Neiband MS, Mani-Varnosfaderani A, Benvidi A. Classification of sphingosine kinase inhibitors using counter propagation artificial neural networks: A systematic route for designing selective SphK inhibitors.
SAR AND QSAR IN ENVIRONMENTAL RESEARCH 2017;
28:91-109. [PMID:
28121178 DOI:
10.1080/1062936x.2017.1280535]
[Citation(s) in RCA: 4] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/25/2016] [Accepted: 01/01/2017] [Indexed: 06/06/2023]
Abstract
Accurate and robust classification models for describing and predicting the activity of 330 chemicals that are sphingosine kinase 1 (SphK1) and/or sphingosine kinase 2 (SphK2) inhibitors were derived. The classification models developed in this work assist in finding selective subspaces in chemical space occupied by particular groups of SphK inhibitors. A combination of a genetic algorithm (GA) and a counter propagation artificial neural network (CPANN) was utilized to select the most efficient subsets of the molecular descriptors. The optimized models in this work reasonably separate active inhibitors of SphK1 from active SphK2 inhibitors. Generally, the CPANN models in this work were used to classify the compounds according to their therapeutic targets and activities. The simplicity of the chosen descriptors and their relative importance sheds some light on the structural features necessary to induce selective inhibitory activity to the studied molecules. The areas under the receiver operating characteristic (ROC) curves for the GA-CPANN models in this work were 0.934 and 0.922 for active SphK1 and SphK2 inhibitors, respectively. Generally, the results in this work suggest some important molecular features and pharmacophores that could help medicinal chemists develop selective and potent SphK inhibitors.
Collapse