SAR/QSAR methods in public health practice

The database makes the poison: How the selection of datasets in QSAR models impacts toxicant prediction of higher tier endpoints

As the United States and the European Union continue their steady march towards the acceptance of new approach methodologies (NAMs), we need to ensure that the available tools are fit for purpose. Critics will be well-positioned to caution against NAMs acceptance and adoption if the tools turn out to be inadequate. In this paper, we focus on Quantitative Structure Activity-Relationship (QSAR) models and highlight how the training database affects quality and performance of these models. Our analysis goes to the point of asking, "are the endpoints extracted from the experimental studies in the database trustworthy, or are they false negatives/positives themselves?" We also discuss the impacts of chemistry on QSAR models, including issues with 2-D structure analyses when dealing with isomers, metabolism, and toxicokinetics. We close our analysis with a discussion of challenges associated with translational toxicology, specifically the lack of adverse outcome pathways/adverse outcome pathway networks (AOPs/AOPNs) for many higher tier endpoints. We recognize that it takes a collaborate effort to build better and higher quality QSAR models especially for higher tier toxicological endpoints. Hence, it is critical to bring toxicologists, statisticians, and machine learning specialists together to discuss and solve these challenges to get relevant predictions.

Exploring pollutant joint effects in disease through interpretable machine learning

Identifying the impact of pollutants on diseases is crucial. However, assessing the health risks posed by the interplay of multiple pollutants is challenging. This study introduces the concept of Pollutants Outcome Disease, integrating multidisciplinary knowledge and employing explainable artificial intelligence (AI) to explore the joint effects of industrial pollutants on diseases. Using lung cancer as a representative case study, an extreme gradient boosting predictive model that integrates meteorological, socio-economic, pollutants, and lung cancer statistical data is developed. The joint effects of industrial pollutants on lung cancer are identified and analyzed by employing the SHAP (Shapley Additive exPlanations) interpretable machine learning technique. Results reveal substantial spatial heterogeneity in emissions from CPG and ILC, highlighting pronounced nonlinear relationships among variables. The model yielded strong predictions (an R of 0.954, an RMSE of 4283, and an R2 of 0.911) and emphasized the impact of pollutant emission amounts on lung cancer responses. Diverse joint effects patterns were observed, varying in terms of patterns, regions (frequency), and the extent of antagonistic and synergistic effects among pollutants. The study provides a new perspective for exploring the joint effects of pollutants on diseases and demonstrates the potential of AI technology to assist scientific discovery.

S2DV: converting SMILES to a drug vector for predicting the activity of anti-HBV small molecules

In the past few decades, chronic hepatitis B caused by hepatitis B virus (HBV) has been one of the most serious diseases to human health. The development of innovative systems is essential for preventing the complex pathogenesis of hepatitis B and reducing side effects caused by drugs. HBV inhibitory drugs have been developed through various compounds, and they are often limited by routine experimental screening and delay drug development. More recently, virtual screening of compounds has gradually been used in drug research with strong computational capability and is further applied in anti-HBV drug screening, thus facilitating a reliable drug screening process. However, the lack of structural information in traditional compound analysis is an important hurdle for unsatisfactory efficiency in drug screening. Here, a natural language processing technique was adopted to analyze compound simplified molecular input line entry system strings. By using the targeted optimized word2vec model for pretraining, we can accurately represent the relationship between the compound and its substructure. The machine learning model based on training results can effectively predict the inhibitory effect of compounds on HBV and liver toxicity. The reliability of the model is verified by the results of wet-lab experiments. In addition, a tool has been published to predict potential compounds. Hence, this article provides a new perspective on the prediction of compound properties for anti-HBV drugs that can help improve hepatitis B diagnosis and further develop human health in the future.

