Future of toxicology--predictive toxicology: An expanded view of "chemical toxicity"

Toxicological assessment of photoactivated tetra-cationic porphyrin molecules under white light exposure in a Caenorhabditis elegans model

Photodynamic therapy (PDT) utilizes the potential of photosensitizing substances to absorb light energy and produce reactive oxygen species. Tetra-cationic porphyrins, which have organic or coordination compounds attached to their periphery, are heterocyclic derivatives with well-described antimicrobial and antitumoral properties. This is due to their ability to produce reactive oxygen species and their photobiological properties in solution. Consequently, these molecules are promising candidates as new and more effective photosensitizers with biomedical, environmental, and other biomedical applications. Prior to human exposure, it is essential to establish the toxicological profile of these molecules using in vivo models. In this study, we used Caenorhabditis elegans, a small free-living nematode, as a model for assessing toxic effects and predicting toxicity in preclinical research. We evaluated the toxic effects of porphyrins (neutral and tetra-cationic) on nematodes under dark/light conditions. Our findings demonstrate that tetra-methylated porphyrins (3TMeP and 4TMeP) at a concentration of 3.3 µg/mL (1.36 and 0.93 µM) exhibit high toxicity (as evidenced by reduced survival, development, and locomotion) under dark conditions. Moreover, photoactivated tetra-methylated porphyrins induce higher ROS levels compared to neutral (3TPyP and 4TPyP), tetra-palladated (3PdTPyP and 4PdTPyP), and tetra-platinated (3PtTPyP and 4PtTPyP) porphyrins, which may be responsible for the observed toxic effects.

In utero exposure to ionizing radiation and metabolic regulation: perspectives for future multi- and trans-generation effects studies

PURPOSE

The radiation protection community has been particularly attentive to the risks of delayed effects on offspring from low dose or low dose-rate exposures to ionizing radiation. Despite this, the current epidemiologic studies and scientific data are still insufficient to provide the necessary evidence for improving risk assessment guidelines. This literature review aims to inform future studies on multigenerational and transgenerational effects. It primarily focuses on animal studies involving in utero exposure and discusses crucial elements for interpreting the results. These elements include in utero exposure scenarios relative to the developmental stages of the embryo/fetus, and the primary biological mechanisms responsible for transmitting heritable or hereditary effects to future generations. The review addresses several issues within the contexts of both multigenerational and transgenerational effects, with a focus on hereditary perspectives.

CONCLUSIONS

Knowledge consolidation in the field of Developmental Origins of Health and Disease (DOHaD) has led us to propose a new study strategy. This strategy aims to address the transgenerational effects of in utero exposure to low dose and low dose-rate radiation. Within this concept, there is a possibility that disruption of epigenetic programming in embryonic and fetal cells may occur. This disruption could lead to metabolic dysfunction, which in turn may cause abnormal responses to future environmental challenges, consequently increasing disease risk. Lastly, we discuss methodological limitations in our studies. These limitations are related to cohort size, follow-up time, model radiosensitivity, and analytical techniques. We propose scientific and analytical strategies for future research in this field.

Advancing Computational Toxicology by Interpretable Machine Learning

Chemical toxicity evaluations for drugs, consumer products, and environmental chemicals have a critical impact on human health. Traditional animal models to evaluate chemical toxicity are expensive, time-consuming, and often fail to detect toxicants in humans. Computational toxicology is a promising alternative approach that utilizes machine learning (ML) and deep learning (DL) techniques to predict the toxicity potentials of chemicals. Although the applications of ML- and DL-based computational models in chemical toxicity predictions are attractive, many toxicity models are "black boxes" in nature and difficult to interpret by toxicologists, which hampers the chemical risk assessments using these models. The recent progress of interpretable ML (IML) in the computer science field meets this urgent need to unveil the underlying toxicity mechanisms and elucidate the domain knowledge of toxicity models. In this review, we focused on the applications of IML in computational toxicology, including toxicity feature data, model interpretation methods, use of knowledge base frameworks in IML development, and recent applications. The challenges and future directions of IML modeling in toxicology are also discussed. We hope this review can encourage efforts in developing interpretable models with new IML algorithms that can assist new chemical assessments by illustrating toxicity mechanisms in humans.

