Optimum DNA curvature using a hybrid approach involving an artificial neural network and genetic algorithm

In the present paper, a hybrid technique involving artificial neural networ k (ANN) and genetic algorithm (GA) has been proposed for performing modelin g and optimization of complex biological systems. In this approach, first a n ANN approximates (models) the nonlinear relationship(s) existing between its input and output example data sets. Next, the GA, which is a stochastic optimization technique, searches the input space of the ANN with a view to optimize the ANN output. The efficacy of this formalism has been tested by conducting a case study involving optimization of DNA curvature characteri zed in terms of the R-L value. Using the ANN-GA methodology, a number of se quences possessing high R-L values have been obtained and analyzed to verif y the existence of features known to be responsible for the occurrence of c urvature. A couple of sequences have also been tested experimentally. The e xperimental results validate qualitatively and also near-quantitatively, th e solutions obtained using the hybrid formalism. The ANN-GA technique is a useful tool to obtain, ahead of experimentation, sequences that yield high R-L values. The methodology is a general one and can be suitably employed f or optimizing any other biological feature.