Clustering of Large Databases of Compounds: Using the MDL “Keys” as Structural Descriptors
Malcolm J. McGregor, Peter V. Pallai · Journal of Chemical Information and Computer Sciences · 1997
An analysis of chemical structures from several commercially available libraries of compounds is presented with a view of acquiring compounds for screening. The Jarvis−Patrick clustering method has been applied, using the MDL “keys” as structural descriptors. The nature of the MDL keys is examined in this context, some features of the clustering algorithm are discussed, and clustering statistics are presented.