objectives of employing ML in the toxicity studies of PFASs: (1) Utilizing ML to establish Quantitative Structure-Activity Relationship (QSAR) models for PFASs with diverse toxicity endpoints, facilitating the targeted toxicity prediction of unidentified PFASs; (2) Investigating and substantiating the Adverse Outcome Pathway (AOP) through the synergy of ML and traditional toxicological methods, with this refining the toxicity assessment framework for PFASs; (3) Dissecting and elucidating the features of established ML models to advance Open Research into the toxicity of PFASs, with a primary focus on determinants and mechanisms. The discourse extends to an in-depth examination of ML studies, segregating findings based on their distinct application trajectories. Given that ML represents a nascent paradigm within PFASs research, this review delineates the collective challenges encountered in the ML-mediated study of PFAS toxicity and proffers strategic guidance for ensuing investigations.

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

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

Prediction of chemical-induced acute toxicity using in vitro assay data and chemical structure

Exposure to various chemicals found in the environment and in the context of drug development can cause acute toxicity. To provide an alternative to in vivo animal toxicity testing, the U.S. Tox21 consortium developed in vitro assays to test a library of approximately 10,000 drugs and environmental chemicals (Tox21 10 K compound library) in a quantitative high-throughput screening (qHTS) approach. In this study, we assessed the utility of Tox21 assay data in comparison with chemical structure information in predicting acute systemic toxicity. Prediction models were developed using four machine learning algorithms, namely Random Forest, Naïve Bayes, eXtreme Gradient Boosting, and Support Vector Machine, and their performance was assessed using the area under the receiver operating characteristic curve (AUC-ROC). The chemical structure-based models as well as the Tox21 assay data demonstrated good predictive power for acute toxicity, achieving AUC-ROC values ranging from 0.83 to 0.93 and 0.73 to 0.79, respectively. We applied the models to predict the acute toxicity potential of the compounds in the Tox21 10 K compound library, most of which were found to be non-toxic. In addition, we identified the Tox21 assays that contributed the most to acute toxicity prediction, such as acetylcholinesterase (AChE) inhibition and p53 induction. Chemical features including organophosphates and carbamates were also identified to be significantly associated with acute toxicity. In conclusion, this study underscores the utility of in vitro assay data in predicting acute toxicity.

Unlocking the potential of AI: Machine learning and deep learning models for predicting carcinogenicity of chemicals

The escalating apprehension surrounding the carcinogenic potential of chemicals emphasizes the imperative need for efficient methods of assessing carcinogenicity. Conventional experimental approaches such as in vitro and in vivo assays, albeit effective, suffer from being costly and time-consuming. In response to this challenge, new alternative methodologies, notably machine learning and deep learning techniques, have attracted attention for their potential in developing carcinogenicity prediction models. This article reviews the progress in predicting carcinogenicity using various machine learning and deep learning algorithms. A comparative analysis on these developed models reveals that support vector machine, random forest, and ensemble learning are commonly preferred for their robustness and effectiveness in predicting chemical carcinogenicity. Conversely, models based on deep learning algorithms, such as feedforward neural network, convolutional neural network, graph convolutional neural network, capsule neural network, and hybrid neural networks, exhibit promising capabilities but are limited by the size of available carcinogenicity datasets. This review provides a comprehensive analysis of current machine learning and deep learning models for carcinogenicity prediction, underscoring the importance of high-quality and large datasets. These observations are anticipated to catalyze future advancements in developing effective and generalizable machine learning and deep learning models for predicting chemical carcinogenicity.

New apoptotic anti-triple-negative breast cancer theobromine derivative inhibiting EGFRWT and EGFRT790M: in silico and in vitro evaluation

A new theobromine-derived EGFR inhibitor (2-(3,7-Dimethyl-2,6-dioxo-2,3,6,7-tetrahydro-1H-purin-1-yl)-N-(2,6-dimethylphenyl)acetamide) has been developed that has the essential structural characteristics to interact with EGFR's pocket. The designed compound is 2,6-di ortho methylphenyl)acetamide derivative of the well-known alkaloid, theobromine, (T-1-DOMPA). Firstly, deep DFT studies have been conducted to study the optimized chemical structure, molecular orbital and chemical reactivity analysis of T-1-DOMPA. Then, T-1-DOMPA's anticancer potentialities were estimated first through a structure-based computational approach. Utilizing molecular docking, molecular dynamics, MD, simulations over 100 ns, MM-PBSA and PLIP studies, T-1-DOMPA bonded to and inhibited the EGFR protein effectively. Subsequently, the ADMET profiles of T-1-DOMPA were computed before preparation, and its drug-likeness was anticipated. Therefore, T-1-DOMPA was prepared for the purposes of scrutinizing both the design and the results obtained in silico. The in vitro potential of T-1-DOMPA against triple-negative breast cancer cell lines, MDA- MB-231, was very promising with an IC50 value of1.8 µM, comparable to the reference drug (0.9 µM), and a much higher selectivity index of 2.6. Interestingly, T-1-DOMPA inhibited three other cancer cell lines (CaCO-2, HepG-2, and A549) with IC50 values of 1.98, 2.53, and 2.39 µM exhibiting selectivity index values of 2,4, 1.9, and 2, respectively. Additionally, T-1-DOMPA prevented effectively the MDA-MB-231cell line's healing and migration abilities. Also, T-1-DOMPA's abilities to induce apoptosis were confirmed by acridine orange/ethidium bromide (AO/EB) staining assay. Finally, T-1-DOMPA caused an up-regulation of the gene expression of the apoptotic gene, Caspase-3, in the treated MDA-MB-231cell.

New thiazolidine-2,4-diones as potential anticancer agents and apoptotic inducers targeting VEGFR-2 kinase: Design, synthesis, in silico and in vitro studies

BACKGROUND

VEGFR-2 has emerged as a prominent positive regulator of cancer progression.

AIM

Discovery of new anticancer agents and apoptotic inducers targeting VEGFR-2.

METHODS

Design and synthesis of new thiazolidine-2,4-diones followed by extensive in vitro studies, including VEGFR-2 inhibition assay, MTT assay, apoptosis analysis, and cell migration assay. In silico investigations including docking, MD simulations, ADMET, toxicity, and DFT studies were performed.

RESULTS

Compound 15 showed the strongest VEGFR-2 inhibitory activity with an IC50 value of 0.066 μM. Additionally, most of the synthesized compounds showed anti-proliferative activity against HepG2 and MCF-7 cancer cell lines at the micromolar range with IC50 values ranging from 0.04 to 4.71 μM, relative to sorafenib (IC50 = 2.24 ± 0.06 and 3.17 ± 0.01 μM against HepG2 and MCF-7, respectively). Also, compound 15 showed selectivity indices of 1.36 and 2.08 against HepG2 and MCF-7, respectively. Furthermore, compound 15 showed a significant apoptotic effect and arrested the cell cycle of MCF-7 cells at the S phase. Moreover, compound 15 had a significant inhibitory effect on the ability of MCF-7 cells to heal from. Docking studies revealed that the synthesized thiazolidine-2,4-diones have a binding pattern approaching sorafenib. MD simulations indicated the stability of compound 15 in the active pocket of VEGFR-2 for 200 ns. ADMET and toxicity studies indicated an acceptable pharmacokinetic profile. DFT studies confirmed the ability of compound 15 to interact with VEGFR-2.

CONCLUSION

Compound 15 has promising anticancer activity targeting VEGFR-2 with significant activity as an apoptosis inducer.

Machine learning framework for predicting cytotoxicity and identifying toxicity drivers of disinfection byproducts

Drinking water disinfection can result in the formation disinfection byproducts (DBPs, > 700 have been identified to date), many of them are reportedly cytotoxic, genotoxic, or developmentally toxic. Analyzing the toxicity levels of these contaminants experimentally is challenging, however, a predictive model could rapidly and effectively assess their toxicity. In this study, machine learning models were developed to predict DBP cytotoxicity based on their chemical information and exposure experiments. The Random Forest model achieved the best performance (coefficient of determination of 0.62 and root mean square error of 0.63) among all the algorithms screened. Also, the results of a probabilistic model demonstrated reliable model predictions. According to the model interpretation, halogen atoms are the most prominent features for DBP cytotoxicity compared to other chemical substructures. The presence of iodine and bromine is associated with increased cytotoxicity levels, while the presence of chlorine is linked to a reduction in cytotoxicity levels. Other factors including chemical substructures (CC, N, CN, and 6-member ring), cell line, and exposure duration can significantly affect the cytotoxicity of DBPs. The similarity calculation indicated that the model has a large applicability domain and can provide reliable predictions for DBPs with unknown cytotoxicity. Finally, this study showed the effectiveness of data augmentation in the scenario of data scarcity.