RespiraTox - Development of a QSAR model to predict human respiratory irritants

Respiratory irritation is an important human health endpoint in chemical risk assessment. There are two established modes of action of respiratory irritation, 1) sensory irritation mediated by the interaction with sensory neurons, potentially stimulating trigeminal nerve, and 2) direct tissue irritation. The aim of our research was to, develop a QSAR method to predict human respiratory irritants, and to potentially reduce the reliance on animal testing for the identification of respiratory irritants. Compounds are classified as irritating based on combined evidence from different types of toxicological data, including inhalation studies with acute and repeated exposure. The curated project database comprised 1997 organic substances, 1553 being classified as irritating and 444 as non-irritating. A comparison of machine learning approaches, including Logistic Regression (LR), Random Forests (RFs), and Gradient Boosted Decision Trees (GBTs), showed, the best classification was obtained by GBTs. The LR model resulted in an area under the curve (AUC) of 0.65, while the optimal performance for both RFs and GBTs gives an AUC of 0.71. In addition to the classification and the information on the applicability domain, the web-based tool provides a list of structurally similar analogues together with their experimental data to facilitate expert review for read-across purposes.

Prediction of toxicity of secondary metabolites

The prediction of toxicological endpoints has gained broad acceptance; it is widely applied in early stages of drug discovery as well as for impurities obtained in the production of generic or equivalent products. In this work, we describe methodologies for the prediction of toxicological endpoints compounds, with a particular focus on secondary metabolites. Case studies include toxicity prediction of natural compound databases with anti-diabetic, anti-malaria and anti-HIV properties.

HIVprotI: an integrated web based platform for prediction and design of HIV proteins inhibitors

A number of anti-retroviral drugs are being used for treating Human Immunodeficiency Virus (HIV) infection. Due to emergence of drug resistant strains, there is a constant quest to discover more effective anti-HIV compounds. In this endeavor, computational tools have proven useful in accelerating drug discovery. Although methods were published to design a class of compounds against a specific HIV protein, but an integrated web server for the same is lacking. Therefore, we have developed support vector machine based regression models using experimentally validated data from ChEMBL repository. Quantitative structure activity relationship based features were selected for predicting inhibition activity of a compound against HIV proteins namely protease (PR), reverse transcriptase (RT) and integrase (IN). The models presented a maximum Pearson correlation coefficient of 0.78, 0.76, 0.74 and 0.76, 0.68, 0.72 during tenfold cross-validation on IC₅₀ and percent inhibition datasets of PR, RT, IN respectively. These models performed equally well on the independent datasets. Chemical space mapping, applicability domain analyses and other statistical tests further support robustness of the predictive models. Currently, we have identified a number of chemical descriptors that are imperative in predicting the compound inhibition potential. HIVprotI platform (http://bioinfo.imtech.res.in/manojk/hivproti) would be useful in virtual screening of inhibitors as well as designing of new molecules against the important HIV proteins for therapeutics development.

Effect doses for protection of human health predicted from physicochemical properties of metals/metalloids

Effect doses (EDs) of metals/metalloids, usually obtained from toxicological experiments are required for developing environmental quality criteria/standards for use in assessment of hazard or risks. However, because in vivo tests are time-consuming, costly and sometimes impossible to conduct, among more than 60 metals/metalloids, there are sufficient data for development of EDs for only approximately 25 metals/metalloids. Hence, it was deemed a challenge to derive EDs for additional metals by use of alternative methods. This study found significant relationships between EDs and physicochemical parameters for twenty-five metals/metalloids. Elements were divided into three classes and then three individual empirical models were developed based on the most relevant parameters for each class. These parameters included log-βn, ΔE₀ and X_m²r, respectively (R² = 0.988, 0.839, 0.871, P < 0.01). Those models can satisfactorily predict EDs for another 25 metals/metalloids. Here, these alternative models for deriving thresholds of toxicity that could be used to perform preliminarily, screen-level health assessments for metals are presented.

