Dataset Information

Identifying diverse metal oxide nanomaterials with lethal effects on embryonic zebrafish using machine learning.

ABSTRACT: Manufacturers of nanomaterial-enabled products need models of endpoints that are relevant to human safety to support the "safe by design" paradigm and avoid late-stage attrition. Increasingly, embryonic zebrafish (Danio Rerio) are recognised as a key human safety relevant in vivo test system. Hence, machine learning models were developed for identifying metal oxide nanomaterials causing lethality to embryonic zebrafish up to 24 hours post-fertilisation, or excess lethality in the period of 24-120 hours post-fertilisation, at concentrations of 250 ppm or less. Models were developed using data from the Nanomaterial Biological-Interactions Knowledgebase for a dataset of 44 diverse, coated and uncoated metal or, in one case, metalloid oxide nanomaterials. Different modelling approaches were evaluated using nested cross-validation on this dataset. Models were initially developed for both lethality endpoints using multiple descriptors representing the composition of the core, shell and surface functional groups, as well as particle characteristics. However, interestingly, the 24 hours post-fertilisation data were found to be harder to predict, which could reflect different exposure routes. Hence, subsequent analysis focused on the prediction of excess lethality at 120 hours-post fertilisation. The use of two data augmentation approaches, applied for the first time in nano-QSAR research, was explored, yet both failed to boost predictive performance. Interestingly, it was found that comparable results to those originally obtained using multiple descriptors could be obtained using a model based upon a single, simple descriptor: the Pauling electronegativity of the metal atom. Since it is widely recognised that a variety of intrinsic and extrinsic nanomaterial characteristics contribute to their toxicological effects, this is a surprising finding. This may partly reflect the need to investigate more sophisticated descriptors in future studies. Future studies are also required to examine how robust these modelling results are on truly external data, which were not used to select the single descriptor model. This will require further laboratory work to generate comparable data to those studied herein.

SUBMITTER: Robinson RLM

PROVIDER: S-EPMC8649207 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:To better assess potential hepatotoxicity of nanomaterials, human liver HepG2 cells were exposed for 3 days to five different CeO2 (either 30 or 100 ?g/ml), 3 SiO2 based (30 ?g/ml) or 1 CuO (3 ?g/ml) nanomaterials with dry primary particle sizes ranging from 15 to 213 nm. Metabolomic assessment of exposed cells was then performed using four mass spectroscopy dependent platforms (LC and GC), finding 344 biochemicals.Four CeO2, 1 SiO2 and 1 CuO nanomaterials increased hepatocyte concentrations of many lipids, particularly free fatty acids and monoacylglycerols but only CuO elevated lysolipids and sphingolipids. In respect to structure-activity, we now know that five out of six tested CeO2, and both SiO2 and CuO, but zero out of four TiO2 nanomaterials have caused this elevated lipids effect in HepG2 cells. Observed decreases in UDP-glucuronate (by CeO2) and S-adenosylmethionine (by CeO2 and CuO) and increased S-adenosylhomocysteine (by CuO and some CeO2) suggest that a nanomaterial exposure increases transmethylation reactions and depletes hepatic methylation and glucuronidation capacity. Our metabolomics data suggests increased free radical attack on nucleotides. There was a clear pattern of nanomaterial-induced decreased nucleotide concentrations coupled with increased concentrations of nucleic acid degradation products. Purine and pyrimidine alterations included concentration increases for hypoxanthine, xanthine, allantoin, urate, inosine, adenosine 3',5'-diphosphate, cytidine and thymidine while decreases were seen for uridine 5'-diphosphate, UDP-glucuronate, uridine 5'-monophosphate, adenosine 5'-diphosphate, adenosine 5'-monophophate, cytidine 5'-monophosphate and cytidine 3'-monophosphate. Observed depletions of both 6-phosphogluconate, NADPH and NADH (all by CeO2) suggest that the HepG2 cells may be deficient in reducing equivalents and thus in a state of oxidative stress.Metal oxide nanomaterial exposure may compromise the methylation, glucuronidation and reduced glutathione conjugation systems; thus Phase II conjugational capacity of hepatocytes may be decreased. This metabolomics study of the effects of nine different nanomaterials has not only confirmed some observations of the prior 2014 study (lipid elevations caused by one CeO2 nanomaterial) but also found some entirely new effects (both SiO2 and CuO nanomaterials also increased the concentrations of several lipid classes, nanomaterial induced decreases in S-adenosylmethionine, UDP-glucuronate, dipeptides, 6-phosphogluconate, NADPH and NADH).

Dataset Information

Identifying diverse metal oxide nanomaterials with lethal effects on embryonic zebrafish using machine learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets