In association studies there is a huge need to cut the number of measured variables on the field of association studies. The most widely used measurement devices' throughput is under the usual number of biomarkers found interesting in a study. Moreover, high-throughput lab instruments are able to measure millions of biomarkers while the number of samples is around several hundred. This ratio of variables and sample size is statistically untreatable, as a result reducing the number of variables is crucial.

Besides the statistical and measurement technology constraints it also important to use intelligent study design methods to optimize for computing and budget constraints as well.

Our tools allow taking budget constraints into consideration when selecting the statistically and biologically relevant variables. By minimizing the number of steps needed in the sequential trials, our approach reduces the costs by cutting down the number of variables in the subsequent steps.

With our unique software tools we can automate the selection of the optimal variable sets under above mentioned hard constraints. This method can significantly enhance the speed, effectiveness and reduce complexity of the study design process.