Background Semantic Web Technology (SWT) makes it possible to integrate and search the large volume of life science datasets in the public domain, as demonstrated by well-known linked data projects such as LODD, Bio2RDF, and Chem2Bio2RDF. Integration of these sets creates large networks of information. We have previously described a tool called WENDI for aggregating information pertaining to new chemical compounds, effectively creating evidence paths relating the compounds to genes, diseases and so on. In this paper we examine the utility of automatically inferring new compound-disease associations (and thus new links in the network) based on semantically marked-up versions of these evidence paths, rule-sets and inference engines. Results Through the implementation of a semantic inference algorithm, rule set, Semantic Web methods (RDF, OWL and SPARQL) and new interfaces, we have created a new tool called Chemogenomic Explorer that uses networks of ontologically annotated RDF statements along with deductive reasoning tools to infer new associations between the query structure and genes and diseases from WENDI results. The tool then permits interactive clustering and filtering of these evidence paths. Conclusions We present a new aggregate approach to inferring links between chemical compounds and diseases using semantic inference. This approach allows multiple evidence paths between compounds and diseases to be identified using a rule-set and semantically annotated data, and for these evidence paths to be clustered to show overall evidence linking the compound to a disease. We believe this is a powerful approach, because it allows compound-disease relationships to be ranked by the amount of evidence supporting them.