Todd M. Martin

CAESAR models for developmental toxicity

BackgroundThe new REACH legislation requires assessment of a large number of chemicals in the European market for several endpoints. Developmental toxicity is one of the most difficult endpoints to assess, on account of the complexity, length and costs of experiments. Following the encouragement of QSAR (in silico) methods provided in the REACH itself, the CAESAR project has developed several models.ResultsTwo QSAR models for developmental toxicity have been developed, using different statistical/mathematical methods. Both models performed well. The first makes a classification based on a random forest algorithm, while the second is based on an adaptive fuzzy partition algorithm. The first model has been implemented and inserted into the CAESAR on-line application, which is java-based software that allows everyone to freely use the models.ConclusionsThe CAESAR QSAR models have been developed with the aim to minimize false negatives in order to make them more usable for REACH. The CAESAR on-line application ensures that both industry and regulators can easily access and use the developmental toxicity model (as well as the models for the other four endpoints).

Does rational selection of training and test sets improve the outcome of QSAR modeling

Prior to using a quantitative structure activity relationship (QSAR) model for external predictions, its predictive power should be established and validated. In the absence of a true external data set, the best way to validate the predictive ability of a model is to perform its statistical external validation. In statistical external validation, the overall data set is divided into training and test sets. Commonly, this splitting is performed using random division. Rational splitting methods can divide data sets into training and test sets in an intelligent fashion. The purpose of this study was to determine whether rational division methods lead to more predictive models compared to random division. A special data splitting procedure was used to facilitate the comparison between random and rational division methods. For each toxicity end point, the overall data set was divided into a modeling set (80% of the overall set) and an external evaluation set (20% of the overall set) using random division. The modeling set was then subdivided into a training set (80% of the modeling set) and a test set (20% of the modeling set) using rational division methods and by using random division. The Kennard-Stone, minimal test set dissimilarity, and sphere exclusion algorithms were used as the rational division methods. The hierarchical clustering, random forest, and k-nearest neighbor (kNN) methods were used to develop QSAR models based on the training sets. For kNN QSAR, multiple training and test sets were generated, and multiple QSAR models were built. The results of this study indicate that models based on rational division methods generate better statistical results for the test sets than models based on random division, but the predictive power of both types of models are comparable.

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 TOPKATs 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.

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.

Preparation of budesonide and budesonide-PLA microparticles using supercritical fluid precipitation technology

The objective of this study was to prepare and characterize microparticles of budesonide alone and budesonide and polylactic acid (PLA) using supercritical fluid (SCF) technology. A precipitation with a compressed antisolvent (PCA) technique employing supercritical CO2 and a nozzle with 100-μm internal diameter was used to prepare microparticles of budesonide and budesonide-PLA. The effect of various operating variables (temperature and pressure of CO2 and flow rates of drug-polymer solution and/or CO2) and formulation variables (0.25%, 0.5%, and 1% budesonide in methylene chloride) on the morphology and size distribution of the microparticles was determined using scanning electron microscopy. In addition, budesonide-PLA particles were characterized for their surface charge and drug-polymer interactions using a zeta meter and differential scanning calorimetry (DSC), respectively. Furthermore, in vitro budesonide release from budesonide-PLA microparticles was determined at 37°C. Using the PCA process, budesonide and budesonide-PLA microparticles with mean diameters of 1 to 2 μm were prepared. An increase in budesonide concentration (0.25%–1% wt/vol) resulted in budesonide microparticles that were fairly spherical and less aggiomerated. In addition, the size of the microparticles increased with an increase in the drug-polymer solution flow rate (1.4–4.7 mL/min) or with a decrease in the CO2 flow rate (50–10 mL/min). Budesonide-PLA microparticles had a drug loading of 7.94%, equivalent to ∼80% encapsulation efficiency. Budesonide-PLA microparticles had a zeta potential of— 37±4 mV, and DSC studies indicated that SCF processing of budesonide-PLA microparticles resulted in the loss of budesonide crystallinity. Finally, in vitro drug release studies at 37°C indicated 50% budesonide release from the budesonide-PLA microparticles at the end of 28 days. Thus, the PCA process was successful in producing budesonide and budesonide-PLA microparticles. In addition, budesonide-PLA microparticles sustained budesonide release for 4 weeks.

Comparison of in silico models for prediction of mutagenicity.

Using a dataset with more than 6000 compounds, the performance of eight quantitative structure activity relationships (QSAR) models was evaluated: ACD/Tox Suite, Absorption, Distribution, Metabolism, Elimination, and Toxicity of chemical substances (ADMET) predictor, Derek, Toxicity Estimation Software Tool (T.E.S.T.), TOxicity Prediction by Komputer Assisted Technology (TOPKAT), Toxtree, CEASAR, and SARpy (SAR in python). In general, the results showed a high level of performance. To have a realistic estimate of the predictive ability, the results for chemicals inside and outside the training set for each model were considered. The effect of applicability domain tools (when available) on the prediction accuracy was also evaluated. The predictive tools included QSAR models, knowledge-based systems, and a combination of both methods. Models based on statistical QSAR methods gave better results.

