Predictive classification on the base of gene expression profiles appeared recently as an attractive strategy for identifying the biological functions of genes. Gene Ontology (GO) provides a valuable source of knowledge for model training and validation. The increasing collection of microarray data represents a valuable source for generating functional hypotheses of uncharacterized genes. This study focused on using support vector machines (SVM) to predict GO biological processes from individual or multiple-tissue transcriptional profiles of aging in Drosophila melanogaster. Ten-fold cross validation was implemented to evaluate the prediction. One-tail Fisher's exact test was conducted on each cross validation and multiple testing was addressed using BH FDR procedure. The results showed that, of the 148 pursued GO biological processes, fifteen terms each had at least one model with FDR-adjusted p-value (Adj.p) <0.05 and six had the values between 0.05 and 0.25. Furthermore, all these models had the prediction sensitivity (SN) over 30% and specificity (SP) over 80%. We proposed the concept of term-tissue specific models indicating the fact that the major part of the optimized prediction models was trained from individual tissue data. Furthermore, we observed that the memberships of the genes involved in all the three pursued children biological processes on mitochondrial electron transport could be predicted from the transcriptional profiles of aging (Adj.p < 0.01). This finding may be important in biology because the genes of mitochondria play a critical role in the longevity of C. elegans and D. melanogaster.