Investigating the mechanisms of bioconcentration through QSAR classification trees

Glacier foreland insect uptake synthetic compounds: an emerging environmental concern

Pesticides, synthetic fragrances and polycyclic aromatic hydrocarbons contaminated two glacier-fed streams (Amola, Mandrone) and one spring (Grostè) in the Italian Alps. Ten compounds (chlorpyrifos (CPY), chlorpyrifos-methyl (CPY-m), galaxolide (HHCB), tonalide (AHTN), fluorene (Flu), phenanthrene (Phen), anthracene (Ant), fluoranthene (Fl), pyrene (Pyr), benzo[a]anthracene (BaA)) accumulated in aquatic larvae of chironomids (Diamesa steinboecki, D. latitarsis, D. bertrami, D. tonsa, D. zernyi, Pseudokiefferiella parva, Orthocladiinae) and tipulids. Their tissue concentrations (detected by gas chromatography coupled with mass spectrometry) ranged from 1.1 ± 0.1 ng/g d.w. (= dry weight) (CPY-m in D. tonsa from Amola) to 68.0 ± 9.1 ng/g d.w. (Pyr in D. steinboecki from Mandrone). HHCB, AHTN, and CPY, with one exception, were accumulated by all aquatic insects. Six compounds (CPY, CPY-m, HHCB, AHTN, Fl, Pyr) also contaminated carabids (Nebria germarii, N. castanea, N. jockischii) predating adults of merolimnic insects. Their tissue concentrations ranged from 1.1 ± 0.3 ng/g d.w. (CPY-m in N. germarii from Mandrone) to 84.6 ± 0.3 ng/g d.w. (HHCB in N. castanea from Grostè). HHCB and AHTN were accumulated by all Nebria species. Intersite and interspecies differences were observed, which might be attributed to different environmental contamination levels. There was a stronger similarity between species from the same site than among the same species from different sites, suggesting that uptake is not species specific. At all sites, the concentration of xenobiotics was higher in larvae than in water and comparable or higher in carabids than in larvae from the same site, suggesting trophic transfer by emerging aquatic insects to their riparian predators.

Predicting Solute Descriptors for Organic Chemicals by a Deep Neural Network (DNN) Using Basic Chemical Structures and a Surrogate Metric

Solute descriptors have been widely used to model chemical transfer processes through poly-parameter linear free energy relationships (pp-LFERs); however, there are still substantial difficulties in obtaining these descriptors accurately and quickly for new organic chemicals. In this research, models (PaDEL-DNN) that require only SMILES of chemicals were built to satisfactorily estimate pp-LFER descriptors using deep neural networks (DNN) and the PaDEL chemical representation. The PaDEL-DNN-estimated pp-LFER descriptors demonstrated good performance in modeling storage-lipid/water partitioning coefficient (log K_{storage-lipid/water}), bioconcentration factor (BCF), aqueous solubility (ESOL), and hydration free energy (freesolve). Then, assuming that the accuracy in the estimated values of widely available properties, e.g., logP (octanol-water partition coefficient), can calibrate estimates for less available but related properties, we proposed logP as a surrogate metric for evaluating the overall accuracy of the estimated pp-LFER descriptors. When using the pp-LFER descriptors to model log K_{storage-lipid/water}, BCF, ESOL, and freesolve, we achieved around 0.1 log unit lower errors for chemicals whose estimated pp-LFER descriptors were deemed "accurate" by the surrogate metric. The interpretation of the PaDEL-DNN models revealed that, for a given test chemical, having several (around 5) "similar" chemicals in the training data set was crucial for accurate estimation while the remaining less similar training chemicals provided reasonable baseline estimates. Lastly, pp-LFER descriptors for over 2800 persistent, bioaccumulative, and toxic chemicals were reasonably estimated by combining PaDEL-DNN with the surrogate metric. Overall, the PaDEL-DNN/surrogate metric and newly estimated descriptors will greatly benefit chemical transfer modeling.

