In this study, a new hybrid docking-quantitative structure–property relationship (QSPR) methodology was used to model and predict the adsorption coe±cients of some small organic compounds on pristine multiwall carbon nanotube (MWCNT). In this method, descriptors are calculated from the reproduced experimental conformations by molecular docking to develop predictive QSPR models. Three MLR models with squared correlation coe±cient (R 2 Þ values of 0.93, 0.94 and 0.95 were selected. The prediction power of models was evaluated on 12-member test set, which was not used during the modeling and led to R 2 values of 0.88, 0.85 and 0.93. This methodology gives new insight into factors in°uenced on the adsorption of nanoparticles.
