Development of Deep Learning Models for Predicting the Effects of Exposure to Engineered Nanomaterials on Daphnia magna

Abstract

This study presents the results of applying deep learning methodologies within the ecotoxicology field, with the objective of training predictive models that can support hazard assessment and eventually the design of safer engineered nanomaterials (ENMs). A workflow applying two different deep learning architectures on microscopic images of Daphnia magna is proposed that can automatically detect possible malformations, such as effects on the length of the tail, and the overall size, and uncommon lipid concentrations and lipid deposit shapes, which are due to direct or parental exposure to ENMs. Next, classification models assign specific objects (heart, abdomen/claw) to classes that depend on lipid densities and compare the results with controls. The models are statistically validated in terms of their prediction accuracy on external D. magna images and illustrate that deep learning technologies can be useful in the nanoinformatics field, because they can automate time‐consuming manual procedures, accelerate the investigation of adverse effects of ENMs, and facilitate the process of designing safer nanostructures. It may even be possible in the future to predict impacts on subsequent generations from images of parental exposure, reducing the time and cost involved in long‐term reproductive toxicity assays over multiple generations.

Mechanistic insights into toxicity pathways induced by nanomaterials in Daphnia magna from analysis of the composition of the acquired protein corona

“…Increasing evidence suggests that the gradual increase in free radicals and oxidative stress with age is the Environmental Science: Nano Paper primary determinant of ageing. 64 The presence of ageing related proteins in the NMs coronas is consistent with the morphological evidence presented previously 34,65 that exposure to Ag NMs results in dramatic tail shortening and increased lipid droplets, two phenotypical traits of ageing, suggesting that the NMs induce accelerated ageing in the developing daphnids. Other proteins which have a high degree of species conservation that were linked to lipid transport, antioxidant processes and developmental processes are copper-zinc superoxide dismutase, vascular endothelial growth factor receptor, and S-adenosylmethionine synthase.…”

Metadata Stewardship in Nanosafety Research: Community-Driven Organisation of Metadata Schemas to Support FAIR Nanoscience Data

“…the NanoXtract tool [ 121 ], developed under the NanoCommons project, has been used to extract a range of different variables from TEM images, and the image nano-descriptors were further exploited to derive a validated predictive model to estimate zeta potential of NMs. Using ML approaches, images of Daphnia magna exposed to a range of ENM were utilised to develop a model for prediction of ENM-induced ageing and toxicity [ 122 ].…”

Multigenerational Exposure to Nano‐TiO2 Induces Ageing as a Stress Response Mitigated by Environmental Interactions

“…The developed nanoinformatics models were able to detect, isolate, and classify regions of interest on the Daphnia images where specific malformations occurred, and assessments were made of the type and the severity of malformations compared with the control daphnids, including the increased lipid concentrations in exposed daphnids, enhancing our understanding of the possible age‐related effect of NM exposure. [ 48 ]…”