A neural network model to describe weight gain of sheep from genes polymorphism, birth weight and birth type.

摘要

Polymerase chain reaction-single strand conformation polymorphism (PCR-SSCP) method was used to determine the growth hormone (GH), leptin, calpain, and calpastatin polymorphism in Iranian Baluchi male sheep. An artificial neural network (ANN) model was developed to describe average daily gain (ADG) in lambs from input parameters of GH, leptin, calpain, and calpastatin polymorphism, birth weight, and birth type. The fitness of the model was tested using R2, MS error, and bias. The developed ANN-model was used to evaluate the relative importance of each input parameter on lambs ADG using a sensitivity analysis method. Three conformational patterns were detected for GH, Leptin, calpain genes, and five conformational patterns were detected for calpastatin gene. The calculated statistical values corresponding to the ANN-model showed a high accuracy of prediction (R2