MitoTarget Modeling Using ANN-Classification Models Based on Fractal SEM Nano-Descriptors: Carbon Nanotubes as Mitochondrial F0F1-ATPase Inhibitors

• Published in: Journal of chemical information and modeling 2019-01, Vol.59 (1), p.86-97
• Main Authors: González-Durruthy, Michael, Manske Nunes, Silvana, Ventura-Lima, Juliane, Gelesky, Marcos A, González-Díaz, Humberto, Monserrat, José M, Concu, Riccardo, Cordeiro, M. Natália D.S
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural networks; Binding sites; Carbon; Carbon nanotubes; Cell death; Classification; Fractal models; Fractals; Model accuracy; Nanomaterials; Nanoparticles; Organic chemistry; Scanning electron microscopy; Selectivity; Toxicity
• ISSN: 1549-9596; 1549-960X
• DOI: 10.1021/acs.jcim.8b00631

Recently, it has been suggested that the mitochondrial oligomycin A-sensitive F0-ATPase subunit is an uncoupling channel linked to apoptotic cell death, and as such, the toxicological inhibition of mitochondrial F0-ATP hydrolase can be an interesting mitotoxicity-based therapy under pathological conditions. In addition, carbon nanotubes (CNTs) have been shown to offer higher selectivity like mitotoxic-targeting nanoparticles. In this work, linear and nonlinear classification algorithms on structure–toxicity relationships with artificial neural network (ANN) models were set up using the fractal dimensions calculated from CNTs as a source of supramolecular chemical information. The potential ability of CNT-family members to induce mitochondrial toxicity-based inhibition of the mitochondrial H+-F0F1-ATPase from in vitro assays was predicted. The attained experimental data suggest that CNTs have a strong ability to inhibit the F0-ATPase active-binding site following the order oxidized–CNT (CNT–COOH > CNT–OH) > pristine–CNT and mimicking the oligomycin A mitotoxicity behavior. Meanwhile, the performance of the ANN models was found to be improved by including different nonlinear combinations of the calculated fractal scanning electron microscopy (SEM) nanodescriptors, leading to models with excellent internal accuracy and predictivity on external data to classify correctly CNT-mitotoxic and nonmitotoxic with specificity (Sp > 98.9%) and sensitivity (Sn > 99.0%) from ANN models compared with linear approaches (LNN) with Sp ≈ Sn > 95.5%. Finally, the present study can contribute toward the rational design of carbon nanomaterials and opens new opportunities toward mitochondrial nanotoxicology-based in silico models.