MOAtox: A comprehensive mode of action and acute aquatic toxicity database for predictive model development

The mode of toxic action (MOA) has been recognized as a key determinant of chemical toxicity and as an alternative to chemical class-based predictive toxicity modeling. However, the development of quantitative structure activity relationship (QSAR) and other models has been limited by the availability of comprehensive high quality MOA and toxicity databases. The current study developed a dataset of MOA assignments for 1213 chemicals that included a diversity of metals, pesticides, and other organic compounds that encompassed six broad and 31 specific MOAs. MOA assignments were made using a combination of high confidence approaches that included international consensus classifications, QSAR predictions, and weight of evidence professional judgment based on an assessment of structure and literature information. A toxicity database of 674 acute values linked to chemical MOA was developed for fish and invertebrates. Additionally, species-specific measured or high confidence estimated acute values were developed for the four aquatic species with the most reported toxicity values: rainbow trout (Oncorhynchus mykiss), fathead minnow (Pimephales promelas), bluegill (Lepomis macrochirus), and the cladoceran (Daphnia magna). Measured acute toxicity values met strict standardization and quality assurance requirements. Toxicity values for chemicals with missing species-specific data were estimated using established interspecies correlation models and procedures (Web-ICE; http://epa.gov/ceampubl/fchain/webice/), with the highest confidence values selected. The resulting dataset of MOA assignments and paired toxicity values are provided in spreadsheet format as a comprehensive standardized dataset available for predictive aquatic toxicology model development.

A Hierarchical Clustering Methodology for the Estimation of Toxicity

ABSTRACT A quantitative structure-activity relationship (QSAR) methodology based on hierarchical clustering was developed to predict toxicological endpoints. This methodology utilizes Wards method to divide a training set into a series of structurally similar clusters. The structural similarity is defined in terms of 2-D physicochemical descriptors (such as connectivity and E-state indices). A genetic algorithm-based technique is used to generate statistically valid QSAR models for each cluster (using the pool of descriptors described above). The toxicity for a given query compound is estimated using the weighted average of the predictions from the closest cluster from each step in the hierarchical clustering assuming that the compound is within the domain of applicability of the cluster. The hierarchical clustering methodology was tested using a Tetrahymena pyriformis acute toxicity data set containing 644 chemicals in the training set and with two prediction sets containing 339 and 110 chemicals. The results from the hierarchical clustering methodology were compared to the results from several different QSAR methodologies.

Prediction of Aquatic Toxicity Mode of Action Using Linear Discriminant and Random Forest Models

The ability to determine the mode of action (MOA) for a diverse group of chemicals is a critical part of ecological risk assessment and chemical regulation. However, existing MOA assignment approaches in ecotoxicology have been limited to a relatively few MOAs, have high uncertainty, or rely on professional judgment. In this study, machine based learning algorithms (linear discriminant analysis and random forest) were used to develop models for assigning aquatic toxicity MOA. These methods were selected since they have been shown to be able to correlate diverse data sets and provide an indication of the most important descriptors. A data set of MOA assignments for 924 chemicals was developed using a combination of high confidence assignments, international consensus classifications, ASTER (ASessment Tools for the Evaluation of Risk) predictions, and weight of evidence professional judgment based an assessment of structure and literature information. The overall data set was randomly divided into a training set (75%) and a validation set (25%) and then used to develop linear discriminant analysis (LDA) and random forest (RF) MOA assignment models. The LDA and RF models had high internal concordance and specificity and were able to produce overall prediction accuracies ranging from 84.5 to 87.7% for the validation set. These results demonstrate that computational chemistry approaches can be used to determine the acute toxicity MOAs across a large range of structures and mechanisms.

Using Toxicological Evidence from QSAR Models in Practice

Leading QSAR models provide supporting documentation in addition to a predicted toxicological value. Such information enables the toxicologist to explore the properties of chemical substances as well as to review and to increase the reliability of toxicity predictions. This article focuses on the use of this information in practice. We explore the supporting documentation provided by the EPISuite, T.E.S.T. and VEGA platforms when evaluating the bioconcentration factor (BCF) of three example compounds. Each compound presents a different challenge: to recognize high reliability, analyze complex evidence of reliability, and recognize uncertainty. In each case, we first describe and discuss the supporting documentation provided by the QSAR platforms. We then discuss the judgments on reliability across sectors from 28 toxicologists who used this supporting information and commented on the process. The article demonstrates both the use of QSAR models as tools to reduce or replace in vivo testing, and the need for scientific expertise and rigor in their use.