Use of metal/metal oxide spherical cluster and hydroxyl metal coordination complex for descriptor calculation in development of nanoparticle cytotoxicity classification model

Machine Learning Models for Predicting Cytotoxicity of Nanomaterials

The wide application of nanomaterials in consumer and medical products has raised concerns about their potential adverse effects on human health. Thus, more and more biological assessments regarding the toxicity of nanomaterials have been performed. However, the different ways the evaluations were performed, such as the utilized assays, cell lines, and the differences of the produced nanoparticles, make it difficult for scientists to analyze and effectively compare toxicities of nanomaterials. Fortunately, machine learning has emerged as a powerful tool for the prediction of nanotoxicity based on the available data. Among different types of toxicity assessments, nanomaterial cytotoxicity was the focus here because of the high sensitivity of cytotoxicity assessment to different treatments without the need for complicated and time-consuming procedures. In this review, we summarized recent studies that focused on the development of machine learning models for prediction of cytotoxicity of nanomaterials. The goal was to provide insight into predicting potential nanomaterial toxicity and promoting the development of safe nanomaterials.

Comprehensive strategies of machine-learning-based quantitative structure-activity relationship models

Early quantitative structure-activity relationship (QSAR) technologies have unsatisfactory versatility and accuracy in fields such as drug discovery because they are based on traditional machine learning and interpretive expert features. The development of Big Data and deep learning technologies significantly improve the processing of unstructured data and unleash the great potential of QSAR. Here we discuss the integration of wet experiments (which provide experimental data and reliable verification), molecular dynamics simulation (which provides mechanistic interpretation at the atomic/molecular levels), and machine learning (including deep learning) techniques to improve QSAR models. We first review the history of traditional QSAR and point out its problems. We then propose a better QSAR model characterized by a new iterative framework to integrate machine learning with disparate data input. Finally, we discuss the application of QSAR and machine learning to many practical research fields, including drug development and clinical trials.

Combined Toxicity of Metal Nanoparticles: Comparison of Individual and Mixture Particles Effect

Toxicity of metal nanoparticles (NPs) are closely associated with increasing intracellular reactive oxygen species (ROS) and the levels of pro-inflammatory mediators. However, NP interactions and surface complexation reactions alter the original toxicity of individual NPs. To date, toxicity studies on NPs have mostly been focused on individual NPs instead of the combination of several species. It is expected that the amount of industrial and highway-acquired NPs released into the environment will further increase in the near future. This raises the possibility that various types of NPs could be found in the same medium, thereby, the adverse effects of each NP either could be potentiated, inhibited or remain unaffected by the presence of the other NPs. After uptake of NPs into the human body from various routes, protein kinases pathways mediate their toxicities. In this context, family of mitogen-activated protein kinases (MAPKs) is mostly efficient. Despite each NP activates almost the same metabolic pathways, the toxicity induced by a single type of NP is different than the case of co-exposure to the combined NPs. The scantiness of toxicological data on NPs combinations displays difficulties to determine, if there is any risk associated with exposure to combined nanomaterials. Currently, in addition to mathematical analysis (Response surface methodology; RSM), the quantitative-structure-activity relationship (QSAR) is used to estimate the toxicity of various metal oxide NPs based on their physicochemical properties and levels applied. In this chapter, it is discussed whether the coexistence of multiple metal NPs alter the original toxicity of individual NP. Additionally, in the part of "Toxicity of diesel emission/exhaust particles (DEP)", the known individual toxicity of metal NPs within the DEP is compared with the data regarding toxicity of total DEP mixture.

Evaluating the cytotoxicity of a large pool of metal oxide nanoparticles to Escherichia coli: Mechanistic understanding through In Vitro and In Silico studies

The toxic effect of eight metal oxide nanoparticles (MONPs) on Escherichia coli was experimentally evaluated following standard bioassay protocols. The obtained cytotoxicity ranking of these studied MONPs is Er₂O₃, Gd₂O₃, CeO₂, Co₂O₃, Mn₂O₃, Co₃O₄, Fe₃O₄/WO₃ (in descending order). The computed EC₅₀ values from experimental data suggested that Er₂O₃ and Gd₂O₃ were the most acutely toxic MONPs to E. coli. To identify the mechanism of toxicity of these 8 MONPs along with 17 other MONPs from our previous study, we employed seven classifications and machine learning (ML) algorithms including linear discriminant analysis (LDA), naïve bayes (NB), multinomial logistic regression (MLogitR), sequential minimal optimization (SMO), AdaBoost, J48, and random forest (RF). We also employed 1^st and 2^nd generation periodic table descriptors developed by us (without any sophisticated computing facilities) along with experimentally analyzed Zeta-potential, to model the cytotoxicity of these MONPs. Based on qualitative validation metrics, the LDA model appeared to be the best among the 7 tested models. The core environment of metal defined by the ratio of the number of core electrons to the number of valence electrons and the electronegativity count of oxygen showed a positive impact on toxicity. The identified properties were important for understanding the mechanisms of nanotoxicity and for predicting the potential environmental risk associated with MONPs exposure. The developed models can be utilized for environmental risk assessment of any untested MONP to E. coli, thereby providing a scientific basis for the design and preparation of safe nanomaterials.

Use of size-dependent electron configuration fingerprint to develop general prediction models for nanomaterials

Due to the lack of nano descriptors that can appropriately represent the wide chemical space of engineered nanomaterials (ENMs), applicability domain of nano-quantitative structure-activity relationship models are limited to certain types of ENMs, such as metal oxides, metals, carbon-based nanomaterials, or quantum dots. In this study, a size-dependent electron configuration fingerprint (SDEC FP) was introduced to estimate the quantity of electrons based on the core, doping, and coating materials of ENMs in different sizes. SDEC FP was used in prediction model development and nanostructure similarity analysis on datasets including metal and carbon-based nanomaterials with and without surface modifications. Cytotoxicity and zeta potential prediction models developed with SDEC FP achieved good prediction accuracies on test set. Nanostructure similarity analysis was performed through principal component analysis which showed that structural similarity between ENMs measured by SDEC FP was highly correlated with their properties.

Importance of Choosing Relevant Biological End Points To Predict Nanoparticle Toxicity with Computational Approaches for Human Health Risk Assessment

Because it is impossible to assess in vitro or in vivo the toxicity of all nanoparticles available on the market on a case-by-case basis, computational approaches have been proposed as useful alternatives to predict in silico the hazard potential of engineered nanoparticles. Despite promising results, a major issue associated with these mathematical models lies in the a priori choice of the physicochemical descriptors and the biological end points. We performed a thorough bibliographic survey on the biological end points used for nanotoxicology purposes and compared them between experimental and computational approaches. They were found to be disparate: while conventional in vitro nanotoxicology assays usually investigate a large array of biological effects using eukaryotic cells (cytotoxicity, pro-inflammatory response, oxidative stress, genotoxicity), computational studies mostly focus on cell viability and also include studies on prokaryotic cells. We may thus wonder the relevance of building complex mathematical models able to predict accurately a biological end point if this latter is not the most relevant to support human health risk assessment. The choice of biological end points clearly deserves to be more carefully discussed. This could bridge the gap between experimental and computational nanotoxicology studies and allow in silico predictive models to reach their full potential.