Kinase inhibitors are a new class of therapeutics with a propensity to inhibit multiple targets(1,2). The biological consequences of multi-kinase activity are poorly defined, and an important step toward understanding the relationship between selectivity, efficacy and safety is the exploration of how inhibitors interact with the human kinome(2-4). We present interaction maps for 38 kinase inhibitors across a panel of 317 kinases representing >50% of the predicted human protein kinome. The data constitute the most comprehensive study of kinase inhibitor selectivity to date and reveal a wide diversity of interaction patterns. To enable a global analysis of the results, we introduce the concept of a selectivity score as a general tool to quantify and differentiate the observed interaction patterns. We further investigate the impact of panel size and find that small assay panels do not provide a robust measure of selectivity.