The adaptive elastic net has been widely studied in the microarray classification due to the elegant performances in gene selection. However, the classification accuracy will be affected if the noise is included. As such, this paper proposes a weighted adaptive elastic net for the binary microarray classification with noise by using the distances from the sample points to both class centers. Furthermore, the performance of adaptive gene selection is proved and the solution path algorithm is developed. Finally, the results on two cancer data added 4 additional samples illustrate that the weighted adaptive elastic net can achieve considerable classification accuracy and select the genes related with diseases.