Substructure mining

Nicolaou, C. A., Pattichis, C. S. (2006) Molecular substructure mining approaches for computer-aided drug discovery a review. Proceedings of the 2006 ITAB Conference, October 26-28, Ioannina, Greece. 

Table 8.1 Comparison of four frequent substructure-mining algorithms in terms of performance,a...

J. Kazius, S. Nijssen, J. Kok, T. Back and A.P IJzerman, Substructure mining using elaborate chemical representation, J. Chem. Inf. Model., 46, 597-605 (2006). 

SheridanRP. (2003) Finding multiactivity substructures by mining databases of drug-like compounds. /. Chem. Inf. Comput. Sci. 43 1037-1050. 

D similarity and substructure searching are among the most widely used methods for mining structural data (9). The basic principle of these methods is that compounds with structural features in common will have similar properties,... 

C. Borgelt and M.R. Berthold, Mining molecular fragments finding relevant substructures of molecules, in Proceedings of the International Conference on Data Mining (ICDM), 2002, pp. 51-58. 

A second benefit of databases is the efficient extraction of information. The database may be mined to detect trends that may not be otherwise noticed. This approach is used to reveal trends such as the metabolically active sites of a molecule and/or a substructure labile to degradative conditions (Kerns et al., 1997). This informa-... 

Bit-strings are sets of binary descriptors (—> vectorial descriptors) and are often used as —> fingerprints or —> structural keys to define —> substructure descriptors and perform quick data mining. 

The two main applications of molecular descriptors have been for screens in substructure searching [4] and for attributes in similarity calculations [5]. Historically, many descriptors were developed first for substructure searching (see Chapter 19 of this book) and then used in similarity calculations for applications such as similarity analysis, clustering, combinatorial library design, and data mining (see Chapters 14,... 

---