AVCpred: an integrated web server for prediction and design of antiviral compounds

Viral infections constantly jeopardize the global public health due to lack of effective antiviral therapeutics. Therefore, there is an imperative need to speed up the drug discovery process to identify novel and efficient drug candidates. In this study, we have developed quantitative structure-activity relationship (QSAR)-based models for predicting antiviral compounds (AVCs) against deadly viruses like human immunodeficiency virus (HIV), hepatitis C virus (HCV), hepatitis B virus (HBV), human herpesvirus (HHV) and 26 others using publicly available experimental data from the ChEMBL bioactivity database. Support vector machine (SVM) models achieved a maximum Pearson correlation coefficient of 0.72, 0.74, 0.66, 0.68, and 0.71 in regression mode and a maximum Matthew's correlation coefficient 0.91, 0.93, 0.70, 0.89, and 0.71, respectively, in classification mode during 10-fold cross-validation. Furthermore, similar performance was observed on the independent validation sets. We have integrated these models in the AVCpred web server, freely available at http://crdd.osdd.net/servers/avcpred. In addition, the datasets are provided in a searchable format. We hope this web server will assist researchers in the identification of potential antiviral agents. It would also save time and cost by prioritizing new drugs against viruses before their synthesis and experimental testing.

Comparative evaluation of 11 in silico models for the prediction of small molecule mutagenicity: role of steric hindrance and electron-withdrawing groups

The goal of this investigation was to perform a comparative analysis on how accurately 11 routinely-used in silico programs correctly predicted the mutagenicity of test compounds that contained either bulky or electron-withdrawing substituents. To our knowledge this is the first study of its kind in the literature. Such substituents are common in many pharmaceutical agents so there is a significant need for reliable in silico programs to predict precisely whether they truly pose a risk for mutagenicity. The predictions from each program were compared to experimental data derived from the Ames II test, a rapid reverse mutagenicity assay with a high degree of agreement with the traditional Ames assay. Eleven in silico programs were evaluated and compared: Derek for Windows, Derek Nexus, Leadscope Model Applier (LSMA), LSMA featuring the in vitro microbial Escherichia coli-Salmonella typhimurium TA102 A-T Suite (LSMA+), TOPKAT, CAESAR, TEST, ChemSilico (±S9 suites), MC4PC and a novel DNA docking model. The presence of bulky or electron-withdrawing functional groups in the vicinity of a mutagenic toxicophore in the test compounds clearly affected the ability of each in silico model to predict non-mutagenicity correctly. This was because of an over reliance on the part of the programs to provide mutagenicity alerts when a particular toxicophore is present irrespective of the structural environment surrounding the toxicophore. From this investigation it can be concluded that these models provide a high degree of specificity (ranging from 71% to 100%) and are generally conservative in their predictions in terms of sensitivity (ranging from 5% t o 78%). These values are in general agreement with most other comparative studies in the literature. Interestingly, the DNA docking model was the most sensitive model evaluated, suggesting a potentially useful new mode of screening for mutagens. Another important finding was that the combination of a quantitative structure-activity relationship and an expert rules system appeared to offer little advantage in terms of sensitivity, despite of the requirement for such a screening paradigm under the ICH M7 regulatory guideline.

Chemoinformatics: Achievements and Challenges, a Personal View

Chemoinformatics provides computer methods for learning from chemical data and for modeling tasks a chemist is facing. The field has evolved in the past 50 years and has substantially shaped how chemical research is performed by providing access to chemical information on a scale unattainable by traditional methods. Many physical, chemical and biological data have been predicted from structural data. For the early phases of drug design, methods have been developed that are used in all major pharmaceutical companies. However, all domains of chemistry can benefit from chemoinformatics methods; many areas that are not yet well developed, but could substantially gain from the use of chemoinformatics methods. The quality of data is of crucial importance for successful results. Computer-assisted structure elucidation and computer-assisted synthesis design have been attempted in the early years of chemoinformatics. Because of the importance of these fields to the chemist, new approaches should be made with better hardware and software techniques. Society's concern about the impact of chemicals on human health and the environment could be met by the development of methods for toxicity prediction and risk assessment. In conjunction with bioinformatics, our understanding of the events in living organisms could be deepened and, thus, novel strategies for curing diseases developed. With so many challenging tasks awaiting solutions, the future is bright for chemoinformatics.