New Theobromine Apoptotic Analogue with Anticancer Potential Targeting the EGFR Protein: Computational and In Vitro Studies

AIM

The aim of this study was to design and examine a novel epidermal growth factor receptor (EGFR) inhibitor with apoptotic properties by utilizing the essential structural characteristics of existing EGFR inhibitors as a foundation.

METHOD

The study began with the natural alkaloid theobromine and developed a new semisynthetic derivative (T-1-PMPA). Computational ADMET assessments were conducted first to evaluate its anticipated safety and general drug-likeness. Deep density functional theory (DFT) computations were initially performed to validate the three-dimensional (3D) structure and reactivity of T-1-PMPA. Molecular docking against the EGFR proteins was conducted to investigate T-1-PMPA's binding affinity and inhibitory potential. Additional molecular dynamics (MD) simulations over 200 ns along with MM-GPSA, PLIP, and principal component analysis of trajectories (PCAT) experiments were employed to verify the binding and inhibitory properties of T-1-PMPA. Afterward, T-1-PMPA was semisynthesized to validate the proposed design and in silico findings through several in vitro examinations.

RESULTS

DFT studies indicated T-1-PMPA's reactivity using electrostatic potential, global reactive indices, and total density of states. Molecular docking, MD simulations, MM-GPSA, PLIP, and ED suggested the binding and inhibitory properties of T-1-PMPA against the EGFR protein. The in silico ADMET predicted T-1-PMPA's safety and general drug-likeness. In vitro experiments demonstrated that T-1-PMPA effectively inhibited EGFRWT and EGFR790m, with IC50 values of 86 and 561 nM, respectively, compared to Erlotinib (31 and 456 nM). T-1-PMPA also showed significant suppression of the proliferation of HepG2 and MCF7 malignant cell lines, with IC50 values of 3.51 and 4.13 μM, respectively. The selectivity indices against the two cancer cell lines indicated the overall safety of T-1-PMPA. Flow cytometry confirmed the apoptotic effects of T-1-PMPA by increasing the total percentage of apoptosis to 42% compared to 31, and 3% in Erlotinib-treated and control cells, respectively. The qRT-PCR analysis further supported the apoptotic effects by revealing significant increases in the levels of Casp3 and Casp9. Additionally, T-1-PMPA controlled the levels of TNFα and IL2 by 74 and 50%, comparing Erlotinib's values (84 and 74%), respectively.

CONCLUSION

In conclusion, our study's findings suggest the potential of T-1-PMPA as a promising apoptotic anticancer lead compound targeting the EGFR.

Artificial intelligence (AI)-it's the end of the tox as we know it (and I feel fine)

The rapid progress of AI impacts diverse scientific disciplines, including toxicology, and has the potential to transform chemical safety evaluation. Toxicology has evolved from an empirical science focused on observing apical outcomes of chemical exposure, to a data-rich field ripe for AI integration. The volume, variety and velocity of toxicological data from legacy studies, literature, high-throughput assays, sensor technologies and omics approaches create opportunities but also complexities that AI can help address. In particular, machine learning is well suited to handle and integrate large, heterogeneous datasets that are both structured and unstructured-a key challenge in modern toxicology. AI methods like deep neural networks, large language models, and natural language processing have successfully predicted toxicity endpoints, analyzed high-throughput data, extracted facts from literature, and generated synthetic data. Beyond automating data capture, analysis, and prediction, AI techniques show promise for accelerating quantitative risk assessment by providing probabilistic outputs to capture uncertainties. AI also enables explanation methods to unravel mechanisms and increase trust in modeled predictions. However, issues like model interpretability, data biases, and transparency currently limit regulatory endorsement of AI. Multidisciplinary collaboration is needed to ensure development of interpretable, robust, and human-centered AI systems. Rather than just automating human tasks at scale, transformative AI can catalyze innovation in how evidence is gathered, data are generated, hypotheses are formed and tested, and tasks are performed to usher new paradigms in chemical safety assessment. Used judiciously, AI has immense potential to advance toxicology into a more predictive, mechanism-based, and evidence-integrated scientific discipline to better safeguard human and environmental wellbeing across diverse populations.

Discovery of new thiazolidine-2,4-dione derivatives as potential VEGFR-2 inhibitors: In vitro and in silico studies

In this study, a series of seven novel 2,4-dioxothiazolidine derivatives with potential anticancer and VEGFR-2 inhibiting abilities were designed and synthesized as VEGFR-2 inhibitors. The synthesized compounds were tested in vitro for their potential to inhibit VEGFR-2 and the growth of HepG2 and MCF-7 cancer cell lines. Among the compounds tested, compound 22 (IC50 = 0.079 μM) demonstrated the highest anti-VEGFR-2 efficacy. Furthermore, it demonstrated significant anti-proliferative activities against HepG2 (IC50 = 2.04 ± 0.06 μM) and MCF-7 (IC50 = 1.21 ± 0.04 M). Additionally, compound 22 also increased the total apoptotic rate of the MCF-7 cancer cell lines with cell cycle arrest at S phase. As well, computational methods were applied to study the VEGFR-2-22 complex at the molecular level. Molecular docking and molecular dynamics (MD) simulations were used to investigate the complex's structural and kinetic characteristics. The DFT calculations further revealed the structural and electronic properties of compound 22. Finally, computational ADMET and toxicity tests were performed indicating the likeness of the proposed compounds to be drugs. The results suggest that compound 22 displays promise as an effective anticancer treatment and can serve as a model for future structural modifications and biological investigations in this field.

MolToxPred: small molecule toxicity prediction using machine learning approach

Different types of chemicals and products may exhibit various health risks when administered into the human body. For toxicity reasons, the number of new drugs entering the market through the conventional drug development process has been reduced over the years. However, with the advent of big data and artificial intelligence, machine learning techniques have emerged as a potential solution for predicting toxicity and ensuring efficient drug development and chemical safety. An ML model for toxicity prediction can reduce experimental costs and time while addressing ethical concerns by drastically reducing the need for animals and clinical trials. Herein, MolToxPred, an ML-based tool, has been developed using a stacked model approach to predict the potential toxicity of small molecules and metabolites. The stacked model consists of random forest, multi-layer perceptron, and LightGBM as base classifiers and Logistic Regression as the meta classifier. For training and validation purposes, a comprehensive set of toxic and non-toxic molecules is curated. Different structural and physicochemical-based features in the form of molecular descriptors and fingerprints were employed. MolToxPred utilizes a comprehensive feature selection process and optimizes its hyperparameters through Bayesian optimization with stratified 5-fold cross-validation. In the evaluation phase, MolToxPred achieved an AUROC of 87.76% on the test set and 88.84% on an external validation set. The McNemar test was used as the post-hoc test to determine if the stacked models' performance was significantly different compared to the base learners. The developed stacked model outperformed its base classifiers and an existing tool in the literature, reaffirming its better performance. The hypothesis is that the incorporation of a diverse set of data, the subsequent feature selection, and a stacked ensemble approach give MolToxPred the edge over other methods. In addition to this, an attempt has been made to identify structural alerts responsible for endpoints of the Tox21 data to determine the association of a molecule with a plausible downstream pathway of action. MolToxPred may be helpful for drug discovery and regulatory pipelines in pharmaceutical and other industries for in silico toxicity prediction of small molecule candidates.

Innovative Biomedical and Technological Strategies for the Control of Bacterial Growth and Infections

Antibiotics comprise one of the most successful groups of pharmaceutical products. Still, they have been associated with developing bacterial resistance, which has become one of the most severe problems threatening human health today. This context has prompted the development of new antibiotics or co-treatments using innovative tools to reverse the resistance context, combat infections, and offer promising antibacterial therapy. For the development of new alternatives, strategies, and/or antibiotics for controlling bacterial growth, it is necessary to know the target bacteria, their classification, morphological characteristics, the antibiotics currently used for therapies, and their respective mechanisms of action. In this regard, genomics, through the sequencing of bacterial genomes, has generated information on diverse genetic resources, aiding in the discovery of new molecules or antibiotic compounds. Nanotechnology has been applied to propose new antimicrobials, revitalize existing drug options, and use strategic encapsulating agents with their biochemical characteristics, making them more effective against various bacteria. Advanced knowledge in bacterial sequencing contributes to the construction of databases, resulting in advances in bioinformatics and the development of new antimicrobials. Moreover, it enables in silico antimicrobial susceptibility testing without the need to cultivate the pathogen, reducing costs and time. This review presents new antibiotics and biomedical and technological innovations studied in recent years to develop or improve natural or synthetic antimicrobial agents to reduce bacterial growth, promote well-being, and benefit users.

