Experimental–Computational Study of Carbon Nanotube Effects on Mitochondrial Respiration: In Silico Nano-QSPR Machine Learning Models Based on New Raman Spectra Transform with Markov–Shannon Entropy Invariants

Abstract

The study of selective toxicity of carbon nanotubes (CNTs) on mitochondria (CNT-mitotoxicity) is of major interest for future biomedical applications. In the current work, the mitochondrial oxygen consumption (E3) is measured under three experimental conditions by exposure to pristine and oxidized CNTs (hydroxylated and carboxylated). Respiratory functional assays showed that the information on the CNT Raman spectroscopy could be useful to predict structural parameters of mitotoxicity induced by CNTs. The in vitro functional assays show that the mitochondrial oxidative phosphorylation by ATP-synthase (or state V3 of respiration) was not perturbed in isolated rat-liver mitochondria. For the first time a star graph (SG) transform of the CNT Raman spectra is proposed in order to obtain the raw information for a nano-QSPR model. Box-Jenkins and perturbation theory operators are used for the SG Shannon entropies. A modified RRegrs methodology is employed to test four regression methods such as multiple linear regression (LM), partial least squares regression (PLS), neural networks regression (NN), and random forest (RF). RF provides the best models to predict the mitochondrial oxygen consumption in the presence of specific CNTs with R of 0.998-0.999 and RMSE of 0.0068-0.0133 (training and test subsets). This work is aimed at demonstrating that the SG transform of Raman spectra is useful to encode CNT information, similarly to the SG transform of the blood proteome spectra in cancer or electroencephalograms in epilepsy and also as a prospective chemoinformatics tool for nanorisk assessment. All data files and R object models are available at https://dx.doi.org/10.6084/m9.figshare.3472349 .

Carbon Nanotubes’ Effect on Mitochondrial Oxygen Flux Dynamics: Polarography Experimental Study and Machine Learning Models using Star Graph Trace Invariants of Raman Spectra

“…Thus, a new type of parameters is proposed, calculated by the application of a Star Graph (SG) transform to the Raman spectra. The SRN transform method, which has been recently introduced and published by our group [ 17 ], uses graphs and network theory tools, and is different from a classic Fourier transformation. The transform technique used herein converts the Raman spectra values into sequences of characters and creates the corresponding SG of this signal.…”

“…A possibility for this kind of signal is to compress them into another series of numerical parameters that quantify useful structural information on all the spectra. In a previous work, the star graphs (SG) of the Raman spectra of CNTs [ 17 ] were introduced. The idea is to transform the signal into a network with star graph (SG) topology.…”

“…These studies have used different matrix invariants such as Markov–Shannon entropies or matrix trace invariants Tr k (also known as spectral moments) to compress the information from proteins, gene, etc. In a previous work, the research focused on how to use Markov–Shannon entropies to compress information from Raman spectra [ 17 ]. However, there is no report on the use of Tr k values in this sense.…”

A Review of Applications Using Mixed Materials of Cellulose, Nanocellulose and Carbon Nanotubes

“…In addition, there are also reports of simulations on mixed materials of NC and CNTs [136,137]. In recent years, as a result of remarkable improvements in computer performance, many researches on NC or CNTs using machine learning have been reported [138][139][140][141][142][143][144]. In the future, research using these machine learning methods will accelerate the development of further mixed materials of cellulose and CNTs research, such as by reducing the time and cost of experiments.…”

Application of Bayesian networks in determining nanoparticle-induced cellular outcomes using transcriptomics

“…Recently, novel models called RASARs (Read-Across Structure Activity Relationships) are being used to define chemical similarity (Luechtefeld et al 2018). Another emerging recent approach, Quantitative Structure-Toxicity Relationships (QSTR) perturbation models, have been applied to estimate toxicity and ecotoxicity of NPs for different endpoints and experimental conditions with remarkable performance (Kleandrova et al 2014a;Luan et al 2014;Kleandrovaet al 2014b, Gonz alez-Durruthy et al 2017. QSTR-perturbation models apply moving average analysis to reconstruct the case descriptors and perturbation theory to get the final optimization function based on differences of case pair combinations.…”