Prediction of organic compounds adsorbed by polyethylene and chlorinated polyethylene microplastics in freshwater using QSAR

Microplastics (MPs), a growing class of emerging pollutants in the environment, have attracted widespread attention due to their adsorption properties. Recent research on MPs has mainly concentrated on seawater, and little work has been conducted on freshwater. Investigating and predicting the adsorption behavior of organic pollutants by MPs are necessary in freshwater. In this study, the adsorption behavior of 13 organic chemicals by polyethylene (PE) and chlorinated polyethylene (CPE) MPs was determined under freshwater conditions. Results shows the majority of the organic chemicals exhibit no distinctive differences in their adsorption on two MPs. However, the adsorption of polycyclic aromatic hydrocarbons and chlorobenzene on CPE is obviously stronger than that on PE, and the result is a counter for two pesticides. Quantitative structure activity relationship (QSAR) analysis was performed for the prediction of adsorption capacity. A QSAR model with acceptable performance (R² = 0.8586) was built to predict the adsorptive affinity (expressed as logK_d) of organic compounds on the PE MPs via multivariable linear regression (MLR) on forty-nine determined and collected data. The octanol/water partition coefficient (logK_ow) and excess molar refractive index (E) play dominant roles in the model. A QSAR model with satisfactory performance (R² = 0.9302) was also established for logK_d values from CPE MPs in freshwater by using 13 adsorption data determined. The logK_ow and most negative charge on Cl atom (Q^-_max,cl) play decisive roles in the adsorption. The findings can provide a scientific basis for the risk assessment of waters contaminated by MPs and organic pollutants.

ImbTreeEntropy and ImbTreeAUC: Novel R Packages for Decision Tree Learning on the Imbalanced Datasets

This paper presents two R packages ImbTreeEntropy and ImbTreeAUC to handle imbalanced data problems. ImbTreeEntropy functionality includes application of a generalized entropy functions, such as Rényi, Tsallis, Sharma–Mittal, Sharma–Taneja and Kapur, to measure impurity of a node. ImbTreeAUC provides non-standard measures to choose an optimal split point for an attribute (as well the optimal attribute for splitting) by employing local, semi-global and global AUC (Area Under the ROC curve) measures. Both packages are applicable for binary and multiclass problems and they support cost-sensitive learning, by defining a misclassification cost matrix, and weighted-sensitive learning. The packages accept all types of attributes, including continuous, ordered and nominal, where the latter type is simplified for multiclass problems to reduce the computational overheads. Both applications enable optimization of the thresholds where posterior probabilities determine final class labels in a way that misclassification costs are minimized. Model overfitting can be managed either during the growing phase or at the end using post-pruning. The packages are mainly implemented in R, however some computationally demanding functions are written in plain C++. In order to speed up learning time, parallel processing is supported as well.

Integrated Assessment of Bioconcentration, Toxicity, and Hazards of Chlorobenzenes in the Aquatic Environment

The evaluation of bioconcentration, toxicity, and hazard (BTH) of persistent lipophilic organic compounds (LOCs) are generally performed as separate rather than integrated assessments. There are adequate data sets in the literature for chlorobenzenes (CBs) consisting of (a) concentrations in aquatic biota (C_B) and water (C_w) in the natural environment, (b) laboratory-derived bioconcentration factors (K_B) and field concentration ratios (CR), the field equivalent factor of K_B, (c) measured internal lethal concentrations (ILC₅₀) and model estimated ILC₅₀ calculated from K_B and lethal concentrations (LC₅₀), and (d) calculated hazard quotients in aquatic biota (HQ_B) and in water (HQ_W). However, there have been no integrated studies of those parameter values based on the respective lipid-based parameters (C_BL, K_BL, CR_L, ILC_50L, HQ_BL) performed. This study utilized the lipid-based parameters for CBs; a group of widely occuring, bioaccumulative, and toxic LOCs, and integrated those parameters into a bioconcentration-toxicity-hazard (BTH_L) index. The values of the parameters were obtained from selected literature with known lipid contents of the aquatic biota. The results showed that the laboratory derived bioconcentration factors, K_BLs, were comparable to the corresponding field based factors, CR_Ls, and the measured internal lethal concentrations, ILC_50L, showed comparable values with the estimated ones. The integrated BTH_L index was less than an order of magnitude or moderately acceptable for the assessment of variability, uncertainty, and predictive power of the index. This integrated assessment can be used to support decision making dealing with CBs in specific and LOCs in general, both in regional and global aquatic environments.