Improving ADMET Prediction Accuracy for Candidate Drugs: Factors to Consider in QSPR Modeling Approaches

Quantitative Structure-Property Relationship (QSPR) employs mathematical and statistical methods to reveal quantitative correlations between the pharmacokinetics of compounds and their molecular structures, as well as their physical and chemical properties. QSPR models have been widely applied in the prediction of drug absorption, distribution, metabolism, excretion, and toxicity (ADMET). However, the accuracy of QSPR models for predicting drug ADMET properties still needs improvement. Therefore, this paper comprehensively reviews the tools employed in various stages of QSPR predictions for drug ADMET. It summarizes commonly used approaches to building QSPR models, systematically analyzing the advantages and limitations of each modeling method to ensure their judicious application. We provide an overview of recent advancements in the application of QSPR models for predicting drug ADMET properties. Furthermore, this review explores the inherent challenges in QSPR modeling while also proposing a range of considerations aimed at enhancing model prediction accuracy. The objective is to enhance the predictive capabilities of QSPR models in the field of drug development and provide valuable reference and guidance for researchers in this domain.

New Thieno[2,3-d]pyrimidines as Anticancer VEGFR-2 Inhibitors with Apoptosis Induction: Design, Synthesis, and Biological and In Silico Studies

BACKGROUND

Vascular endothelial growth factor receptor-2 (VEGFR-2) is a critical protein involved in tumor progression, making it an attractive target for cancer therapy.

OBJECTIVE

This study aimed to synthesize and evaluate novel thieno[2,3-d]pyrimidine analogues as potential anticancer VEGFR-2 inhibitors.

METHODS

The thieno[2,3-d]pyrimidine analogues were synthesized following the pharmacophoric features of VEGFR-2 inhibitors. The anticancer potential was assessed against PC3 and HepG2 cell lines. The VEGFR-2 inhibition was evaluated through IC50 determination. Cell cycle analysis and apoptosis assays were performed to elucidate the mechanisms of action. Molecular docking, molecular dynamics simulations, MM-GBSA, and PLIP studies were conducted to investigate the binding affinities and interactions with VEGFR-2. Additionally, in silico ADMET studies were performed.

RESULTS

Compound 8b demonstrated significant anti-proliferative activities with IC50 values of 16.35 μM and 8.24 μM against PC3 and HepG2 cell lines, respectively, surpassing sorafenib and exhibiting enhanced selectivity indices. Furthermore, compound 8b showed an IC50 value of 73 nM for VEGFR-2 inhibition. Cell cycle analysis revealed G2-M phase arrest, while apoptosis assays demonstrated increased apoptosis in HepG2 cells. Molecular docking and dynamic simulations confirmed the binding affinity and interaction of compound 8b with VEGFR-2, supported by MMGBSA and PLIP studies. In silico ADMET studies indicated the drug development potential of the synthesized thieno[2,3-d]pyrimidines.

CONCLUSION

The study highlights compound 8b as a promising VEGFR-2 inhibitor with potent anti-proliferative activities. Its mechanism of action involves cell cycle arrest and induction of apoptosis. Further, molecular docking and dynamic simulations support the strong binding affinity of compound 8b to VEGFR-2.

Isolation and in silico investigation of cannflavins from Cannabis sativa leaves as potential anti-SARS-CoV-2 agents targeting the Papain-Like Protease

This study aimed to isolate and identify three prenylflavonoids (cannflavin A, B, and C) from Cannabis sativa leaves using different chromatographic techniques. The potential of the isolated compounds against SARS-CoV-2 was suggested through several in silico analysis. Structural similarity studies against nine co-crystallized ligands of SARS-CoV-2's proteins indicated the similarities of the isolated cannflavins with the SARS-CoV-2 Papain-Like Protease (PLP) ligand, Y95. Then, flexible allignment study confirmed this similarity. Docking experiments showed successful binding of all cannflavins within the active pocket of PLP, with energies comparable to Y95. Among them, cannflavin A demonstrated the most similar binding mode, while cannflavin C exhibited the best energy. Molecular dynamics (MD) simulations and MM-GPSA confirmed the accurate binding of cannflavin A to the PLP. In silico ADMET studies indicated favourable drug-like properties for all three compounds, suggesting their potential as anti-SARS-CoV-2 agents. Further In vitro and In vivo investigations are necessary to validate these findings and establish their efficacy and safety profiles.

Computer-Assisted Drug Discovery of a Novel Theobromine Derivative as an EGFR Protein-Targeted Apoptosis Inducer

The overexpression of the Epidermal Growth Factor Receptor (EGFR) marks it as a pivotal target in cancer treatment, with the aim of reducing its proliferation and inducing apoptosis. This study aimed at the CADD of a new apoptotic EGFR inhibitor. The natural alkaloid, theobromine, was used as a starting point to obtain a new semisynthetic (di-ortho-chloro acetamide) derivative (T-1-DOCA). Firstly, T-1-DOCA's total electron density, energy gap, reactivity indices, and electrostatic surface potential were determined by DFT calculations, Then, molecular docking studies were carried out to predict the potential of T-1-DOCA against wild and mutant EGFR proteins. T-1-DOCA's correct binding was further confirmed by molecular dynamics (MD) over 100 ns, MM-GPSA, and PLIP experiments. In vitro, T-1-DOCA showed noticeable efficacy compared to erlotinib by suppressing EGFRWT and EGFRT790M with IC50 values of 56.94 and 269.01 nM, respectively. T-1-DOCA inhibited also the proliferation of H1975 and HCT-116 malignant cell lines, exhibiting IC50 values of 14.12 and 23.39 µM, with selectivity indices of 6.8 and 4.1, respectively, indicating its anticancer potential and general safety. The apoptotic effects of T-1-DOCA were indicated by flow cytometric analysis and were further confirmed through its potential to increase the levels of BAX, Casp3, and Casp9, and decrease Bcl-2 levels. In conclusion, T-1-DOCA, a new apoptotic EGFR inhibitor, was designed and evaluated both computationally and experimentally. The results suggest that T-1-DOCA is a promising candidate for further development as an anti-cancer drug.

New thiazolidine-2,4-diones as effective anti-proliferative and anti-VEGFR-2 agents: Design, synthesis, in vitro, docking, MD simulations, DFT, ADMET, and toxicity studies

Novel thiazolidine-2,4-dione derivatives, 11a-g, were designed, and synthesized targeting the VEGFR-2 protein. The in vitro studies indicated the abilities of the synthesized derivatives to inhibit VEGFR-2 and prevent the growth of two different cancer cell types, HepG2 and MCF-7. Compound 11 f exhibited the strongest anti-VEGFR-2 activity (IC50 = 0.053 µM). As well, compound 11 f showed impressive anti-proliferative activity against the mentioned cancer cell lines with IC50 values of 0.64 ± 0.01 and 0.53 ± 0.04 µM, respectively. Additionally, compound 11 f arrested the MCF-7 cell cycle at the S phase and increased the overall apoptosis percentage. Furthermore, cell migration assay revealed that compound 11 f has a significant ability to prevent migration and healing potentialities of MCF-7. Moreover, computational studies were used to conduct the molecular investigation of the VEGFR-2-11 f complex. The kinetic and structural features of the complex were examined using molecular dynamics simulations and molecular docking. Besides, Principal component analysis (PCA) was used to explain the dynamics of the VEGFR-2-11 f complex at various spatial scales. The DFT calculations also provided further clarity regarding compound 11 f's structural and electronic features. To evaluate how closely the developed compounds might look like drugs, ADMET and toxicity experiments were computed. To conclude, the presented study demonstrates the potential of compound 11 f as a viable anti-cancer drug, which can serve as a prototype for future structural modifications and further biological investigations.

