High-level high-throughput experiments such as systematic genome screens provide new kind of challenges for data mining. While traditional approaches like multi-dimensional clustering are successfully used, we believe that deeper and more subtle correlations are to be found when background knowledge is included into consideration. It is natural to apply a knowledge enriched approach to analyze results of systematic genome screens of well-studied model organisms, such as Saccharomyces cerevisiae (bakers yeast), to leverage the existing knowledge. In our work, Inductive Logic Programming has been used to mine results of yeast synthetic lethal (SL) and synthetic dosage lethal (SDL) screens in the presence of the background knowledge. The background knowledge used for these experiments consists of a subset of the Genome Ontology (GO). Since the rules are insightful, they should prove to be helpful in assisting the analysis of SL and SDL screens. The application of ILP represents a novel and promising approach to this problem.