Predicting chemically-induced skin reactions. Part I: QSAR models of skin sensitization and their application to identify potentially hazardous compounds

Predictive classification-based read-across for diverse functional vitiligo-linked chemical exposomes (ViCE): A new approach for the assessment of chemical safety for the vitiligo disease in humans

We have explored a new approach using a similarity measure-based read-across derived hypothesis to address the precise risk assessment of vitiligo active chemicals. In this analysis, we initially prepared a data set by combining vitiligo active compounds taken from the previous literature with non-vitiligo chemicals, which are non-skin sensitizers reported in another literature. Afterward, we performed the manual curation process to obtain a curated dataset. Furthermore, the optimum similarity measure was identified from a validation set using a pool of 47 descriptors from the analysis of the most discriminating features. The identified optimum similarity measure (i.e., Euclidean distance-based similarity along with seven close source compounds) has been utilized in the read-across derived similarity-based classification studies on close source congeners concerning target compounds. In this study, we identified the positive and negative contributing features toward the assessment of vitiligo potential as well, including the estimation of target chemicals with better accuracy. The applicability domain status of the reported compounds was also studied, and the outliers were identified. As there are no comparative studies in this regard to the best of our knowledge, we can further affirm that it is the first report on the in-silico identification of potential vitiligo-linked chemical exposomes (ViCE) based on the similarity measure of the read-across.

Prediction and Prioritisation of Novel Anthelmintic Candidates from Public Databases Using Deep Learning and Available Bioactivity Data Sets

The control of socioeconomically important parasitic roundworms (nematodes) of animals has become challenging or ineffective due to problems associated with widespread resistance in these worms to most classes of chemotherapeutic drugs (anthelmintics) currently available. Thus, there is an urgent need to discover and develop novel compounds with unique mechanisms of action to underpin effective parasite control programmes. Here, we evaluated an in silico (computational) approach to accelerate the discovery of new anthelmintics against the parasitic nematode Haemonchus contortus (barber's pole worm) as a model system. Using a supervised machine learning workflow, we trained and assessed a multi-layer perceptron classifier on a labelled dataset of 15,000 small-molecule compounds, for which extensive bioactivity data were previously obtained for H. contortus via high-throughput screening, as well as evidence-based datasets from the peer-reviewed literature. This model achieved 83% precision and 81% recall on the class of 'active' compounds during testing, despite a high imbalance in the training data, with only 1% of compounds carrying this label. The trained model was then used to infer nematocidal candidates by in silico screening of 14.2 million compounds from the ZINC15 database. An experimental assessment of 10 of these candidates showed significant inhibitory effects on the motility and development of H. contortus larvae and adults in vitro, with two compounds exhibiting high potency for further exploration as lead candidates. These findings indicate that the present machine learning-based approach could accelerate the in silico prediction and prioritisation of anthelmintic small molecules for subsequent in vitro and in vivo validations.

Bidirectional Long Short-Term Memory (BiLSTM) Neural Networks with Conjoint Fingerprints: Application in Predicting Skin-Sensitizing Agents in Natural Compounds

Skin sensitization, or allergic contact dermatitis, represents a critical end point in toxicity assessment, with profound implications for drug safety and regulatory decision-making. This study aims to develop a robust deep-learning-based quantitative structure-activity relationship framework for accurately predicting skin sensitization toxicity, particularly in the context of natural-product-derived compounds. To achieve this, we explored advanced recurrent neural network architectures, including long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and bidirectional GRU, to model the intricate structure-toxicity relationships inherent in molecular compounds. We aim to optimize and improve predictive performance by training a cohort of 55 models with a diverse set of molecular fingerprints. Notably, the BiLSTM model, which integrates SMILES tokens with RDKit fingerprints, achieved superior predictive performance, underscoring its capability to effectively capture key molecular determinants of skin sensitization. An extensive applicability domain analysis coupled with an in-depth evaluation of feature importance provided new insights into the key molecular attributes that influence sensitization propensity. We further evaluated the BiLSTM model using a natural product data set, where it demonstrated exceptional generalization capabilities. The model achieved an accuracy of 86.5%, a Matthews correlation coefficient of 75.2%, a sensitivity of 100%, an area under the curve of 88%, a specificity of 75%, and an F1-score of 88.8%. Remarkably, the model effectively categorized natural products by discriminating sensitizing from non-sensitizing agents across various natural product subcategories. These results underscore the potential of BiLSTM-based models as powerful in silico tools for modern drug discovery efforts and regulatory assessments, especially in the field of natural products.

An Integrated Fuzzy Neural Network and Topological Data Analysis for Molecular Graph Representation Learning and Property Forecasting

Within a recent decade, graph neural network (GNN) has emerged as a powerful neural architecture for various graph-structured data modelling and task-driven representation learning problems. Recent studies have highlighted the remarkable capabilities of GNNs in handling complex graph representation learning tasks, achieving state-of-the-art results in node/graph classification, regression, and generation. However, most traditional GNN-based architectures like GCN and GraphSAGE still faced several challenges related to the capability of preserving the multi-scaled topological structures. These models primarily focus on capturing local neighborhood information, often failing to retain global structural features essential for graph-level representation and classification tasks. Furthermore, their expressiveness is limited when learning topological structures in complex molecular graph datasets. To overcome these limitations, in this paper, we proposed a novel graph neural architecture which is an integration between neuro-fuzzy network and topological graph learning approach, naming as: FTPG. Specifically, within our proposed FTPG model, we introduce a novel approach to molecular graph representation and property prediction by integrating multi-scaled topological graph learning with advanced neural components. The architecture employs separate graph neural learning modules to effectively capture both local graph-based structures as well as global topological features. Moreover, to further address feature uncertainty in the global-view representation, a multi-layered neuro-fuzzy network is incorporated within our model to enhance the robustness and expressiveness of the learned molecular graph embeddings. This combinatorial approach can assist to leverage the strengths of multi-view and multi-modal neural learning, enabling FTPG to deliver superior performance in molecular graph tasks. Extensive experiments on real-world/benchmark molecular datasets demonstrate the effectiveness of our proposed FTPG model. It consistently outperforms state-of-the-art GNN-based baselines categorized in different approaches, including canonical local proximity message passing based, graph transformer-based, and topology-driven approaches.