Computer-assisted drug discovery (CADD) of an anti-cancer derivative of the theobromine alkaloid inhibiting VEGFR-2

VEGFR-2 is a significant target in cancer treatment, inhibiting angiogenesis and impeding tumor growth. Utilizing the essential pharmacophoric structural properties, a new semi-synthetic theobromine analogue (T-1-MBHEPA) was designed as VEGFR-2 inhibitor. Firstly, T-1-MBHEPA's stability and reactivity were indicated through several DFT computations. Additionally, molecular docking, MD simulations, MM-GPSA, PLIP, and essential dynamics (ED) experiments suggested T-1-MBHEPA's strong binding capabilities to VEGFR-2. Its computational ADMET profiles were also studied before the semi-synthesis and indicated a good degree of drug-likeness. T-1-MBHEPA was then semi-synthesized to evaluate the design and the in silico findings. It was found that, T-1-MBHEPA inhibited VEGFR-2 with an IC50 value of 0.121 ± 0.051 µM, as compared to sorafenib which had an IC50 value of 0.056 µM. Similarly, T-1-MBHEPA inhibited the proliferation of HepG2 and MCF7 cell lines with IC50 values of 4.61 and 4.85 µg/mL respectively - comparing sorafenib's IC50 values which were 2.24 µg/mL and 3.17 µg/mL respectively. Interestingly, T-1-MBHEPA revealed a noteworthy IC50 value of 80.0 µM against the normal cell lines exhibiting exceptionally high selectivity indexes (SI) of 17.4 and 16. 5 against the examined cell lines, respectively. T-1-MBHEPA increased the percentage of apoptotic MCF7 cells in early and late stages, respectively, from 0.71 % to 7.22 % and from 0.13 % to 2.72 %, while the necrosis percentage was increased to 11.41 %, in comparison to 2.22 % in control cells. Furthermore, T-1-MBHEPA reduced the production of pro-inflammatory cytokines TNF-α and IL-2 in the treated MCF7 cells by 33 % and 58 %, respectively indicating an additional anti-angiogenic mechanism. Also, T-1-MBHEPA decreased significantly the potentialities of MCF7 cells to heal and migrate from 65.9 % to 7.4 %. Finally, T-1-MBHEPA's oral treatment didn't show toxicity on the liver function (ALT and AST) and the kidney function (creatinine and urea) levels of mice.

Machine Learning Methods for Endocrine Disrupting Potential Identification Based on Single-Cell Data

Humans are continuously exposed to a variety of toxicants and chemicals which is exacerbated during and after environmental catastrophes such as floods, earthquakes, and hurricanes. The hazardous chemical mixtures generated during these events threaten the health and safety of humans and other living organisms. This necessitates the development of rapid decision-making tools to facilitate mitigating the adverse effects of exposure on the key modulators of the endocrine system, such as the estrogen receptor alpha (ERα), for example. The mechanistic stages of the estrogenic transcriptional activity can be measured with high content/high throughput microscopy-based biosensor assays at the single-cell level, which generates millions of object-based minable data points. By combining computational modeling and experimental analysis, we built a highly accurate data-driven classification framework to assess the endocrine disrupting potential of environmental compounds. The effects of these compounds on the ERα pathway are predicted as being receptor agonists or antagonists using the principal component analysis (PCA) projections of high throughput, high content image analysis descriptors. The framework also combines rigorous preprocessing steps and nonlinear machine learning algorithms, such as the Support Vector Machines and Random Forest classifiers, to develop highly accurate mathematical representations of the separation between ERα agonists and antagonists. The results show that Support Vector Machines classify the unseen chemicals correctly with more than 96% accuracy using the proposed framework, where the preprocessing and the PCA steps play a key role in suppressing experimental noise and unraveling hidden patterns in the dataset.

Anti-breast cancer potential of a new xanthine derivative: In silico, antiproliferative, selectivity, VEGFR-2 inhibition, apoptosis induction and migration inhibition studies

BACKGROUND

The overexpression of VEGFR-2 receptors in breast cancer provides a valuable approach to anticancer strategies. Targeting VEGFR-2, a new semisynthetic compound (T-1-MCPAB) has been designed.

METHODS

Computational methods (ADMET, toxicity, DFT, Molecular Docking, Molecular Dynamics Simulations, MM-GBSA, PLIP, and PCAT) were conducted. In addition to the semi-synthesis, in vitro studies (anti-VEGFR-2, anti-proliferative, flow cytometry, and wound scratch assay) were employed.

RESULTS

ADME and toxicity profiles of T-1-MCPAB studies indicated its overall drug-likeness showing results much better than Sorafenib. Then, T-1-MCPAB's exact 3D structure, stability, and reactivity were evoked by the DFT calculations. Molecular docking, molecular dynamics simulations, MM-GPSA, PLIP, and PCAT studies denoted the correct binding and inhibiting potential of T-1-MCPAB, towards VEGFR-2 protein. After the semisynthesis, T-1-MCPAB inhibited VEGFR-2 with an IC50 of 0.135 µM, which was comparable to sorafenib's IC50 of 0.0591 µM. T-1-MCPAB also showed a notable performance against MCF7 and T47D breast cancer cell lines with IC50 values of 30.95 µM and 63.64 µM, respectively, and had high selectivity index values of 3.7 and 1.8, respectively. Furthermore, T-1-MCPAB influenced early and late apoptosis and significantly decreased the potential of MCF7 cells to heal and migrate.

CONCLUSION

T-1-MCPAB is a promising VEGFR-2 inhibitor with potential for breast cancer treatment. Further chemical and biological studies are needed to explore its potential as a therapeutic agent.

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.

What is the ecotoxicity of a given chemical for a given aquatic species? Predicting interactions between species and chemicals using recommender system techniques

Ecotoxicological safety assessment of chemicals requires toxicity data on multiple species, despite the general desire of minimizing animal testing. Predictive models, specifically machine learning (ML) methods, are one of the tools capable of solving this apparent contradiction as they allow to generalize toxicity patterns across chemicals and species. However, despite the availability of large public toxicity datasets, the data is highly sparse, complicating model development. The aim of this study is to provide insights into how ML can predict toxicity using a large but sparse dataset. We developed models to predict LC50-values, based on experimental LC50-data covering 2431 organic chemicals and 1506 aquatic species from the ECOTOX-database. Several well-known ML techniques were evaluated and a new ML model was developed, inspired by recommender systems. This new model involves a simple linear model that learns low-rank interactions between species and chemicals using factorization machines. We evaluated the predictive performances of the developed models based on two validation settings: 1) predicting unseen chemical-species pairs, and 2) predicting unseen chemicals. The results of this study show that ML models can accurately predict LC50-values in both validation settings. Moreover, we show that the novel factorization machine approach can match well-tuned, complex, ML approaches.

A Theobromine Derivative with Anticancer Properties Targeting VEGFR-2: Semisynthesis, in silico and in vitro Studies

A computer-assisted drug design (CADD) approach was utilized to design a new acetamido-N-(para-fluorophenyl)benzamide) derivative of the naturally occurring alkaloid, theobromine, (T-1-APFPB), following the pharmacophoric features of VEGFR-2 inhibitors. The stability and reactivity of T-1-AFPB were assessed through density functional theory (DFT) calculations. Molecular docking assessments showed T-1-AFPB's potential to bind with and inhibit VEGFR-2. The precise binding of T-1-AFPB against VEGFR-2 with optimal energy was further confirmed through several molecular dynamics (MD) simulations, PLIP, MM-GBSA, and PCA studies. Then, T-1-AFPB (4-(2-(3,7-Dimethyl-2,6-dioxo-2,3,6,7-tetrahydro-1H-purin-1-yl)acetamido)-N-(4-fluorophenyl)benzamide) was semi-synthesized and the in vitro assays showed its potential to inhibit VEGFR-2 with an IC50 value of 69 nM (sorafenib's IC50 was 56 nM) and to inhibit the growth of HepG2 and MCF-7 cancer cell lines with IC50 values of 2.24±0.02 and 3.26±0.02 μM, respectively. Moreover, T-1-AFPB displayed very high selectivity indices against normal Vero cell lines. Furthermore, T-1-AFPB induced early (from 0.72 to 19.12) and late (from 0.13 to 6.37) apoptosis in HepG2 cell lines. In conclusion, the combined computational and experimental approaches demonstrated the efficacy and safety of T-1-APFPB providing it as a promising lead VEGFR-2 inhibitor for further development aiming at cancer therapy.

