QSAR model for the prediction of bio-concentration factor using aqueous solubility and descriptors considering various electronic effects

Pesticide effect on earthworm lethality via interpretable machine learning

Earthworms are among the most important animals (invertebrates) for soil health. Many chemical substances released into nature for agricultural development, such as pesticides, may have unwanted effects on those organisms. However, it is essential to understand the extent of the impact of chemicals on soil health first and then make the proper decisions for regulatory or commercial purposes. We hypothesize that there is an expressible quantitative structure-activity relationship (QSAR) between the structure of pesticide compounds and the acute toxicity effect of earthworm species Eisenia fetida. The description of this relationship allows for a better assessment of the impact of chemicals on the said earthworm. To describe this relationship, a dataset of chemicals was collected from open-access sources to develop a mathematical model. A novel approach, combining genetic algorithm and Bayesian optimization, was used to select structural features into the model and to optimize model parameters. The final QSAR classification model was created with the Random Forest algorithm and exhibited good prediction Accuracy of 0.78 on training set and 0.80 on test set. The model representation follows FAIR principles and is available on QsarDB.org.

Fragments quantum descriptors in classification of bio-accumulative compounds

The aim of the following research is to assess the applicability of calculated quantum properties of molecular fragments as molecular descriptors in machine learning classification task. The research is based on bio-concentration and QM9-extended databases. A number of compounds with results from quantum-chemical calculations conducted with Psi4 quantum chemistry package was also added to the quantum properties database. Classification results are compared with a baseline of random guesses and predictions obtained with the traditional RDKit generated molecular descriptors. Chosen classification metrics show that results obtained with fragments quantum descriptors fall between results from baseline and those provided by molecular descriptors widely applied in cheminformatics. According to the results, the implementation of principal component analysis, causes a drop in categorization metrics.

The Relevance of Goodness-of-fit, Robustness and Prediction Validation Categories of OECD-QSAR Principles with Respect to Sample Size and Model Type

We investigated the relevance of the validation principles on the Quantitative Structure Activity Relationship models issued by Organization for Economic and Co-operation and Development. We checked the goodness-of-fit, robustness and predictivity categories in linear and nonlinear models using benchmark datasets. Most of our conclusions are drawn using the sample size dependence of the different validation parameters. We found that the goodness-of-fit parameters misleadingly overestimate the models on small samples. In the case of neural network and support vector models, the feasibility of the goodness-of-fit parameters often might be questioned. We propose to use the simplest y-scrambling method to estimate chance correlation. We found that the leave-one-out and leave-many-out cross-validation parameters can be rescaled to each other in all models and the computationally feasible method should be chosen depending on the model type. We assessed the interdependence of the validation parameters by calculating their rank correlations. Goodness of fit and robustness correlate quite well over a sample size for linear models and one of the approaches might be redundant. In the rank correlation between internal and external validation parameters, we found that the assignment of good and bad modellable data to the training or the test causes negative correlations.

Predicting the Bioconcentration Factor in Fish from Molecular Structures

The bioconcentration factor (BCF) is one of the metrics used to evaluate the potential of a substance to bioaccumulate into aquatic organisms. In this work, linear and non-linear regression QSARs were developed for the prediction of log BCF using different computational approaches, and starting from a large and structurally heterogeneous dataset. The new MLR-OLS and ANN regression models have good fitting with R2 values of 0.62 and 0.70, respectively, and comparable external predictivity with R2ext 0.64 and 0.65 (RMSEext of 0.78 and 0.76), respectively. Furthermore, linear and non-linear classification models were developed using the regulatory threshold BCF >2000. A class balanced subset was used to develop classification models which were applied to chemicals not used to create the QSARs. These classification models are characterized by external and internal accuracy up to 84% and 90%, respectively, and sensitivity and specificity up to 90% and 80%, respectively. QSARs presented in this work are validated according to regulatory requirements and their quality is in line with other tools available for the same endpoint and dataset, with the advantage of low complexity and easy application through the software QSAR-ME Profiler. These QSARs can be used as alternatives for, or in combination with, existing models to support bioaccumulation assessment procedures.

