Predicting the toxicity of unknown chemicals based on gSpan algorithm
Rongbin Xu · Journal of Hefei University of Technology · 2007
The graph-based substructure pattern mining algorithm called gSpan,which discovers frequent substructures without candidate generation,is introduced first.gSpan builds a new lexicographic order among graphs and maps each graph to a unique minimum DFS code as its canonical label.Based on this lexicographic order,gSpan adopts the depth-first search strategy to mine frequent connected subgraphs efficiently.When it is applied to the chemical compound dataset Chemical-340,gSpan can find the compound set with same substructure as a chemical compound with toxicity,and then the toxicity of unknown chemicals can be predicted.This study is important to the related fields.