A Novel Machine Learning Model and a Web Portal for Predicting the Human Skin Sensitization Effects of Chemical Agents

Skin sensitization is a significant concern for chemical safety assessments. Traditional animal assays often fail to predict human responses accurately, and ethical constraints limit the collection of human data, necessitating a need for reliable in silico models of skin sensitization prediction. This study introduces HuSSPred, an in silico tool based on the Human Predictive Patch Test (HPPT). HuSSPred aims to enhance the reliability of predicting human skin sensitization effects for chemical agents to support their regulatory assessment. We have curated an extensive HPPT database and performed chemical space analysis and grouping. Binary and multiclass QSAR models were developed with Bayesian hyperparameter optimization. Model performance was evaluated via five-fold cross-validation. We performed model validation with reference data from the Defined Approaches for Skin Sensitization (DASS) app. HuSSPred models demonstrated strong predictive performance with CCR ranging from 55 to 88%, sensitivity between 48 and 89%, and specificity between 37 and 92%. The positive predictive value (PPV) ranged from 84 to 97%, versus negative predictive value (NPV) from 22 to 65%, and coverage was between 75 and 93%. Our models exhibited comparable or improved performance compared to existing tools, and the external validation showed the high accuracy and sensitivity of the developed models. HuSSPred provides a reliable, open-access, and ethical alternative to traditional testing for skin sensitization. Its high accuracy and reasonable coverage make it a valuable resource for regulatory assessments, aligning with the 3Rs principles. The publicly accessible HuSSPred web tool offers a user-friendly interface for predicting skin sensitization based on chemical structure.

Identification of metabolites from the gut microbiota in hypertension via network pharmacology and molecular docking

Hypertension is the most prevalent cardiovascular disease, affecting one-third of adults. All antihypertensive drugs have potential side effects. Gut metabolites influence hypertension. The objective of this study was to identify antihypertensive gut metabolites through network pharmacology and molecular docking techniques and to validate their antihypertensive mechanisms via in vitro experiments. A total of 10 core antihypertensive targets and 18 gut metabolites that act on hypertension were identified. Four groups of protein metabolites, namely, CXCL8-baicalein, CXCL8-baicalin, CYP1A1-urolithin A, and PTGS2-equol, which have binding energies of - 7.7, - 8.5, - 7.2, and - 8.8 kcal-mol-1, respectively, were found to have relatively high affinities. Based on its drug-likeness properties in silico and toxicological properties, equol was identified as a potential antihypertensive metabolite. On the basis of the results of network pharmacology and molecular docking, equol may exert antihypertensive effects by regulating the IL-17 signaling pathway and PTGS2. A phenylephrine-induced H9c2 cell model was subsequently utilized to verify that equol inhibits cell hypertrophy (P < 0.05) by inhibiting the IL-17 signaling pathway and PTGS2 (P < 0.05). This study demonstrated that equol has the potential to be developed as a novel therapeutic agent for the treatment of hypertension.

In Silico Prediction of Skin Sensitization for Compounds via Flexible Evidence Combination Based on Machine Learning and Dempster-Shafer Theory

Skin sensitization is increasingly becoming a significant concern in the development of drugs and cosmetics due to consumer safety and occupational health problems. In silico methods have emerged as alternatives to traditional in vivo animal testing due to ethical and economic considerations. In this study, machine learning methods were used to build quantitative structure-activity relationship (QSAR) models on five skin sensitization data sets (GPMT, LLNA, DPRA, KeratinoSens, and h-CLAT), achieving effective predictive accuracies (correct classification rates of 0.688-0.764 on test sets). To address the complex mechanisms of human skin sensitization, the Dempster-Shafer theory was applied to merge multiple QSAR models, resulting in an evidence-based integrated decision model. Various evidence combinations and combination rules were explored, with the self-defined Q3 rule showing superior balance. The combination of evidence such as GPMT and KeratinoSens and h-CLAT achieved a correct classification rate (CCR) of 0.880 and coverage of 0.893 while maintaining the competitiveness of other combinations. Additionally, the Shapley additive explanations (SHAP) method was used to interpret important features and substructures related to skin sensitization. A comparative analysis of an external human test set demonstrated the superior performance of the proposed method. Finally, to enhance accessibility, the workflow was implemented into a user-friendly software named HSkinSensDS.

2-Hydroxymethyl-18-crown-6 as an efficient organocatalyst for α-aminophosphonates synthesized under eco-friendly conditions, DFT, molecular docking and ADME/T studies

Eco-friendly and simple procedure has been developed for the synthesis of α-aminophosphonates that act as topoisomerase II α-inhibiting anticancer agent, using 2-hydroxymethyl-18-crown-6 as an unexpected homogeneous organocatalyst in multicomponents reaction of aromatic aldehyde, aniline and diethylphosphite in one pot via Kabachnik-Fields reaction. This efficient method proceeds with catalytic amount, transition metal-free, at room temperature within short reaction time, giving the α-aminophosphonates derivatives (4a-r) in high chemical yields (up to 80%). Theoretical DFT calculations of three compounds (4p, 4q and 4r) were carried out in a gas phase at CAM-B3LYP 6-31G (d,p) basis set to predict the molecular geometries and chemical reactivity descriptors. The frontier orbital energies (HOMO/LUMO) were described the charge transfer and used to predict structure-activity relationship study. Molecular electrostatic potential (MEP) has also been analyzed. Molecular docking studies are implemented to analyze the binding energy and compared with Adriamycin against 1ZXM receptor which to be considered as antitumor candidates. In silico pharmacological ADMET properties as Drug likeness and oral activity have been carried out based on Lipinski's rule of five.Communicated by Ramaswamy H. Sarma.

Antifungal Constituents of Piper crocatum and Their Activities as Ergosterol Biosynthesis Inhibitors Discovered via In Silico Study Using ADMET and Drug-Likeness Analysis

Along with the increasing resistance of Candida spp. to some antibiotics, it is necessary to find new antifungal drugs, one of which is from the medicinal plant Red Betel (Piper crocatum). The purpose of this research is to isolate antifungal constituents from P. crocatum and evaluate their activities as ergosterol biosynthesis inhibitors via an in silico study of ADMET and drug-likeness analysis. Two new active compounds 1 and 2 and a known compound 3 were isolated, and their structures were determined using spectroscopic methods, while their bioactivities were evaluated via in vitro and in silico studies, respectively. Antifungal compound 3 was the most active compared to 1 and 2 with zone inhibition values of 14.5, 11.9, and 13.0 mm, respectively, at a concentration of 10% w/v, together with MIC/MFC at 0.31/1.2% w/v. Further in silico study demonstrated that compound 3 had a stronger ΔG than the positive control and compounds 1 and 2 with -11.14, -12.78, -12.00, and -6.89 Kcal/mol against ERG1, ERG2, ERG11, and ERG24, respectively, and also that 3 had the best Ki with 6.8 × 10-3, 4 × 10-4, 1.6 × 10-3, and 8.88 μM. On the other hand, an ADMET analysis of 1-3 met five parameters, while 1 had one violation of Ro5. Based on the research data, the promising antifungal constituents of P. crocatum allow P. crocatum to be proposed as a new antifungal candidate to treat and cure infections due to C. albicans.

