Lung cancer accounts for one third of all cancer related deaths worldwide. Computational models simulating cancer cell behavior can provide valuable insights into the quantitative understanding of the inherent complexity of neoplastic systems through an interdisciplinary approach. We have been working on the development and analysis of multiscale agent-based models to investigate the growth dynamics of non-small cell lung cancer (NSCLC). Our proposed innovative methods can be used to help identify biomarkers across different biological levels, thereby generate novel hypotheses and help guide further experiments.