Converting Nanotoxicity Data to Information Using Artificial Intelligence and Simulation

Abstract

Decades of nanotoxicology research have generated extensive and diverse data sets. However, data is not equal to information. The question is how to extract critical information buried in vast data streams. Here we show that artificial intelligence (AI) and molecular simulation play key roles in transforming nanotoxicity data into critical information, i.e., constructing the quantitative nanostructure (physicochemical properties)–toxicity relationships, and elucidating the toxicity-related molecular mechanisms. For AI and molecular simulation to realize their full impacts in this mission, several obstacles must be overcome. These include the paucity of high-quality nanomaterials (NMs) and standardized nanotoxicity data, the lack of model-friendly databases, the scarcity of specific and universal nanodescriptors, and the inability to simulate NMs at realistic spatial and temporal scales. This review provides a comprehensive and representative, but not exhaustive, summary of the current capability gaps and tools required to fill these formidable gaps. Specifically, we discuss the applications of AI and molecular simulation, which can address the large-scale data challenge for nanotoxicology research. The need for model-friendly nanotoxicity databases, powerful nanodescriptors, new modeling approaches, molecular mechanism analysis, and design of the next-generation NMs are also critically discussed. Finally, we provide a perspective on future trends and challenges.

Nanoparticles traversing the extracellular matrix induce biophysical perturbation of fibronectin depicted by surface chemistry

“…68 However, the effects of NPs on the structure and function of the ECM are not well understood, and studying interactions between NPs and specific biomolecules in the ECM at the molecular level in vivo can be challenging. 69 In this study, we designed a set of gold NPs conjugated with different ligands to investigate their interactions with Fn-III, a prevalent component of the ECM. Our simulations have provided insights into how NPs perturb Fn-III at both structural and mechanical levels, as illustrated in Fig.…”

Emerging trends and future challenges of advanced 2D nanomaterials for combating bacterial resistance

“…However, the quantitative relationships between nanostructures, physicochemical properties, and nanotoxicity can be established conveniently using ML. The key parameters contributing to their nanotoxicity are size, shape, hydrophobicity, and surface charge [ 41 , 251 ].…”

“…Rigorous characterizations of NMs are required to ensure the quality of NMs and the reliability of nanotoxicity data. Moreover, a preliminary standard for reporting nanotoxicity data has been proposed lately, suggesting that the displayed data should include three major components, i.e., material characterization, biological characterization, and comprehensive experimental protocols [ 251 ]. Nanotoxicity data availability can be improved with precise nanotoxicity quantification, which typically requires several crucial study objectives, such as determining quantitative experimental indicators, minimum toxicity value, and toxicity test method [ 254 ].…”

“…Created with BioRender.com . Nanotoxicity studies were taken and Reproduced with permission [ 251 ]. Copyright © 2023, American Chemical Society.…”

Predicting zeta potential of liposomes from their structure: A nano-QSPR model for DOPE, DC-Chol, DOTAP, and EPC formulations

“…Nano-QSAR/QSPR aims to use experimental data to obtain a model based on nanomaterial descriptors (nanodescriptors) numerically expressing the variability of nanoforms’ structure to predict the physicochemical properties or biological activity of NMs. An established nano-QSAR/QSPR model allows for identifying the most significant structural features affecting the properties of nanomaterials and determining their potential toxicity mechanisms [9] , [10] . Puzyn et al [11] proposed the first nano-QSAR model to predict the cytotoxicity of metal oxide nanomaterials toward Escherichia coli.…”