Sample-size dependence of validation parameters in linear regression models and in QSAR

The dependence of statistical validation parameters was investigated on the size of the sample taken in fit of multivariate linear curves. We observed that R² and related internal parameters were misleading as they overestimated the goodness-of-fit of models at small sample size. Cross-validation metrics showed correct trends. It was possible to scale the leave-one-out and the leave-many-out results close to identical by correcting the degrees of freedom of the models. y and x-randomized validation parameters were calculated and the methods provided close to identical results. We suggest to use the simplest methods in both cases. The external parameters followed correct trends with respect to the sample size, but their sensitivity differed. We plotted the Roy-Ojha metrics in 2D and we coloured them with respect to other external parameters to provide an easy classification of models. The rank correlations were calculated between the performance parameters. Up to a sample size, goodness-of-fit and robustness were distinguishable, but above a certain sample size, the parameters were redundant. The external-internal pairs were weakly correlated. Our data show that all the three aspects of validation are necessary at small sample sizes, but the internal check of robustness is not informative above a given sample size.

Modelling of antiproliferative activity measured in HeLa cervical cancer cells in a series of xanthene derivatives

Cancer remains one of the leading causes of death in humans, and new drug substances are therefore being developed. Thus, the anti-cancer activity of xanthene derivatives has become an important topic in the development of new and potent anti-cancer drug substances. Previously published novel series of xanthen-3-one and xanthen-1,8-dione derivatives have been synthesized in one of our laboratories and showed anti-proliferative activity in HeLa cancer cell lines. This series serves as a good basis to develop quantitative structure-activity relationship (QSAR), to study the relations between anti-proliferative activity and chemical structures. A QSAR model has been derived that relies only on two-dimensional molecular descriptors, providing mechanistic insight into the anti-proliferative activity of xanthene derivatives. The model is validated internally and externally and additionally with the set of inactive compounds of the original data, confirming model applicability for the design and discovery of novel xanthene derivatives. The QSAR model is available at the QsarDB repository (http://dx.doi.10.15152/QDB.237).

Statistical relationship between metabolic decomposition and chemical uptake predicts bioconcentration factor data for diverse chemical exposures

BACKGROUND

A challenge of in vitro to in vivo extrapolation (IVIVE) is to predict the physical state of organisms exposed to chemicals in the environment from in vitro exposure assay data. Although toxicokinetic modeling approaches promise to bridge in vitro screening data with in vivo effects, they are often encumbered by a need for redesign or re-parameterization when applied to different tissues or chemicals.

RESULTS

We demonstrate a parameterization of reverse toxicokinetic (rTK) models developed for the adult zebrafish (Danio rerio) based upon particle swarm optimizations (PSO) of the chemical uptake and degradation rates that predict bioconcentration factors (BCF) for a broad range of chemicals. PSO reveals a relationship between chemical uptake and decomposition parameter values that predicts chemical-specific BCF values with moderate statistical agreement to a limited yet diverse chemical dataset, and all without a need to retrain the model to new data.

CONCLUSIONS

The presented model requires only the octanol-water partitioning ratio to predict BCFs to a fidelity consistent with existing QSAR models. This success begs re-evaluation of the modeling assumptions; specifically, it suggests that chemical uptake into arterial blood may be limited by transport across gill membranes (diffusion) rather than by counter-current flow between gill lamellae (convection). Therefore, more detailed molecular modeling of aquatic respiration may further improve predictive accuracy of the rTK approach.

