Recording Evolution Supervised by a Genetic Algorithm for Quantitative Structure-Activity Relationship Optimization
A genetic algorithm for structure-activity relationships optimization was developed and implemented. The genetic algorithm was designed to be feed with families of molecular descriptors, and was tested on Molecular Descriptors Family. The objective of the genetic algorithm was to optimize the multiple linear regressions with four descriptors for prediction of octanol-water partition coefficient (expressed in logarithmic scale) of a series of 206 polychlorinated biphenyls. Relevant factors for evolution were parameterized in the implementation of the evolutionary program. The configuration file allows running of the genetic algorithm under different settings of parameters. The defined parameters were parameters used to characterize the adaptation to the environment (three parameters), to characterize the breading sample (four), the reproduction (four), the evolution objective (two), the selection (ten), the survival (four), and the program execution (three).
Simulating evolution, Genetic algorithms (GAs), Structure-Activity Relationships (SARs), Multiple Linear Regressions (MLRs)..