Traditional clinical development of an experimental therapy utilizes the “one-size-fits-all” approach by testing the regimen in an unselected or untargeted patient population with a specific disease. The assumption is that response in the population with the disease is homogeneous. With the advent of targeted therapies, selection of treatment can be tailored to the genetic makeup of each individual. Therefore, these targeted therapies may benefit only a subset of the entire population and traditional statistical designs may no longer be appropriate or efficient. Statistical designs involving predictive biomarkers generally fall into 2 categories: classical designs and adaptive designs. We give a brief overview of the literature, and discuss the challenges and opportunities in the era of biomarker-based personalized medicine from a pharmaceutical industry perspective with some recent examples and case studies. SAS codes on implementation and evaluation of operating characteristics of some methods will be available in an upcoming book chapter.