Lies and Liabilities: Computational Assessment of High-Throughput Screening Hits to Identify Artifact Compounds

Hits from high-throughput screening (HTS) of chemical libraries are often false positives due to their interference with assay detection technology. In response, we generated the largest publicly available library of chemical liabilities and developed "Liability Predictor," a free web tool to predict HTS artifacts. More specifically, we generated, curated, and integrated HTS data sets for thiol reactivity, redox activity, and luciferase (firefly and nano) activity and developed and validated quantitative structure-interference relationship (QSIR) models to predict these nuisance behaviors. The resulting models showed 58-78% external balanced accuracy for 256 external compounds per assay. QSIR models developed and validated herein identify nuisance compounds among experimental hits more reliably than do popular PAINS filters. Both the models and the curated data sets were implemented in "Liability Predictor," publicly available at https://liability.mml.unc.edu/. "Liability Predictor" may be used as part of chemical library design or for triaging HTS hits.

Prediction-Inspired Intelligent Training for the Development of Classification Read-across Structure-Activity Relationship (c-RASAR) Models for Organic Skin Sensitizers: Assessment of Classification Error Rate from Novel Similarity Coefficients

The advancements in the field of cheminformatics have led to a reduction in animal testing to estimate the activity, property, and toxicity of query chemicals. Read-across structure-activity relationship (RASAR) is an emerging concept that utilizes various similarity functions derived from chemical information to develop highly predictive models. Unlike quantitative structure-activity relationship (QSAR) models, RASAR descriptors of a query compound are computed from its close congeners instead of the compound itself, thus targeting predictions in the model training phase. The objective of the present study is not to propose new QSAR models for skin sensitization but to demonstrate the enhancement in the quality of predictions of the skin-sensitizing potential of organic compounds by developing classification-based RASAR (c-RASAR) models. A diverse, previously curated data set was collected from the literature for which 2D descriptors were computed. The extracted essential features were then used to develop a classification-based linear discriminant analysis (LDA) QSAR model. Furthermore, from the read-across-based predictions, RASAR descriptors were calculated using the basic settings of the hyperparameters for the Laplacian Kernel-based optimum similarity measure. After feature selection, an LDA c-RASAR model was developed, which superseded the prediction quality of the LDA-QSAR model. Various other combinations of RASAR descriptors were also taken to develop additional c-RASAR models, all showing better prediction quality than the LDA QSAR model while using a lower number of descriptors. Various other machine learning c-RASAR models were also developed for comparison purposes. In this work, we have proposed and analyzed three new similarity metrics: gm_class, sm1, and sm2. The first one is an indicator variable used to generate a simple univariate c-RASAR model with good prediction ability, while the remaining two are similarity indices used to analyze possible activity cliffs in the training and test sets and are believed to play an important role in the modelability analysis of data sets.

Molecular Descriptors Property Prediction Using Transformer-Based Approach

In this study, we introduce semi-supervised machine learning models designed to predict molecular properties. Our model employs a two-stage approach, involving pre-training and fine-tuning. Particularly, our model leverages a substantial amount of labeled and unlabeled data consisting of SMILES strings, a text representation system for molecules. During the pre-training stage, our model capitalizes on the Masked Language Model, which is widely used in natural language processing, for learning molecular chemical space representations. During the fine-tuning stage, our model is trained on a smaller labeled dataset to tackle specific downstream tasks, such as classification or regression. Preliminary results indicate that our model demonstrates comparable performance to state-of-the-art models on the chosen downstream tasks from MoleculeNet. Additionally, to reduce the computational overhead, we propose a new approach taking advantage of 3D compound structures for calculating the attention score used in the end-to-end transformer model to predict anti-malaria drug candidates. The results show that using the proposed attention score, our end-to-end model is able to have comparable performance with pre-trained models.

The VEGA Tool to Check the Applicability Domain Gives Greater Confidence in the Prediction of In Silico Models

A sound assessment of in silico models and their applicability domain can support the use of new approach methodologies (NAMs) in chemical risk assessment and requires increasing the users' confidence in this approach. Several approaches have been proposed to evaluate the applicability domain of such models, but their prediction power still needs a thorough assessment. In this context, the VEGA tool capable of assessing the applicability domain of in silico models is examined for a range of toxicological endpoints. The VEGA tool evaluates chemical structures and other features related to the predicted endpoints and is efficient in measuring applicability domain, enabling the user to identify less accurate predictions. This is demonstrated with many models addressing different endpoints, towards toxicity of relevance to human health, ecotoxicological endpoints, environmental fate, physicochemical and toxicokinetic properties, for both regression models and classifiers.

In silico study of novel niclosamide derivatives, SARS-CoV-2 nonstructural proteins catalytic residue-targeting small molecules drug candidates

The severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2)-mediated coronavirus disease 2019 (COVID-19) infection remains a global pandemic and health emergency with overwhelming social and economic impacts throughout the world. Therapeutics for COVID-19 are limited to only remdesivir; therefore, there is a need for combined, multidisciplinary efforts to develop new therapeutic molecules and explore the effectiveness of existing drugs against SARS-CoV-2. In the present study, we reported eight (SCOV-L-02, SCOV-L-09, SCOV-L-10, SCOV-L-11, SCOV-L-15, SCOV-L-18, SCOV-L-22, and SCOV-L-23) novel structurally related small-molecule derivatives of niclosamide (SCOV-L series) for their targeting potential against angiotensin-converting enzyme-2 (ACE2), type II transmembrane serine protease (TMPRSS2), and SARS-COV-2 nonstructural proteins (NSPs) including NSP5 (3CLpro), NSP3 (PLpro), and RdRp. Our correlation analysis suggested that ACE2 and TMPRSS2 modulate host immune response via regulation of immune-infiltrating cells at the site of tissue/organs entries. In addition, we identified some TMPRSS2 and ACE2 microRNAs target regulatory networks in SARS-CoV-2 infection and thus open up a new window for microRNAs-based therapy for the treatment of SARS-CoV-2 infection. Our in vitro study revealed that with the exception of SCOV-L-11 and SCOV-L-23 which were non-active, the SCOV-L series exhibited strict antiproliferative activities and non-cytotoxic effects against ACE2- and TMPRSS2-expressing cells. Our molecular docking for the analysis of receptor-ligand interactions revealed that SCOV-L series demonstrated high ligand binding efficacies (at higher levels than clinical drugs) against the ACE2, TMPRSS2, and SARS-COV-2 NSPs. SCOV-L-18, SCOV-L-15, and SCOV-L-09 were particularly found to exhibit strong binding affinities with three key SARS-CoV-2's proteins: 3CLpro, PLpro, and RdRp. These compounds bind to the several catalytic residues of the proteins, and satisfied the criteria of drug-like candidates, having good adsorption, distribution, metabolism, excretion, and toxicity (ADMET) pharmacokinetic profile. Altogether, the present study suggests the therapeutic potential of SCOV-L series for preventing and managing SARs-COV-2 infection and are currently under detailed investigation in our lab.

