Quantifying the inference power of a drug screen for predictive analysis

A model for drug sensitivity prediction is often inferred from the response of a training drug screen. Quantifying the inference power of perturbations before experimentation will assist in selecting drugs screens with higher predictive power. In this article, we present a novel approach to quantify the inference power of a drug screen based on drug target profiles and biologically motivated monotonicity constraints. We have tested our algorithm on synthetically and experimentally generated datasets and the results illustrate the suitability of the proposed measure in estimating information gained from an experimental drug screen.