Mathematical structural descriptors and mutagenicity assessment: a study with congeneric and diverse datasets^$

ABSTRACT

Quantitative bioactivity and toxicity assessment of chemical compounds plays a central role in drug discovery as it saves a substantial amount of resources. To this end, high-performance computing has enabled researchers and practitioners to leverage hundreds, or even thousands, of computed molecular descriptors for the activity prediction of candidate compounds. In this paper, we evaluate the utility of two large groups of chemical descriptors by such predictive modelling, as well as chemical structure discovery, through empirical analysis. We use a suite of commercially available and in-house software to calculate molecular descriptors for two sets of chemical mutagens – a homogeneous set of 95 amines, and a diverse set of 508 chemicals. Using calculated descriptors, we model the mutagenic activity of these compounds using a number of methods from the statistics and machine-learning literature, and use robust principal component analysis to investigate the low-dimensional subspaces that characterize these chemicals. Our results suggest that combining different sets of descriptors is likely to result in a better predictive model – but that depends on the compounds being modelled and the modelling technique being used.

KEYWORDS:

• molecular descriptors
• variable selection
• dimension reduction
• machine learning
• two-deep cross-validation
• quantitative structure–activity relationship (QSAR)

Acknowledgement

The research of SM is supported by George Michailidis.

Supplementary material

Supplementary material (Supplementary Tables 1–4) is available here: https://doi.org/10.1080/1062936X.2018.1496475 along with the published article. Supplementary files 1, 2 and 4 give more details about the descriptors used, and file 3 gives individual split results for all methods and both datasets. All data and code are available in GitHub: https://github.com/shubhobm/Mutagenicity-assessment.