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
posted on 2014-12-16, 00:00authored byValeria
V. Kleandrova, Feng Luan, Humberto González-Díaz, Juan M. Ruso, Alejandro Speck-Planche, M. Natália D. S. Cordeiro
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.