Chemical structure and correlation analysis of HIV-1 NNRT and NRT inhibitors and database-curated, published inhibition constants with chemical structure in diverse datasets

Human immunodeficiency virus (HIV-1) reverse transcriptase is a major target for designing anti-HIV drugs. Developed inhibitors are divided into non-nucleoside analog reverse-transcriptase inhibitors (NNRTIs) and nucleoside analog reverse-transcriptase inhibitors (NRTIs) depending on their mechanism. Given that many inhibitors have been studied and for many of them binding affinity constants have been calculated, it is beneficial to analyze the chemical landscape of these families of inhibitors and correlate these inhibition constants with molecular structure descriptors. For this, the HIV-1 RT data was retrieved from the ChEMBL database, carefully curated, and original literature verified, grouped into NRTIs and NNRTIs, analyzed using a hierarchical scaffold classification method and modelled with best multi-linear regression approach. Analysis of the HIV-1 NNRTIs subset results in ten different common structural parent types of oxazepanone, piperazinone, pyrazine, oxazinanone, diazinanone, pyridine, pyrrole, diazepanone, thiazole, and triazine. The same analysis for HIV-1 NRTIs groups structures into four different parent types of uracil, pyrimide, pyrimidione, and imidazole. Each scaffold tree corresponding to the parent types has been carefully analyzed and examined, and changes in chemical structure favorable to potency and stability are highlighted. For both subsets, descriptive and predictive QSAR models are derived, discussed and externally validated, revealing general trends in relationships between molecular structure and binding affinity constants in structurally diverse datasets. Data and QSAR models are available at the QsarDB repository (http://dx.doi.org/10.15152/QDB.202).

Linear and nonlinear models for predicting fish bioconcentration factors for pesticides

This work is devoted to the applications of the multiple linear regression (MLR), multilayer perceptron neural network (MLP NN) and projection pursuit regression (PPR) to quantitative structure-property relationship analysis of bioconcentration factors (BCFs) of pesticides tested on Bluegill (Lepomis macrochirus). Molecular descriptors of a total of 107 pesticides were calculated with the DRAGON Software and selected by inverse enhanced replacement method. Based on the selected DRAGON descriptors, a linear model was built by MLR, nonlinear models were developed using MLP NN and PPR. The robustness of the obtained models was assessed by cross-validation and external validation using test set. Outliers were also examined and deleted to improve predictive power. Comparative results revealed that PPR achieved the most accurate predictions. This study offers useful models and information for BCF prediction, risk assessment, and pesticide formulation.

Classifying bio-concentration factor with random forest algorithm, influence of the bio-accumulative vs. non-bio-accumulative compound ratio to modelling result, and applicability domain for random forest model

In environmental risk assessment, the bio-concentration factor (BCF) is a widely used parameter in the estimation of the bio-accumulation potential of chemicals. BCF data often have an uneven distribution of classes (bio-accumulative vs. non-bio-accumulative), which could severely bias the classification results towards the prevailing class. The present study focuses on the influence of uneven distribution of the classes in training phase of Random Forest (RF) classification models. Three different training set designs were used and descriptors selected to the models based on the occurrence frequency in RF trees and considering the mechanistic aspects they reflect. Models were compared and their classification performance was analysed, indicating good predictive characteristics (sensitivity = 0.90 and specificity = 0.83) for the balanced set; also imbalanced sets have their strengths in certain application scenarios. The confidence of classifications was assessed with a new schema for the applicability domain that makes use of the RF proximity matrix by analysing the similarity between the predicted compound and the training set of the model. All developed models were made available in the transparent, accessible and reproducible way in QsarDB repository (http://dx.doi.org/10.15152/QDB.116).

Meta-analysis of toxicity and teratogenicity of 133 chemicals from zebrafish developmental toxicity studies

Zebrafish developmental toxicity testing is an emerging field, which faces considerable challenges regarding data meta-analysis and the establishment of standardized test protocols. Here, we present an initial correlation study on toxicity of 133 chemicals based on data in the literature to ascertain predictive developmental toxicity endpoints. We found that the physical properties of chemicals (BCF or logP) did not fully predict lethality or developmental outcomes. Instead, individual outcomes such as pericardial edema and yolk sac edema were more reliable indicators of developmental toxicity. In addition, we ranked the chemicals based on toxicity with the Toxicological Priority Index (ToxPi) program and via a teratogenic ratio, and found that perfluorooctane sulfonate (PFOS) had the highest ToxPi score, triphenyltin acetate had the highest average ToxPi score (corrected for missing data and having more than 4 outcomes), and N-methyl-dithiocarbamate had the highest teratogenic ratio.

