Nowadays, cervical cancer is the second common female malignant tumor in global scenario that threatens the health of the female. Aging is the most important risk factor for various chronic diseases. Biological age should scale with chronological age under typical or control conditions but also be responsive to interventions that slow aging or exposures that accelerate aging. However, identifying models that are both accurate predictors of chronological age in control conditions as well as responsive to interventions remains a challenge. Here, initially gene expression was examined using DNA methylation data from Uterine Cervical Cancer. Then we utilized the evolved gene expression profile raised under normal Uterine Cervix (control) samples or under Uterine Cervix Tumor (experimental) samples to develop novel multi-objective optimized age regression models across two objectives. The regression models yielded excellent results in terms of all two objectives. We obtained the best regression age model with MAE of 1.72 and 4.14 of responsive angle ( \(\theta \) ). The best model’s features had been applied to determine respective miRNA-target gene mapping through miRWalk online database. Following the identification of miRNA-target gene associations, the Cytoscape online platform was utilized to construct the network and corresponding sub-networks and to perform network analysis using various centrality metrics. Our top hub genes are ZBTB16,TMEM135, MAP2K6, FOXP1, SAMD8, XPR1, ELAVL2, NPAS3, GREM1, and BCL11B. Moreover, our study yielded the first two-objective optimized expression age regression models and identified hub genes through miRNA-target gene regulatory network analysis. The approach as well as the regression models is applicable to a variety of designs in population and experimental studies.