Mitochondrial Permeability Transition Pore (MPTP) is involved in neurodegeneration, hepatotoxicity, cardiac necrosis, nervous and muscular dystrophies. We used different experimental protocols to determine the mitoprotective activity (%P) of different carbon nanotubes (CNT) against mitochondrial swelling in multiple boundary conditions (bj). The experimental boundary conditions explored included different sub-sets of combinations of the following factors b0 = three different mitochondrial swelling assays using the MPT-inductor (Ca2+, Fe3+, H2O2) combined or not with a second MPT-inductor and swelling control assays using MPT-inhibitor (CsA, RR, EGTA), b1 = exposure time (0–600 s), and b2 = CNT concentrations (0–5 μg ml−1). Other boundary conditions (bk) changed were the CNT structural parameters b3 = CNT type (SW, SW + DW, MW), b4 = CNT functionalization type (H, OH, COOH). We also changed different of CNT like b5 = molecular weight/functionalization ratio (minW/maxW) or b6 = maximal and minimal diameter (Dmin/Dmax) as physic-chemical properties (Vk). Next, we employed chemoinformatics ideas to develop a new Perturbation Theory (PT) model able to predict the %P of CNT in multiple experimental conditions. We investigated different output functions of the absorbance ′f(εij) used in PL4/PL5 methods like (εij, 1/εij, 1/εij2, or −log εij) as alternative outputs of the model. The inputs are in the form an additive functions with linear/non-linear terms. The first term is a function 0f(<εij>) of the average absorbance <εij> (expected value) in different assays (bj). The concentration dependent terms are linear functions of concentration, or hill-shaped curves similar to PL4/PL5 functions (used in dose–response analysis). The CNT structure perturbation terms are linear/non-linear functions of Box–Jenkins operators (ΔVkj). The ΔVkj are moving averages (deviations) of the Vk of the CNT with respect to their expected values . The best model found predicted the values of absorbance (measure of mitoprotective activity vs. mitochondrial swelling) with regression coefficient R2 = 0.997 for >6000 experimental data points (q2 = 0.994). Last, we used the model to carry out a simulation of the changes on mitoprotective activity for CNT family after one increase of 1–10% of the minWi and maxDi of CNT.