Systems Biology and Biomarkers of Early Effects for Occupational Exposure Limit Setting

In a recent National Research Council document, new strategies for risk assessment were described to enable more accurate and quicker assessments. This report suggested that evaluating individual responses through increased use of bio-monitoring could improve dose-response estimations. Identification of specific biomarkers may be useful for diagnostics or risk prediction as they have the potential to improve exposure assessments. This paper discusses systems biology, biomarkers of effect, and computational toxicology approaches and their relevance to the occupational exposure limit setting process. The systems biology approach evaluates the integration of biological processes and how disruption of these processes by chemicals or other hazards affects disease outcomes. This type of approach could provide information used in delineating the mode of action of the response or toxicity, and may be useful to define the low adverse and no adverse effect levels. Biomarkers of effect are changes measured in biological systems and are considered to be preclinical in nature. Advances in computational methods and experimental -omics methods that allow the simultaneous measurement of families of macromolecules such as DNA, RNA, and proteins in a single analysis have made these systems approaches feasible for broad application. The utility of the information for risk assessments from -omics approaches has shown promise and can provide information on mode of action and dose-response relationships. As these techniques evolve, estimation of internal dose and response biomarkers will be a critical test of these new technologies for application in risk assessment strategies. While proof of concept studies have been conducted that provide evidence of their value, challenges with standardization and harmonization still need to be overcome before these methods are used routinely.

Identification of putative estrogen receptor-mediated endocrine disrupting chemicals using QSAR- and structure-based virtual screening approaches

Identification of endocrine disrupting chemicals is one of the important goals of environmental chemical hazard screening. We report on the development of validated in silico predictors of chemicals likely to cause estrogen receptor (ER)-mediated endocrine disruption to facilitate their prioritization for future screening. A database of relative binding affinity of a large number of ERα and/or ERβ ligands was assembled (546 for ERα and 137 for ERβ). Both single-task learning (STL) and multi-task learning (MTL) continuous quantitative structure-activity relationship (QSAR) models were developed for predicting ligand binding affinity to ERα or ERβ. High predictive accuracy was achieved for ERα binding affinity (MTL R(2)=0.71, STL R(2)=0.73). For ERβ binding affinity, MTL models were significantly more predictive (R(2)=0.53, p<0.05) than STL models. In addition, docking studies were performed on a set of ER agonists/antagonists (67 agonists and 39 antagonists for ERα, 48 agonists and 32 antagonists for ERβ, supplemented by putative decoys/non-binders) using the following ER structures (in complexes with respective ligands) retrieved from the Protein Data Bank: ERα agonist (PDB ID: 1L2I), ERα antagonist (PDB ID: 3DT3), ERβ agonist (PDB ID: 2NV7), and ERβ antagonist (PDB ID: 1L2J). We found that all four ER conformations discriminated their corresponding ligands from presumed non-binders. Finally, both QSAR models and ER structures were employed in parallel to virtually screen several large libraries of environmental chemicals to derive a ligand- and structure-based prioritized list of putative estrogenic compounds to be used for in vitro and in vivo experimental validation.

Prediction of acute mammalian toxicity using QSAR methods: a case study of sulfur mustard and its breakdown products

Predicting toxicity quantitatively, using Quantitative Structure Activity Relationships (QSAR), has matured over recent years to the point that the predictions can be used to help identify missing comparison values in a substance's database. In this manuscript we investigate using the lethal dose that kills fifty percent of a test population (LD₅₀) for determining relative toxicity of a number of substances. In general, the smaller the LD₅₀ value, the more toxic the chemical, and the larger the LD₅₀ value, the lower the toxicity. When systemic toxicity and other specific toxicity data are unavailable for the chemical(s) of interest, during emergency responses, LD₅₀ values may be employed to determine the relative toxicity of a series of chemicals. In the present study, a group of chemical warfare agents and their breakdown products have been evaluated using four available rat oral QSAR LD₅₀ models. The QSAR analysis shows that the breakdown products of Sulfur Mustard (HD) are predicted to be less toxic than the parent compound as well as other known breakdown products that have known toxicities. The QSAR estimated break down products LD₅₀ values ranged from 299 mg/kg to 5,764 mg/kg. This evaluation allows for the ranking and toxicity estimation of compounds for which little toxicity information existed; thus leading to better risk decision making in the field.