LightGBM: An Effective and Scalable Algorithm for Prediction of Chemical Toxicity-Application to the Tox21 and Mutagenicity Data Sets

Machine learning algorithms have attained widespread use in assessing the potential toxicities of pharmaceuticals and industrial chemicals because of their faster speed and lower cost compared to experimental bioassays. Gradient boosting is an effective algorithm that often achieves high predictivity, but historically the relative long computational time limited its applications in predicting large compound libraries or developing in silico predictive models that require frequent retraining. LightGBM, a recent improvement of the gradient boosting algorithm, inherited its high predictivity but resolved its scalability and long computational time by adopting a leaf-wise tree growth strategy and introducing novel techniques. In this study, we compared the predictive performance and the computational time of LightGBM to deep neural networks, random forests, support vector machines, and XGBoost. All algorithms were rigorously evaluated on publicly available Tox21 and mutagenicity data sets using a Bayesian optimization integrated nested 10-fold cross-validation scheme that performs hyperparameter optimization while examining model generalizability and transferability to new data. The evaluation results demonstrated that LightGBM is an effective and highly scalable algorithm offering the best predictive performance while consuming significantly shorter computational time than the other investigated algorithms across all Tox21 and mutagenicity data sets. We recommend LightGBM for applications of in silico safety assessment and also other areas of cheminformatics to fulfill the ever-growing demand for accurate and rapid prediction of various toxicity or activity related end points of large compound libraries present in the pharmaceutical and chemical industry.

In vitro or not in vitro: a short journey through a long history

The aim of ecotoxicology is to study toxic effects on constituents of ecosystems, with the protection goal being populations and communities rather than individual organisms. In this ecosystem perspective, the use of in vitro methodologies measuring cellular and subcellular endpoints at a first glance appears to be odd. Nevertheless, more recently in vitro approaches gained momentum in ecotoxicology. In this article, we will discuss important application domains of in vitro methods in ecotoxicology. One area is the use of in vitro assays to replace, reduce, and refine (3R) in vivo tests. Research in this field has focused mainly on the use of in vitro cytotoxicity assays with fish cells as non-animal alternative to the in vivo lethality test with fish and on in vitro biotransformation assays as part of an alternative testing strategy for bioaccumulation testing with fish. Lessons learned from this research include the importance of a critical evaluation of the sensitivity, specificity and exposure conditions of in vitro assays, as well as the availability of appropriate in vitro-in vivo extrapolation models. In addition to this classical 3R application, other application domains of in vitro assays in ecotoxicology include the screening and prioritization of chemical hazards, the categorization of chemicals according to their modes of action and the provision of mechanistic information for the pathway-based prediction of adverse outcomes. The applications discussed in this essay may highlight the potential of in vitro technologies to enhance the environmental hazard assessment of single chemicals and complex mixtures at a reduced need of animal testing.

Quantitative Regression Models for the Prediction of Chemical Properties by an Efficient Workflow

Rapid safety assessment is more and more needed for the increasing chemicals both in chemical industries and regulators around the world. The traditional experimental methods couldn't meet the current demand any more. With the development of the information technology and the growth of experimental data, in silico modeling has become a practical and rapid alternative for the assessment of chemical properties, especially for the toxicity prediction of organic chemicals. In this study, a quantitative regression workflow was built by KNIME to predict chemical properties. With this regression workflow, quantitative values of chemical properties can be obtained, which is different from the binary-classification model or multi-classification models that can only give qualitative results. To illustrate the usage of the workflow, two predictive models were constructed based on datasets of Tetrahymena pyriformis toxicity and Aqueous solubility. The qcv (2) and qtest (2) of 5-fold cross validation and external validation for both types of models were greater than 0.7, which implies that our models are robust and reliable, and the workflow is very convenient and efficient in prediction of various chemical properties.