The identification of metabolites from gut microbiota in NAFLD via network pharmacology

The metabolites of gut microbiota show favorable therapeutic effects on nonalcoholic fatty liver disease (NAFLD), but the active metabolites and mechanisms against NAFLD have not been documented. The aim of the study was to investigate the active metabolites and mechanisms of gut microbiota against NAFLD by network pharmacology. We obtained a total of 208 metabolites from the gutMgene database and retrieved 1256 targets from similarity ensemble approach (SEA) and 947 targets from the SwissTargetPrediction (STP) database. In the SEA and STP databases, we identified 668 overlapping targets and obtained 237 targets for NAFLD. Thirty-eight targets were identified out of those 237 and 223 targets retrieved from the gutMgene database, and were considered the final NAFLD targets of metabolites from the microbiome. The results of molecular docking tests suggest that, of the 38 targets, mitogen-activated protein kinase 8-compound K and glycogen synthase kinase-3 beta-myricetin complexes might inhibit the Wnt signaling pathway. The microbiota-signaling pathways-targets-metabolites network analysis reveals that Firmicutes, Fusobacteria, the Toll-like receptor signaling pathway, mitogen-activated protein kinase 1, and phenylacetylglutamine are notable components of NAFLD and therefore to understanding its processes and possible therapeutic approaches. The key components and potential mechanisms of metabolites from gut microbiota against NAFLD were explored utilizing network pharmacology analyses. This study provides scientific evidence to support the therapeutic efficacy of metabolites for NAFLD and suggests holistic insights on which to base further research.

On modeling and utilizing chemical compound information with deep learning technologies: A task-oriented approach

A large number of chemical compounds are available in databases such as PubChem and ZINC. However, currently known compounds, though large, represent only a fraction of possible compounds, which is known as chemical space. Many of these compounds in the databases are annotated with properties and assay data that can be used for drug discovery efforts. For this goal, a number of machine learning algorithms have been developed and recent deep learning technologies can be effectively used to navigate chemical space, especially for unknown chemical compounds, in terms of drug-related tasks. In this article, we survey how deep learning technologies can model and utilize chemical compound information in a task-oriented way by exploiting annotated properties and assay data in the chemical compounds databases. We first compile what kind of tasks are trying to be accomplished by machine learning methods. Then, we survey deep learning technologies to show their modeling power and current applications for accomplishing drug related tasks. Next, we survey deep learning techniques to address the insufficiency issue of annotated data for more effective navigation of chemical space. Chemical compound information alone may not be powerful enough for drug related tasks, thus we survey what kind of information, such as assay and gene expression data, can be used to improve the prediction power of deep learning models. Finally, we conclude this survey with four important newly developed technologies that are yet to be fully incorporated into computational analysis of chemical information.

Validation of Quantitative Structure-Activity Relationship (QSAR) and Quantitative Structure-Property Relationship (QSPR) approaches as alternatives to skin sensitization risk assessment

The aim of this study was conducted to validate the physicochemical properties of a total of 362 chemicals [305 skin sensitizers (212 in the previous study + 93 additional new chemicals), 57 non-skin sensitizers (38 in the previous study + 19 additional new chemicals)] for skin sensitization risk assessment using quantitative structure-activity relationship (QSAR)/quantitative structure-property relationship (QSPR) approaches. The average melting point (MP), surface tension (ST), and density (DS) of the 305 skin sensitizers and 57 non-sensitizers were used to determine the cutoff values distinguishing positive and negative sensitization, and correlation coefficients were employed to derive effective 3-fold concentration (EC3 (%)) values. QSAR models were also utilized to assess skin sensitization. The sensitivity, specificity, and accuracy were 80, 15, and 70%, respectively, for the Toxtree QSAR model; 88, 46, and 81%, respectively, for Vega; and 56, 61, and 56%, respectively, for Danish EPA QSAR. Surprisingly, the sensitivity, specificity, and accuracy were 60, 80, and 64%, respectively, when MP, ST, and DS (MP+ST+DS) were used in this study. Further, MP+ST+DS exhibited a sensitivity of 77%, specificity 57%, and accuracy 73% when the derived EC3 values were classified into local lymph node assay (LLNA) skin sensitizer and non-sensitizer categories. Thus, MP, ST, and DS may prove useful in predicting EC3 values as not only an alternative approach to animal testing but also for skin sensitization risk assessment.

Molecular insights on ABL kinase activation using tree-based machine learning models and molecular docking

Abelson kinase (c-Abl) is a non-receptor tyrosine kinase involved in several biological processes essential for cell differentiation, migration, proliferation, and survival. This enzyme's activation might be an alternative strategy for treating diseases such as neutropenia induced by chemotherapy, prostate, and breast cancer. Recently, a series of compounds that promote the activation of c-Abl has been identified, opening a promising ground for c-Abl drug development. Structure-based drug design (SBDD) and ligand-based drug design (LBDD) methodologies have significantly impacted recent drug development initiatives. Here, we combined SBDD and LBDD approaches to characterize critical chemical properties and interactions of identified c-Abl's activators. We used molecular docking simulations combined with tree-based machine learning models-decision tree, AdaBoost, and random forest to understand the c-Abl activators' structural features required for binding to myristoyl pocket, and consequently, to promote enzyme and cellular activation. We obtained predictive and robust models with Matthews correlation coefficient values higher than 0.4 for all endpoints and identified characteristics that led to constructing a structure-activity relationship model (SAR).

Simplex representation of molecular structure as universal QSAR/QSPR tool

We review the development and application of the Simplex approach for the solution of various QSAR/QSPR problems. The general concept of the simplex method and its varieties are described. The advantages of utilizing this methodology, especially for the interpretation of QSAR/QSPR models, are presented in comparison to other fragmentary methods of molecular structure representation. The utility of SiRMS is demonstrated not only in the standard QSAR/QSPR applications, but also for mixtures, polymers, materials, and other complex systems. In addition to many different types of biological activity (antiviral, antimicrobial, antitumor, psychotropic, analgesic, etc.), toxicity and bioavailability, the review examines the simulation of important properties, such as water solubility, lipophilicity, as well as luminescence, and thermodynamic properties (melting and boiling temperatures, critical parameters, etc.). This review focuses on the stereochemical description of molecules within the simplex approach and details the possibilities of universal molecular stereo-analysis and stereochemical configuration description, along with stereo-isomerization mechanism and molecular fragment "topography" identification.

