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

Pantelis Karatzas,Laura‐Jayne A Ellis,Iseult Lynch,Dimitra‐Danai Varsou,Andreas Tsoumanis,Georgia Melagraki,Philip Doganis,Haralambos Sarimveis,Antreas Afantitis

doi:10.1002/smll.202001080

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.

Highlights

QSAR-perturbation models,[11,12,13] and workflows predicting molecular initiating events and key events in adverse outcomeNanotechnology has emerged at the forefront of science and pathways (AOPs).[14]
The results from the deep learning models that were trained for the implementation of the workflow presented in the previous section, and the development of a completely automated tool, which is able to perform the object recognition and the malformation assessment procedure, are presented
All models were trained on a PC with an Intel Core i3 processor, 16 GB of RAM, and an NVIDIA GeForce GTX 1070 graphics processing units (GPU) running on the GPU using the TensorFlow open source library for training deep learning machine learning models

Summary

Introduction

QSAR-perturbation models,[11,12,13] and workflows predicting molecular initiating events and key events in adverse outcomeNanotechnology has emerged at the forefront of science and pathways (AOPs).[14]. One of the most promising new areas in artificial intelligence (AI) and machine learning for building predictive models are the so-called deep learning technologies,[17] which are extensions of the traditional neural networks architectures, using more hidden layers and a larger variety of activation functions,[18] that is, functions that map the input to the output response of each neuron. Convolutional neural networks (CNNs) have shown state-of-the-art performance for image classification, segmentation, and object detection and tracking.[19] Extremely accurate deep learning models have been created in many disciplines using only electronic images as input information. Güven and Oktay applied CNN to distinguish Fe3O4 ENMs from background[25] and in a follow-up study, Oktay and Gurses[26] applied multiple output CNNs (MO-CNN) to detect the locations of Fe3O4 ENMs in electronic images, to provide their boundaries, and to define their size and shape based on the segmentation output

Methods

Results

Conclusion