ToxCast Chemical Landscape: Paving the Road to 21st Century Toxicology

The U.S. Environmental Protection Agency's (EPA) ToxCast program is testing a large library of Agency-relevant chemicals using in vitro high-throughput screening (HTS) approaches to support the development of improved toxicity prediction models. Launched in 2007, Phase I of the program screened 310 chemicals, mostly pesticides, across hundreds of ToxCast assay end points. In Phase II, the ToxCast library was expanded to 1878 chemicals, culminating in the public release of screening data at the end of 2013. Subsequent expansion in Phase III has resulted in more than 3800 chemicals actively undergoing ToxCast screening, 96% of which are also being screened in the multi-Agency Tox21 project. The chemical library unpinning these efforts plays a central role in defining the scope and potential application of ToxCast HTS results. The history of the phased construction of EPA's ToxCast library is reviewed, followed by a survey of the library contents from several different vantage points. CAS Registry Numbers are used to assess ToxCast library coverage of important toxicity, regulatory, and exposure inventories. Structure-based representations of ToxCast chemicals are then used to compute physicochemical properties, substructural features, and structural alerts for toxicity and biotransformation. Cheminformatics approaches using these varied representations are applied to defining the boundaries of HTS testability, evaluating chemical diversity, and comparing the ToxCast library to potential target application inventories, such as used in EPA's Endocrine Disruption Screening Program (EDSP). Through several examples, the ToxCast chemical library is demonstrated to provide comprehensive coverage of the knowledge domains and target inventories of potential interest to EPA. Furthermore, the varied representations and approaches presented here define local chemistry domains potentially worthy of further investigation (e.g., not currently covered in the testing library or defined by toxicity "alerts") to strategically support data mining and predictive toxicology modeling moving forward.

Low potency toxins reveal dense interaction networks in metabolism

BACKGROUND

The chemicals of metabolism are constructed of a small set of atoms and bonds. This may be because chemical structures outside the chemical space in which life operates are incompatible with biochemistry, or because mechanisms to make or utilize such excluded structures has not evolved. In this paper I address the extent to which biochemistry is restricted to a small fraction of the chemical space of possible chemicals, a restricted subset that I call Biochemical Space. I explore evidence that this restriction is at least in part due to selection again specific structures, and suggest a mechanism by which this occurs.

RESULTS

Chemicals that contain structures that our outside Biochemical Space (UnBiological groups) are more likely to be toxic to a wide range of organisms, even though they have no specifically toxic groups and no obvious mechanism of toxicity. This correlation of UnBiological with toxicity is stronger for low potency (millimolar) toxins. I relate this to the observation that most chemicals interact with many biological structures at low millimolar toxicity. I hypothesise that life has to select its components not only to have a specific set of functions but also to avoid interactions with all the other components of life that might degrade their function.

CONCLUSIONS

The chemistry of life has to form a dense, self-consistent network of chemical structures, and cannot easily be arbitrarily extended. The toxicity of arbitrary chemicals is a reflection of the disruption to that network occasioned by trying to insert a chemical into it without also selecting all the other components to tolerate that chemical. This suggests new ways to test for the toxicity of chemicals, and that engineering organisms to make high concentrations of materials such as chemical precursors or fuels may require more substantial engineering than just of the synthetic pathways involved.

Pattern recognition for cytotoxicity mode of action (MOA) of chemicals by using a high-throughput real-time cell analyzer

Slope and entropy are extracted from the relative normalized cell index collected from RTCA. Then the median value is selected to denote the main mode of actin (MoA) of chemical. Hierarchical cluster is used for pattern recognition of MoA.