Integrated Cheminformatics-Molecular Docking Approach to Drug Discovery Against Viruses

BACKGROUND

In the current study, we present an integrated in silico cheminformaticsmolecular docking approach to screen and test potential therapeutic compounds against viruses. Fluoroquinolones have been shown to inhibit HCV replication by targeting HCV NS3-helicase. Based on this observation, we hypothesized that natural analogs of fluoroquinolones will have similar or superior inhibitory potential while having potentially fewer adverse effects.

METHODS

To screen for natural analogs of fluoroquinolones, we devised an integrated in silico Cheminformatics-Molecular Docking approach. We used 17 fluoroquinolones as bait reference, to screen large databases of natural analogs. 10399 natural compounds and their derivatives were retrieved from the databases. From these compounds, molecules bearing physicochemical similarities with fluoroquinolones were analyzed using a cheminformatics-docking approach.

RESULTS

From the 10399 compounds screened using our cheminformatics approach, only 20 compounds were found to share physicochemical similarities with fluoroquinolones, while the remaining 10379 compounds were physiochemically different from fluoroquinolones. Molecular docking analysis showed 32 amino acids in the HCV NS3 active site that were most frequently targeted by fluoroquinolones and their natural analogues, indicating a functional similarity between the two groups of compounds.

CONCLUSION

This study describes a speedy and inexpensive approach to complement drug discovery and design against viral agents. The in silico analyses we used here can be employed to shortlist promising compounds/putative drugs that can be further tested in wet-lab.

Application of the hard and soft, acids and bases (HSAB) theory as a method to predict cumulative neurotoxicity

Xenobiotic electrophiles can form covalent adducts that may impair protein function, damage DNA, and may lead a range of adverse effects. Cumulative neurotoxicity is one adverse effect that has been linked to covalent protein binding as a Molecular Initiating Event (MIE). This paper describes a mechanistic in silico chemical screening approach for neurotoxicity based on Hard and Soft Acids and Bases (HSAB) theory. We evaluated the applicability of HSAB-based electrophilicity screening protocol for neurotoxicity on 19 positive and 19 negative reference chemicals. These reference chemicals were identified from the literature, using available information on mechanisms of neurotoxicity whenever possible. In silico screening was based on structural alerts for protein binding motifs and electrophilicity index in the range of known neurotoxicants. The approach demonstrated both a high positive prediction rate (82-90 %) and specificity (90 %). The overall sensitivity was relatively lower (47 %). However, when predicting the toxicity of chemicals known or suspected of acting via non-specific adduct formation mechanism, the HSAB approach identified 7/8 (sensitivity 88 %) of positive control chemicals correctly. Consequently, the HSAB-based screening is a promising approach of identifying possible neurotoxins with adduct formation molecular initiating events. While the approach must be expanded over time to capture a wider range of MIEs involved in neurotoxicity, the mechanistic nature of the screen allows users to flag chemicals for possible adduct formation MIEs. Thus, the HSAB based toxicity screening is a promising strategy for toxicity assessment and chemical prioritization in neurotoxicology and other health endpoints that involve adduct formation.

Synthesis, Antitumor Activity and Molecular Docking Studies on Seven Novel Thiazacridine Derivatives

AIM AND OBJECTIVE

In the last decades, cancer has become a major problem in public health all around the globe. Chimeric chemical structures have been established as an important trend on medicinal chemistry in the last years. Thiazacridines are hybrid molecules composed of a thiazolidine and acridine nucleus, both pharmacophores that act on important biological targets for cancer. By the fact it is a serious disease, seven new 3-acridin-9-ylmethyl-thiazolidine-2,4-dione derivatives were synthesized, characterized, analyzed by computer simulation and tested in tumor cells. In order to find out if the compounds have therapeutic potential.

MATERIALS AND METHODS

Seven new 3-acridin-9-ylmethyl-thiazolidine-2,4-dione derivatives were synthesized through Michael addition and Knoevenagel condensation strategies. Characterization was performed by NMR and Infrared spectroscopy techniques. Regarding biological activity, thiazacridines were tested against solid and hematopoietic tumoral cell lines, namely Jurkat (acute T-cell leukemia); HL-60 (acute promyelocytic leukemia); DU 145 (prostate cancer); MOLT-4 (acute lymphoblastic leukemia); RAJI (Burkitt's lymphoma); K562 (chronic myelogenous leukemia) and normal cells PBMC (healthy volunteers). Molecular docking analysis was also performed in order to assess major targets of these new compounds. Cell cycle and clonogenic assay were also performed.

RESULTS

Compound LPSF/AA-62 (9f) exhibited the most potent anticancer activity against HL-60 (IC50 3,7±1,7 μM), MOLT-4 (IC50 5,7±1,1 μM), Jurkat (IC50 18,6 μM), Du-145 (IC50 20±5 μM) and Raji (IC50 52,3±9,2 μM). While the compound LPSF/AA-57 (9b) exhibited anticancer activity against the K562 cell line (IC50 51,8±7,8 μM). Derivative LPSF/AA-62 (9f) did not interfere in the cell cycle phases of the Molt-4 lineage. However, the LPSF/AA-62 (9f) derivative significantly reduced the formation of prostate cancer cell clones. The compound LPSF/AA-62 (9f) has shown strong anchorage stability with enzymes topoisomerases 1 and 2, in particular due the presence of chlorine favored hydrogen bonds with topoisomerase 1.

CONCLUSION

The 3-(acridin-9-ylmethyl)-5-((10-chloroanthracen-9-yl)methylene)thiazolidine-2,4-dione (LPSF/AA-62) presented the most promising results, showing anti-tumor activity in 5 of the 6 cell types tested, especially inhibiting the formation of colonies of prostate tumor cells (DU-145).