Naïve Bayes QSDR classification based on spiral-graph Shannon entropies for protein biomarkers in human colon cancer

Fast cancer diagnosis represents a real necessity in applied medicine due to the importance of this disease. Thus, theoretical models can help as prediction tools. Graph theory representation is one option because it permits us to numerically describe any real system such as the protein macromolecules by transforming real properties into molecular graph topological indices. This study proposes a new classification model for proteins linked with human colon cancer by using spiral graph topological indices of protein amino acid sequences. The best quantitative structure-disease relationship model is based on eleven Shannon entropy indices. It was obtained with the Naïve Bayes method and shows excellent predictive ability (90.92%) for new proteins linked with this type of cancer. The statistical analysis confirms that this model allows diagnosing the absence of human colon cancer obtaining an area under receiver operating characteristic of 0.91. The methodology presented can be used for any type of sequential information such as any protein and nucleic acid sequence.

Modeling chemical interaction profiles: I. Spectral data-activity relationship and structure-activity relationship models for inhibitors and non-inhibitors of cytochrome P450 CYP3A4 and CYP2D6 isozymes

An interagency collaboration was established to model chemical interactions that may cause adverse health effects when an exposure to a mixture of chemicals occurs. Many of these chemicals—drugs, pesticides, and environmental pollutant—interact at the level of metabolic biotransformations mediated by cytochrome P450 (CYP) enzymes. In the present work, spectral data-activity relationship (SDAR) and structure-activity relationship (SAR) approaches were used to develop machine-learning classifiers of inhibitors and non-inhibitors of the CYP3A4 and CYP2D6 isozymes. The models were built upon 602 reference pharmaceutical compounds whose interactions have been deduced from clinical data, and 100 additional chemicals that were used to evaluate model performance in an external validation (EV) test. SDAR is an innovative modeling approach that relies on discriminant analysis applied to binned nuclear magnetic resonance (NMR) spectral descriptors. In the present work, both 1D ¹³C and 1D ¹⁵N-NMR spectra were used together in a novel implementation of the SDAR technique. It was found that increasing the binning size of 1D ¹³C-NMR and ¹⁵N-NMR spectra caused an increase in the tenfold cross-validation (CV) performance in terms of both the rate of correct classification and sensitivity. The results of SDAR modeling were verified using SAR. For SAR modeling, a decision forest approach involving from 6 to 17 Mold² descriptors in a tree was used. Average rates of correct classification of SDAR and SAR models in a hundred CV tests were 60% and 61% for CYP3A4, and 62% and 70% for CYP2D6, respectively. The rates of correct classification of SDAR and SAR models in the EV test were 73% and 86% for CYP3A4, and 76% and 90% for CYP2D6, respectively. Thus, both SDAR and SAR methods demonstrated a comparable performance in modeling a large set of structurally diverse data. Based on unique NMR structural descriptors, the new SDAR modeling method complements the existing SAR techniques, providing an independent estimator that can increase confidence in a structure-activity assessment. When modeling was applied to hazardous environmental chemicals, it was found that up to 20% of them may be substrates and up to 10% of them may be inhibitors of the CYP3A4 and CYP2D6 isoforms. The developed models provide a rare opportunity for the environmental health branch of the public health service to extrapolate to hazardous chemicals directly from human clinical data. Therefore, the pharmacological and environmental health branches are both expected to benefit from these reported models.