Toxicokinetic Triage for Environmental Chemicals

Toxicokinetic (TK) models link administered doses to plasma, blood, and tissue concentrations. High-throughput TK (HTTK) performs in vitro to in vivo extrapolation to predict TK from rapid in vitro measurements and chemical structure-based properties. A significant toxicological application of HTTK has been "reverse dosimetry," in which bioactive concentrations from in vitro screening studies are converted into in vivo doses (mg/kg BW/day). These doses are predicted to produce steady-state plasma concentrations that are equivalent to in vitro bioactive concentrations. In this study, we evaluate the impact of the approximations and assumptions necessary for reverse dosimetry and develop methods to determine whether HTTK tools are appropriate or may lead to false conclusions for a particular chemical. Based on literature in vivo data for 87 chemicals, we identified specific properties (eg, in vitro HTTK data, physico-chemical descriptors, and predicted transporter affinities) that correlate with poor HTTK predictive ability. For 271 chemicals we developed a generic HT physiologically based TK (HTPBTK) model that predicts non-steady-state chemical concentration time-courses for a variety of exposure scenarios. We used this HTPBTK model to find that assumptions previously used for reverse dosimetry are usually appropriate, except most notably for highly bioaccumulative compounds. For the thousands of man-made chemicals in the environment that currently have no TK data, we propose a 4-element framework for chemical TK triage that can group chemicals into 7 different categories associated with varying levels of confidence in HTTK predictions. For 349 chemicals with literature HTTK data, we differentiated those chemicals for which HTTK approaches are likely to be sufficient, from those that may require additional data.

The impact of composite AUC estimates on the prediction of systemic exposure in toxicology experiments

Current toxicity protocols relate measures of systemic exposure (i.e. AUC, C_max) as obtained by non-compartmental analysis to observed toxicity. A complicating factor in this practice is the potential bias in the estimates defining safe drug exposure. Moreover, it prevents the assessment of variability. The objective of the current investigation was therefore (a) to demonstrate the feasibility of applying nonlinear mixed effects modelling for the evaluation of toxicokinetics and (b) to assess the bias and accuracy in summary measures of systemic exposure for each method. Here, simulation scenarios were evaluated, which mimic toxicology protocols in rodents. To ensure differences in pharmacokinetic properties are accounted for, hypothetical drugs with varying disposition properties were considered. Data analysis was performed using non-compartmental methods and nonlinear mixed effects modelling. Exposure levels were expressed as area under the concentration versus time curve (AUC), peak concentrations (C_max) and time above a predefined threshold (TAT). Results were then compared with the reference values to assess the bias and precision of parameter estimates. Higher accuracy and precision were observed for model-based estimates (i.e. AUC, C_max and TAT), irrespective of group or treatment duration, as compared with non-compartmental analysis. Despite the focus of guidelines on establishing safety thresholds for the evaluation of new molecules in humans, current methods neglect uncertainty, lack of precision and bias in parameter estimates. The use of nonlinear mixed effects modelling for the analysis of toxicokinetics provides insight into variability and should be considered for predicting safe exposure in humans.

Chemical information matters: an e-Research perspective on information and data sharing in the chemical sciences

Recently, a number of organisations have called for open access to scientific information and especially to the data obtained from publicly funded research, among which the Royal Society report and the European Commission press release are particularly notable. It has long been accepted that building research on the foundations laid by other scientists is both effective and efficient. Regrettably, some disciplines, chemistry being one, have been slow to recognise the value of sharing and have thus been reluctant to curate their data and information in preparation for exchanging it. The very significant increases in both the volume and the complexity of the datasets produced has encouraged the expansion of e-Research, and stimulated the development of methodologies for managing, organising, and analysing "big data". We review the evolution of cheminformatics, the amalgam of chemistry, computer science, and information technology, and assess the wider e-Science and e-Research perspective. Chemical information does matter, as do matters of communicating data and collaborating with data. For chemistry, unique identifiers, structure representations, and property descriptors are essential to the activities of sharing and exchange. Open science entails the sharing of more than mere facts: for example, the publication of negative outcomes can facilitate better understanding of which synthetic routes to choose, an aspiration of the Dial-a-Molecule Grand Challenge. The protagonists of open notebook science go even further and exchange their thoughts and plans. We consider the concepts of preservation, curation, provenance, discovery, and access in the context of the research lifecycle, and then focus on the role of metadata, particularly the ontologies on which the emerging chemical Semantic Web will depend. Among our conclusions, we present our choice of the "grand challenges" for the preservation and sharing of chemical information.

