Evaluating genotoxicity of metal oxide nanoparticles: Application of advanced supervised and unsupervised machine learning techniques.

Presence of missing data points in datasets is among main challenges in handling the toxicological data for nanomaterials. As the processing of missing data is an important part of data analysis, we have introduced a read-across approach that uses a combination of supervised and unsupervised machine learning techniques to fill the missing values. A series of classification models (supervised learning) was developed to predict class label, and self-organizing map approach (unsupervised learning) was used to estimate relative distances between nanoparticles and refine results obtained during supervised learning. In this study, genotoxicity of 49 silicon and metal oxide nanoparticles in Ames and Comet tests. Collected literature data did not demonstrate significant variations related to the change of size including selected bulk materials. Genotoxicity-related features of nanomaterials were represented by ionic characteristics. General tendencies found in the current study were convincingly linked to known theories of genotoxic action at nano-level. Mechanisms of primary and secondary genotoxic effects were discussed in the context of developed models.

[1]  V. V. Kleandrova,et al.  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. , 2014, Environmental science & technology.

[2]  Ovidiu Ivanciuc,et al.  Applications of Support Vector Machines in Chemistry , 2007 .

[3]  Bhanuramya Mangalampalli,et al.  Genotoxicity study of nickel oxide nanoparticles in female Wistar rats after acute oral exposure , 2017, Mutagenesis.

[4]  David F. Rogers,et al.  Similarity and distance measures for cellular manufacturing. Part I. A survey , 1993 .

[5]  Jerzy Leszczynski,et al.  Genotoxicity induced by metal oxide nanoparticles: a weight of evidence study and effect of particle surface and electronic properties , 2018, Nanotoxicology.

[6]  Ilmari Pyykkö,et al.  Multilaboratory evaluation of 15 bioassays for (eco)toxicity screening and hazard ranking of engineered nanomaterials: FP7 project NANOVALID , 2016, Nanotoxicology.

[7]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[8]  Gyula Dura,et al.  Potential toxic effects of iron oxide nanoparticles in in vivo and in vitro experiments , 2012, Journal of applied toxicology : JAT.

[9]  M. Dusinska,et al.  CHAPTER 14. Analysis of nanoparticle-induced DNA damage by the comet assay , 2014 .

[10]  Jerzy Leszczynski,et al.  Review of Current and Emerging Approaches for Quantitative Nanostructure-Activity Relationship Modeling: The Case of Inorganic Nanoparticles , 2016 .

[11]  Julia L. Brumaghim,et al.  Metal-mediated DNA damage and cell death: mechanisms, detection methods, and cellular consequences. , 2014, Metallomics : integrated biometal science.

[12]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[13]  Weida Tong,et al.  Decision Forest: Combining the Predictions of Multiple Independent Decision Tree Models , 2003, J. Chem. Inf. Comput. Sci..

[14]  E Sabbioni,et al.  Comparative genotoxicity of cobalt nanoparticles and ions on human peripheral leukocytes in vitro. , 2008, Mutagenesis.

[15]  Marjana Novic,et al.  The way to cover prediction for cytotoxicity for all existing nano-sized metal oxides by using neural network method , 2017, Nanotoxicology.

[16]  Yang Liu,et al.  An introduction to decision tree modeling , 2004 .

[17]  Maria Dusinska,et al.  Mechanisms of genotoxicity. A review of in vitro and in vivo studies with engineered nanoparticles , 2014, Nanotoxicology.

[18]  M. Kumari,et al.  Genotoxicity analysis of cerium oxide micro and nanoparticles in Wistar rats after 28 days of repeated oral administration. , 2014, Mutagenesis.

[19]  Youn-Joo An,et al.  Microbial toxicity of metal oxide nanoparticles (CuO, NiO, ZnO, and Sb2O3) to Escherichia coli, Bacillus subtilis, and Streptococcus aureus. , 2011, The Science of the total environment.

[20]  A. Cuschieri,et al.  Membrane lipid peroxidation by the peroxidase-like activity of magnetite nanoparticles. , 2014, Chemical communications.

[21]  J. Marrero,et al.  Comparison of imputation methods for missing laboratory data in medicine , 2013, BMJ Open.

[22]  Jerzy Leszczynski,et al.  Causal inference methods to assist in mechanistic interpretation of classification nano-SAR models , 2015 .

[23]  Peter Jenkinson,et al.  Initial in vitro screening approach to investigate the potential health and environmental hazards of Envirox™ – a nanoparticulate cerium oxide diesel fuel additive , 2007, Particle and Fibre Toxicology.

[24]  Jerzy Leszczynski,et al.  From basic physics to mechanisms of toxicity: the "liquid drop" approach applied to develop predictive classification models for toxicity of metal oxide nanoparticles. , 2014, Nanoscale.

[25]  Jerzy Leszczynski,et al.  Genotoxicity of metal oxide nanomaterials: review of recent data and discussion of possible mechanisms. , 2015, Nanoscale.

[26]  Yong Yin,et al.  Similarity coefficient methods applied to the cell formation problem: a comparative investigation , 2005, Comput. Ind. Eng..

[27]  M. Bishop,et al.  Assessment by Ames test and comet assay of toxicity potential of polymer used to develop field-capable rapid-detection device to analyze environmental samples , 2014, Applied Nanoscience.

[28]  Michael Ed. Hohn,et al.  Binary coefficients: A theoretical and empirical study , 1976 .

[29]  F. Rossi,et al.  Genotoxicity and morphological transformation induced by cobalt nanoparticles and cobalt chloride: an in vitro study in Balb/3T3 mouse fibroblasts. , 2009, Mutagenesis.

[30]  Jerzy Leszczynski,et al.  Towards understanding mechanisms governing cytotoxicity of metal oxides nanoparticles: Hints from nano-QSAR studies , 2015, Nanotoxicology.

[31]  Mark T. D. Cronin,et al.  Addressing a bottle neck for regulation of nanomaterials: quantitative read-across (Nano-QRA) algorithm for cases when only limited data is available , 2017 .

[32]  P. Bork,et al.  Molecular eco-systems biology: towards an understanding of community function , 2008, Nature Reviews Microbiology.

[33]  Jerzy Leszczynski,et al.  How the toxicity of nanomaterials towards different species could be simultaneously evaluated: a novel multi-nano-read-across approach. , 2018, Nanoscale.

[34]  Antonio Marcomini,et al.  Grouping and Read-Across Approaches for Risk Assessment of Nanomaterials , 2015, International journal of environmental research and public health.

[35]  Stephen Mann,et al.  Nanoparticles can cause DNA damage across a cellular barrier. , 2009, Nature nanotechnology.

[36]  Reinhard Kreiling,et al.  A critical appraisal of existing concepts for the grouping of nanomaterials. , 2014, Regulatory toxicology and pharmacology : RTP.

[37]  A. El-Ansary,et al.  On the Toxicity of Therapeutically Used Nanoparticles: An Overview , 2009, Journal of toxicology.

[38]  Laetitia Gonzalez,et al.  Genotoxicity of engineered nanomaterials: A critical review , 2008 .

[39]  Jerzy Leszczynski,et al.  Evaluating the toxicity of TiO2-based nanoparticles to Chinese hamster ovary cells and Escherichia coli: a complementary experimental and computational approach , 2017, Beilstein journal of nanotechnology.

[40]  M. Gong,et al.  Superparamagnetic core/shell GoldMag nanoparticles: size-, concentration- and time-dependent cellular nanotoxicity on human umbilical vein endothelial cells and the suitable conditions for magnetic resonance imaging , 2015, Journal of Nanobiotechnology.