This document discusses linking biodiversity collection data to applied research through data mining. It outlines a process to: 1) Identify relationships between plant and insect groups using secondary compound data; 2) Map the distributions of host plants and herbivorous insects; and 3) Compare distributions using visualization and statistics. The document also addresses challenges like incomplete taxonomic knowledge and lack of geo-referenced specimens that limit data integration and application. Developing open data standards and integrating museum, monitoring and environmental datasets can help overcome these challenges.