Collaborative SAR Modeling and Prospective In Vitro Validation of Oxidative Stress Activation in Human HepG2 Cells

Oxidative stress is the consequence of an abnormal increase of reactive oxygen species (ROS). ROS are generated mainly during the metabolism in both normal and pathological conditions as well as from exposure to xenobiotics. Xenobiotics can, on the one hand, disrupt molecular machinery involved in redox processes and, on the other hand, reduce the effectiveness of the antioxidant activity. Such dysregulation may lead to oxidative damage when combined with oxidative stress overpassing the cell capacity to detoxify ROS. In this work, a green fluorescent protein (GFP)-tagged nuclear factor erythroid 2-related factor 2 (NRF2)-regulated sulfiredoxin reporter (Srxn1-GFP) was used to measure the antioxidant response of HepG2 cells to a large series of drug and drug-like compounds (2230 compounds). These compounds were then classified as positive or negative depending on cellular response and distributed among different modeling groups to establish structure-activity relationship (SAR) models. A selection of models was used to prospectively predict oxidative stress induced by a new set of compounds subsequently experimentally tested to validate the model predictions. Altogether, this exercise exemplifies the different challenges of developing SAR models of a phenotypic cellular readout, model combination, chemical space selection, and results interpretation.

A novel thieno[2,3-d]pyrimidine derivative inhibiting vascular endothelial growth factor receptor-2: A story of computer-aided drug discovery

Following the pharmacophoric features of vascular endothelial growth factor receptor 2 (VEGFR-2) inhibitors, a novel thieno[2,3-d]pyrimidine derivative has been designed and its activity against VEGFR-2 has been demonstrated by molecular docking studies that showed an accurate binding mode and an excellent binding energy. Furthermore, the recorded binding was confirmed by a series of molecular dynamics simulation studies, which also revealed precise energetic, conformational, and dynamic changes. Additionally, molecular mechanics with generalized Born and surface area solvation and polymer-induced liquid precursors studies were conducted and verified the results of the MD simulations. Next, in silico absorption, distribution, metabolism, excretion, and toxicity studies have also been conducted to examine the general drug-like nature of the designed candidate. According to the previous results, the thieno[2,3-d]pyrimidine derivative was synthesized. Fascinatingly, it inhibited VEGFR-2 (IC50  = 68.13 nM) and demonstrated strong inhibitory activity toward human liver (HepG2), and prostate (PC3) cell lines with IC50 values of 6.60 and 11.25 µM, respectively. As well, it was safe and showed a high selectivity index against normal cell lines (WI-38). Finally, the thieno[2,3-d]pyrimidine derivative arrested the growth of the HepG2 cells at the G2/M phase inducing both early and late apoptosis. These results were further confirmed through the ability of the thieno[2,3-d]pyrimidine derivative to induce significant changes in the apoptotic genes levels of caspase-3, caspase-9, Bcl-2 associated X-protein, and B-cell lymphoma 2.

Discovery of new thieno[2,3-d]pyrimidines as EGFR tyrosine kinase inhibitors for cancer treatment

Background: EGFR has been considered a vital molecular target in cancer management. Aim: The discovery of new thieno[2,3-d]pyrimidine derivatives as EGFR tyrosine kinase inhibitors. Methods: Nine derivatives were designed, synthesized and subjected to in vitro and in silico studies. Results: Compound 7a significantly inhibited the growth of HepG2 and PC3 cells for both EGFR wild-type and EGFRT790M. Compound 7a caused a significant apoptotic effect, arresting HepG2 cells' growth in the S and G2/M phases. Docking and molecular dynamics simulation studies confirmed the correct and stable binding modes of the synthesized compounds against the active sites. Conclusion: Compound 7a is a promising dual EGFR inhibitor for cancer treatment.

Navigating the bridge between wet and dry lab toxicology research to address current challenges with high-dimensional data

Toxicology research has rapidly evolved, leveraging increasingly advanced technologies in high-throughput approaches to yield important information on toxicological mechanisms and health outcomes. Data produced through toxicology studies are consequently becoming larger, often producing high-dimensional data. These types of data hold promise for imparting new knowledge, yet inherently have complexities causing them to be a rate-limiting element for researchers, particularly those that are housed in "wet lab" settings (i.e., researchers that use liquids to analyze various chemicals and biomarkers as opposed to more computationally focused, "dry lab" researchers). These types of challenges represent topics of ongoing conversation amongst our team and researchers in the field. The aim of this perspective is to i) summarize hurdles in analyzing high-dimensional data in toxicology that require improved training and translation for wet lab researchers, ii) highlight example methods that have aided in translating data analysis techniques to wet lab researchers; and iii) describe challenges that remain to be effectively addressed, to date, in toxicology research. Specific aspects include methodologies that could be introduced to wet lab researchers, including data pre-processing, machine learning, and data reduction. Current challenges discussed include model interpretability, study biases, and data analysis training. Example efforts implemented to translate these data analysis techniques are also mentioned, including online data analysis resources and hands-on workshops. Questions are also posed to continue conversation in the toxicology community. Contents of this perspective represent timely issues broadly occurring in the fields of bioinformatics and toxicology that require ongoing dialogue between wet and dry lab researchers.

Artificial Intelligence in Drug Toxicity Prediction: Recent Advances, Challenges, and Future Perspectives

Toxicity prediction is a critical step in the drug discovery process that helps identify and prioritize compounds with the greatest potential for safe and effective use in humans, while also reducing the risk of costly late-stage failures. It is estimated that over 30% of drug candidates are discarded owing to toxicity. Recently, artificial intelligence (AI) has been used to improve drug toxicity prediction as it provides more accurate and efficient methods for identifying the potentially toxic effects of new compounds before they are tested in human clinical trials, thus saving time and money. In this review, we present an overview of recent advances in AI-based drug toxicity prediction, including the use of various machine learning algorithms and deep learning architectures, of six major toxicity properties and Tox21 assay end points. Additionally, we provide a list of public data sources and useful toxicity prediction tools for the research community and highlight the challenges that must be addressed to enhance model performance. Finally, we discuss future perspectives for AI-based drug toxicity prediction. This review can aid researchers in understanding toxicity prediction and pave the way for new methods of drug discovery.

Using Machine Learning to make nanomaterials sustainable

Sustainable development is a key challenge for contemporary human societies; failure to achieve sustainability could threaten human survival. In this review article, we illustrate how Machine Learning (ML) could support more sustainable development, covering the basics of data gathering through each step of the Environmental Risk Assessment (ERA). The literature provides several examples showing how ML can be employed in most steps of a typical ERA.A key observation is that there are currently no clear guidance for using such autonomous technologies in ERAs or which standards/checks are required. Steering thus seems to be the most important task for supporting the use of ML in the ERA of nano- and smart-materials. Resources should be devoted to developing a strategy for implementing ML in ERA with a strong emphasis on data foundations, methodologies, and the related sensitivities/uncertainties. We should recognise historical errors and biases (e.g., in data) to avoid embedding them during ML programming.

CSM-Toxin: A Web-Server for Predicting Protein Toxicity

Biologics are one of the most rapidly expanding classes of therapeutics, but can be associated with a range of toxic properties. In small-molecule drug development, early identification of potential toxicity led to a significant reduction in clinical trial failures, however we currently lack robust qualitative rules or predictive tools for peptide- and protein-based biologics. To address this, we have manually curated the largest set of high-quality experimental data on peptide and protein toxicities, and developed CSM-Toxin, a novel in-silico protein toxicity classifier, which relies solely on the protein primary sequence. Our approach encodes the protein sequence information using a deep learning natural languages model to understand "biological" language, where residues are treated as words and protein sequences as sentences. The CSM-Toxin was able to accurately identify peptides and proteins with potential toxicity, achieving an MCC of up to 0.66 across both cross-validation and multiple non-redundant blind tests, outperforming other methods and highlighting the robust and generalisable performance of our model. We strongly believe the CSM-Toxin will serve as a valuable platform to minimise potential toxicity in the biologic development pipeline. Our method is freely available as an easy-to-use webserver.

A New Anticancer Semisynthetic Theobromine Derivative Targeting EGFR Protein: CADDD Study

A new lead compound has been designed as an antiangiogenic EGFR inhibitor that has the pharmacophoric characteristics to bind with the catalytic pocket of EGFR protein. The designed lead compound is a (para-chloro)acetamide derivative of the alkaloid, theobromine, (T-1-PCPA). At first, we started with deep density functional theory (DFT) calculations for T-1-PCPA to confirm and optimize its 3D structure. Additionally, the DFT studies identified the electrostatic potential, global reactive indices and total density of states expecting a high level of reactivity for T-1-PCPA. Secondly, the affinity of T-1-PCPA to bind and inhibit the EGFR protein was studied and confirmed through detailed structure-based computational studies including the molecular docking against EGFR^WT and EGFR^T790M, Molecular dynamics (MD) over 100 ns, MM-GPSA and PLIP experiments. Before the preparation, the computational ADME and toxicity profiles of T-1-PCPA have been investigated and its safety and the general drug-likeness predicted. Accordingly, T-1-PCPA was semi-synthesized to scrutinize the proposed design and the obtained in silico results. Interestingly, T-1-PCPA inhibited in vitro EGFR^WT with an IC₅₀ value of 25.35 nM, comparing that of erlotinib (5.90 nM). Additionally, T-1-PCPA inhibited the growth of A549 and HCT-116 malignant cell lines with IC₅₀ values of 31.74 and 20.40 µM, respectively, comparing erlotinib that expressed IC₅₀ values of 6.73 and 16.35 µM, respectively.

