Development of Generalized QSAR Models for Predicting Cytotoxicity and Genotoxicity of Metal Oxides Nanoparticles

Abstract

In recent years, nanomaterials have gained tremendous attention due to their wide variety of industrial applications including food packaging, consumer products, nanomedicines, etc. The fascinating properties of nanoparticles which are responsible for creating several exciting opportunities, however, are also accountable for growing concerns of their toxic effects on humans as well as the environment. Thus, in the present study, the authors have developed generalized models for predicting the cytotoxicity and genotoxicity of seven metal oxide nanoparticles. The models not only take into account the structural features, but also the diverse experimental conditions under which the toxicity of nanoparticles was determined. The diverse experimental conditions were captured in the generalized models using the Box-Jenkins moving average approach. Here, two machine learning techniques, namely, linear discriminant analysis and random forest were utilized to build the final models. Importantly, the validation metrics showed that the developed models have significant discriminatory power.

Multi-Target In-Silico modeling strategies to discover novel angiotensin converting enzyme and neprilysin dual inhibitors

“…The molecular structural and biological data for 983 compounds which includes ACE (474) and NEP (509) with inhibitory activity against ACE and NEP enzymes of Rattus norvegicus (Supporting file S1 ) were extracted from the ChEMBL database ( https://www.ebi.ac.uk/chembl ). The selected compounds dataset was subjected to biological and chemical curation 49 by removing the molecules that lack information such as SMILES, units of activity, and duplicates. Structures were standardised, neutralised, and cleaned and salts were removed to get a dataset of 715 compounds which makes ACE (357) and NEP (358) (Supporting file S2 ) followed by 3D optimization using MMFF94 force-field by OpenBabel 50 , 51 .…”

The nanosafety assessment of ENMs under a dermal exposure scenario: from key molecular events toin silicomodeling tools

“…7), nano-(Q)SAR enables the given toxic effects of ENMs to be determined by their 197 With the EU ban on animal testing, (Q)SAR has been extensively used as an alternative approach in mechanistic interpretation, tiered testing, grouping, and ranking the toxic potency of ENMs for risk assessment. Table 5 summarizes recent (Q)SAR studies regarding the cytotoxicity (cellular uptake and HaCaT cell viability) and/or genotoxicity (results of the bacterial reverse mutation test) of MeOx NPs, 112,[198][199][200][201][202][203][204][205][206][207][208][209] carbon nanotubes 210,211 and fullerenes. 212,213 Datasets for (Q)SAR modeling can be obtained from literature, databases or experiments and should contain sufficient chemically diverse data.…”

“…197 With the EU ban on animal testing, (Q)SAR has been extensively used as an alternative approach in mechanistic interpretation, tiered testing, grouping, and ranking the toxic potency of ENMs for risk assessment. Table 5 summarizes recent (Q)SAR studies regarding the cytotoxicity (cellular uptake and HaCaT cell viability) and/or genotoxicity (results of the bacterial reverse mutation test) of MeOx NPs, 112,198–209 carbon nanotubes 210,211 and fullerenes. 212,213…”

A review on the structural characterization of nanomaterials for nano-QSAR models

“…A different approach of multi-task QSAR models to incorporate the endpoint conditions is to use them as modifying factors of the descriptors. For such a modification, using a Box–Jenkins approach, Ambure et al [ 72 ] classified the dataset based on two endpoints and several experimental protocols, cell line targets, exposure times, and doses. Other authors use perturbation QSAR models to incorporate endpoint conditions such as the specific toxicity measurement [ 18 , 74 ], the biological target [ 18 – 19 74 ], the exposure time [ 18 , 74 ], and the incubation conditions [ 19 ].…”