Skip to main content
. Author manuscript; available in PMC: 2015 Dec 3.
Published in final edited form as: J Comput Biol. 2010 Mar;17(3):443–457. doi: 10.1089/cmb.2009.0165

Algorithm 2.

DivideCluster

Input: Root r, maximum p-value of interest maxPvalue
Output: A set of subsets of vertices of the subtree rooted at r that form significant clusters
if p-value(r)> maxPvalue then
  return ϕ
else
  if p-value(r) < p-value(leftChild(r)) and p-value(r) < p-value(leftChild(r)) then
   return {V (r)} % where V(r) is the set of vertices in the subtree rooted at r.
  else
   return DivideCluster(leftChild(r), maxPvalue) ∪ DivideCluster(rightChild(r), maxPvalue)
  end if
end if