Comparative analysis of local and consensus quantitative structure-activity relationship approaches for the prediction of bioconcentration factor

Quantitative structure-activity relationships (QSARs) are broadly classified as global or local, depending on their molecular constitution. Global models use large and diverse training sets covering a wide range of chemical space. Local models focus on smaller structurally or chemically similar subsets that are conventionally selected by human experts or alternatively using clustering analysis. The current study focuses on the comparative analysis of different clustering algorithms (expectation-maximization, K-means and hierarchical) for seven different descriptor sets as structural characteristics and two rule-based approaches to select subsets for designing local QSAR models. A total of 111 local QSAR models are developed for predicting bioconcentration factor. Predictions from local models were compared with corresponding predictions from the global model. The comparison of coefficients of determination (r(2)) and standard deviations for local models with similar subsets from the global model show improved prediction quality in 97% of cases. The descriptor content of derived QSARs is discussed and analyzed. Local QSAR models were further consolidated within the framework of consensus approach. All different consensus approaches increased performance over the global and local models. The consensus approach reduced the number of strongly deviating predictions by evening out prediction errors, which were produced by some local QSARs.

Rapid quantification of pharmaceuticals and pesticides in passive samplers using ultra high performance liquid chromatography coupled to high resolution mass spectrometry

The presence of both pharmaceuticals and pesticides in the aquatic environment has become a well-known environmental issue during the last decade. An increasing demand however still exists for sensitive and reliable monitoring tools for these rather polar contaminants in the marine environment. In recent years, the great potential of passive samplers or equilibrium based sampling techniques for evaluation of the fate of these contaminants has been shown in literature. Therefore, we developed a new analytical method for the quantification of a high number of pharmaceuticals and pesticides in passive sampling devices. The analytical procedure consisted of extraction using 1:1 methanol/acetonitrile followed by detection with ultra-high performance liquid chromatography coupled to high resolution and high mass accuracy Orbitrap mass spectrometry. Validation of the analytical method resulted in limits of quantification and recoveries ranging between 0.2 and 20 ng per sampler sheet and between 87.9 and 105.2%, respectively. Determination of the sampler-water partition coefficients of all compounds demonstrated that several pharmaceuticals and most pesticides exert a high affinity for the polydimethylsiloxane passive samplers. Finally, the developed analytical methods were used to measure the time-weighted average (TWA) concentrations of the targeted pollutants in passive samplers, deployed at eight stations in the Belgian coastal zone. Propranolol, carbamazepine and seven pesticides were found to be very abundant in the passive samplers. These obtained long-term and large-scale TWA concentrations will contribute in assessing the environmental and human health risk of these emerging pollutants.

Quantitative structure-activity relationship analysis of acute toxicity of diverse chemicals to Daphnia magna with whole molecule descriptors

Quantitative structure-activity relationship analysis and estimation of toxicological effects at lower-mid trophic levels provide first aid means to understand the toxicity of chemicals. Daphnia magna serves as a good starting point for such toxicity studies and is also recognized for regulatory use in estimating the risk of chemicals. The ECOTOX database was queried and analysed for available data and a homogenous subset of 253 compounds for the endpoint LC50 48 h was established. A four-parameter quantitative structure-activity relationship was derived (coefficient of determination, r (2) = 0.740) for half of the compounds and internally validated (leave-one-out cross-validated coefficient of determination, [Formula: see text] = 0.714; leave-many-out coefficient of determination, [Formula: see text] = 0.738). External validation was carried out with the remaining half of the compounds (coefficient of determination for external validation, [Formula: see text] = 0.634). Two of the descriptors in the model (log P, average bonding information content) capture the structural characteristics describing penetration through bio-membranes. Another two descriptors (energy of highest occupied molecular orbital, weighted partial negative surface area) capture the electronic structural characteristics describing the interaction between the chemical and its hypothetic target in the cell. The applicability domain was subsequently analysed and discussed.