Frequent graph mining and its application to molecular databases

Molecular fragment mining is a promising approach for discovering novel fragments for drugs. We investigate a method for mining fragments which consists of three phases: first, a preprocessing phase for turning molecular databases into graph databases; second, the Gaston frequent graph mining phase for mining frequent paths, free trees and cyclic graphs; and third, a postprocessing phase in which redundant frequent fragments are removed. We devote most of our attention to the frequent graph mining phase, as this phase is computationally the most demanding, but also look at the other phases.