Machine Learning Consensus To Predict the Binding to the Androgen Receptor within the CoMPARA Project

The nuclear androgen receptor (AR) is one of the most relevant biological targets of Endocrine Disrupting Chemicals (EDCs), which produce adverse effects by interfering with hormonal regulation and endocrine system functioning. This paper describes novel in silico models to identify organic AR modulators in the context of the Collaborative Modeling Project of Androgen Receptor Activity (CoMPARA), coordinated by the National Center of Computational Toxicology (U.S. Environmental Protection Agency). The collaborative project involved 35 international research groups to prioritize the experimental tests of approximatively 40k compounds, based on the predictions provided by each participant. In this paper, we describe our machine learning approach to predict the binding to AR, which is based on a consensus of a multivariate Bernoulli Naive Bayes, a Random Forest, and N-Nearest Neighbor classification models. The approach was developed in compliance with the Organization of Economic Cooperation and Development (OECD) principles, trained on 1687 ToxCast molecules classified according to 11 in vitro assays, and further validated on a set of 3,882 external compounds. The models provided robust and reliable predictions and were used to gather novel data-driven insights on the structural features related to AR binding, agonism, and antagonism.

Structural alerts for the identification of bioaccumulative compounds

Legislators have included bioaccumulation in the evaluation of chemicals in the framework of the European Registration, Evaluation, Authorization, and Restriction of Chemicals (REACH) regulation. REACH requires information on the bioconcentration factor (BCF), which is a parameter for assessing bioaccumulation and encourages the use of a weight-of-evidence approach, including predictions from quantitative structure-activity relationships (QSARs). This study presents a novel approach, based on structural alerts, to be used as a decision-support system for the identification of substances with bioaccumulation potential. In a regulatory framework, these alerts can be integrated with other sources of information, such as experimental and in silico data, to reduce the uncertainty of the assessment, thereby supporting a weight-of-evidence approach. Moreover, the identified alerts have a direct connection with relevant structural features, thus fostering the applicability and interpretability of the approach. The structural alerts were identified on 779 chemicals annotated for their fish BCF, and the approach was then validated on 278 external molecules. The developed decision-support system allowed identification of 77% of bioaccumulative chemicals and was competitive with more complex QSAR models used in regulatory assessments. The approach is implemented in an easy-to-use workflow, provided free of charge. Integr Environ Assess Manag 2019;15:19-28. © 2018 SETAC.

Acceptable-by-design QSARs to predict the dietary biomagnification of organic chemicals in fish

This work presents the first-time QSAR approach to predict the laboratory-based fish biomagnification factor (BMF) of organic chemicals, to be used as a supporting tool for assessing bioaccumulation at the regulatory level. The developed strategy is based on 2 levels of prediction, with a varying trade-off between interpretability and performance according to the user's needs. We designed our models to be intrinsically acceptable at the regulatory level (in what we defined as "acceptable-by-design" strategy), by (i) complying with OECD principles directly in the approach development phase, (ii) choosing easy-to-apply modeling techniques, (iii) preferring simple descriptors when possible, and (iv) striving to provide data-driven mechanistic insights. Our novel tool has an error comparable to the observed experimental inter- and intraspecies variability and is stable on borderline compounds (root mean square error [RMSE] ranging from RMSE = 0.45 to RMSE = 0.45 log units on test data). Additionally, the models' molecular descriptors are carefully described and interpreted, allowing us to gather additional mechanistic insights into the structural features controlling the dietary bioaccumulation of chemicals in fish. To improve the transparency and promote the application of the model, the data set and the stand alone prediction tool are provided free of charge at https://github.com/grisoniFr/bmf_qsar Integr Environ Assess Manag 2019;15:51-63. © 2018 SETAC.