Anticancer derivative of the natural alkaloid, theobromine, inhibiting EGFR protein: Computer-aided drug discovery approach

A new semisynthetic derivative of the natural alkaloid, theobromine, has been designed as a lead antiangiogenic compound targeting the EGFR protein. The designed compound is an (m-tolyl)acetamide theobromine derivative, (T-1-MTA). Molecular Docking studies have shown a great potential for T-1-MTA to bind to EGFR. MD studies (100 ns) verified the proposed binding. By MM-GBSA analysis, the exact binding with optimal energy of T-1-MTA was also identified. Then, DFT calculations were performed to identify the stability, reactivity, electrostatic potential, and total electron density of T-1-MTA. Furthermore, ADMET analysis indicated the T-1-MTA's general likeness and safety. Accordingly, T-1-MTA has been synthesized to be examined in vitro. Intriguingly, T-1-MTA inhibited the EGFR protein with an IC50 value of 22.89 nM and demonstrated cytotoxic activities against the two cancer cell lines, A549, and HCT-116, with IC50 values of 22.49, and 24.97 μM, respectively. Interestingly, T-1-MTA's IC50 against the normal cell lines, WI-38, was very high (55.14 μM) indicating high selectivity degrees of 2.4 and 2.2, respectively. Furthermore, the flow cytometry analysis of A549 treated with T-1-MTA showed significantly increased ratios of early apoptosis (from 0.07% to 21.24%) as well as late apoptosis (from 0.73% to 37.97%).

Design, Molecular Modeling, MD Simulations, Essential Dynamics, ADMET, DFT, Synthesis, Anti-proliferative, and Apoptotic Evaluations of a New Anti-VEGFR-2 Nicotinamide Analogue

OBJECTIVES

This study aims to design and evaluate (in silico and in vitro) a new nicotinamide derivative as an inhibitor of VEGFR-2, a major mediator of angiogenesis Methods: The following in silico studies were performed; DFT calculations, molecular modelling, MD simulations, MM-GBSA, PLIP, and PCAT studies. The compound's in silico (ADMET) analysis was also conducted. Subsequently, the compound ((E)-N-(4-(1-(2-(4-(4-Chlorobenzamido)benzoyl)hydrazono)ethyl) phenyl)nicotinamide) was successfully synthesized and designated as compound X. In vitro, VEGFR-2 inhibition and cytotoxicity of compound X against HCT-116 and A549 cancer cell lines and normal Vero cell lines were conducted. Apoptosis induction and migration assay of HCT-116 cell lines after treatment with compound X were also evaluated.

RESULTS

DFT calculations assigned stability and reactivity of compound X. Molecular docking and MD simulations indicated its excellent binding against VEGFR-2. Furthermore, MM-GBSA analysis, PLIP experiments, and PCAT studies confirmed compound X's correct binding with optimal dynamics and energy. ADMET analysis expressed its general likeness and safety. The in vitro assays demonstrated that compound X effectively inhibited VEGFR-2, with an IC50 value of 0.319 ± 0.013 μM and displayed cytotoxicity against HCT-116 and A549 cancer cell lines, with IC50 values of 57.93 and 78.82 μM, respectively. Importantly, compound X exhibited minimal toxicity towards the non-cancerous Vero cell lines, (IC50 = 164.12 μM). Additionally, compound X significantly induced apoptosis of HCT-116 cell lines and inhibited their potential to migrate and heal.

CONCLUSION

In summary, the presented study has identified compound X as a promising candidate for the development of a novel apoptotic lead anticancer drug.

Traditional Machine and Deep Learning for Predicting Toxicity Endpoints

Molecular structure property modeling is an increasingly important tool for predicting compounds with desired properties due to the expensive and resource-intensive nature and the problem of toxicity-related attrition in late phases during drug discovery and development. Lately, the interest for applying deep learning techniques has increased considerably. This investigation compares the traditional physico-chemical descriptor and machine learning-based approaches through autoencoder generated descriptors to two different descriptor-free, Simplified Molecular Input Line Entry System (SMILES) based, deep learning architectures of Bidirectional Encoder Representations from Transformers (BERT) type using the Mondrian aggregated conformal prediction method as overarching framework. The results show for the binary CATMoS non-toxic and very-toxic datasets that for the former, almost equally balanced, dataset all methods perform equally well while for the latter dataset, with an 11-fold difference between the two classes, the MolBERT model based on a large pre-trained network performs somewhat better compared to the rest with high efficiency for both classes (0.93-0.94) as well as high values for sensitivity, specificity and balanced accuracy (0.86-0.87). The descriptor-free, SMILES-based, deep learning BERT architectures seem capable of producing well-balanced predictive models with defined applicability domains. This work also demonstrates that the class imbalance problem is gracefully handled through the use of Mondrian conformal prediction without the use of over- and/or under-sampling, weighting of classes or cost-sensitive methods.

Applications of In Silico Models to Predict Drug-Induced Liver Injury

Drug-induced liver injury (DILI) is a major cause of the withdrawal of pre-marketed drugs, typically attributed to oxidative stress, mitochondrial damage, disrupted bile acid homeostasis, and innate immune-related inflammation. DILI can be divided into intrinsic and idiosyncratic DILI with cholestatic liver injury as an important manifestation. The diagnosis of DILI remains a challenge today and relies on clinical judgment and knowledge of the insulting agent. Early prediction of hepatotoxicity is an important but still unfulfilled component of drug development. In response, in silico modeling has shown good potential to fill the missing puzzle. Computer algorithms, with machine learning and artificial intelligence as a representative, can be established to initiate a reaction on the given condition to predict DILI. DILIsym is a mechanistic approach that integrates physiologically based pharmacokinetic modeling with the mechanisms of hepatoxicity and has gained increasing popularity for DILI prediction. This article reviews existing in silico approaches utilized to predict DILI risks in clinical medication and provides an overview of the underlying principles and related practical applications.

The Discovery of Potential SARS-CoV-2 Natural Inhibitors among 4924 African Metabolites Targeting the Papain-like Protease: A Multi-Phase In Silico Approach

Four compounds, hippacine, 4,2'-dihydroxy-4'-methoxychalcone, 2',5'-dihydroxy-4-methoxychalcone, and wighteone, were selected from 4924 African natural metabolites as potential inhibitors against SARS-CoV-2 papain-like protease (PLpro, PDB ID: 3E9S). A multi-phased in silico approach was employed to select the most similar metabolites to the co-crystallized ligand (TTT) of the PLpro through molecular fingerprints and structural similarity studies. Followingly, to examine the binding of the selected metabolites with the PLpro (molecular docking. Further, to confirm this binding through molecular dynamics simulations. Finally, in silico ADMET and toxicity studies were carried out to prefer the most convenient compounds and their drug-likeness. The obtained results could be a weapon in the battle against COVID-19 via more in vitro and in vivo studies.

MS2Tox Machine Learning Tool for Predicting the Ecotoxicity of Unidentified Chemicals in Water by Nontarget LC-HRMS

To achieve water quality objectives of the zero pollution action plan in Europe, rapid methods are needed to identify the presence of toxic substances in complex water samples. However, only a small fraction of chemicals detected with nontarget high-resolution mass spectrometry can be identified, and fewer have ecotoxicological data available. We hypothesized that ecotoxicological data could be predicted for unknown molecular features in data-rich high-resolution mass spectrometry (HRMS) spectra, thereby circumventing time-consuming steps of molecular identification and rapidly flagging molecules of potentially high toxicity in complex samples. Here, we present MS2Tox, a machine learning method, to predict the toxicity of unidentified chemicals based on high-resolution accurate mass tandem mass spectra (MS²). The MS2Tox model for fish toxicity was trained and tested on 647 lethal concentration (LC₅₀) values from the CompTox database and validated for 219 chemicals and 420 MS² spectra from MassBank. The root mean square error (RMSE) of MS2Tox predictions was below 0.89 log-mM, while the experimental repeatability of LC₅₀ values in CompTox was 0.44 log-mM. MS2Tox allowed accurate prediction of fish LC₅₀ values for 22 chemicals detected in water samples, and empirical evidence suggested the right directionality for another 68 chemicals. Moreover, by incorporating structural information, e.g., the presence of carbonyl-benzene, amide moieties, or hydroxyl groups, MS2Tox outperforms baseline models that use only the exact mass or log K_OW.