Predictive toxicology of cobalt ferrite nanoparticles: comparative in-vitro study of different cellular models using methods of knowledge discovery from data

BACKGROUND

Cobalt-ferrite nanoparticles (Co-Fe NPs) are attractive for nanotechnology-based therapies. Thus, exploring their effect on viability of seven different cell lines representing different organs of the human body is highly important.

METHODS

The toxicological effects of Co-Fe NPs were studied by in-vitro exposure of A549 and NCIH441 cell-lines (lung), precision-cut lung slices from rat, HepG2 cell-line (liver), MDCK cell-line (kidney), Caco-2 TC7 cell-line (intestine), TK6 (lymphoblasts) and primary mouse dendritic-cells. Toxicity was examined following exposure to Co-Fe NPs in the concentration range of 0.05 -1.2 mM for 24 and 72 h, using Alamar blue, MTT and neutral red assays. Changes in oxidative stress were determined by a dichlorodihydrofluorescein diacetate based assay. Data analysis and predictive modeling of the obtained data sets were executed by employing methods of Knowledge Discovery from Data with emphasis on a decision tree model (J48).

RESULTS

Different dose-response curves of cell viability were obtained for each of the seven cell lines upon exposure to Co-Fe NPs. Increase of oxidative stress was induced by Co-Fe NPs and found to be dependent on the cell type. A high linear correlation (R2=0.97) was found between the toxicity of Co-Fe NPs and the extent of ROS generation following their exposure to Co-Fe NPs. The algorithm we applied to model the observed toxicity belongs to a type of supervised classifier. The decision tree model yielded the following order with decrease of the ranking parameter: NP concentrations (as the most influencing parameter), cell type (possessing the following hierarchy of cell sensitivity towards viability decrease: TK6 > Lung slices > NCIH441 > Caco-2 = MDCK > A549 > HepG2 = Dendritic) and time of exposure, where the highest-ranking parameter (NP concentration) provides the highest information gain with respect to toxicity. The validity of the chosen decision tree model J48 was established by yielding a higher accuracy than that of the well-known "naive bayes" classifier.

CONCLUSIONS

The observed correlation between the oxidative stress, caused by the presence of the Co-Fe NPs, with the hierarchy of sensitivity of the different cell types towards toxicity, suggests that oxidative stress is one possible mechanism for the toxicity of Co-Fe NPs.

On the origins of drug polypharmacology

The ability of many drugs, unintended most often, to interact with multiple proteins is commonly referred to as polypharmacology. Could this be a reminiscent chemical signature of early protein evolution?

Toxicity data informatics: supporting a new paradigm for toxicity prediction

ABSTRACT Chemical toxicity data at all levels of description, from treatment-level dose response data to a high-level summarized toxicity "endpoint," effectively circumscribe, enable, and limit predictive toxicology approaches and capabilities. Several new and evolving public data initiatives focused on the world of chemical toxicity information-as represented here by ToxML (Toxicology XML standard), DSSTox (Distributed Structure-Searchable Toxicity Database Network), and ACToR (Aggregated Computational Toxicology Resource)-are contributing to the creation of a more unified, mineable, and modelable landscape of public toxicity data. These projects address different layers in the spectrum of toxicological data representation and detail and, additionally, span diverse domains of toxicology and chemistry in relation to industry and environmental regulatory concerns. For each of the three projects, data standards are the key to enabling "read-across" in relation to toxicity data and chemical-indexed information. In turn, "read-across" capability enables flexible data mining, as well as meaningful aggregation of lower levels of toxicity information to summarized, modelable endpoints spanning sufficient areas of chemical space for building predictive models. By means of shared data standards and transparent and flexible rules for data aggregation, these and related public data initiatives are effectively spanning the divides among experimental toxicologists, computational modelers, and the world of chemically indexed, publicly available toxicity information.

