Consensus models to predict oral rat acute toxicity and validation on a dataset coming from the industrial context

We report predictive models of acute oral systemic toxicity representing a follow-up of our previous work in the framework of the NICEATM project. It includes the update of original models through the addition of new data and an external validation of the models using a dataset relevant for the chemical industry context. A regression model for LD₅₀ and multi-class classification model for toxicity classes according to the Global Harmonized System categories were prepared. ISIDA descriptors were used to encode molecular structures. Machine learning algorithms included support vector machine (SVM), random forest (RF) and naïve Bayesian. Selected individual models were combined in consensus. The different datasets were compared using the generative topographic mapping approach. It appeared that the NICEATM datasets were lacking some relevant chemotypes for chemical industry. The new models trained on enlarged data sets have applicability domains (AD) sufficiently large to accommodate industrial compounds. The fraction of compounds inside the models' AD increased from 58% (NICEATM model) to 94% (new model). The increase of training sets improved models' prediction performance: RMSE values decreased from 0.56 to 0.47 and balanced accuracies increased from 0.69 to 0.71 for NICEATM and new models, respectively.

QSPR models for bioconcentration factor (BCF): are they able to predict data of industrial interest?

The bioconcentration factor (BCF), a key parameter required by the REACH regulation, estimates the tendency for a xenobiotic to concentrate inside living organisms. In silico methods can be valid alternatives to costly data measurements. However, in the industrial context, these theoretical approaches may fail to predict BCF with reasonable accuracy. We analyzed whether models built on public data only have adequate performances when challenged to predict industrial compounds. A new set of 1129 compounds has been collected by merging publicly available datasets. Generative Topographic Mapping was employed to compare this chemical space with a set of new compounds issued from the industry. Some new chemotypes absent in the training set (such as siloxanes) have been detected. A new BCF model has been built using ISIDA (In SIlico design and Data Analysis) fragment descriptors, support vector regression and random forest machine-learning methods. It has been externally validated on: (i) collected data from the literature and (ii) industrial data. The latter also served as benchmark for the freely available tools VEGA, EPISuite, TEST, OPERA. New model performs (RMSE of 0.58 log BCF units) comparably to existing ones but benefits of an extended applicability, covering the industrial set chemical space (78% data coverage).

Adapting SimpleTreat for simulating behaviour of chemical substances during industrial sewage treatment

The multimedia model SimpleTreat, evaluates the distribution and elimination of chemicals by municipal sewage treatment plants (STP). It is applied in the framework of REACH (Registration, Evaluation, Authorization and Restriction of Chemicals). This article describes an adaptation of this model for application to industrial sewage treatment plants (I-STP). The intended use of this re-parametrized model is focused on risk assessment during manufacture and subsequent uses of chemicals, also in the framework of REACH. The results of an inquiry on the operational characteristics of industrial sewage treatment installations were used to re-parameterize the model. It appeared that one property of industrial sewage, i.e. Biological Oxygen Demand (BOD) in combination with one parameter of the activated sludge process, the hydraulic retention time (HRT) is satisfactory to define treatment of industrial wastewater by means of the activated sludge process. The adapted model was compared to the original municipal version, SimpleTreat 4.0, by means of a sensitivity analysis. The consistency of the model output was assessed by computing the emission to water from an I-STP of a set of fictitious chemicals. This set of chemicals exhibit a range of physico-chemical and biodegradability properties occurring in industrial wastewater. Predicted removal rates of a chemical from raw sewage are higher in industrial than in municipal STPs. The latter have typically shorter hydraulic retention times with diminished opportunity for elimination of the chemical due to volatilization and biodegradation.