| Abstract
| - As the structural diversity in a quantitative structure−activity relationship (QSAR) model increases,constructing a good model becomes increasingly difficult, and simply performing variable selection mightnot be sufficient to improve the model quality to make it practically usable. To combat this difficulty, anapproach based on piecewise hypersphere modeling by particle swarm optimization (PHMPSO) is developedin this paper. It treats the linear models describing the sought-for subsets as hyperspheres which have differentradii in the data space. According to the attribute of each hypersphere, all compounds in the training set areallocated to hyperspheres to construct submodels, and particle swarm optimization (PSO) is applied to searchthe optimal hyperspheres for finding satisfactory piecewise linear models. A new objective function isformulated to determine the appropriate piecewise models. The performance is assessed using three QSARdata sets. Experimental results have shown the good performance of this technique in improving the QSARmodeling.
|