Deep Learning-driven research for drug discovery: Tackling Malaria

Malaria is an infectious disease that affects over 216 million people worldwide, killing over 445,000 patients annually. Due to the constant emergence of parasitic resistance to the current antimalarial drugs, the discovery of new drug candidates is a major global health priority. Aiming to make the drug discovery processes faster and less expensive, we developed binary and continuous Quantitative Structure-Activity Relationships (QSAR) models implementing deep learning for predicting antiplasmodial activity and cytotoxicity of untested compounds. Then, we applied the best models for a virtual screening of a large database of chemical compounds. The top computational predictions were evaluated experimentally against asexual blood stages of both sensitive and multi-drug-resistant Plasmodium falciparum strains. Among them, two compounds, LabMol-149 and LabMol-152, showed potent antiplasmodial activity at low nanomolar concentrations (EC50 <500 nM) and low cytotoxicity in mammalian cells. Therefore, the computational approach employing deep learning developed here allowed us to discover two new families of potential next generation antimalarial agents, which are in compliance with the guidelines and criteria for antimalarial target candidates.

Efficient identification of novel anti-glioma lead compounds by machine learning models

Glioblastoma multiforme (GBM) is the most devastating and widespread primary central nervous system tumor. Pharmacological treatment of this malignance is limited by the selective permeability of the blood-brain barrier (BBB) and relies on a single drug, temozolomide (TMZ), thus making the discovery of new compounds challenging and urgent. Therefore, aiming to discover new anti-glioma drugs, we developed robust machine learning models for predicting anti-glioma activity and BBB penetration ability of new compounds. Using these models, we prioritized 41 compounds from our in-house library of compounds, for further in vitro testing against three glioma cell lines and astrocytes. Subsequently, the most potent and selective compounds were resynthesized and tested in vivo using an orthotopic glioma model. This approach revealed two lead candidates, 4m and 4n, which efficiently decreased malignant glioma development in mice, probably by inhibiting thioredoxin reductase activity, as shown by our enzymological assays. Moreover, these two compounds did not promote body weight reduction, death of animals, or altered hematological and toxicological markers, making then good candidates for lead optimization as anti-glioma drug candidates.

Application of an integrated cheminformatics-molecular docking approach for discovery for physicochemically similar analogs of fluoroquinolones as putative HCV inhibitors

BACKGROUND

Hepatitis C Virus (HCV) infection is a major public health concern across the globe. At present, direct-acting antivirals are the treatment of choice. However, the long-term effect of this therapy has yet to be ascertained. Previously, fluoroquinolones have been reported to inhibit HCV replication by targeting NS3 protein. Therefore, it is logical to hypothesize that the natural analogs of fluoroquinolones will exhibit NS3 inhibitory activity with substantially lesser side effects.

METHOD

In this study, we tested the application of a recently devised integrated in-silico Cheminformatics-Molecular Docking approach to identify physicochemically similar natural analogs of fluoroquinolones from the available databases (Ambinter, Analyticon, Indofines, Specs, and TimTec). Molecular docking and ROC curve analyses were performed, using PatchDock and Graphpad software, respectively, to compare and analyze drug-protein interactions between active natural analogs, Fluoroquinolones, and HCV NS3 protein.

RESULT

In our analysis, we were able to shortlist 18 active natural analogs, out of 10,399, that shared physicochemical properties with the template drugs (fluoroquinolones). These analogs showed comparable binding efficacy with fluoroquinolones in targeting 32 amino acids in the HCV NS3 active site that are crucial for NS3 activity. Our approach had around 80 % sensitivity and 70 % specificity in identifying physicochemically similar analogs of fluoroquinolones.

CONCLUSION

Our current data suggest that our approach can be efficiently applied to identify putative HCV drug inhibitors that can be taken for in vitro testing. This approach can be applied to discover physicochemically similar analogs of virtually any drug, thus providing a speedy and inexpensive approach to complement drug discovery and design, which can tremendously economize on time and money spent on the screening of putative drugs.

Skin Doctor: Machine Learning Models for Skin Sensitization Prediction that Provide Estimates and Indicators of Prediction Reliability

The ability to predict the skin sensitization potential of small organic molecules is of high importance to the development and safe application of cosmetics, drugs and pesticides. One of the most widely accepted methods for predicting this hazard is the local lymph node assay (LLNA). The goal of this work was to develop in silico models for the prediction of the skin sensitization potential of small molecules that go beyond the state of the art, with larger LLNA data sets and, most importantly, a robust and intuitive definition of the applicability domain, paired with additional indicators of the reliability of predictions. We explored a large variety of molecular descriptors and fingerprints in combination with random forest and support vector machine classifiers. The most suitable models were tested on holdout data, on which they yielded competitive performance (Matthews correlation coefficients up to 0.52; accuracies up to 0.76; areas under the receiver operating characteristic curves up to 0.83). The most favorable models are available via a public web service that, in addition to predictions, provides assessments of the applicability domain and indicators of the reliability of the individual predictions.

Cheminformatics-driven discovery of polymeric micelle formulations for poorly soluble drugs

Many drug candidates fail therapeutic development because of poor aqueous solubility. We have conceived a computer-aided strategy to enable polymeric micelle-based delivery of poorly soluble drugs. We built models predicting both drug loading efficiency (LE) and loading capacity (LC) using novel descriptors of drug-polymer complexes. These models were employed for virtual screening of drug libraries, and eight drugs predicted to have either high LE and high LC or low LE and low LC were selected. Three putative positives, as well as three putative negative hits, were confirmed experimentally (implying 75% prediction accuracy). Fortuitously, simvastatin, a putative negative hit, was found to have the desired micelle solubility. Podophyllotoxin and simvastatin (LE of 95% and 87% and LC of 43% and 41%, respectively) were among the top five polymeric micelle-soluble compounds ever studied experimentally. The success of the strategy described herein suggests its broad utility for designing drug delivery systems.

Predicting Skin Permeability by Means of Computational Approaches: Reliability and Caveats in Pharmaceutical Studies

The skin is the main barrier between the internal body environment and the external one. The characteristics of this barrier and its properties are able to modify and affect drug delivery and chemical toxicity parameters. Therefore, it is not surprising that permeability of many different compounds has been measured through several in vitro and in vivo techniques. Moreover, many different in silico approaches have been used to identify the correlation between the structure of the permeants and their permeability, to reproduce the skin behavior, and to predict the ability of specific chemicals to permeate this barrier. A significant number of issues, like interlaboratory variability, experimental conditions, data set building rationales, and skin site of origin and hydration, still prevent us from obtaining a definitive predictive skin permeability model. This review wants to show the main advances and the principal approaches in computational methods used to predict this property, to enlighten the main issues that have arisen, and to address the challenges to develop in future research.

