Computational Tool for Risk Assessment of Nanomaterials: Novel QSTR-Perturbation Model for Simultaneous Prediction of Ecotoxicity and Cytotoxicity of Uncoated and Coated Nanoparticles under Multiple Experimental Conditions

Nanomaterials have revolutionized
modern science and technology
due to their multiple applications in engineering, physics, chemistry,
and biomedicine. Nevertheless, the use and manipulation of nanoparticles
(NPs) can bring serious damages to living organisms and their ecosystems.
For this reason, ecotoxicity and cytotoxicity assays are of special
interest in order to determine the potential harmful effects of NPs.
Processes based on ecotoxicity and cytotoxicity tests can significantly
consume time and financial resources. In this sense, alternative approaches
such as quantitative structure–activity/toxicity relationships
(QSAR/QSTR) modeling have provided important insights for the better
understanding of the biological behavior of NPs that may be responsible
for causing toxicity. Until now, QSAR/QSTR models have predicted ecotoxicity
or cytotoxicity separately against only one organism (bioindicator
species or cell line) and have not reported information regarding
the quantitative influence of characteristics other than composition
or size. In this work, we developed a unified QSTR-perturbation model
to simultaneously probe ecotoxicity and cytotoxicity of NPs under
different experimental conditions, including diverse measures of toxicities,
multiple biological targets, compositions, sizes and conditions to
measure those sizes, shapes, times during which the biological targets
were exposed to NPs, and coating agents. The model was created from
36488 cases (NP–NP pairs) and exhibited accuracies higher than
98% in both training and prediction sets. The model was used to predict
toxicities of several NPs that were not included in the original data
set. The results of the predictions suggest that the present QSTR-perturbation
model can be employed as a highly promising tool for the fast and
efficient assessment of ecotoxicity and cytotoxicity of NPs.

纳米材料因其在工程、物理、化学和生物医学领域的广泛应用而彻底革新了现代科学技术。然而，纳米颗粒（NPs）的利用和处理可能对生物体及其生态系统造成严重损害。鉴于此，生态毒性和细胞毒性实验对于确定NPs潜在的有害效应具有重要意义。基于生态毒性和细胞毒性测试的过程会显著消耗时间和财力资源。在此意义上，诸如定量结构-活性/毒性关系（QSAR/QSTR）建模等替代方法已为更深入理解可能导致毒性的NPs的生物行为提供了重要见解。迄今为止，QSAR/QSTR模型仅针对单一生物体（生物指示物种或细胞系）分别预测了生态毒性和细胞毒性，并未报告有关除组成或尺寸之外的特征的定量影响信息。在本研究中，我们开发了一种统一的QSAR-perturbation模型，以在多种实验条件下同时探究NPs的生态毒性和细胞毒性，包括各种毒性度量、多种生物靶标、组成、尺寸及其测量条件、生物靶标暴露于NPs期间的时间以及涂层剂。该模型基于36488个案例（NP-NP对）构建，在训练集和预测集中均表现出超过98%的准确率。该模型被用于预测原始数据集中未包含的几种NPs的毒性。预测结果表明，目前的QSAR-perturbation模型可作为快速高效评估NPs生态毒性和细胞毒性的极具潜力的工具。