Adaptation of high-throughput screening in drug discovery-toxicological screening tests

High-throughput screening (HTS) is one of the newest techniques used in drug design and may be applied in biological and chemical sciences. This method, due to utilization of robots, detectors and software that regulate the whole process, enables a series of analyses of chemical compounds to be conducted in a short time and the affinity of biological structures which is often related to toxicity to be defined. Since 2008 we have implemented the automation of this technique and as a consequence, the possibility to examine 100,000 compounds per day. The HTS method is more frequently utilized in conjunction with analytical techniques such as NMR or coupled methods e.g., LC-MS/MS. Series of studies enable the establishment of the rate of affinity for targets or the level of toxicity. Moreover, researches are conducted concerning conjugation of nanoparticles with drugs and the determination of the toxicity of such structures. For these purposes there are frequently used cell lines. Due to the miniaturization of all systems, it is possible to examine the compound's toxicity having only 1-3 mg of this compound. Determination of cytotoxicity in this way leads to a significant decrease in the expenditure and to a reduction in the length of the study.

Quantitative structure-activity relationship modeling of rat acute toxicity by oral exposure

Few quantitative structure-activity relationship (QSAR) studies have successfully modeled large, diverse rodent toxicity end points. In this study, a comprehensive data set of 7385 compounds with their most conservative lethal dose (LD(50)) values has been compiled. A combinatorial QSAR approach has been employed to develop robust and predictive models of acute toxicity in rats caused by oral exposure to chemicals. To enable fair comparison between the predictive power of models generated in this study versus a commercial toxicity predictor, TOPKAT (Toxicity Prediction by Komputer Assisted Technology), a modeling subset of the entire data set was selected that included all 3472 compounds used in TOPKAT's training set. The remaining 3913 compounds, which were not present in the TOPKAT training set, were used as the external validation set. QSAR models of five different types were developed for the modeling set. The prediction accuracy for the external validation set was estimated by determination coefficient R(2) of linear regression between actual and predicted LD(50) values. The use of the applicability domain threshold implemented in most models generally improved the external prediction accuracy but expectedly led to the decrease in chemical space coverage; depending on the applicability domain threshold, R(2) ranged from 0.24 to 0.70. Ultimately, several consensus models were developed by averaging the predicted LD(50) for every compound using all five models. The consensus models afforded higher prediction accuracy for the external validation data set with the higher coverage as compared to individual constituent models. The validated consensus LD(50) models developed in this study can be used as reliable computational predictors of in vivo acute toxicity.

Computational toxicology: an overview of the sources of data and of modelling methods

BACKGROUND

Toxicology has the goal of ensuring the safety of humans, animals and the environment. Computational toxicology is an area of active development and great potential. There are tangible reasons for the emerging interest in this discipline from academia, industry, regulatory bodies and governments.

RESULTS

Pharmaceuticals, personal health care products, nutritional ingredients and products of the chemical industries are all potential hazards and need to be assessed. Toxicological tests for these products are costly, frequently use laboratory animals and are time-consuming. This delays end-user access to improved products or, conversely, the timely withdrawal of dangerous substances from the market. The aim of computational toxicology is to accelerate the assessment of potentially dangerous substances through in silico models.

CONCLUSIONS

In this review, we provide an overview of the development of models for computational toxicology. Addressing the significant divide between the experimental and computational worlds-believed to be a prime hindrance to computational toxicology-we briefly consider the fundamental issue of toxicological data and the assays they stem from. Different kinds of models that can be built using such data are presented: computational filters, models for specific toxicological endpoints and tools for the generation of testable hypotheses.

Predictive models for carcinogenicity and mutagenicity: frameworks, state-of-the-art, and perspectives

Mutagenicity and carcinogenicity are endpoints of major environmental and regulatory concern. These endpoints are also important targets for development of alternative methods for screening and prediction due to the large number of chemicals of potential concern and the tremendous cost (in time, money, animals) of rodent carcinogenicity bioassays. Both mutagenicity and carcinogenicity involve complex, cellular processes that are only partially understood. Advances in technologies and generation of new data will permit a much deeper understanding. In silico methods for predicting mutagenicity and rodent carcinogenicity based on chemical structural features, along with current mutagenicity and carcinogenicity data sets, have performed well for local prediction (i.e., within specific chemical classes), but are less successful for global prediction (i.e., for a broad range of chemicals). The predictivity of in silico methods can be improved by improving the quality of the data base and endpoints used for modelling. In particular, in vitro assays for clastogenicity need to be improved to reduce false positives (relative to rodent carcinogenicity) and to detect compounds that do not interact directly with DNA or have epigenetic activities. New assays emerging to complement or replace some of the standard assays include Vitotox, GreenScreenGC, and RadarScreen. The needs of industry and regulators to assess thousands of compounds necessitate the development of high-throughput assays combined with innovative data-mining and in silico methods. Various initiatives in this regard have begun, including CAESAR, OSIRIS, CHEMOMENTUM, CHEMPREDICT, OpenTox, EPAA, and ToxCast. In silico methods can be used for priority setting, mechanistic studies, and to estimate potency. Ultimately, such efforts should lead to improvements in application of in silico methods for predicting carcinogenicity to assist industry and regulators and to enhance protection of public health.

