Deep Learning-Enabled Morphometric Analysis for Toxicity Screening Using Zebrafish Larvae

Highly sensitive response to the toxicity of environmental chemicals in transparent casper zebrafish

The response sensitivity to toxic substances is the most concerned performance of animal model in chemical risk assessment. Casper (mitfaw2/w2;mpv17a9/a9), a transparent zebrafish mutant, is a useful in vivo model for toxicological assessment. However, the ability of casper to respond to the toxicity of exogenous chemicals is unknown. In this study, zebrafish embryos were exposed to five environmental chemicals, chlorpyrifos, lindane, α-endosulfan, bisphenol A, tetrabromobisphenol A (TBBPA), and an antiepileptic drug valproic acid. The half-lethal concentration (LC50) values of these chemicals in casper embryos were 62-87 % of that in the wild-type. After TBBPA exposure, the occurrence of developmental defects in the posterior blood island of casper embryos was increased by 67-77 % in relative to the wild-type, and the half-maximal effective concentration (EC50) in casper was 73 % of that in the wild-type. Moreover, the casper genetic background significantly increased the hyperlocomotion caused by chlorpyrifos and lindane exposure compared with the wild-type. These results demonstrated that casper had greater susceptibility to toxicity than wild-type zebrafish in acute toxicity, developmental toxicity and neurobehavioral toxicity assessments. Our data will inform future toxicological studies in casper and accelerate the development of efficient approaches and strategies for toxicity assessment via the use of casper.

Bringing Artificial Intelligence (AI) into Environmental Toxicology Studies: A Perspective of AI-Enabled Zebrafish High-Throughput Screening

The booming development of artificial intelligence (AI) has brought excitement to many research fields that could benefit from its big data analysis capability for causative relationship establishment and knowledge generation. In toxicology studies using zebrafish, the microscopic images and videos that illustrate the developmental stages, phenotypic morphologies, and animal behaviors possess great potential to facilitate rapid hazard assessment and dissection of the toxicity mechanism of environmental pollutants. However, the traditional manual observation approach is both labor-intensive and time-consuming. In this Perspective, we aim to summarize the current AI-enabled image and video analysis tools to realize the full potential of AI. For image analysis, AI-based tools allow fast and objective determination of morphological features and extraction of quantitative information from images of various sorts. The advantages of providing accurate and reproducible results while avoiding human intervention play a critical role in speeding up the screening process. For video analysis, AI-based tools enable the tracking of dynamic changes in both microscopic cellular events and macroscopic animal behaviors. The subtle changes revealed by video analysis could serve as sensitive indicators of adverse outcomes. With AI-based toxicity analysis in its infancy, exciting developments and applications are expected to appear in the years to come.

Deep learning in water protection of resources, environment, and ecology: achievement and challenges

The breathtaking economic development put a heavy toll on ecology, especially on water pollution. Efficient water resource management has a long-term influence on the sustainable development of the economy and society. Economic development and ecology preservation are tangled together, and the growth of one is not possible without the other. Deep learning (DL) is ubiquitous in autonomous driving, medical imaging, speech recognition, etc. The spectacular success of deep learning comes from its power of richer representation of data. In view of the bright prospects of DL, this review comprehensively focuses on the development of DL applications in water resources management, water environment protection, and water ecology. First, the concept and modeling steps of DL are briefly introduced, including data preparation, algorithm selection, and model evaluation. Finally, the advantages and disadvantages of commonly used algorithms are analyzed according to their structures and mechanisms, and recommendations on the selection of DL algorithms for different studies, as well as prospects for the application and development of DL in water science are proposed. This review provides references for solving a wider range of water-related problems and brings further insights into the intelligent development of water science.

Developmental toxicity and estrogenicity of glyphosate in zebrafish in vivo and in silico studies

As the most heavily used herbicide globally, glyphosate (GLY) has been detected in a variety of environments and has raised concerns about its ecological and health effects. There is debate as to whether GLY may disrupt the endocrine system. Here, we investigated the developmental toxicity of GLY in zebrafish based on deep learning-enabled morphometric analysis (DLMA). In addition, the estrogenic activity of GLY was assessed by endocrine disruption prediction, docking study and in vivo experiments. Results showed that exposure to environmental concentrations of GLY negatively impacted zebrafish development, causing yolk edema and pericardial edema. Endocrine disruption prediction suggested that GLY may target estrogen receptors (ER). Molecular docking analysis revealed binding of GLY to three zebrafish ER. In vivo zebrafish experiment, GLY enhanced the protein levels of ERα and the mRNA levels of cyp19a, HSD17b1, vtg1, vtg2, esr1, esr2a and esr2b. These results suggest that GLY may act as an endocrine disruptor by targeting ER, which warrants further attention for its potential toxicity to aquatic animals.