Next-generation DNA sequencing technologies have flooded databases and hard drives worldwide with large data sets, but are researchers getting the most they can out of this deluge of data? In a new study in the October issue of Applications in Plant Sciences, Dr. Brent Berger and colleagues propose one way to sift the remaining gold out of large sequence data sets. The authors show that a new data mining technique can be used to glean valuable information from existing data sets, and prove the concept by retrieving sequence from genes influencing the peculiar floral structures seen in the plant family Goodeniaceae.