Dependence of QSAR Models on the Selection of Trial Descriptor Sets: A Demonstration Using Nanotoxicity Endpoints of Decorated Nanotubes

Abstract

Little attention has been given to the selection of trial descriptor sets when designing a QSAR analysis even though a great number of descriptor classes, and often a greater number of descriptors within a given class, are now available. This paper reports an effort to explore interrelationships between QSAR models and descriptor sets. Zhou and co-workers (Zhou et al., Nano Lett. 2008, 8 (3), 859-865) designed, synthesized, and tested a combinatorial library of 80 surface modified, that is decorated, multi-walled carbon nanotubes for their composite nanotoxicity using six endpoints all based on a common 0 to 100 activity scale. Each of the six endpoints for the 29 most nanotoxic decorated nanotubes were incorporated as the training set for this study. The study reported here includes trial descriptor sets for all possible combinations of MOE, VolSurf, and 4D-fingerprints (FP) descriptor classes, as well as including and excluding explicit spatial contributions from the nanotube. Optimized QSAR models were constructed from these multiple trial descriptor sets. It was found that (a) both the form and quality of the best QSAR models for each of the endpoints are distinct and (b) some endpoints are quite dependent upon 4D-FP descriptors of the entire nanotube-decorator complex. However, other endpoints yielded equally good models only using decorator descriptors with and without the decorator-only 4D-FP descriptors. Lastly, and most importantly, the quality, significance, and interpretation of a QSAR model were found to be critically dependent on the trial descriptor sets used within a given QSAR endpoint study.

Exploring possible mechanisms of action for the nanotoxicity and protein binding of decorated nanotubes: interpretation of physicochemical properties from optimal QSAR models

“…We previously explored (Shao et al, 2013) the relationship between the six nanotoxicity endpoints and different molecular descriptor classes (Tseng et al, 2012) to develop optimum QSAR models for each of the six endpoint training sets as reported by Zhou et al (Zhou et al, 2008). The resulting high quality and optimal QSAR models based on molecular information, capturing the individual decorator and the complete DNC, indicated that each of the endpoints required a different combination of descriptor classes.…”

“…The first is that the proposed mechanical mechanisms have been derived from optimized QSAR models (Shao et al, 2013) as "mechanism of action" templates. Instead of examining specific descriptors -physicochemical properties -in isolation, all of the molecular properties within the QSAR model are viewed as a whole.…”

“…Would we then be able to learn something about how the nanomaterials and/or each region of the nanomaterials interact with the biological system of interest? The goal of the work reported herein is to gain a better understanding of the detailed mechanisms of action for how a set of decoratednanotube complexes (DNC) interacts with six biological systems based on a set of optimal QSAR models constructed from mixed classes of molecular descriptors (Shao et al, 2013).…”

Current situation on the availability of nanostructure–biological activity data

“…Despite these limitations, there is a growing literature on the use of (Q)SARlike models in nanotoxicology studies. There are a great number of reviews [3,5,10,[12][13][14] and research articles [15][16][17][18][19][20][21][22][23][24][25][26][27][28] devoted to the investigations of in silico modelling of ENM toxicity in peer-reviewed scientific journals.…”

Nano(Q)SAR: Challenges, pitfalls and perspectives

“…Having an agreement on suitable descriptors is important, as past workers found that the choice of descriptors can affect the quality, significance and interpretation of nano-(Q)SAR model 10,52 . It may be that descriptors can be selected or adapted from traditional chemical descriptors, but it is highly likely that descriptors specifically developed for nanomaterials are needed.…”