Integrated fuzzy concentration addition-independent action (IFCA-IA) model outperforms two-stage prediction (TSP) for predicting mixture toxicity

Mixture toxicities were determined for 12 industrial organic chemicals bearing four different modes of toxic action (MOAs) to Vibrio fischeri, to compare the predictability of the integrated fuzzy concentration addition-independent action (IFCA-IA) model and the two-stage prediction (TSP) model. Three mixtures were designed: The first and second mixtures were based on the ratios of each component at the 1% and 50% effect concentrations (EC(1) and EC(50)), respectively; and the third mixture contained an equimolar ratio of individual components. For the EC(1), EC(50) and equimolar ratio, prediction errors from the IFCA-IA model at the 50% experimental mixture effects were 0.3%, 6% and 0.6%, respectively; while for the TSP model, the corresponding errors were 2.8%, 19% and 24%, respectively. Thus, the IFCA-IA model performed better than the TSP model. The IFCA-IA model calculated two weight coefficients from the molecular structural descriptors, which weigh the relation between concentration addition (CA) and independent action (IA) through the fuzzy membership functions. Thus, MOAs are not pre-requisites for mixture toxicity prediction by the IFCA-IA approach, implying the practicability of this method in toxicity assessment of mixtures.

Use of cell viability assay data improves the prediction accuracy of conventional quantitative structure-activity relationship models of animal carcinogenicity

BACKGROUND

To develop efficient approaches for rapid evaluation of chemical toxicity and human health risk of environmental compounds, the National Toxicology Program (NTP) in collaboration with the National Center for Chemical Genomics has initiated a project on high-throughput screening (HTS) of environmental chemicals. The first HTS results for a set of 1,408 compounds tested for their effects on cell viability in six different cell lines have recently become available via PubChem.

OBJECTIVES

We have explored these data in terms of their utility for predicting adverse health effects of the environmental agents.

METHODS AND RESULTS

Initially, the classification k nearest neighbor (kNN) quantitative structure-activity relationship (QSAR) modeling method was applied to the HTS data only, for a curated data set of 384 compounds. The resulting models had prediction accuracies for training, test (containing 275 compounds together), and external validation (109 compounds) sets as high as 89%, 71%, and 74%, respectively. We then asked if HTS results could be of value in predicting rodent carcinogenicity. We identified 383 compounds for which data were available from both the Berkeley Carcinogenic Potency Database and NTP-HTS studies. We found that compounds classified by HTS as "actives" in at least one cell line were likely to be rodent carcinogens (sensitivity 77%); however, HTS "inactives" were far less informative (specificity 46%). Using chemical descriptors only, kNN QSAR modeling resulted in 62.3% prediction accuracy for rodent carcinogenicity applied to this data set. Importantly, the prediction accuracy of the model was significantly improved (72.7%) when chemical descriptors were augmented by HTS data, which were regarded as biological descriptors.

CONCLUSIONS

Our studies suggest that combining NTP-HTS profiles with conventional chemical descriptors could considerably improve the predictive power of computational approaches in toxicology.

