On average it takes approximately 13 years and over 1 billion dollars to take a new medical entity (NME) from a concept to an approved product. As high as 40% of the drugs fail to make it thru to market at a significant cost and even with the best of preclinical testing some do cause unexpected or "idiosyncratic" toxicity. In order to reduce the length of the development timeline, support problem solving, provide improved decision making and reduce late stage attrition, many pharmaceutical companies are developing methodology to predict safety issues earlier in this process. While the exchange of scientific knowledge is still primarily thru the published medical literature, advances in semantic technology have dramatically changed the way a scientist accesses data and information. In particular, ontology development coupled with natural language processing, have made a huge impact on the review of the scientific literature and extraction of data from internal and external sources. Creation of highly linked knowledge bases enables the development of predictive methods as well as supports problem solving. These activities have been shown to be highly useful in reducing time and effort. The Knowledge Engineering initiative within AstraZeneca has recently delivered the first version of a knowledgebase that integrates internal and external evidence for connections between key concepts such as targets, pathways, compounds, diseases, preclinical, and clinical outcome from Chemistry, Competitive, Disease and Safety Intelligence workstreams. This talk will describe the system; demonstrate the impact of this new platform with specific examples from Safety, and discuss lessons learned during its development.