The Impact of Novel Assessment Methodologies in Toxicology on Green Chemistry and Chemical Alternatives

The field of experimental toxicology is rapidly advancing by incorporating novel techniques and methods that provide a much more granular view into the mechanisms of potential adverse effects of chemical exposures on human health. The data from various in vitro assays and computational models are useful not only for increasing confidence in hazard and risk decisions, but also are enabling better, faster and cheaper assessment of a greater number of compounds, mixtures, and complex products. This is of special value to the field of green chemistry where design of new materials or alternative uses of existing ones is driven, at least in part, by considerations of safety. This article reviews the state of the science and decision-making in scenarios when little to no data may be available to draw conclusions about which choice in green chemistry is "safer." It is clear that there is no "one size fits all" solution and multiple data streams need to be weighed in making a decision. Moreover, the overall level of familiarity of the decision-makers and scientists alike with new assessment methodologies, their validity, value and limitations is evolving. Thus, while the "impact" of the new developments in toxicology on the field of green chemistry is great already, it is premature to conclude that the data from new assessment methodologies have been widely accepted yet.

Discovery of new potent hits against intracellular Trypanosoma cruzi by QSAR-based virtual screening

Chagas disease is a neglected tropical disease (NTD) caused by the protozoan parasite Trypanosoma cruzi and is primarily transmitted to humans by the feces of infected Triatominae insects during their blood meal. The disease affects 6-8 million people, mostly in Latin America countries, and kills more people in the region each year than any other parasite-born disease, including malaria. Moreover, patient numbers are currently increasing in non-endemic, developed countries, such as Australia, Japan, Canada, and the United States. The treatment is limited to one drug, benznidazole, which is only effective in the acute phase of the disease and is very toxic. Thus, there is an urgent need to develop new, safer, and effective drugs against the chronic phase of Chagas disease. Using a QSAR-based virtual screening followed by in vitro experimental evaluation, we report herein the identification of novel potent and selective hits against T. cruzi intracellular stage. We developed and validated binary QSAR models for prediction of anti-trypanosomal activity and cytotoxicity against mammalian cells using the best practices for QSAR modeling. These models were then used for virtual screening of a commercial database, leading to the identification of 39 virtual hits. Further in vitro assays showed that seven compounds were potent against intracellular T. cruzi at submicromolar concentrations (EC₅₀ < 1 μM) and were very selective (SI > 30). Furthermore, other six compounds were also inside the hit criteria for Chagas disease, which presented activity at low micromolar concentrations (EC₅₀ < 10 μM) against intracellular T. cruzi and were also selective (SI > 15). Moreover, we performed a multi-parameter analysis for the comparison of tested compounds regarding their balance between potency, selectivity, and predicted ADMET properties. In the next studies, the most promising compounds will be submitted to additional in vitro and in vivo assays in acute model of Chagas disease, and can be further optimized for the development of new promising drug candidates against this important yet neglected disease.

Multi-Descriptor Read Across (MuDRA): A Simple and Transparent Approach for Developing Accurate Quantitative Structure-Activity Relationship Models

Multiple approaches to quantitative structure-activity relationship (QSAR) modeling using various statistical or machine learning techniques and different types of chemical descriptors have been developed over the years. Oftentimes models are used in consensus to make more accurate predictions at the expense of model interpretation. We propose a simple, fast, and reliable method termed Multi-Descriptor Read Across (MuDRA) for developing both accurate and interpretable models. The method is conceptually related to the well-known kNN approach but uses different types of chemical descriptors simultaneously for similarity assessment. To benchmark the new method, we have built MuDRA models for six different end points (Ames mutagenicity, aquatic toxicity, hepatotoxicity, hERG liability, skin sensitization, and endocrine disruption) and compared the results with those generated with conventional consensus QSAR modeling. We find that models built with MuDRA show consistently high external accuracy similar to that of conventional QSAR models. However, MuDRA models excel in terms of transparency, interpretability, and computational efficiency. We posit that due to its methodological simplicity and reliable predictive accuracy, MuDRA provides a powerful alternative to a much more complex consensus QSAR modeling. MuDRA is implemented and freely available at the Chembench web portal ( https://chembench.mml.unc.edu/mudra ).

Risks of Allergic Contact Dermatitis Elicited by Nickel, Chromium, and Organic Sensitizers: Quantitative Models Based on Clinical Patch Test Data

Risks of allergic contact dermatitis (ACD) from consumer products intended for extended (nonpiercing) dermal contact are regulated by E.U. Directive EN 1811 that limits released Ni to a weekly equivalent dermal load of ≤0.5 μg/cm² . Similar approaches for thousands of known organic sensitizers are hampered by inability to quantify respective ACD-elicitation risk levels. To help address this gap, normalized values of cumulative risk for eliciting a positive ("≥+") clinical patch test response reported in 12 studies for a total of n = 625 Ni-sensitized patients were modeled in relation to observed ACD-eliciting Ni loads, yielding an approximate lognormal (LN) distribution with a geometric mean and standard deviation of GM_Ni = 15 μg/cm² and GSD_Ni = 8.0, respectively. Such data for five sensitizers (including formaldehyde and 2-hydroxyethyl methacrylate) were also ∼LN distributed, but with a common GSD value equal to GSD_Ni and with heterogeneous sensitizer-specific GM values each defining a respective ACD-eliciting potency GM_Ni /GM relative to Ni. Such potencies were also estimated for nine (meth)acrylates by applying this general LN ACD-elicitation risk model to respective sets of fewer data. ACD-elicitation risk patterns observed for Cr(VI) (n = 417) and Cr(III) (n = 78) were fit to mixed-LN models in which ∼30% and ∼40% of the most sensitive responders, respectively, were estimated to exhibit a LN response also governed by GSD_Ni . The observed common LN-response shape parameter GSD_Ni may reflect a common underlying ACD mechanism and suggests a common interim approach to quantitative ACD-elicitation risk assessment based on available clinical data.

Current nonclinical testing paradigms in support of safe clinical trials: An IQ Consortium DruSafe perspective

The transition from nonclinical to First-in-Human (FIH) testing is one of the most challenging steps in drug development. In response to serious outcomes in a recent Phase 1 trial (sponsored by Bial), IQ Consortium/DruSafe member companies reviewed their nonclinical approach to progress small molecules safely to FIH trials. As a common practice, safety evaluation begins with target selection and continues through iterative in silico and in vitro screening to identify molecules with increased probability of acceptable in vivo safety profiles. High attrition routinely occurs during this phase. In vivo exploratory and pivotal FIH-enabling toxicity studies are then conducted to identify molecules with a favorable benefit-risk profile for humans. The recent serious incident has reemphasized the importance of nonclinical testing plans that are customized to the target, the molecule, and the intended clinical plan. Despite the challenges and inherent risks of transitioning from nonclinical to clinical testing, Phase 1 studies have a remarkably good safety record. Given the rapid scientific evolution of safety evaluation, testing paradigms and regulatory guidance must evolve with emerging science. The authors posit that the practices described herein, together with science-based risk assessment and management, support safe FIH trials while advancing development of important new medicines.