Combinatorial QSAR modeling of chemical toxicants tested against Tetrahymena pyriformis

Selecting most rigorous quantitative structure-activity relationship (QSAR) approaches is of great importance in the development of robust and predictive models of chemical toxicity. To address this issue in a systematic way, we have formed an international virtual collaboratory consisting of six independent groups with shared interests in computational chemical toxicology. We have compiled an aqueous toxicity data set containing 983 unique compounds tested in the same laboratory over a decade against Tetrahymena pyriformis. A modeling set including 644 compounds was selected randomly from the original set and distributed to all groups that used their own QSAR tools for model development. The remaining 339 compounds in the original set (external set I) as well as 110 additional compounds (external set II) published recently by the same laboratory (after this computational study was already in progress) were used as two independent validation sets to assess the external predictive power of individual models. In total, our virtual collaboratory has developed 15 different types of QSAR models of aquatic toxicity for the training set. The internal prediction accuracy for the modeling set ranged from 0.76 to 0.93 as measured by the leave-one-out cross-validation correlation coefficient ( Q abs2). The prediction accuracy for the external validation sets I and II ranged from 0.71 to 0.85 (linear regression coefficient R absI2) and from 0.38 to 0.83 (linear regression coefficient R absII2), respectively. The use of an applicability domain threshold implemented in most models generally improved the external prediction accuracy but at the same time led to a decrease in chemical space coverage. Finally, several consensus models were developed by averaging the predicted aquatic toxicity for every compound using all 15 models, with or without taking into account their respective applicability domains. We find that consensus models afford higher prediction accuracy for the external validation data sets with the highest space coverage as compared to individual constituent models. Our studies prove the power of a collaborative and consensual approach to QSAR model development. The best validated models of aquatic toxicity developed by our collaboratory (both individual and consensus) can be used as reliable computational predictors of aquatic toxicity and are available from any of the participating laboratories.

Computational chemistry approach for the early detection of drug-induced idiosyncratic liver toxicity

Idiosyncratic drug toxicity (IDT), considered as a toxic host-dependent event, with an apparent lack of dose response relationship, is usually not predictable from early phases of clinical trials, representing a particularly confounding complication in drug development. Albeit a rare event (usually <1/5000), IDT is often life threatening and is one of the major reasons new drugs never reach the market or are withdrawn post marketing. Computational methodologies, like the computer-based approach proposed in the present study, can play an important role in addressing IDT in early drug discovery. We report for the first time a systematic evaluation of classification models to predict idiosyncratic hepatotoxicity based on linear discriminant analysis (LDA), artificial neural networks (ANN), and machine learning algorithms (OneR) in conjunction with a 3D molecular structure representation and feature selection methods. These modeling techniques (LDA, feature selection to prevent over-fitting and multicollinearity, ANN to capture nonlinear relationships in the data, as well as the simple OneR classifier) were found to produce QSTR models with satisfactory internal cross-validation statistics and predictivity on an external subset of chemicals. More specifically, the models reached values of accuracy/sensitivity/specificity over 84%/78%/90%, respectively in the training series along with predictivity values ranging from ca. 78 to 86% of correctly classified drugs. An LDA-based desirability analysis was carried out in order to select the levels of the predictor variables needed to trigger the more desirable drug, i.e. the drug with lower potential for idiosyncratic hepatotoxicity. Finally, two external test sets were used to evaluate the ability of the models in discriminating toxic from nontoxic structurally and pharmacologically related drugs and the ability of the best model (LDA) in detecting potential idiosyncratic hepatotoxic drugs, respectively. The computational approach proposed here can be considered as a useful tool in early IDT prognosis.

The expanding role of predictive toxicology: an update on the (Q)SAR models for mutagens and carcinogens

Different regulatory schemes worldwide, and in particular, the preparation for the new REACH (Registration, Evaluation and Authorization of CHemicals) legislation in Europe, increase the reliance on estimation methods for predicting potential chemical hazard. To meet the increased expectations, the availability of valid (Q)SARs becomes a critical issue, especially for endpoints that have complex mechanisms of action, are time-and cost-consuming, and require a large number of animals to test. Here, findings from the survey on (Q)SARs for mutagenicity and carcinogenicity, initiated by the European Chemicals Bureau (ECB) and carried out by the Istituto Superiore di Sanita' are summarized, key aspects are discussed, and a broader view towards future needs and perspectives is given.