Feature　selection　techniques　have　been　widely　applied　to　bioinformatics,　where　decision　forests　(DF)　is　an　important　one.　To　prove　the　advantage　of　DF,　Significance　Analysis　of　Microarray　(SAM),　PCA　and　ReliefF　were　employed　to　compare　with　it.　Support　Vectors　Machine　(SVM)　was　used　to　test　the　feature　genes　selected　by　the　four　methods.　The　comparison　results　show　that　feature　genes　selected　by　DF　contain　more　classification　information　and　can　get　higher　accuracy　rate　when　were　applied　to　classification.　As　a　reliable　method,　DF　should　be　applied　in　bioinformatics　broadly.　©　2010　Springer-Verlag　Berlin　Heidelberg.