Chemical toxicity prediction for major classes of industrial chemicals: Is it possible to develop universal models covering cosmetics, drugs, and pesticides?

Computational models have earned broad acceptance for assessing chemical toxicity during early stages of drug discovery or environmental safety assessment. The majority of publicly available QSAR toxicity models have been developed for datasets including mostly drugs or drug-like compounds. We have evaluated and compared chemical spaces occupied by cosmetics, drugs, and pesticides, and explored whether current computational models of toxicity endpoints can be universally applied to all these chemicals. Our analysis of the chemical space overlap and applicability domain (AD) of models built previously for twenty different toxicity endpoints showed that most of these models afforded high coverage (>90%) for all three classes of compounds analyzed herein. Only T. pyriformis models demonstrated lower coverage for drugs and pesticides (38% and 54%, respectively). These results show that, for the most part, historical QSAR models built with data available for different toxicity endpoints can be used for toxicity assessment of novel chemicals irrespective of the intended commercial use; however, the AD restriction is necessary to assure the expected prediction accuracy. Local models may need to be developed to capture chemicals that appear as outliers with respect to global models.

Phantom PAINS: Problems with the Utility of Alerts for Pan-Assay INterference CompoundS

The use of substructural alerts to identify Pan-Assay INterference compoundS (PAINS) has become a common component of the triage process in biological screening campaigns. These alerts, however, were originally derived from a proprietary library tested in just six assays measuring protein-protein interaction (PPI) inhibition using the AlphaScreen detection technology only; moreover, 68% (328 out of the 480 alerts) were derived from four or fewer compounds. In an effort to assess the reliability of these alerts as indicators of pan-assay interference, we performed a large-scale analysis of the impact of PAINS alerts on compound promiscuity in bioassays using publicly available data in PubChem. We found that the majority (97%) of all compounds containing PAINS alerts were actually infrequent hitters in AlphaScreen assays measuring PPI inhibition. We also found that the presence of PAINS alerts, contrary to expectations, did not reflect any heightened assay activity trends across all assays in PubChem including AlphaScreen, luciferase, beta-lactamase, or fluorescence-based assays. In addition, 109 PAINS alerts were present in 3570 extensively assayed, but consistently inactive compounds called Dark Chemical Matter. Finally, we observed that 87 small molecule FDA-approved drugs contained PAINS alerts and profiled their bioassay activity. Based on this detailed analysis of PAINS alerts in nonproprietary compound libraries, we caution against the blind use of PAINS filters to detect and triage compounds with possible PAINS liabilities and recommend that such conclusions should be drawn only by conducting orthogonal experiments.

SkinSensDB: a curated database for skin sensitization assays

Skin sensitization is an important toxicological endpoint for chemical hazard determination and safety assessment. Prediction of chemical skin sensitizer had traditionally relied on data from rodent models. The development of the adverse outcome pathway (AOP) and associated alternative in vitro assays have reshaped the assessment of skin sensitizers. The integration of multiple assays as key events in the AOP has been shown to have improved prediction performance. Current computational models to predict skin sensitization mainly based on in vivo assays without incorporating alternative in vitro assays. However, there are few freely available databases integrating both the in vivo and the in vitro skin sensitization assays for development of AOP-based skin sensitization prediction models. To facilitate the development of AOP-based prediction models, a skin sensitization database named SkinSensDB has been constructed by curating data from published AOP-related assays. In addition to providing datasets for developing computational models, SkinSensDB is equipped with browsing and search tools which enable the assessment of new compounds for their skin sensitization potentials based on data from structurally similar compounds. SkinSensDB is publicly available at http://cwtung.kmu.edu.tw/skinsensdb.

Chembench: A Publicly Accessible, Integrated Cheminformatics Portal

The enormous increase in the amount of publicly available chemical genomics data and the growing emphasis on data sharing and open science mandates that cheminformaticians also make their models publicly available for broad use by the scientific community. Chembench is one of the first publicly accessible, integrated cheminformatics Web portals. It has been extensively used by researchers from different fields for curation, visualization, analysis, and modeling of chemogenomics data. Since its launch in 2008, Chembench has been accessed more than 1 million times by more than 5000 users from a total of 98 countries. We report on the recent updates and improvements that increase the simplicity of use, computational efficiency, accuracy, and accessibility of a broad range of tools and services for computer-assisted drug design and computational toxicology available on Chembench. Chembench remains freely accessible at https://chembench.mml.unc.edu.

QSAR models of human data can enrich or replace LLNA testing for human skin sensitization

Skin sensitization is a major environmental and occupational health hazard. Although many chemicals have been evaluated in humans, there have been no efforts to model these data to date. We have compiled, curated, analyzed, and compared the available human and LLNA data. Using these data, we have developed reliable computational models and applied them for virtual screening of chemical libraries to identify putative skin sensitizers. The overall concordance between murine LLNA and human skin sensitization responses for a set of 135 unique chemicals was low (R = 28-43%), although several chemical classes had high concordance. We have succeeded to develop predictive QSAR models of all available human data with the external correct classification rate of 71%. A consensus model integrating concordant QSAR predictions and LLNA results afforded a higher CCR of 82% but at the expense of the reduced external dataset coverage (52%). We used the developed QSAR models for virtual screening of CosIng database and identified 1061 putative skin sensitizers; for seventeen of these compounds, we found published evidence of their skin sensitization effects. Models reported herein provide more accurate alternative to LLNA testing for human skin sensitization assessment across diverse chemical data. In addition, they can also be used to guide the structural optimization of toxic compounds to reduce their skin sensitization potential.

Alarms about structural alerts

Structural alerts are widely accepted in chemical toxicology and regulatory decision support as a simple and transparent means to flag potential chemical hazards or group compounds into categories for read-across. However, there has been a growing concern that alerts disproportionally flag too many chemicals as toxic, which questions their reliability as toxicity markers. Conversely, the rigorously developed and properly validated statistical QSAR models can accurately and reliably predict the toxicity of a chemical; however, their use in regulatory toxicology has been hampered by the lack of transparency and interpretability. We demonstrate that contrary to the common perception of QSAR models as "black boxes" they can be used to identify statistically significant chemical substructures (QSAR-based alerts) that influence toxicity. We show through several case studies, however, that the mere presence of structural alerts in a chemical, irrespective of the derivation method (expert-based or QSAR-based), should be perceived only as hypotheses of possible toxicological effect. We propose a new approach that synergistically integrates structural alerts and rigorously validated QSAR models for a more transparent and accurate safety assessment of new chemicals.