(E)-N-(3-(1-(2-(4-(2,2,2-Trifluoroacetamido)benzoyl)hydrazono)ethyl)phenyl)nicotinamide: A Novel Pyridine Derivative for Inhibiting Vascular Endothelial Growth Factor Receptor-2: Synthesis, Computational, and Anticancer Studies

(E)-N-(3-(1-(2-(4-(2,2,2-Trifluoroacetamido)benzoyl)hydrazono)ethyl)phenyl)nicotinamide (compound 10) was designed as an antiangiogenic VEGFR-2 inhibitor with the essential pharmacophoric structural properties to interact with the catalytic pocket of VEGFR-2. The designed derivative was synthesized, and its structure was confirmed through Ms, elemental, ¹H, and ¹³C spectral data. The potentiality of the designed pyridine derivative to bind with and inhibit the vascular endothelial growth factor receptor-2 (VEGFR-2) enzyme was indicated by molecular docking assessments. In addition, six molecular dynamic (MD) experiments proved its correct binding with VEGFR-2 over 100 ns. Additionally, the molecular mechanics energies, combined with the generalized born and surface area (MM-GBSA) analysis, identified the precise binding with optimum energy. To explore the stability and reactivity of the designed pyridine derivative, density functional theory (DFT) calculations, including electrostatic potential maps and total electron density, were carried out. Additionally, the absorption, distribution, metabolism, excretion, and toxicity (ADMET) analysis demonstrated its general likeness and its safety. The designed compound was synthesized to evaluate its effects against VEGFR-2 protein, cancer, and normal cells. The in vitro results were concordant with the in silico results, because the new pyridine derivative (compound 10) displayed VEGFR-2 inhibition with an IC₅₀ value of 65 nM and displayed potent cytotoxic properties against hepatic (HepG2) and breast (MCF-7) cancer cell lines with IC₅₀ values of 21.00 and 26.10 μM, respectively; additionally, it exhibited high selectivity indices against the normal cell lines (W-38) of 1.55 and 1.25, respectively. The obtained results present compound 10 as a new lead VEGFR-2 inhibitor for further biological investigation and chemical modifications.

A New Theobromine-Based EGFRWT and EGFRT790M Inhibitor and Apoptosis Inducer: Design, Semi-Synthesis, Docking, DFT, MD Simulations, and In Vitro Studies

The essential pharmacophoric structural properties were applied to design a new derivative of theobromine as an antiangiogenic EGFR inhibitor. The designed candidate is a (para-nitrophenyl)acetamide derivative of the natural alkaloid, theobromine (T-2-PNPA). The potentialities of T-2-PNPA to inhibit the EGFR protein were studied computationally in an extensive way. Firstly, the molecular docking against EGFRWT and EGFRT790M demonstrated T-2-PNPA’s capabilities of binding with the targeted receptors. Then, the MD experiments (for 100 ns) illustrated through six different studies the changes that occurred in the energy as well as in the structure of EGFR–T-2-PNPA complex. Additionally, an MM-GBSA analysis determined the exact energy of binding and the essential residues. Furthermore, DFT calculations investigated the stability, reactivity, and electrostatic potential of T-2-PNPA. Finally, ADMET and toxicity studies confirmed both the safety as well as the general likeness of T-2-PNPA. Consequently, T-2-PNPA was prepared for the in vitro biological studies. T-2-PNPA inhibited EGFRWT and EGFRT790M with IC50 values of 7.05 and 126.20 nM, respectively, which is comparable with erlotinib activities (5.91 and 202.40, respectively). Interestingly, T-2-PNPA expressed cytotoxic potentialities against A549 and HCT-116 cells with IC50 values of 11.09 and 21.01 µM, respectively, which is again comparable with erlotinib activities (6.73 and 16.35, respectively). T-2-PNPA was much safer against WI-38 (IC50 = 48.06 µM) than erlotinib (IC50 = 31.17 µM). The calculated selectivity indices of T-2-PNPA against A549 and HCT-116 cells were 4.3 and 2.3, respectively. This manuscript presents a new lead anticancer compound (T-2-PNPA) that has been synthesized for the first time and exhibited promising in silico and in vitro anticancer potentialities.

New Anticancer Theobromine Derivative Targeting EGFRWT and EGFRT790M: Design, Semi-Synthesis, In Silico, and In Vitro Anticancer Studies

Based on the pharmacophoric features of EGFR inhibitors, a new semisynthetic theobromine-derived compound was designed to interact with the catalytic pocket of EGFR. Molecular docking against wild (EGFR^WT; PDB: 4HJO) and mutant (EGFR^T790M; PDB: 3W2O) types of EGFR-TK indicated that the designed theobromine derivative had the potential to bind to that pocket as an antiangiogenic inhibitor. The MD and MM-GBSA experiments identified the exact binding with optimum energy and dynamics. Additionally, the DFT calculations studied electrostatic potential, stability, and total electron density of the designed theobromine derivative. Both in silico ADMET and toxicity analyses demonstrated its general likeness and safety. We synthesized the designed theobromine derivative (compound XI) which showed an IC₅₀ value of 17.23 nM for EGFR inhibition besides IC₅₀ values of 21.99 and 22.02 µM for its cytotoxicity against A549 and HCT-116 cell lines, respectively. Interestingly, compound XI expressed a weak cytotoxic potential against the healthy W138 cell line (IC₅₀ = 49.44 µM, 1.6 times safer than erlotinib), exhibiting the high selectivity index of 2.2. Compound XI arrested the growth of A549 at the G2/M stage and increased the incidence of apoptosis.

Structure-Based Virtual Screening, Docking, ADMET, Molecular Dynamics, and MM-PBSA Calculations for the Discovery of Potential Natural SARS-CoV-2 Helicase Inhibitors from the Traditional Chinese Medicine

Continuing our antecedent work against COVID-19, a set of 5956 compounds of traditional Chinese medicine have been virtually screened for their potential against SARS-CoV-2 helicase (PDB ID: 5RMM). Initially, a fingerprint study with VXG, the ligand of the target enzyme, disclosed the similarity of 187 compounds. Then, a molecular similarity study declared the most similar 40 compounds. Subsequently, molecular docking studies were carried out to examine the binding modes and energies. Then, the most appropriate 26 compounds were subjected to in silico ADMET and toxicity studies to select the most convenient inhibitors to be: (1R,2S)-ephedrine (57), (1R,2S)-norephedrine (59), 2-(4-(pyrrolidin-1-yl)phenyl)acetic acid (84), 1-phenylpropane-1,2-dione (195), 2-methoxycinnamic acid (246), 2-methoxybenzoic acid (364), (R)-2-((R)-5-oxopyrrolidin-3-yl)-2-phenylacetic acid (405), (Z)-6-(3-hydroxy-4-methoxystyryl)-4-methoxy-2H-pyran-2-one (533), 8-chloro-2-(2-phenylethyl)-5,6,7-trihydroxy-5,6,7,8-tetrahydrochromone (637), 3-((1R,2S)-2-(dimethylamino)-1-hydroxypropyl)phenol (818), (R)-2-ethyl-4-(1-hydroxy-2-(methylamino)ethyl)phenol (5159), and (R)-2-((1S,2S,5S)-2-benzyl-5-hydroxy-4-methylcyclohex-3-en-1-yl)propane-1,2-diol (5168). Among the selected 12 compounds, the metabolites, compound 533 showed the best docking scores. Interestingly, the MD simulation studies for compound 533, the one with the highest docking score, over 100 ns showed its correct binding to SARS-CoV-2 helicase with low energy and optimum dynamics. Finally, MM-PBSA studies showed that 533 bonded favorably to SARS-CoV-2 helicase with a free energy value of −83 kJ/mol. Further, the free energy decomposition study determined the essential amino acid residues that contributed favorably to the binding process. The obtained results give a huge hope to find a cure for COVID-19 through further in vitro and in vivo studies for the selected compounds.

