Recursive distance partitioning algorithm for common pharmacophore identification

An improved method for exhaustively identifying common pharmacophores from a given list of 3D conformers is proposed. The method partitions feature lists into multidimensional boxes according to the distances between the pharmacophore centers. Unlike some existing techniques, each feature list is mapped into multiple boxes to ensure that good matches will never be missed due to the partitioning. To circumvent the computational complexity of the problem, a recursive distance partitioning (RDP) algorithm is introduced, in which the partitioning and the elimination of unqualified feature lists are carried out at multiple levels. The method is demonstrated to be both accurate and efficient.