Detecting the bioaccumulation patterns of chemicals through data-driven approaches

This work investigates the bioaccumulation patterns of 168 organic chemicals in fish, by comparing their bioconcentration factor (BCF), biomagnification factor (BMF) and octanol-water partitioning coefficient (K_OW). It aims to gain insights on the relationships between dietary and non-dietary bioaccumulation in aquatic environment, on the effectiveness of K_OW and BCF to detect compounds that bioaccumulate through diet, as well as to detect the presence of structure-related bioaccumulation patterns. A linear relationship between logBMF and logK_OW was observed (logBMF = 1.14·logBCF - 6.20) up to logK_OW ≈ 4, as well as between logBMF and logBCF (logBMF = 0.96·logBCF - 4.06) up to a logBCF ≈ 5. 10% of compounds do not satisfy the linear BCF-BMF relationship. The deviations from such linear relationships were further investigated with the aid of a self-organizing map and canonical correlation analysis, which allowed us to shed light on some structure-related patterns. Finally, the usage of K_OW- and BCF-based thresholds to detect compounds that accumulate through diet led to many false positives (47%-91% for K_OW), and a moderate number of false negatives (up to 5% for BCF). These results corroborate the need of using the experimental BMF for hazard assessment practices, as well as of developing computational tools for BMF prediction.

Molecular Descriptors for Structure-Activity Applications: A Hands-On Approach

Molecular descriptors capture diverse parts of the structural information of molecules and they are the support of many contemporary computer-assisted toxicological and chemical applications. After briefly introducing some fundamental concepts of structure-activity applications (e.g., molecular descriptor dimensionality, classical vs. fingerprint description, and activity landscapes), this chapter guides the readers through a step-by-step explanation of molecular descriptors rationale and application. To this end, the chapter illustrates a case study of a recently published application of molecular descriptors for modeling the activity on cytochrome P450.

Impact of Molecular Descriptors on Computational Models

Molecular descriptors encode a wide variety of molecular information and have become the support of many contemporary chemoinformatic and bioinformatic applications. They grasp specific molecular features (e.g., geometry, shape, pharmacophores, or atomic properties) and directly affect computational models, in terms of outcome, performance, and applicability. This chapter aims to illustrate the impact of different molecular descriptors on the structural information captured and on the perceived chemical similarity among molecules. After introducing the fundamental concepts of molecular descriptor theory and application, a step-by-step retrospective virtual screening procedure guides users through the fundamental processing steps and discusses the impact of different types of molecular descriptors.

Membrane partitioning of ionic liquid cations, anions and ion pairs - Estimating the bioconcentration potential of organic ions

Recent efforts have been directed towards better understanding the persistency and toxicity of ionic liquids (ILs) in the context of the "benign-by-design" approach, but the assessment of their bioaccumulation potential remains neglected. This paper reports the experimental membrane partitioning of IL cations (imidazolium, pyridinium, pyrrolidinium, phosphonium), anions ([C(CN)₃]^-, [B(CN)₄]^-, [FSO₂)₂N]^-, [(C₂F₅)₃PF₃]^-, [(CF₃SO₂)₂N]^-) and their combinations as a measure for estimating the bioconcentration factor (BCF). Both cations and anions can have a strong affinity for phosphatidylcholine bilayers, which is mainly driven by the hydrophobicity of the ions. This affinity is often reflected in the ecotoxicological impact. Our data revealed that the bioconcentration potential of IL cations and anions is much higher than expected from octanol-water-partitioning based estimations that have recently been presented. For some ILs, the membrane-water partition coefficient reached levels corresponding to BCFs that might become relevant in terms of the "B" (bioaccumulation potential) classification under REACH. However, this preliminary estimation need to be confirmed by in vivo bioconcentration studies.