Using Jupyter Notebooks for re-training machine learning models

Machine learning (ML) models require an extensive, user-driven selection of molecular descriptors in order to learn from chemical structures to predict actives and inactives with a high reliability. In addition, privacy concerns often restrict the access to sufficient data, leading to models with a narrow chemical space. Therefore, we propose a framework of re-trainable models that can be transferred from one local instance to another, and further allow a less extensive descriptor selection. The models are shared via a Jupyter Notebook, allowing the evaluation and implementation of a broader chemical space by keeping most of the tunable parameters pre-defined. This enables the models to be updated in a decentralized, facile, and fast manner. Herein, the method was evaluated with six transporter datasets (BCRP, BSEP, OATP1B1, OATP1B3, MRP3, P-gp), which revealed the general applicability of this approach.

The Computational Preventive Potential of the Rare Flavonoid, Patuletin, Isolated from Tagetes patula, against SARS-CoV-2

The rare flavonoid, patuletin, was isolated from the flowers of Tagetes patula growing in Egypt. The rarity of the isolated compound inspired us to scrutinize its preventive effect against COVID-19 utilizing a multi-step computational approach. Firstly, a structural similarity study was carried out against nine ligands of nine SARS-CoV-2 proteins. The results showed a large structural similarity between patuletin and F86, the ligand of SARS-CoV-2 RNA-dependent RNA polymerase (RdRp). Then, a 3D-Flexible alignment study of patuletin and F86 verified the proposed similarity. To determine the binding opportunity, patuletin was docked against the RdRp showing a correct binding inside its active pocket with an energy of −20 kcal/mol that was comparable to that of F86 (−23 kcal/mol). Following, several MD simulations as well as MM-PBSA studies authenticated the accurate binding of patuletin in the RdRp via the correct dynamic and energetic behaviors over 100 ns. Additionally, in silico ADMET studies showed the general safety and drug-likeness of patuletin.

Orthogonal assay for validation of Tox21 PPARγ data and applicability to in silico prediction model

High-throughput screening data from the Tox21 database is used for prioritizing hazardous chemicals and building in silico-based toxicity prediction models. One of the Tox21 dataset, peroxisome proliferator-activated receptor-gamma (PPARγ), a nuclear receptor superfamily, identified various endpoints in HEK293 cells. PPARγ mediates various toxic effects when its receptors are activated or inhibited by ligands such as thiazolidinedione and GW9662. In this study, an orthogonal assay was constructed to verify the effectiveness of the Tox21 PPARγ data, and the effect of highly reliable data on in silico model construction was investigated. The orthogonal assay was a reporter gene assay based on the PPARγ ligand binding domain in CV-1 cells. Only 39% of agonists and 55% of antagonists had similar responses in CV-1 and HEK293 cells. Thus, the effectiveness of Tox21 data on PPARγ may vary depending on the cell line. However, in silico PLS-DA analysis with only high-reliability data (i.e., the same response in both cell lines), yielded more accurate prediction of the activity of potential chemical ligands, despite the small number of samples. Thus, obtaining reliable chemical screening data for PPARγ through orthogonal analysis, even for only limited chemicals, supports the construction of highly predictive in silico models with improved screening efficiency.

Studying and mitigating the effects of data drifts on ML model performance at the example of chemical toxicity data

Machine learning models are widely applied to predict molecular properties or the biological activity of small molecules on a specific protein. Models can be integrated in a conformal prediction (CP) framework which adds a calibration step to estimate the confidence of the predictions. CP models present the advantage of ensuring a predefined error rate under the assumption that test and calibration set are exchangeable. In cases where the test data have drifted away from the descriptor space of the training data, or where assay setups have changed, this assumption might not be fulfilled and the models are not guaranteed to be valid. In this study, the performance of internally valid CP models when applied to either newer time-split data or to external data was evaluated. In detail, temporal data drifts were analysed based on twelve datasets from the ChEMBL database. In addition, discrepancies between models trained on publicly-available data and applied to proprietary data for the liver toxicity and MNT in vivo endpoints were investigated. In most cases, a drastic decrease in the validity of the models was observed when applied to the time-split or external (holdout) test sets. To overcome the decrease in model validity, a strategy for updating the calibration set with data more similar to the holdout set was investigated. Updating the calibration set generally improved the validity, restoring it completely to its expected value in many cases. The restored validity is the first requisite for applying the CP models with confidence. However, the increased validity comes at the cost of a decrease in model efficiency, as more predictions are identified as inconclusive. This study presents a strategy to recalibrate CP models to mitigate the effects of data drifts. Updating the calibration sets without having to retrain the model has proven to be a useful approach to restore the validity of most models.

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.

Ecological risk assessment for difenoconazole in aquatic ecosystems using a web-based interspecies correlation estimation (ICE)-species sensitivity distribution (SSD) model

Difenoconazole is a typical triazole fungicide that can inhibit demethylation during ergosterol synthesis. Due to its wide use, difenoconazole is frequently detected in surface water, paddy water, agricultural water, and other aquatic environments. Presently, an assessment of the ecological risk posed by difenoconazole in aquatic ecosystems is lacking. Here, a web-based interspecies correlation estimation (ICE)-species sensitivity distribution (SSD) model was first applied to assess the ecological risk of difenoconazole in aquatic environments. Meanwhile, maximum acceptable concentration (MAC), maximum risk-free concentration (MRFC), and risk quotient (RQ) values were used to evaluate the potential risk of difenoconazole to aquatic organisms. Our results showed that an aquatic MAC value of 0.31 μg/L was acceptable for difenoconazole in aquatic environments. Further, the detected concentration of difenoconazole was lower than the MRFC value of 0.09 μg/L indicating no risk to aquatic organisms. Assessment data suggested that difenoconazole exhibited potential risks to eight studied aquatic ecosystems (including surface water, paddy water, and agricultural water) in different countries (RQ > 1), indicating that difenoconazole overuse could cause adverse effects to aquatic organisms in these aquatic ecosystems. Thus, restricted use and rational use of difenoconazole are recommended.

Machine Learning Models for Predicting Cytotoxicity of Nanomaterials

The wide application of nanomaterials in consumer and medical products has raised concerns about their potential adverse effects on human health. Thus, more and more biological assessments regarding the toxicity of nanomaterials have been performed. However, the different ways the evaluations were performed, such as the utilized assays, cell lines, and the differences of the produced nanoparticles, make it difficult for scientists to analyze and effectively compare toxicities of nanomaterials. Fortunately, machine learning has emerged as a powerful tool for the prediction of nanotoxicity based on the available data. Among different types of toxicity assessments, nanomaterial cytotoxicity was the focus here because of the high sensitivity of cytotoxicity assessment to different treatments without the need for complicated and time-consuming procedures. In this review, we summarized recent studies that focused on the development of machine learning models for prediction of cytotoxicity of nanomaterials. The goal was to provide insight into predicting potential nanomaterial toxicity and promoting the development of safe nanomaterials.

Joint Decision-Making Model Based on Consensus Modeling Technology for the Prediction of Drug-Induced Liver Injury

Drug-induced liver injury (DILI) is the major cause of clinical trial failure and postmarketing withdrawals of approved drugs. It is very expensive and time-consuming to evaluate hepatotoxicity using animal or cell-based experiments in the early stage of drug development. In this study, an in silico model based on the joint decision-making strategy was developed for DILI assessment using a relatively large dataset of 2608 compounds. Five consensus models were developed with PaDEL descriptors and PubChem, Substructure, Estate, and Klekota–Roth fingerprints, respectively. Submodels for each consensus model were obtained through joint optimization. The parameters and features of each submodel were optimized jointly based on the hybrid quantum particle swarm optimization (HQPSO) algorithm. The application domain (AD) based on the frequency-weighted and distance (FWD)-based method and Tanimoto similarity index showed the wide AD of the qualified consensus models. A joint decision-making model was integrated by the qualified consensus models, and the overwhelming majority principle was used to improve the performance of consensus models. The application scope narrowing caused by the overwhelming majority principle was successfully solved by joint decision-making. The proposed model successfully predicted 99.2% of the compounds in the test set, with an accuracy of 80.0%, a sensitivity of 83.9, and a specificity of 73.3%. For an external validation set containing 390 compounds collected from DILIrank, 98.2% of the compounds were successfully predicted with an accuracy of 79.9%, a sensitivity of 97.1%, and a specificity of 66.0%. Furthermore, 25 privileged substructures responsible for DILI were identified from Substructure, PubChem, and Klekota–Roth fingerprints. These privileged substructures can be regarded as structural alerts in hepatotoxicity evaluation. Compared with the main published studies, our method exhibits certain advantage in data size, transparency, and standardization of the modeling process and accuracy and credibility of prediction results. It is a promising tool for virtual screening in the early stage of drug development.