We have created a knowledge graph based on major data sources used in ecotoxicological risk assessment. We have applied this knowledge graph to an important task in risk assessment, namely chemical effect prediction. We have evaluated nine knowledge graph embedding models from a selection of geometric, decomposition, and convolutional models on this prediction task. We show that using knowledge graph embeddings can increase the accuracy of effect prediction with neural networks. Furthermore, we have implemented a fine-tuning architecture which adapts the knowledge graph embeddings to the effect prediction task and leads to a better performance. Finally, we evaluate certain characteristics of the knowledge graph embedding models to shed light on the individual model performance.
Extrapolation of adverse biological (toxic) effects of chemicals is an important contribution to expand available hazard data in (eco)toxicology without the use of animals in laboratory experiments. In this work, we extrapolate effects based on a knowledge graph (KG) consisting of the most relevant effect data as domain-specific background knowledge. An effect prediction model, with and without background knowledge, was used to predict mean adverse biological effect concentration of chemicals as a prototypical type of stressors. The background knowledge improves the model prediction performance by up to 40\% in terms of $R^2$ (\ie coefficient of determination). We use the KG and KG embeddings to provide quantitative and qualitative insights into the predictions. These insights are expected to improve the confidence in effect prediction. Larger scale implementation of such extrapolation models should be expected to support hazard and risk assessment, by simplifying and reducing testing needs.
Microplastics (MP) are contaminants of emerging concern in aquatic ecosystems. While the number of studies is rapidly increasing, a comparison of the toxicity of MP and natural particulate matter is largely missing. In addition, research focusses on the impacts of hydrophobic chemicals sorbed to plastics. However, the interactive effects of MP and hydrophilic, dissolved chemicals remain largely unknown. Therefore, we conducted chronic toxicity studies with larvae of the freshwater dipteran Chironomus riparius exposed to unplasticised polyvinyl chloride MP (PVC-MP) as well as kaolin and diatomite as reference materials for 28 days. In addition, we investigated the effects of particles in combination with the neonicotinoid imidacloprid in a multiple-stressor experiment. High concentrations of kaolin positively affected the chironomids. In contrast, exposure to diatomite and PVC-MP reduced the emergence and mass of C. riparius. Likewise, the toxicity of imidacloprid was enhanced in the presence of PVC-MP and slightly decreased in the co-exposure with kaolin. Overall, parallel experiments and chemical analysis indicate that the toxicity of PVC-MP was not caused by leached or sorbed chemicals. Our study demonstrates that PVC-MP induce more severe effects than both natural particulate materials. However, the latter are not benign per se, as the case of diatomite highlights. Considering the high, environmentally irrelevant concentrations needed to induce adverse effects, C. riparius is insensitive to exposures to PVC-MP.
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)