The origin and evolution of assessment criteria for persistent, bioaccumulative and toxic (PBT) chemicals and persistent organic pollutants (POPs)

General public concern over the effects of persistent chemicals began in the early 1960s. Since then, significant scientific advances have increased our understanding of persistent, bioaccumulative, and toxic (PBT) chemicals and the properties and processes that influence their fates in, and adverse effects on, human health and the environment. In addition to the scientific advances, a number of legislations and agreements for national, international, and global identification and control of PBT chemicals have been adopted. However, some of the rationales and thoughts that were relied upon when the first criteria were developed to identify and categorize PBT chemicals and then POPs (persistent organic pollutants) have not been carried forward. Criteria have been based upon available data of neutral hydrophobic substances as reference chemicals, derived under laboratory conditions. They evolved over the last decades due to the diversification of the protection aims under various national regulatory frameworks and international agreements, advances in methods for estimation of physical/chemical properties, and the identification of chemicals which are non-traditional POPs. Criteria are not defined purely by science; they also are subject to the aims of policy. This paper offers a historical perspective on the development of criteria for PBT chemicals and POPs. It also offers suggestions for rationalization of protection goals, describes some emerging procedures for identification of compounds of concern, and proposes information that needs to be considered when applying criteria to screening and/or evaluation of new chemicals.

Expert QSAR system for predicting the bioconcentration factor under the REACH regulation

Expert systems are a rational integration of several models that generally aim to exploit their advantages and overcome their drawbacks. This work is founded on our previously published Quantitative Structure-Activity Relationship (QSAR) classification scheme, which detects compounds whose Bioconcentration Factor (BCF) is (1) well predicted by the octanol-water partition coefficient (KOW), (2) underestimated by KOW or (3) overestimated by KOW. The classification scheme served as the starting point to identify and combine the best BCF model for each class among three VEGA models and one KOW-based equation. The rationalized model integration showed stability and surprising performance on unknown data when compared with benchmark BCF models. Model simplicity, transparency and mechanistic interpretation were fostered in order to allow for its application and acceptance within the REACH framework.

In Silico Prediction of Cytochrome P450-Drug Interaction: QSARs for CYP3A4 and CYP2C9

Cytochromes P450 (CYP) are the main actors in the oxidation of xenobiotics and play a crucial role in drug safety, persistence, bioactivation, and drug-drug/food-drug interaction. This work aims to develop Quantitative Structure-Activity Relationship (QSAR) models to predict the drug interaction with two of the most important CYP isoforms, namely 2C9 and 3A4. The presented models are calibrated on 9122 drug-like compounds, using three different modelling approaches and two types of molecular description (classical molecular descriptors and binary fingerprints). For each isoform, three classification models are presented, based on a different approach and with different advantages: (1) a very simple and interpretable classification tree; (2) a local (k-Nearest Neighbor) model based classical descriptors and; (3) a model based on a recently proposed local classifier (N-Nearest Neighbor) on binary fingerprints. The salient features of the work are (1) the thorough model validation and the applicability domain assessment; (2) the descriptor interpretation, which highlighted the crucial aspects of P450-drug interaction; and (3) the consensus aggregation of models, which largely increased the prediction accuracy.

Quantitative modeling of bioconcentration factors of carbonyl herbicides using multivariate image analysis

The bioconcentration factor (BCF) is an important parameter used to estimate the propensity of chemicals to accumulate in aquatic organisms from the ambient environment. While simple regressions for estimating the BCF of chemical compounds from water solubility or the n-octanol/water partition coefficient have been proposed in the literature, these models do not always yield good correlations and more descriptive variables are required for better modeling of BCF data for a given series of organic pollutants, such as some herbicides. Thus, the logBCF values for a set of carbonyl herbicides comprising amide, urea, carbamate and thiocarbamate groups were quantitatively modeled using multivariate image analysis (MIA) descriptors, derived from colored image representations for chemical structures. The logBCF model was calibrated and vigorously validated (r(2) = 0.79, q(2) = 0.70 and rtest(2) = 0.81), providing a comprehensive three-parameter linear equation after variable selection (logBCF = 5.682 - 0.00233 × X9774 - 0.00070 × X813 - 0.00273 × X5144); the variables represent pixel coordinates in the multivariate image. Finally, chemical interpretation of the obtained models in terms of the structural characteristics responsible for the enhanced or reduced logBCF values was performed, providing key leads in the prospective development of more eco-friendly synthetic herbicides.