Multivariate statistical analysis for selecting optimal descriptors in the toxicity modeling of nanomaterials

Sunil Kr. Jha, Tae Hyun Yoon, Zhaoqing Pan

Abstract: Highlights•A novel data mining procedure for selection of significant nanomaterials descriptors.•The selected descriptors result in the best visual discrimination of nanomaterial toxicity.•A maximum class separability index J was obtained with selected descriptors.•An association between the theoretical results with the QNTR model was established.